{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.772115699165286, "eval_steps": 500, "global_step": 9146, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 8.442113483110496e-05, "grad_norm": 1.328125, "learning_rate": 0.0, "loss": 2.125244140625, "step": 1 }, { "epoch": 0.00016884226966220993, "grad_norm": 1.296875, "learning_rate": 1.3368983957219251e-07, "loss": 1.9607311487197876, "step": 2 }, { "epoch": 0.0002532634044933149, "grad_norm": 1.265625, "learning_rate": 2.6737967914438503e-07, "loss": 2.043924331665039, "step": 3 }, { "epoch": 0.00033768453932441986, "grad_norm": 1.3671875, "learning_rate": 4.010695187165776e-07, "loss": 2.026930093765259, "step": 4 }, { "epoch": 0.00042210567415552485, "grad_norm": 1.203125, "learning_rate": 5.347593582887701e-07, "loss": 2.0335264205932617, "step": 5 }, { "epoch": 0.0005065268089866298, "grad_norm": 1.296875, "learning_rate": 6.684491978609626e-07, "loss": 2.050231456756592, "step": 6 }, { "epoch": 0.0005909479438177348, "grad_norm": 1.1796875, "learning_rate": 8.021390374331552e-07, "loss": 1.897997260093689, "step": 7 }, { "epoch": 0.0006753690786488397, "grad_norm": 1.2578125, "learning_rate": 9.358288770053476e-07, "loss": 1.9478609561920166, "step": 8 }, { "epoch": 0.0007597902134799448, "grad_norm": 1.1953125, "learning_rate": 1.0695187165775401e-06, "loss": 2.076531410217285, "step": 9 }, { "epoch": 0.0008442113483110497, "grad_norm": 1.3515625, "learning_rate": 1.2032085561497326e-06, "loss": 1.9904580116271973, "step": 10 }, { "epoch": 0.0009286324831421546, "grad_norm": 1.234375, "learning_rate": 1.3368983957219252e-06, "loss": 1.9623366594314575, "step": 11 }, { "epoch": 0.0010130536179732597, "grad_norm": 1.2265625, "learning_rate": 1.4705882352941177e-06, "loss": 1.9411804676055908, "step": 12 }, { "epoch": 0.0010974747528043646, "grad_norm": 1.2578125, "learning_rate": 1.6042780748663105e-06, "loss": 2.0749149322509766, "step": 13 }, { "epoch": 0.0011818958876354695, "grad_norm": 1.2109375, "learning_rate": 1.7379679144385028e-06, "loss": 2.0237343311309814, "step": 14 }, { "epoch": 0.0012663170224665745, "grad_norm": 1.28125, "learning_rate": 1.8716577540106951e-06, "loss": 1.9836944341659546, "step": 15 }, { "epoch": 0.0013507381572976794, "grad_norm": 1.234375, "learning_rate": 2.0053475935828877e-06, "loss": 1.9241527318954468, "step": 16 }, { "epoch": 0.0014351592921287844, "grad_norm": 1.2109375, "learning_rate": 2.1390374331550802e-06, "loss": 1.9899762868881226, "step": 17 }, { "epoch": 0.0015195804269598895, "grad_norm": 1.1796875, "learning_rate": 2.2727272727272728e-06, "loss": 1.9511314630508423, "step": 18 }, { "epoch": 0.0016040015617909944, "grad_norm": 1.21875, "learning_rate": 2.4064171122994653e-06, "loss": 1.9583555459976196, "step": 19 }, { "epoch": 0.0016884226966220994, "grad_norm": 1.28125, "learning_rate": 2.540106951871658e-06, "loss": 1.9849799871444702, "step": 20 }, { "epoch": 0.0017728438314532043, "grad_norm": 1.2734375, "learning_rate": 2.6737967914438504e-06, "loss": 1.9751487970352173, "step": 21 }, { "epoch": 0.0018572649662843093, "grad_norm": 1.21875, "learning_rate": 2.807486631016043e-06, "loss": 1.9378634691238403, "step": 22 }, { "epoch": 0.0019416861011154142, "grad_norm": 1.1484375, "learning_rate": 2.9411764705882355e-06, "loss": 1.9503949880599976, "step": 23 }, { "epoch": 0.0020261072359465193, "grad_norm": 1.2421875, "learning_rate": 3.074866310160428e-06, "loss": 1.9599615335464478, "step": 24 }, { "epoch": 0.0021105283707776243, "grad_norm": 1.3125, "learning_rate": 3.208556149732621e-06, "loss": 1.9962809085845947, "step": 25 }, { "epoch": 0.0021949495056087292, "grad_norm": 1.234375, "learning_rate": 3.342245989304813e-06, "loss": 1.946889877319336, "step": 26 }, { "epoch": 0.002279370640439834, "grad_norm": 1.0625, "learning_rate": 3.4759358288770056e-06, "loss": 1.9723025560379028, "step": 27 }, { "epoch": 0.002363791775270939, "grad_norm": 1.34375, "learning_rate": 3.6096256684491977e-06, "loss": 2.0332465171813965, "step": 28 }, { "epoch": 0.002448212910102044, "grad_norm": 1.1953125, "learning_rate": 3.7433155080213903e-06, "loss": 1.9587448835372925, "step": 29 }, { "epoch": 0.002532634044933149, "grad_norm": 1.375, "learning_rate": 3.877005347593583e-06, "loss": 1.9579399824142456, "step": 30 }, { "epoch": 0.002617055179764254, "grad_norm": 1.203125, "learning_rate": 4.010695187165775e-06, "loss": 1.9381061792373657, "step": 31 }, { "epoch": 0.002701476314595359, "grad_norm": 1.203125, "learning_rate": 4.144385026737968e-06, "loss": 1.9947659969329834, "step": 32 }, { "epoch": 0.0027858974494264638, "grad_norm": 1.2578125, "learning_rate": 4.2780748663101604e-06, "loss": 2.0155372619628906, "step": 33 }, { "epoch": 0.0028703185842575687, "grad_norm": 1.234375, "learning_rate": 4.411764705882353e-06, "loss": 1.9596723318099976, "step": 34 }, { "epoch": 0.0029547397190886737, "grad_norm": 1.3203125, "learning_rate": 4.5454545454545455e-06, "loss": 1.9457374811172485, "step": 35 }, { "epoch": 0.003039160853919779, "grad_norm": 1.328125, "learning_rate": 4.6791443850267385e-06, "loss": 1.9989172220230103, "step": 36 }, { "epoch": 0.003123581988750884, "grad_norm": 1.140625, "learning_rate": 4.812834224598931e-06, "loss": 2.0565860271453857, "step": 37 }, { "epoch": 0.003208003123581989, "grad_norm": 1.203125, "learning_rate": 4.9465240641711236e-06, "loss": 1.907299518585205, "step": 38 }, { "epoch": 0.003292424258413094, "grad_norm": 1.2421875, "learning_rate": 5.080213903743316e-06, "loss": 2.0861012935638428, "step": 39 }, { "epoch": 0.0033768453932441988, "grad_norm": 1.15625, "learning_rate": 5.213903743315509e-06, "loss": 2.0501785278320312, "step": 40 }, { "epoch": 0.0034612665280753037, "grad_norm": 1.2109375, "learning_rate": 5.347593582887701e-06, "loss": 1.9673408269882202, "step": 41 }, { "epoch": 0.0035456876629064086, "grad_norm": 1.2109375, "learning_rate": 5.481283422459893e-06, "loss": 2.032482862472534, "step": 42 }, { "epoch": 0.0036301087977375136, "grad_norm": 1.1875, "learning_rate": 5.614973262032086e-06, "loss": 1.8963875770568848, "step": 43 }, { "epoch": 0.0037145299325686185, "grad_norm": 1.265625, "learning_rate": 5.748663101604279e-06, "loss": 1.978920817375183, "step": 44 }, { "epoch": 0.0037989510673997235, "grad_norm": 1.265625, "learning_rate": 5.882352941176471e-06, "loss": 1.9035186767578125, "step": 45 }, { "epoch": 0.0038833722022308284, "grad_norm": 1.375, "learning_rate": 6.016042780748663e-06, "loss": 1.901247262954712, "step": 46 }, { "epoch": 0.003967793337061934, "grad_norm": 1.0703125, "learning_rate": 6.149732620320856e-06, "loss": 1.9065340757369995, "step": 47 }, { "epoch": 0.004052214471893039, "grad_norm": 1.2421875, "learning_rate": 6.283422459893049e-06, "loss": 2.030879020690918, "step": 48 }, { "epoch": 0.004136635606724144, "grad_norm": 1.2578125, "learning_rate": 6.417112299465242e-06, "loss": 1.9359263181686401, "step": 49 }, { "epoch": 0.004221056741555249, "grad_norm": 1.1953125, "learning_rate": 6.550802139037433e-06, "loss": 2.0174038410186768, "step": 50 }, { "epoch": 0.0043054778763863535, "grad_norm": 1.109375, "learning_rate": 6.684491978609626e-06, "loss": 1.9571208953857422, "step": 51 }, { "epoch": 0.0043898990112174584, "grad_norm": 1.296875, "learning_rate": 6.818181818181818e-06, "loss": 1.9087326526641846, "step": 52 }, { "epoch": 0.004474320146048563, "grad_norm": 1.1875, "learning_rate": 6.951871657754011e-06, "loss": 1.9576740264892578, "step": 53 }, { "epoch": 0.004558741280879668, "grad_norm": 1.109375, "learning_rate": 7.085561497326204e-06, "loss": 1.9764344692230225, "step": 54 }, { "epoch": 0.004643162415710773, "grad_norm": 1.1640625, "learning_rate": 7.2192513368983955e-06, "loss": 2.022599697113037, "step": 55 }, { "epoch": 0.004727583550541878, "grad_norm": 1.1171875, "learning_rate": 7.3529411764705884e-06, "loss": 2.0208380222320557, "step": 56 }, { "epoch": 0.004812004685372983, "grad_norm": 1.1640625, "learning_rate": 7.4866310160427806e-06, "loss": 2.012392044067383, "step": 57 }, { "epoch": 0.004896425820204088, "grad_norm": 1.1640625, "learning_rate": 7.6203208556149735e-06, "loss": 1.9484633207321167, "step": 58 }, { "epoch": 0.004980846955035193, "grad_norm": 1.2265625, "learning_rate": 7.754010695187166e-06, "loss": 1.9917792081832886, "step": 59 }, { "epoch": 0.005065268089866298, "grad_norm": 1.140625, "learning_rate": 7.887700534759358e-06, "loss": 1.9387459754943848, "step": 60 }, { "epoch": 0.005149689224697403, "grad_norm": 1.109375, "learning_rate": 8.02139037433155e-06, "loss": 1.961553931236267, "step": 61 }, { "epoch": 0.005234110359528508, "grad_norm": 1.0625, "learning_rate": 8.155080213903744e-06, "loss": 2.0139670372009277, "step": 62 }, { "epoch": 0.005318531494359613, "grad_norm": 1.171875, "learning_rate": 8.288770053475937e-06, "loss": 2.0457303524017334, "step": 63 }, { "epoch": 0.005402952629190718, "grad_norm": 1.0703125, "learning_rate": 8.42245989304813e-06, "loss": 2.0239944458007812, "step": 64 }, { "epoch": 0.005487373764021823, "grad_norm": 1.0625, "learning_rate": 8.556149732620321e-06, "loss": 1.980904221534729, "step": 65 }, { "epoch": 0.0055717948988529276, "grad_norm": 1.1953125, "learning_rate": 8.689839572192514e-06, "loss": 1.9216364622116089, "step": 66 }, { "epoch": 0.0056562160336840325, "grad_norm": 1.15625, "learning_rate": 8.823529411764707e-06, "loss": 1.929849624633789, "step": 67 }, { "epoch": 0.005740637168515137, "grad_norm": 1.109375, "learning_rate": 8.957219251336898e-06, "loss": 2.0185208320617676, "step": 68 }, { "epoch": 0.005825058303346242, "grad_norm": 1.03125, "learning_rate": 9.090909090909091e-06, "loss": 1.998822569847107, "step": 69 }, { "epoch": 0.005909479438177347, "grad_norm": 1.015625, "learning_rate": 9.224598930481284e-06, "loss": 2.049919843673706, "step": 70 }, { "epoch": 0.005993900573008452, "grad_norm": 1.0859375, "learning_rate": 9.358288770053477e-06, "loss": 1.9375364780426025, "step": 71 }, { "epoch": 0.006078321707839558, "grad_norm": 0.9921875, "learning_rate": 9.49197860962567e-06, "loss": 1.9939838647842407, "step": 72 }, { "epoch": 0.006162742842670663, "grad_norm": 1.0390625, "learning_rate": 9.625668449197861e-06, "loss": 1.8953495025634766, "step": 73 }, { "epoch": 0.006247163977501768, "grad_norm": 1.1171875, "learning_rate": 9.759358288770054e-06, "loss": 1.956281304359436, "step": 74 }, { "epoch": 0.006331585112332873, "grad_norm": 1.1640625, "learning_rate": 9.893048128342247e-06, "loss": 1.9785192012786865, "step": 75 }, { "epoch": 0.006416006247163978, "grad_norm": 0.984375, "learning_rate": 1.0026737967914438e-05, "loss": 1.9069865942001343, "step": 76 }, { "epoch": 0.006500427381995083, "grad_norm": 1.015625, "learning_rate": 1.0160427807486631e-05, "loss": 1.9474656581878662, "step": 77 }, { "epoch": 0.006584848516826188, "grad_norm": 0.94921875, "learning_rate": 1.0294117647058824e-05, "loss": 1.9781436920166016, "step": 78 }, { "epoch": 0.006669269651657293, "grad_norm": 1.03125, "learning_rate": 1.0427807486631017e-05, "loss": 1.9159150123596191, "step": 79 }, { "epoch": 0.0067536907864883975, "grad_norm": 1.0234375, "learning_rate": 1.056149732620321e-05, "loss": 1.9701225757598877, "step": 80 }, { "epoch": 0.0068381119213195025, "grad_norm": 0.9296875, "learning_rate": 1.0695187165775402e-05, "loss": 1.8809062242507935, "step": 81 }, { "epoch": 0.006922533056150607, "grad_norm": 0.984375, "learning_rate": 1.0828877005347594e-05, "loss": 1.935987114906311, "step": 82 }, { "epoch": 0.007006954190981712, "grad_norm": 0.88671875, "learning_rate": 1.0962566844919786e-05, "loss": 1.984593391418457, "step": 83 }, { "epoch": 0.007091375325812817, "grad_norm": 1.0, "learning_rate": 1.1096256684491979e-05, "loss": 1.8839921951293945, "step": 84 }, { "epoch": 0.007175796460643922, "grad_norm": 0.9609375, "learning_rate": 1.1229946524064172e-05, "loss": 1.9441258907318115, "step": 85 }, { "epoch": 0.007260217595475027, "grad_norm": 0.95703125, "learning_rate": 1.1363636363636365e-05, "loss": 1.8973525762557983, "step": 86 }, { "epoch": 0.007344638730306132, "grad_norm": 0.9609375, "learning_rate": 1.1497326203208558e-05, "loss": 1.9007680416107178, "step": 87 }, { "epoch": 0.007429059865137237, "grad_norm": 0.90625, "learning_rate": 1.163101604278075e-05, "loss": 1.899832844734192, "step": 88 }, { "epoch": 0.007513480999968342, "grad_norm": 0.88671875, "learning_rate": 1.1764705882352942e-05, "loss": 1.9373090267181396, "step": 89 }, { "epoch": 0.007597902134799447, "grad_norm": 0.93359375, "learning_rate": 1.1898395721925135e-05, "loss": 1.9875869750976562, "step": 90 }, { "epoch": 0.007682323269630552, "grad_norm": 0.96875, "learning_rate": 1.2032085561497326e-05, "loss": 1.8901667594909668, "step": 91 }, { "epoch": 0.007766744404461657, "grad_norm": 0.99609375, "learning_rate": 1.2165775401069519e-05, "loss": 1.9771250486373901, "step": 92 }, { "epoch": 0.007851165539292762, "grad_norm": 0.9453125, "learning_rate": 1.2299465240641712e-05, "loss": 2.0209479331970215, "step": 93 }, { "epoch": 0.007935586674123868, "grad_norm": 0.98828125, "learning_rate": 1.2433155080213903e-05, "loss": 1.8805432319641113, "step": 94 }, { "epoch": 0.008020007808954972, "grad_norm": 0.91015625, "learning_rate": 1.2566844919786098e-05, "loss": 1.9795063734054565, "step": 95 }, { "epoch": 0.008104428943786077, "grad_norm": 0.796875, "learning_rate": 1.2700534759358291e-05, "loss": 1.926485538482666, "step": 96 }, { "epoch": 0.008188850078617181, "grad_norm": 1.015625, "learning_rate": 1.2834224598930484e-05, "loss": 1.8431096076965332, "step": 97 }, { "epoch": 0.008273271213448287, "grad_norm": 0.96484375, "learning_rate": 1.2967914438502673e-05, "loss": 1.8361625671386719, "step": 98 }, { "epoch": 0.008357692348279391, "grad_norm": 0.91796875, "learning_rate": 1.3101604278074866e-05, "loss": 1.883225917816162, "step": 99 }, { "epoch": 0.008442113483110497, "grad_norm": 0.9140625, "learning_rate": 1.323529411764706e-05, "loss": 1.8896217346191406, "step": 100 }, { "epoch": 0.008526534617941601, "grad_norm": 1.015625, "learning_rate": 1.3368983957219252e-05, "loss": 1.939318299293518, "step": 101 }, { "epoch": 0.008610955752772707, "grad_norm": 0.91796875, "learning_rate": 1.3502673796791445e-05, "loss": 2.0161287784576416, "step": 102 }, { "epoch": 0.008695376887603811, "grad_norm": 0.86328125, "learning_rate": 1.3636363636363637e-05, "loss": 1.873775839805603, "step": 103 }, { "epoch": 0.008779798022434917, "grad_norm": 0.87890625, "learning_rate": 1.377005347593583e-05, "loss": 1.838181495666504, "step": 104 }, { "epoch": 0.008864219157266021, "grad_norm": 0.89453125, "learning_rate": 1.3903743315508022e-05, "loss": 1.9048762321472168, "step": 105 }, { "epoch": 0.008948640292097127, "grad_norm": 0.90234375, "learning_rate": 1.4037433155080215e-05, "loss": 1.9458690881729126, "step": 106 }, { "epoch": 0.00903306142692823, "grad_norm": 0.890625, "learning_rate": 1.4171122994652408e-05, "loss": 1.89558744430542, "step": 107 }, { "epoch": 0.009117482561759337, "grad_norm": 0.80078125, "learning_rate": 1.4304812834224598e-05, "loss": 1.9426310062408447, "step": 108 }, { "epoch": 0.00920190369659044, "grad_norm": 1.0390625, "learning_rate": 1.4438502673796791e-05, "loss": 1.8917754888534546, "step": 109 }, { "epoch": 0.009286324831421547, "grad_norm": 0.90625, "learning_rate": 1.4572192513368984e-05, "loss": 1.8961366415023804, "step": 110 }, { "epoch": 0.00937074596625265, "grad_norm": 0.90625, "learning_rate": 1.4705882352941177e-05, "loss": 1.9466640949249268, "step": 111 }, { "epoch": 0.009455167101083756, "grad_norm": 0.86328125, "learning_rate": 1.4839572192513372e-05, "loss": 1.8768799304962158, "step": 112 }, { "epoch": 0.00953958823591486, "grad_norm": 0.94921875, "learning_rate": 1.4973262032085561e-05, "loss": 1.8597853183746338, "step": 113 }, { "epoch": 0.009624009370745966, "grad_norm": 0.796875, "learning_rate": 1.5106951871657754e-05, "loss": 1.8677215576171875, "step": 114 }, { "epoch": 0.009708430505577072, "grad_norm": 0.87109375, "learning_rate": 1.5240641711229947e-05, "loss": 1.8632084131240845, "step": 115 }, { "epoch": 0.009792851640408176, "grad_norm": 0.9296875, "learning_rate": 1.5374331550802142e-05, "loss": 1.9065274000167847, "step": 116 }, { "epoch": 0.009877272775239282, "grad_norm": 0.7734375, "learning_rate": 1.5508021390374333e-05, "loss": 1.836403489112854, "step": 117 }, { "epoch": 0.009961693910070386, "grad_norm": 0.87109375, "learning_rate": 1.5641711229946524e-05, "loss": 1.7858612537384033, "step": 118 }, { "epoch": 0.010046115044901492, "grad_norm": 0.7890625, "learning_rate": 1.5775401069518716e-05, "loss": 1.859024167060852, "step": 119 }, { "epoch": 0.010130536179732596, "grad_norm": 0.80078125, "learning_rate": 1.590909090909091e-05, "loss": 1.8895431756973267, "step": 120 }, { "epoch": 0.010214957314563702, "grad_norm": 0.7578125, "learning_rate": 1.60427807486631e-05, "loss": 1.7572628259658813, "step": 121 }, { "epoch": 0.010299378449394806, "grad_norm": 0.7109375, "learning_rate": 1.6176470588235296e-05, "loss": 1.7738324403762817, "step": 122 }, { "epoch": 0.010383799584225912, "grad_norm": 0.72265625, "learning_rate": 1.6310160427807487e-05, "loss": 1.8484822511672974, "step": 123 }, { "epoch": 0.010468220719057016, "grad_norm": 0.72265625, "learning_rate": 1.644385026737968e-05, "loss": 1.864670753479004, "step": 124 }, { "epoch": 0.010552641853888121, "grad_norm": 0.72265625, "learning_rate": 1.6577540106951873e-05, "loss": 1.8579388856887817, "step": 125 }, { "epoch": 0.010637062988719225, "grad_norm": 0.7421875, "learning_rate": 1.6711229946524065e-05, "loss": 1.81029212474823, "step": 126 }, { "epoch": 0.010721484123550331, "grad_norm": 0.84375, "learning_rate": 1.684491978609626e-05, "loss": 1.9490948915481567, "step": 127 }, { "epoch": 0.010805905258381435, "grad_norm": 0.6640625, "learning_rate": 1.697860962566845e-05, "loss": 1.8464043140411377, "step": 128 }, { "epoch": 0.010890326393212541, "grad_norm": 0.59375, "learning_rate": 1.7112299465240642e-05, "loss": 1.8284928798675537, "step": 129 }, { "epoch": 0.010974747528043645, "grad_norm": 0.6328125, "learning_rate": 1.7245989304812833e-05, "loss": 1.8673239946365356, "step": 130 }, { "epoch": 0.011059168662874751, "grad_norm": 0.65625, "learning_rate": 1.7379679144385028e-05, "loss": 1.8275914192199707, "step": 131 }, { "epoch": 0.011143589797705855, "grad_norm": 0.67578125, "learning_rate": 1.7513368983957222e-05, "loss": 1.8065005540847778, "step": 132 }, { "epoch": 0.011228010932536961, "grad_norm": 0.59375, "learning_rate": 1.7647058823529414e-05, "loss": 1.857276439666748, "step": 133 }, { "epoch": 0.011312432067368065, "grad_norm": 0.6015625, "learning_rate": 1.7780748663101605e-05, "loss": 1.7462191581726074, "step": 134 }, { "epoch": 0.01139685320219917, "grad_norm": 0.5625, "learning_rate": 1.7914438502673796e-05, "loss": 1.7964261770248413, "step": 135 }, { "epoch": 0.011481274337030275, "grad_norm": 0.57421875, "learning_rate": 1.804812834224599e-05, "loss": 1.9629755020141602, "step": 136 }, { "epoch": 0.01156569547186138, "grad_norm": 0.5390625, "learning_rate": 1.8181818181818182e-05, "loss": 1.7771934270858765, "step": 137 }, { "epoch": 0.011650116606692485, "grad_norm": 0.58984375, "learning_rate": 1.8315508021390377e-05, "loss": 1.707434058189392, "step": 138 }, { "epoch": 0.01173453774152359, "grad_norm": 0.59375, "learning_rate": 1.8449197860962568e-05, "loss": 1.7817274332046509, "step": 139 }, { "epoch": 0.011818958876354695, "grad_norm": 0.63671875, "learning_rate": 1.858288770053476e-05, "loss": 1.7188000679016113, "step": 140 }, { "epoch": 0.0119033800111858, "grad_norm": 0.54296875, "learning_rate": 1.8716577540106954e-05, "loss": 1.8668544292449951, "step": 141 }, { "epoch": 0.011987801146016904, "grad_norm": 0.5625, "learning_rate": 1.8850267379679145e-05, "loss": 1.8192412853240967, "step": 142 }, { "epoch": 0.01207222228084801, "grad_norm": 0.4765625, "learning_rate": 1.898395721925134e-05, "loss": 1.8579820394515991, "step": 143 }, { "epoch": 0.012156643415679116, "grad_norm": 0.56640625, "learning_rate": 1.9117647058823528e-05, "loss": 1.7671030759811401, "step": 144 }, { "epoch": 0.01224106455051022, "grad_norm": 0.5625, "learning_rate": 1.9251336898395722e-05, "loss": 1.7492763996124268, "step": 145 }, { "epoch": 0.012325485685341326, "grad_norm": 0.546875, "learning_rate": 1.9385026737967914e-05, "loss": 1.7107436656951904, "step": 146 }, { "epoch": 0.01240990682017243, "grad_norm": 0.4921875, "learning_rate": 1.951871657754011e-05, "loss": 1.8031744956970215, "step": 147 }, { "epoch": 0.012494327955003536, "grad_norm": 0.55078125, "learning_rate": 1.96524064171123e-05, "loss": 1.7771755456924438, "step": 148 }, { "epoch": 0.01257874908983464, "grad_norm": 0.515625, "learning_rate": 1.9786096256684494e-05, "loss": 1.8336461782455444, "step": 149 }, { "epoch": 0.012663170224665746, "grad_norm": 0.498046875, "learning_rate": 1.9919786096256686e-05, "loss": 1.7519659996032715, "step": 150 }, { "epoch": 0.01274759135949685, "grad_norm": 0.451171875, "learning_rate": 2.0053475935828877e-05, "loss": 1.8044791221618652, "step": 151 }, { "epoch": 0.012832012494327956, "grad_norm": 0.515625, "learning_rate": 2.018716577540107e-05, "loss": 1.8188161849975586, "step": 152 }, { "epoch": 0.01291643362915906, "grad_norm": 0.486328125, "learning_rate": 2.0320855614973263e-05, "loss": 1.7916196584701538, "step": 153 }, { "epoch": 0.013000854763990165, "grad_norm": 0.482421875, "learning_rate": 2.0454545454545457e-05, "loss": 1.7575993537902832, "step": 154 }, { "epoch": 0.01308527589882127, "grad_norm": 0.458984375, "learning_rate": 2.058823529411765e-05, "loss": 1.6987340450286865, "step": 155 }, { "epoch": 0.013169697033652375, "grad_norm": 0.443359375, "learning_rate": 2.072192513368984e-05, "loss": 1.8200926780700684, "step": 156 }, { "epoch": 0.01325411816848348, "grad_norm": 0.427734375, "learning_rate": 2.0855614973262035e-05, "loss": 1.8017897605895996, "step": 157 }, { "epoch": 0.013338539303314585, "grad_norm": 0.46484375, "learning_rate": 2.0989304812834226e-05, "loss": 1.7288614511489868, "step": 158 }, { "epoch": 0.01342296043814569, "grad_norm": 0.48046875, "learning_rate": 2.112299465240642e-05, "loss": 1.7568933963775635, "step": 159 }, { "epoch": 0.013507381572976795, "grad_norm": 0.48046875, "learning_rate": 2.125668449197861e-05, "loss": 1.6533349752426147, "step": 160 }, { "epoch": 0.0135918027078079, "grad_norm": 0.455078125, "learning_rate": 2.1390374331550803e-05, "loss": 1.8711092472076416, "step": 161 }, { "epoch": 0.013676223842639005, "grad_norm": 0.490234375, "learning_rate": 2.1524064171122994e-05, "loss": 1.7215443849563599, "step": 162 }, { "epoch": 0.013760644977470109, "grad_norm": 0.421875, "learning_rate": 2.165775401069519e-05, "loss": 1.8298475742340088, "step": 163 }, { "epoch": 0.013845066112301215, "grad_norm": 0.40625, "learning_rate": 2.179144385026738e-05, "loss": 1.7997795343399048, "step": 164 }, { "epoch": 0.013929487247132319, "grad_norm": 0.435546875, "learning_rate": 2.192513368983957e-05, "loss": 1.8313461542129517, "step": 165 }, { "epoch": 0.014013908381963425, "grad_norm": 0.41796875, "learning_rate": 2.2058823529411766e-05, "loss": 1.669368863105774, "step": 166 }, { "epoch": 0.014098329516794529, "grad_norm": 0.435546875, "learning_rate": 2.2192513368983957e-05, "loss": 1.822940468788147, "step": 167 }, { "epoch": 0.014182750651625635, "grad_norm": 0.435546875, "learning_rate": 2.2326203208556152e-05, "loss": 1.6993708610534668, "step": 168 }, { "epoch": 0.014267171786456739, "grad_norm": 0.408203125, "learning_rate": 2.2459893048128343e-05, "loss": 1.8978465795516968, "step": 169 }, { "epoch": 0.014351592921287844, "grad_norm": 0.44921875, "learning_rate": 2.2593582887700535e-05, "loss": 1.706860065460205, "step": 170 }, { "epoch": 0.014436014056118949, "grad_norm": 0.4140625, "learning_rate": 2.272727272727273e-05, "loss": 1.8202499151229858, "step": 171 }, { "epoch": 0.014520435190950054, "grad_norm": 0.4296875, "learning_rate": 2.286096256684492e-05, "loss": 1.824023723602295, "step": 172 }, { "epoch": 0.01460485632578116, "grad_norm": 0.427734375, "learning_rate": 2.2994652406417115e-05, "loss": 1.7672007083892822, "step": 173 }, { "epoch": 0.014689277460612264, "grad_norm": 0.37109375, "learning_rate": 2.3128342245989306e-05, "loss": 1.8351781368255615, "step": 174 }, { "epoch": 0.01477369859544337, "grad_norm": 0.4375, "learning_rate": 2.32620320855615e-05, "loss": 1.7259196043014526, "step": 175 }, { "epoch": 0.014858119730274474, "grad_norm": 0.4296875, "learning_rate": 2.339572192513369e-05, "loss": 1.7269465923309326, "step": 176 }, { "epoch": 0.01494254086510558, "grad_norm": 0.400390625, "learning_rate": 2.3529411764705884e-05, "loss": 1.821407675743103, "step": 177 }, { "epoch": 0.015026961999936684, "grad_norm": 0.353515625, "learning_rate": 2.3663101604278075e-05, "loss": 1.784788966178894, "step": 178 }, { "epoch": 0.01511138313476779, "grad_norm": 0.375, "learning_rate": 2.379679144385027e-05, "loss": 1.7493873834609985, "step": 179 }, { "epoch": 0.015195804269598894, "grad_norm": 0.380859375, "learning_rate": 2.393048128342246e-05, "loss": 1.7073981761932373, "step": 180 }, { "epoch": 0.01528022540443, "grad_norm": 0.37109375, "learning_rate": 2.4064171122994652e-05, "loss": 1.6896225214004517, "step": 181 }, { "epoch": 0.015364646539261104, "grad_norm": 0.359375, "learning_rate": 2.4197860962566847e-05, "loss": 1.6936519145965576, "step": 182 }, { "epoch": 0.01544906767409221, "grad_norm": 0.3515625, "learning_rate": 2.4331550802139038e-05, "loss": 1.7741918563842773, "step": 183 }, { "epoch": 0.015533488808923314, "grad_norm": 0.38671875, "learning_rate": 2.4465240641711233e-05, "loss": 1.6846513748168945, "step": 184 }, { "epoch": 0.01561790994375442, "grad_norm": 0.3515625, "learning_rate": 2.4598930481283424e-05, "loss": 1.6753698587417603, "step": 185 }, { "epoch": 0.015702331078585523, "grad_norm": 0.353515625, "learning_rate": 2.4732620320855615e-05, "loss": 1.6828277111053467, "step": 186 }, { "epoch": 0.01578675221341663, "grad_norm": 0.35546875, "learning_rate": 2.4866310160427807e-05, "loss": 1.7489651441574097, "step": 187 }, { "epoch": 0.015871173348247735, "grad_norm": 0.32421875, "learning_rate": 2.5e-05, "loss": 1.6562385559082031, "step": 188 }, { "epoch": 0.015955594483078837, "grad_norm": 0.357421875, "learning_rate": 2.5133689839572196e-05, "loss": 1.752255916595459, "step": 189 }, { "epoch": 0.016040015617909943, "grad_norm": 0.32421875, "learning_rate": 2.5267379679144387e-05, "loss": 1.6461892127990723, "step": 190 }, { "epoch": 0.01612443675274105, "grad_norm": 0.326171875, "learning_rate": 2.5401069518716582e-05, "loss": 1.6989247798919678, "step": 191 }, { "epoch": 0.016208857887572155, "grad_norm": 0.365234375, "learning_rate": 2.5534759358288773e-05, "loss": 1.738647699356079, "step": 192 }, { "epoch": 0.016293279022403257, "grad_norm": 0.34765625, "learning_rate": 2.5668449197860968e-05, "loss": 1.7751637697219849, "step": 193 }, { "epoch": 0.016377700157234363, "grad_norm": 0.33984375, "learning_rate": 2.5802139037433156e-05, "loss": 1.7976731061935425, "step": 194 }, { "epoch": 0.01646212129206547, "grad_norm": 0.314453125, "learning_rate": 2.5935828877005347e-05, "loss": 1.6858679056167603, "step": 195 }, { "epoch": 0.016546542426896575, "grad_norm": 0.33984375, "learning_rate": 2.606951871657754e-05, "loss": 1.6646181344985962, "step": 196 }, { "epoch": 0.016630963561727677, "grad_norm": 0.33984375, "learning_rate": 2.6203208556149733e-05, "loss": 1.7433137893676758, "step": 197 }, { "epoch": 0.016715384696558783, "grad_norm": 0.337890625, "learning_rate": 2.6336898395721927e-05, "loss": 1.767628788948059, "step": 198 }, { "epoch": 0.01679980583138989, "grad_norm": 0.3203125, "learning_rate": 2.647058823529412e-05, "loss": 1.7524398565292358, "step": 199 }, { "epoch": 0.016884226966220994, "grad_norm": 0.326171875, "learning_rate": 2.6604278074866313e-05, "loss": 1.74588942527771, "step": 200 }, { "epoch": 0.0169686481010521, "grad_norm": 0.314453125, "learning_rate": 2.6737967914438505e-05, "loss": 1.6769405603408813, "step": 201 }, { "epoch": 0.017053069235883202, "grad_norm": 0.373046875, "learning_rate": 2.68716577540107e-05, "loss": 1.8567266464233398, "step": 202 }, { "epoch": 0.017137490370714308, "grad_norm": 0.291015625, "learning_rate": 2.700534759358289e-05, "loss": 1.777935266494751, "step": 203 }, { "epoch": 0.017221911505545414, "grad_norm": 0.357421875, "learning_rate": 2.713903743315508e-05, "loss": 1.8501813411712646, "step": 204 }, { "epoch": 0.01730633264037652, "grad_norm": 0.400390625, "learning_rate": 2.7272727272727273e-05, "loss": 1.7105507850646973, "step": 205 }, { "epoch": 0.017390753775207622, "grad_norm": 0.3359375, "learning_rate": 2.7406417112299464e-05, "loss": 1.7768598794937134, "step": 206 }, { "epoch": 0.017475174910038728, "grad_norm": 0.306640625, "learning_rate": 2.754010695187166e-05, "loss": 1.724770188331604, "step": 207 }, { "epoch": 0.017559596044869834, "grad_norm": 0.34765625, "learning_rate": 2.767379679144385e-05, "loss": 1.6228628158569336, "step": 208 }, { "epoch": 0.01764401717970094, "grad_norm": 0.294921875, "learning_rate": 2.7807486631016045e-05, "loss": 1.7256659269332886, "step": 209 }, { "epoch": 0.017728438314532042, "grad_norm": 0.37890625, "learning_rate": 2.7941176470588236e-05, "loss": 1.6646493673324585, "step": 210 }, { "epoch": 0.017812859449363148, "grad_norm": 0.337890625, "learning_rate": 2.807486631016043e-05, "loss": 1.6725589036941528, "step": 211 }, { "epoch": 0.017897280584194254, "grad_norm": 0.27734375, "learning_rate": 2.8208556149732622e-05, "loss": 1.6902320384979248, "step": 212 }, { "epoch": 0.01798170171902536, "grad_norm": 0.275390625, "learning_rate": 2.8342245989304817e-05, "loss": 1.6928725242614746, "step": 213 }, { "epoch": 0.01806612285385646, "grad_norm": 0.30078125, "learning_rate": 2.8475935828877005e-05, "loss": 1.5781304836273193, "step": 214 }, { "epoch": 0.018150543988687567, "grad_norm": 0.322265625, "learning_rate": 2.8609625668449196e-05, "loss": 1.7764650583267212, "step": 215 }, { "epoch": 0.018234965123518673, "grad_norm": 0.310546875, "learning_rate": 2.874331550802139e-05, "loss": 1.7397682666778564, "step": 216 }, { "epoch": 0.01831938625834978, "grad_norm": 0.330078125, "learning_rate": 2.8877005347593582e-05, "loss": 1.7766120433807373, "step": 217 }, { "epoch": 0.01840380739318088, "grad_norm": 0.34765625, "learning_rate": 2.9010695187165777e-05, "loss": 1.7068922519683838, "step": 218 }, { "epoch": 0.018488228528011987, "grad_norm": 0.3515625, "learning_rate": 2.9144385026737968e-05, "loss": 1.6976367235183716, "step": 219 }, { "epoch": 0.018572649662843093, "grad_norm": 0.2890625, "learning_rate": 2.9278074866310162e-05, "loss": 1.622002363204956, "step": 220 }, { "epoch": 0.0186570707976742, "grad_norm": 0.28125, "learning_rate": 2.9411764705882354e-05, "loss": 1.7273814678192139, "step": 221 }, { "epoch": 0.0187414919325053, "grad_norm": 0.26953125, "learning_rate": 2.954545454545455e-05, "loss": 1.755499005317688, "step": 222 }, { "epoch": 0.018825913067336407, "grad_norm": 0.287109375, "learning_rate": 2.9679144385026743e-05, "loss": 1.7516047954559326, "step": 223 }, { "epoch": 0.018910334202167513, "grad_norm": 0.28515625, "learning_rate": 2.9812834224598934e-05, "loss": 1.6972614526748657, "step": 224 }, { "epoch": 0.01899475533699862, "grad_norm": 0.283203125, "learning_rate": 2.9946524064171122e-05, "loss": 1.6488020420074463, "step": 225 }, { "epoch": 0.01907917647182972, "grad_norm": 0.28515625, "learning_rate": 3.0080213903743313e-05, "loss": 1.7137165069580078, "step": 226 }, { "epoch": 0.019163597606660827, "grad_norm": 0.2890625, "learning_rate": 3.0213903743315508e-05, "loss": 1.7045425176620483, "step": 227 }, { "epoch": 0.019248018741491933, "grad_norm": 0.291015625, "learning_rate": 3.0347593582887703e-05, "loss": 1.5897020101547241, "step": 228 }, { "epoch": 0.01933243987632304, "grad_norm": 0.251953125, "learning_rate": 3.0481283422459894e-05, "loss": 1.7361674308776855, "step": 229 }, { "epoch": 0.019416861011154144, "grad_norm": 0.263671875, "learning_rate": 3.0614973262032085e-05, "loss": 1.668805718421936, "step": 230 }, { "epoch": 0.019501282145985246, "grad_norm": 0.25390625, "learning_rate": 3.0748663101604283e-05, "loss": 1.7969800233840942, "step": 231 }, { "epoch": 0.019585703280816352, "grad_norm": 0.2578125, "learning_rate": 3.0882352941176475e-05, "loss": 1.6294102668762207, "step": 232 }, { "epoch": 0.019670124415647458, "grad_norm": 0.294921875, "learning_rate": 3.1016042780748666e-05, "loss": 1.6172089576721191, "step": 233 }, { "epoch": 0.019754545550478564, "grad_norm": 0.2734375, "learning_rate": 3.114973262032086e-05, "loss": 1.6447440385818481, "step": 234 }, { "epoch": 0.019838966685309666, "grad_norm": 0.267578125, "learning_rate": 3.128342245989305e-05, "loss": 1.6804364919662476, "step": 235 }, { "epoch": 0.019923387820140772, "grad_norm": 0.255859375, "learning_rate": 3.141711229946524e-05, "loss": 1.6159039735794067, "step": 236 }, { "epoch": 0.020007808954971878, "grad_norm": 0.23828125, "learning_rate": 3.155080213903743e-05, "loss": 1.673288345336914, "step": 237 }, { "epoch": 0.020092230089802984, "grad_norm": 0.2421875, "learning_rate": 3.168449197860963e-05, "loss": 1.694177508354187, "step": 238 }, { "epoch": 0.020176651224634086, "grad_norm": 0.228515625, "learning_rate": 3.181818181818182e-05, "loss": 1.7464886903762817, "step": 239 }, { "epoch": 0.020261072359465192, "grad_norm": 0.232421875, "learning_rate": 3.195187165775401e-05, "loss": 1.631304383277893, "step": 240 }, { "epoch": 0.020345493494296298, "grad_norm": 0.298828125, "learning_rate": 3.20855614973262e-05, "loss": 1.6505829095840454, "step": 241 }, { "epoch": 0.020429914629127403, "grad_norm": 0.23828125, "learning_rate": 3.22192513368984e-05, "loss": 1.653456687927246, "step": 242 }, { "epoch": 0.020514335763958506, "grad_norm": 0.302734375, "learning_rate": 3.235294117647059e-05, "loss": 1.664780855178833, "step": 243 }, { "epoch": 0.02059875689878961, "grad_norm": 0.28515625, "learning_rate": 3.2486631016042783e-05, "loss": 1.6132854223251343, "step": 244 }, { "epoch": 0.020683178033620717, "grad_norm": 0.2392578125, "learning_rate": 3.2620320855614975e-05, "loss": 1.6054643392562866, "step": 245 }, { "epoch": 0.020767599168451823, "grad_norm": 0.28515625, "learning_rate": 3.2754010695187166e-05, "loss": 1.6813796758651733, "step": 246 }, { "epoch": 0.020852020303282925, "grad_norm": 0.271484375, "learning_rate": 3.288770053475936e-05, "loss": 1.6535072326660156, "step": 247 }, { "epoch": 0.02093644143811403, "grad_norm": 0.216796875, "learning_rate": 3.302139037433155e-05, "loss": 1.6887404918670654, "step": 248 }, { "epoch": 0.021020862572945137, "grad_norm": 0.2578125, "learning_rate": 3.3155080213903747e-05, "loss": 1.6360723972320557, "step": 249 }, { "epoch": 0.021105283707776243, "grad_norm": 0.23828125, "learning_rate": 3.328877005347594e-05, "loss": 1.650930404663086, "step": 250 }, { "epoch": 0.021189704842607345, "grad_norm": 0.2421875, "learning_rate": 3.342245989304813e-05, "loss": 1.775699257850647, "step": 251 }, { "epoch": 0.02127412597743845, "grad_norm": 0.21875, "learning_rate": 3.355614973262032e-05, "loss": 1.6011549234390259, "step": 252 }, { "epoch": 0.021358547112269557, "grad_norm": 0.2421875, "learning_rate": 3.368983957219252e-05, "loss": 1.63565993309021, "step": 253 }, { "epoch": 0.021442968247100663, "grad_norm": 0.19921875, "learning_rate": 3.382352941176471e-05, "loss": 1.6239936351776123, "step": 254 }, { "epoch": 0.021527389381931765, "grad_norm": 0.212890625, "learning_rate": 3.39572192513369e-05, "loss": 1.6757053136825562, "step": 255 }, { "epoch": 0.02161181051676287, "grad_norm": 0.25390625, "learning_rate": 3.409090909090909e-05, "loss": 1.6380906105041504, "step": 256 }, { "epoch": 0.021696231651593977, "grad_norm": 0.23828125, "learning_rate": 3.4224598930481284e-05, "loss": 1.7857682704925537, "step": 257 }, { "epoch": 0.021780652786425082, "grad_norm": 0.30078125, "learning_rate": 3.4358288770053475e-05, "loss": 1.634804129600525, "step": 258 }, { "epoch": 0.021865073921256188, "grad_norm": 0.224609375, "learning_rate": 3.4491978609625666e-05, "loss": 1.6430922746658325, "step": 259 }, { "epoch": 0.02194949505608729, "grad_norm": 0.2578125, "learning_rate": 3.4625668449197864e-05, "loss": 1.620516300201416, "step": 260 }, { "epoch": 0.022033916190918396, "grad_norm": 0.22265625, "learning_rate": 3.4759358288770055e-05, "loss": 1.7324585914611816, "step": 261 }, { "epoch": 0.022118337325749502, "grad_norm": 0.2138671875, "learning_rate": 3.489304812834225e-05, "loss": 1.6399444341659546, "step": 262 }, { "epoch": 0.022202758460580608, "grad_norm": 0.1982421875, "learning_rate": 3.5026737967914445e-05, "loss": 1.7303389310836792, "step": 263 }, { "epoch": 0.02228717959541171, "grad_norm": 0.2119140625, "learning_rate": 3.5160427807486636e-05, "loss": 1.6785047054290771, "step": 264 }, { "epoch": 0.022371600730242816, "grad_norm": 0.2021484375, "learning_rate": 3.529411764705883e-05, "loss": 1.6898620128631592, "step": 265 }, { "epoch": 0.022456021865073922, "grad_norm": 0.21875, "learning_rate": 3.542780748663101e-05, "loss": 1.6914153099060059, "step": 266 }, { "epoch": 0.022540442999905028, "grad_norm": 0.31640625, "learning_rate": 3.556149732620321e-05, "loss": 1.6811327934265137, "step": 267 }, { "epoch": 0.02262486413473613, "grad_norm": 0.2158203125, "learning_rate": 3.56951871657754e-05, "loss": 1.6661674976348877, "step": 268 }, { "epoch": 0.022709285269567236, "grad_norm": 0.1962890625, "learning_rate": 3.582887700534759e-05, "loss": 1.6090959310531616, "step": 269 }, { "epoch": 0.02279370640439834, "grad_norm": 0.203125, "learning_rate": 3.596256684491979e-05, "loss": 1.6685075759887695, "step": 270 }, { "epoch": 0.022878127539229447, "grad_norm": 0.2890625, "learning_rate": 3.609625668449198e-05, "loss": 1.6768285036087036, "step": 271 }, { "epoch": 0.02296254867406055, "grad_norm": 0.283203125, "learning_rate": 3.622994652406417e-05, "loss": 1.685678243637085, "step": 272 }, { "epoch": 0.023046969808891656, "grad_norm": 0.1982421875, "learning_rate": 3.6363636363636364e-05, "loss": 1.5455156564712524, "step": 273 }, { "epoch": 0.02313139094372276, "grad_norm": 0.2490234375, "learning_rate": 3.649732620320856e-05, "loss": 1.6235915422439575, "step": 274 }, { "epoch": 0.023215812078553867, "grad_norm": 0.2333984375, "learning_rate": 3.6631016042780753e-05, "loss": 1.6722954511642456, "step": 275 }, { "epoch": 0.02330023321338497, "grad_norm": 0.173828125, "learning_rate": 3.6764705882352945e-05, "loss": 1.6781400442123413, "step": 276 }, { "epoch": 0.023384654348216075, "grad_norm": 0.35546875, "learning_rate": 3.6898395721925136e-05, "loss": 1.6264418363571167, "step": 277 }, { "epoch": 0.02346907548304718, "grad_norm": 0.1787109375, "learning_rate": 3.703208556149733e-05, "loss": 1.5784552097320557, "step": 278 }, { "epoch": 0.023553496617878287, "grad_norm": 0.21875, "learning_rate": 3.716577540106952e-05, "loss": 1.7144521474838257, "step": 279 }, { "epoch": 0.02363791775270939, "grad_norm": 0.208984375, "learning_rate": 3.729946524064171e-05, "loss": 1.7383825778961182, "step": 280 }, { "epoch": 0.023722338887540495, "grad_norm": 0.265625, "learning_rate": 3.743315508021391e-05, "loss": 1.6372531652450562, "step": 281 }, { "epoch": 0.0238067600223716, "grad_norm": 0.236328125, "learning_rate": 3.75668449197861e-05, "loss": 1.6228333711624146, "step": 282 }, { "epoch": 0.023891181157202707, "grad_norm": 0.2431640625, "learning_rate": 3.770053475935829e-05, "loss": 1.6486774682998657, "step": 283 }, { "epoch": 0.02397560229203381, "grad_norm": 0.2080078125, "learning_rate": 3.783422459893048e-05, "loss": 1.6995890140533447, "step": 284 }, { "epoch": 0.024060023426864915, "grad_norm": 0.24609375, "learning_rate": 3.796791443850268e-05, "loss": 1.6786799430847168, "step": 285 }, { "epoch": 0.02414444456169602, "grad_norm": 0.2158203125, "learning_rate": 3.810160427807487e-05, "loss": 1.6294466257095337, "step": 286 }, { "epoch": 0.024228865696527126, "grad_norm": 0.205078125, "learning_rate": 3.8235294117647055e-05, "loss": 1.613938331604004, "step": 287 }, { "epoch": 0.024313286831358232, "grad_norm": 0.1865234375, "learning_rate": 3.8368983957219254e-05, "loss": 1.643754482269287, "step": 288 }, { "epoch": 0.024397707966189335, "grad_norm": 0.189453125, "learning_rate": 3.8502673796791445e-05, "loss": 1.676320195198059, "step": 289 }, { "epoch": 0.02448212910102044, "grad_norm": 0.2001953125, "learning_rate": 3.8636363636363636e-05, "loss": 1.677209734916687, "step": 290 }, { "epoch": 0.024566550235851546, "grad_norm": 0.17578125, "learning_rate": 3.877005347593583e-05, "loss": 1.6806318759918213, "step": 291 }, { "epoch": 0.024650971370682652, "grad_norm": 0.201171875, "learning_rate": 3.8903743315508025e-05, "loss": 1.6042048931121826, "step": 292 }, { "epoch": 0.024735392505513754, "grad_norm": 0.1845703125, "learning_rate": 3.903743315508022e-05, "loss": 1.6461666822433472, "step": 293 }, { "epoch": 0.02481981364034486, "grad_norm": 0.1787109375, "learning_rate": 3.917112299465241e-05, "loss": 1.6454133987426758, "step": 294 }, { "epoch": 0.024904234775175966, "grad_norm": 0.21484375, "learning_rate": 3.93048128342246e-05, "loss": 1.6769849061965942, "step": 295 }, { "epoch": 0.02498865591000707, "grad_norm": 0.29296875, "learning_rate": 3.94385026737968e-05, "loss": 1.6461772918701172, "step": 296 }, { "epoch": 0.025073077044838174, "grad_norm": 0.369140625, "learning_rate": 3.957219251336899e-05, "loss": 1.6901971101760864, "step": 297 }, { "epoch": 0.02515749817966928, "grad_norm": 0.1748046875, "learning_rate": 3.970588235294117e-05, "loss": 1.6783556938171387, "step": 298 }, { "epoch": 0.025241919314500386, "grad_norm": 0.24609375, "learning_rate": 3.983957219251337e-05, "loss": 1.6704989671707153, "step": 299 }, { "epoch": 0.02532634044933149, "grad_norm": 0.2001953125, "learning_rate": 3.997326203208556e-05, "loss": 1.620956540107727, "step": 300 }, { "epoch": 0.025410761584162594, "grad_norm": 0.173828125, "learning_rate": 4.0106951871657754e-05, "loss": 1.5801584720611572, "step": 301 }, { "epoch": 0.0254951827189937, "grad_norm": 0.23046875, "learning_rate": 4.024064171122995e-05, "loss": 1.6391675472259521, "step": 302 }, { "epoch": 0.025579603853824805, "grad_norm": 0.2001953125, "learning_rate": 4.037433155080214e-05, "loss": 1.681141972541809, "step": 303 }, { "epoch": 0.02566402498865591, "grad_norm": 0.197265625, "learning_rate": 4.0508021390374334e-05, "loss": 1.6290760040283203, "step": 304 }, { "epoch": 0.025748446123487014, "grad_norm": 0.234375, "learning_rate": 4.0641711229946525e-05, "loss": 1.5970537662506104, "step": 305 }, { "epoch": 0.02583286725831812, "grad_norm": 0.19921875, "learning_rate": 4.0775401069518723e-05, "loss": 1.5655194520950317, "step": 306 }, { "epoch": 0.025917288393149225, "grad_norm": 0.2265625, "learning_rate": 4.0909090909090915e-05, "loss": 1.6569820642471313, "step": 307 }, { "epoch": 0.02600170952798033, "grad_norm": 0.1728515625, "learning_rate": 4.10427807486631e-05, "loss": 1.6506669521331787, "step": 308 }, { "epoch": 0.026086130662811433, "grad_norm": 0.251953125, "learning_rate": 4.11764705882353e-05, "loss": 1.6907908916473389, "step": 309 }, { "epoch": 0.02617055179764254, "grad_norm": 0.337890625, "learning_rate": 4.131016042780749e-05, "loss": 1.6352953910827637, "step": 310 }, { "epoch": 0.026254972932473645, "grad_norm": 0.240234375, "learning_rate": 4.144385026737968e-05, "loss": 1.7730376720428467, "step": 311 }, { "epoch": 0.02633939406730475, "grad_norm": 0.21875, "learning_rate": 4.157754010695187e-05, "loss": 1.7978978157043457, "step": 312 }, { "epoch": 0.026423815202135853, "grad_norm": 0.208984375, "learning_rate": 4.171122994652407e-05, "loss": 1.6218576431274414, "step": 313 }, { "epoch": 0.02650823633696696, "grad_norm": 0.216796875, "learning_rate": 4.184491978609626e-05, "loss": 1.6569616794586182, "step": 314 }, { "epoch": 0.026592657471798065, "grad_norm": 0.2333984375, "learning_rate": 4.197860962566845e-05, "loss": 1.6202179193496704, "step": 315 }, { "epoch": 0.02667707860662917, "grad_norm": 0.18359375, "learning_rate": 4.211229946524064e-05, "loss": 1.7037616968154907, "step": 316 }, { "epoch": 0.026761499741460276, "grad_norm": 0.2158203125, "learning_rate": 4.224598930481284e-05, "loss": 1.631556749343872, "step": 317 }, { "epoch": 0.02684592087629138, "grad_norm": 0.1767578125, "learning_rate": 4.2379679144385025e-05, "loss": 1.6630661487579346, "step": 318 }, { "epoch": 0.026930342011122484, "grad_norm": 0.1953125, "learning_rate": 4.251336898395722e-05, "loss": 1.6807876825332642, "step": 319 }, { "epoch": 0.02701476314595359, "grad_norm": 0.2177734375, "learning_rate": 4.2647058823529415e-05, "loss": 1.7034814357757568, "step": 320 }, { "epoch": 0.027099184280784696, "grad_norm": 0.2138671875, "learning_rate": 4.2780748663101606e-05, "loss": 1.6218129396438599, "step": 321 }, { "epoch": 0.0271836054156158, "grad_norm": 0.173828125, "learning_rate": 4.29144385026738e-05, "loss": 1.7147356271743774, "step": 322 }, { "epoch": 0.027268026550446904, "grad_norm": 0.1943359375, "learning_rate": 4.304812834224599e-05, "loss": 1.6585593223571777, "step": 323 }, { "epoch": 0.02735244768527801, "grad_norm": 0.263671875, "learning_rate": 4.318181818181819e-05, "loss": 1.7174975872039795, "step": 324 }, { "epoch": 0.027436868820109116, "grad_norm": 0.232421875, "learning_rate": 4.331550802139038e-05, "loss": 1.667706847190857, "step": 325 }, { "epoch": 0.027521289954940218, "grad_norm": 0.1865234375, "learning_rate": 4.344919786096257e-05, "loss": 1.6775442361831665, "step": 326 }, { "epoch": 0.027605711089771324, "grad_norm": 0.30078125, "learning_rate": 4.358288770053476e-05, "loss": 1.5877385139465332, "step": 327 }, { "epoch": 0.02769013222460243, "grad_norm": 0.193359375, "learning_rate": 4.371657754010696e-05, "loss": 1.640734076499939, "step": 328 }, { "epoch": 0.027774553359433535, "grad_norm": 0.185546875, "learning_rate": 4.385026737967914e-05, "loss": 1.6260770559310913, "step": 329 }, { "epoch": 0.027858974494264638, "grad_norm": 0.19921875, "learning_rate": 4.3983957219251334e-05, "loss": 1.7310994863510132, "step": 330 }, { "epoch": 0.027943395629095744, "grad_norm": 0.1923828125, "learning_rate": 4.411764705882353e-05, "loss": 1.6155489683151245, "step": 331 }, { "epoch": 0.02802781676392685, "grad_norm": 0.1875, "learning_rate": 4.4251336898395724e-05, "loss": 1.6029187440872192, "step": 332 }, { "epoch": 0.028112237898757955, "grad_norm": 0.1689453125, "learning_rate": 4.4385026737967915e-05, "loss": 1.5732088088989258, "step": 333 }, { "epoch": 0.028196659033589058, "grad_norm": 0.2138671875, "learning_rate": 4.4518716577540106e-05, "loss": 1.5981018543243408, "step": 334 }, { "epoch": 0.028281080168420163, "grad_norm": 0.22265625, "learning_rate": 4.4652406417112304e-05, "loss": 1.673264980316162, "step": 335 }, { "epoch": 0.02836550130325127, "grad_norm": 0.193359375, "learning_rate": 4.4786096256684495e-05, "loss": 1.7577487230300903, "step": 336 }, { "epoch": 0.028449922438082375, "grad_norm": 0.1708984375, "learning_rate": 4.491978609625669e-05, "loss": 1.6538015604019165, "step": 337 }, { "epoch": 0.028534343572913477, "grad_norm": 0.181640625, "learning_rate": 4.5053475935828885e-05, "loss": 1.7013806104660034, "step": 338 }, { "epoch": 0.028618764707744583, "grad_norm": 0.2060546875, "learning_rate": 4.518716577540107e-05, "loss": 1.6485984325408936, "step": 339 }, { "epoch": 0.02870318584257569, "grad_norm": 0.234375, "learning_rate": 4.532085561497326e-05, "loss": 1.517539381980896, "step": 340 }, { "epoch": 0.028787606977406795, "grad_norm": 0.248046875, "learning_rate": 4.545454545454546e-05, "loss": 1.551689624786377, "step": 341 }, { "epoch": 0.028872028112237897, "grad_norm": 0.1767578125, "learning_rate": 4.558823529411765e-05, "loss": 1.6209485530853271, "step": 342 }, { "epoch": 0.028956449247069003, "grad_norm": 0.2158203125, "learning_rate": 4.572192513368984e-05, "loss": 1.6820018291473389, "step": 343 }, { "epoch": 0.02904087038190011, "grad_norm": 0.173828125, "learning_rate": 4.585561497326203e-05, "loss": 1.6782886981964111, "step": 344 }, { "epoch": 0.029125291516731214, "grad_norm": 0.197265625, "learning_rate": 4.598930481283423e-05, "loss": 1.5906819105148315, "step": 345 }, { "epoch": 0.02920971265156232, "grad_norm": 0.2490234375, "learning_rate": 4.612299465240642e-05, "loss": 1.6698112487792969, "step": 346 }, { "epoch": 0.029294133786393423, "grad_norm": 0.21484375, "learning_rate": 4.625668449197861e-05, "loss": 1.6762646436691284, "step": 347 }, { "epoch": 0.02937855492122453, "grad_norm": 0.1708984375, "learning_rate": 4.6390374331550804e-05, "loss": 1.6669747829437256, "step": 348 }, { "epoch": 0.029462976056055634, "grad_norm": 0.259765625, "learning_rate": 4.6524064171123e-05, "loss": 1.5830177068710327, "step": 349 }, { "epoch": 0.02954739719088674, "grad_norm": 0.328125, "learning_rate": 4.665775401069519e-05, "loss": 1.633512258529663, "step": 350 }, { "epoch": 0.029631818325717842, "grad_norm": 0.263671875, "learning_rate": 4.679144385026738e-05, "loss": 1.6372344493865967, "step": 351 }, { "epoch": 0.029716239460548948, "grad_norm": 0.19921875, "learning_rate": 4.6925133689839576e-05, "loss": 1.6901577711105347, "step": 352 }, { "epoch": 0.029800660595380054, "grad_norm": 0.2021484375, "learning_rate": 4.705882352941177e-05, "loss": 1.6307382583618164, "step": 353 }, { "epoch": 0.02988508173021116, "grad_norm": 0.263671875, "learning_rate": 4.719251336898396e-05, "loss": 1.6109126806259155, "step": 354 }, { "epoch": 0.029969502865042262, "grad_norm": 0.20703125, "learning_rate": 4.732620320855615e-05, "loss": 1.6498794555664062, "step": 355 }, { "epoch": 0.030053923999873368, "grad_norm": 0.21875, "learning_rate": 4.745989304812835e-05, "loss": 1.5965901613235474, "step": 356 }, { "epoch": 0.030138345134704474, "grad_norm": 0.169921875, "learning_rate": 4.759358288770054e-05, "loss": 1.75397789478302, "step": 357 }, { "epoch": 0.03022276626953558, "grad_norm": 0.2255859375, "learning_rate": 4.772727272727273e-05, "loss": 1.653810739517212, "step": 358 }, { "epoch": 0.030307187404366682, "grad_norm": 0.375, "learning_rate": 4.786096256684492e-05, "loss": 1.5896506309509277, "step": 359 }, { "epoch": 0.030391608539197788, "grad_norm": 0.1650390625, "learning_rate": 4.799465240641711e-05, "loss": 1.6134613752365112, "step": 360 }, { "epoch": 0.030476029674028893, "grad_norm": 0.1767578125, "learning_rate": 4.8128342245989304e-05, "loss": 1.6493794918060303, "step": 361 }, { "epoch": 0.03056045080886, "grad_norm": 0.1630859375, "learning_rate": 4.8262032085561496e-05, "loss": 1.6243436336517334, "step": 362 }, { "epoch": 0.0306448719436911, "grad_norm": 0.205078125, "learning_rate": 4.8395721925133694e-05, "loss": 1.6628968715667725, "step": 363 }, { "epoch": 0.030729293078522207, "grad_norm": 0.2099609375, "learning_rate": 4.8529411764705885e-05, "loss": 1.7168322801589966, "step": 364 }, { "epoch": 0.030813714213353313, "grad_norm": 0.1650390625, "learning_rate": 4.8663101604278076e-05, "loss": 1.594575047492981, "step": 365 }, { "epoch": 0.03089813534818442, "grad_norm": 0.2001953125, "learning_rate": 4.879679144385027e-05, "loss": 1.6924620866775513, "step": 366 }, { "epoch": 0.03098255648301552, "grad_norm": 0.1650390625, "learning_rate": 4.8930481283422465e-05, "loss": 1.6595031023025513, "step": 367 }, { "epoch": 0.031066977617846627, "grad_norm": 0.171875, "learning_rate": 4.906417112299466e-05, "loss": 1.6142343282699585, "step": 368 }, { "epoch": 0.031151398752677733, "grad_norm": 0.1767578125, "learning_rate": 4.919786096256685e-05, "loss": 1.6298370361328125, "step": 369 }, { "epoch": 0.03123581988750884, "grad_norm": 0.232421875, "learning_rate": 4.933155080213904e-05, "loss": 1.5820232629776, "step": 370 }, { "epoch": 0.03132024102233994, "grad_norm": 0.16015625, "learning_rate": 4.946524064171123e-05, "loss": 1.6089168787002563, "step": 371 }, { "epoch": 0.03140466215717105, "grad_norm": 0.16796875, "learning_rate": 4.959893048128342e-05, "loss": 1.5618541240692139, "step": 372 }, { "epoch": 0.03148908329200215, "grad_norm": 0.1728515625, "learning_rate": 4.973262032085561e-05, "loss": 1.5935381650924683, "step": 373 }, { "epoch": 0.03157350442683326, "grad_norm": 0.169921875, "learning_rate": 4.986631016042781e-05, "loss": 1.646912693977356, "step": 374 }, { "epoch": 0.031657925561664364, "grad_norm": 0.1787109375, "learning_rate": 5e-05, "loss": 1.647168517112732, "step": 375 }, { "epoch": 0.03174234669649547, "grad_norm": 0.2109375, "learning_rate": 4.9999999152469955e-05, "loss": 1.6908448934555054, "step": 376 }, { "epoch": 0.031826767831326576, "grad_norm": 0.1865234375, "learning_rate": 4.9999996609879875e-05, "loss": 1.6108005046844482, "step": 377 }, { "epoch": 0.031911188966157675, "grad_norm": 0.166015625, "learning_rate": 4.999999237222993e-05, "loss": 1.7013576030731201, "step": 378 }, { "epoch": 0.03199561010098878, "grad_norm": 0.193359375, "learning_rate": 4.999998643952042e-05, "loss": 1.6321340799331665, "step": 379 }, { "epoch": 0.032080031235819886, "grad_norm": 0.173828125, "learning_rate": 4.999997881175172e-05, "loss": 1.5991294384002686, "step": 380 }, { "epoch": 0.03216445237065099, "grad_norm": 0.2197265625, "learning_rate": 4.999996948892438e-05, "loss": 1.5656390190124512, "step": 381 }, { "epoch": 0.0322488735054821, "grad_norm": 0.2255859375, "learning_rate": 4.999995847103901e-05, "loss": 1.5711092948913574, "step": 382 }, { "epoch": 0.032333294640313204, "grad_norm": 0.2021484375, "learning_rate": 4.999994575809637e-05, "loss": 1.7250126600265503, "step": 383 }, { "epoch": 0.03241771577514431, "grad_norm": 0.185546875, "learning_rate": 4.9999931350097305e-05, "loss": 1.6777377128601074, "step": 384 }, { "epoch": 0.032502136909975415, "grad_norm": 0.1708984375, "learning_rate": 4.999991524704281e-05, "loss": 1.6000385284423828, "step": 385 }, { "epoch": 0.032586558044806514, "grad_norm": 0.25, "learning_rate": 4.999989744893396e-05, "loss": 1.6580829620361328, "step": 386 }, { "epoch": 0.03267097917963762, "grad_norm": 0.2177734375, "learning_rate": 4.999987795577198e-05, "loss": 1.6379798650741577, "step": 387 }, { "epoch": 0.032755400314468726, "grad_norm": 0.216796875, "learning_rate": 4.9999856767558185e-05, "loss": 1.6709696054458618, "step": 388 }, { "epoch": 0.03283982144929983, "grad_norm": 0.177734375, "learning_rate": 4.9999833884294e-05, "loss": 1.707483172416687, "step": 389 }, { "epoch": 0.03292424258413094, "grad_norm": 0.1787109375, "learning_rate": 4.9999809305980996e-05, "loss": 1.617606282234192, "step": 390 }, { "epoch": 0.03300866371896204, "grad_norm": 0.35546875, "learning_rate": 4.999978303262082e-05, "loss": 1.6143022775650024, "step": 391 }, { "epoch": 0.03309308485379315, "grad_norm": 0.1884765625, "learning_rate": 4.999975506421527e-05, "loss": 1.6086864471435547, "step": 392 }, { "epoch": 0.033177505988624255, "grad_norm": 0.201171875, "learning_rate": 4.999972540076623e-05, "loss": 1.6895543336868286, "step": 393 }, { "epoch": 0.033261927123455354, "grad_norm": 0.166015625, "learning_rate": 4.9999694042275725e-05, "loss": 1.5802457332611084, "step": 394 }, { "epoch": 0.03334634825828646, "grad_norm": 0.212890625, "learning_rate": 4.999966098874587e-05, "loss": 1.7272273302078247, "step": 395 }, { "epoch": 0.033430769393117565, "grad_norm": 0.205078125, "learning_rate": 4.9999626240178895e-05, "loss": 1.5807899236679077, "step": 396 }, { "epoch": 0.03351519052794867, "grad_norm": 0.154296875, "learning_rate": 4.9999589796577185e-05, "loss": 1.6195176839828491, "step": 397 }, { "epoch": 0.03359961166277978, "grad_norm": 0.1689453125, "learning_rate": 4.999955165794319e-05, "loss": 1.7861069440841675, "step": 398 }, { "epoch": 0.03368403279761088, "grad_norm": 0.166015625, "learning_rate": 4.99995118242795e-05, "loss": 1.5783746242523193, "step": 399 }, { "epoch": 0.03376845393244199, "grad_norm": 0.16015625, "learning_rate": 4.999947029558882e-05, "loss": 1.6338080167770386, "step": 400 }, { "epoch": 0.033852875067273094, "grad_norm": 0.17578125, "learning_rate": 4.999942707187396e-05, "loss": 1.5950722694396973, "step": 401 }, { "epoch": 0.0339372962021042, "grad_norm": 0.16796875, "learning_rate": 4.999938215313786e-05, "loss": 1.6279484033584595, "step": 402 }, { "epoch": 0.0340217173369353, "grad_norm": 0.1650390625, "learning_rate": 4.999933553938356e-05, "loss": 1.5851905345916748, "step": 403 }, { "epoch": 0.034106138471766405, "grad_norm": 0.2060546875, "learning_rate": 4.999928723061421e-05, "loss": 1.671072006225586, "step": 404 }, { "epoch": 0.03419055960659751, "grad_norm": 0.18359375, "learning_rate": 4.999923722683311e-05, "loss": 1.6361126899719238, "step": 405 }, { "epoch": 0.034274980741428616, "grad_norm": 0.177734375, "learning_rate": 4.9999185528043625e-05, "loss": 1.7074302434921265, "step": 406 }, { "epoch": 0.03435940187625972, "grad_norm": 0.166015625, "learning_rate": 4.999913213424927e-05, "loss": 1.6302869319915771, "step": 407 }, { "epoch": 0.03444382301109083, "grad_norm": 0.2216796875, "learning_rate": 4.999907704545367e-05, "loss": 1.5708085298538208, "step": 408 }, { "epoch": 0.034528244145921934, "grad_norm": 0.166015625, "learning_rate": 4.9999020261660554e-05, "loss": 1.6435413360595703, "step": 409 }, { "epoch": 0.03461266528075304, "grad_norm": 0.1796875, "learning_rate": 4.999896178287378e-05, "loss": 1.6925349235534668, "step": 410 }, { "epoch": 0.03469708641558414, "grad_norm": 0.2236328125, "learning_rate": 4.99989016090973e-05, "loss": 1.712814450263977, "step": 411 }, { "epoch": 0.034781507550415244, "grad_norm": 0.1689453125, "learning_rate": 4.999883974033521e-05, "loss": 1.6848944425582886, "step": 412 }, { "epoch": 0.03486592868524635, "grad_norm": 0.162109375, "learning_rate": 4.9998776176591686e-05, "loss": 1.7230862379074097, "step": 413 }, { "epoch": 0.034950349820077456, "grad_norm": 0.2021484375, "learning_rate": 4.999871091787106e-05, "loss": 1.6065634489059448, "step": 414 }, { "epoch": 0.03503477095490856, "grad_norm": 0.166015625, "learning_rate": 4.9998643964177736e-05, "loss": 1.5686445236206055, "step": 415 }, { "epoch": 0.03511919208973967, "grad_norm": 0.2001953125, "learning_rate": 4.999857531551626e-05, "loss": 1.6673470735549927, "step": 416 }, { "epoch": 0.03520361322457077, "grad_norm": 0.181640625, "learning_rate": 4.99985049718913e-05, "loss": 1.6607754230499268, "step": 417 }, { "epoch": 0.03528803435940188, "grad_norm": 0.173828125, "learning_rate": 4.99984329333076e-05, "loss": 1.5891169309616089, "step": 418 }, { "epoch": 0.03537245549423298, "grad_norm": 0.173828125, "learning_rate": 4.999835919977007e-05, "loss": 1.6083825826644897, "step": 419 }, { "epoch": 0.035456876629064084, "grad_norm": 0.173828125, "learning_rate": 4.99982837712837e-05, "loss": 1.560625433921814, "step": 420 }, { "epoch": 0.03554129776389519, "grad_norm": 0.1591796875, "learning_rate": 4.99982066478536e-05, "loss": 1.5845134258270264, "step": 421 }, { "epoch": 0.035625718898726295, "grad_norm": 0.2138671875, "learning_rate": 4.9998127829485e-05, "loss": 1.6090176105499268, "step": 422 }, { "epoch": 0.0357101400335574, "grad_norm": 0.171875, "learning_rate": 4.999804731618324e-05, "loss": 1.6487338542938232, "step": 423 }, { "epoch": 0.03579456116838851, "grad_norm": 0.1865234375, "learning_rate": 4.9997965107953796e-05, "loss": 1.6026346683502197, "step": 424 }, { "epoch": 0.03587898230321961, "grad_norm": 0.2890625, "learning_rate": 4.999788120480222e-05, "loss": 1.6471757888793945, "step": 425 }, { "epoch": 0.03596340343805072, "grad_norm": 0.2177734375, "learning_rate": 4.999779560673421e-05, "loss": 1.7442162036895752, "step": 426 }, { "epoch": 0.03604782457288182, "grad_norm": 0.1796875, "learning_rate": 4.999770831375558e-05, "loss": 1.670325517654419, "step": 427 }, { "epoch": 0.03613224570771292, "grad_norm": 0.3359375, "learning_rate": 4.999761932587224e-05, "loss": 1.638523817062378, "step": 428 }, { "epoch": 0.03621666684254403, "grad_norm": 0.271484375, "learning_rate": 4.9997528643090216e-05, "loss": 1.6496593952178955, "step": 429 }, { "epoch": 0.036301087977375135, "grad_norm": 0.15234375, "learning_rate": 4.999743626541566e-05, "loss": 1.6297506093978882, "step": 430 }, { "epoch": 0.03638550911220624, "grad_norm": 0.22265625, "learning_rate": 4.999734219285486e-05, "loss": 1.6009860038757324, "step": 431 }, { "epoch": 0.03646993024703735, "grad_norm": 0.17578125, "learning_rate": 4.9997246425414155e-05, "loss": 1.6040416955947876, "step": 432 }, { "epoch": 0.03655435138186845, "grad_norm": 0.21875, "learning_rate": 4.999714896310006e-05, "loss": 1.623840570449829, "step": 433 }, { "epoch": 0.03663877251669956, "grad_norm": 0.2138671875, "learning_rate": 4.9997049805919184e-05, "loss": 1.5443058013916016, "step": 434 }, { "epoch": 0.036723193651530664, "grad_norm": 0.1650390625, "learning_rate": 4.999694895387824e-05, "loss": 1.5645354986190796, "step": 435 }, { "epoch": 0.03680761478636176, "grad_norm": 0.1845703125, "learning_rate": 4.999684640698408e-05, "loss": 1.6609272956848145, "step": 436 }, { "epoch": 0.03689203592119287, "grad_norm": 0.150390625, "learning_rate": 4.999674216524364e-05, "loss": 1.5747487545013428, "step": 437 }, { "epoch": 0.036976457056023974, "grad_norm": 0.162109375, "learning_rate": 4.9996636228664005e-05, "loss": 1.6016149520874023, "step": 438 }, { "epoch": 0.03706087819085508, "grad_norm": 0.1591796875, "learning_rate": 4.999652859725235e-05, "loss": 1.574514389038086, "step": 439 }, { "epoch": 0.037145299325686186, "grad_norm": 0.1630859375, "learning_rate": 4.999641927101597e-05, "loss": 1.642641544342041, "step": 440 }, { "epoch": 0.03722972046051729, "grad_norm": 0.1904296875, "learning_rate": 4.999630824996228e-05, "loss": 1.6668645143508911, "step": 441 }, { "epoch": 0.0373141415953484, "grad_norm": 0.16796875, "learning_rate": 4.999619553409881e-05, "loss": 1.6570793390274048, "step": 442 }, { "epoch": 0.0373985627301795, "grad_norm": 0.17578125, "learning_rate": 4.9996081123433194e-05, "loss": 1.5708426237106323, "step": 443 }, { "epoch": 0.0374829838650106, "grad_norm": 0.166015625, "learning_rate": 4.99959650179732e-05, "loss": 1.5874372720718384, "step": 444 }, { "epoch": 0.03756740499984171, "grad_norm": 0.1689453125, "learning_rate": 4.999584721772669e-05, "loss": 1.6510897874832153, "step": 445 }, { "epoch": 0.037651826134672814, "grad_norm": 0.16796875, "learning_rate": 4.999572772270166e-05, "loss": 1.654332160949707, "step": 446 }, { "epoch": 0.03773624726950392, "grad_norm": 0.19140625, "learning_rate": 4.99956065329062e-05, "loss": 1.5029308795928955, "step": 447 }, { "epoch": 0.037820668404335026, "grad_norm": 0.1640625, "learning_rate": 4.999548364834855e-05, "loss": 1.6114341020584106, "step": 448 }, { "epoch": 0.03790508953916613, "grad_norm": 0.2138671875, "learning_rate": 4.999535906903702e-05, "loss": 1.687586784362793, "step": 449 }, { "epoch": 0.03798951067399724, "grad_norm": 0.15234375, "learning_rate": 4.999523279498006e-05, "loss": 1.6075860261917114, "step": 450 }, { "epoch": 0.03807393180882834, "grad_norm": 0.203125, "learning_rate": 4.999510482618624e-05, "loss": 1.5738216638565063, "step": 451 }, { "epoch": 0.03815835294365944, "grad_norm": 0.158203125, "learning_rate": 4.9994975162664244e-05, "loss": 1.6063048839569092, "step": 452 }, { "epoch": 0.03824277407849055, "grad_norm": 0.1611328125, "learning_rate": 4.999484380442284e-05, "loss": 1.6410285234451294, "step": 453 }, { "epoch": 0.03832719521332165, "grad_norm": 0.1650390625, "learning_rate": 4.9994710751470946e-05, "loss": 1.572738766670227, "step": 454 }, { "epoch": 0.03841161634815276, "grad_norm": 0.1806640625, "learning_rate": 4.999457600381758e-05, "loss": 1.5742180347442627, "step": 455 }, { "epoch": 0.038496037482983865, "grad_norm": 0.166015625, "learning_rate": 4.999443956147189e-05, "loss": 1.663893461227417, "step": 456 }, { "epoch": 0.03858045861781497, "grad_norm": 0.1689453125, "learning_rate": 4.999430142444313e-05, "loss": 1.6465950012207031, "step": 457 }, { "epoch": 0.03866487975264608, "grad_norm": 0.1669921875, "learning_rate": 4.9994161592740636e-05, "loss": 1.606226921081543, "step": 458 }, { "epoch": 0.03874930088747718, "grad_norm": 0.18359375, "learning_rate": 4.999402006637391e-05, "loss": 1.5371336936950684, "step": 459 }, { "epoch": 0.03883372202230829, "grad_norm": 0.1875, "learning_rate": 4.999387684535255e-05, "loss": 1.6241360902786255, "step": 460 }, { "epoch": 0.03891814315713939, "grad_norm": 0.1787109375, "learning_rate": 4.999373192968626e-05, "loss": 1.5835801362991333, "step": 461 }, { "epoch": 0.03900256429197049, "grad_norm": 0.17578125, "learning_rate": 4.999358531938487e-05, "loss": 1.6126748323440552, "step": 462 }, { "epoch": 0.0390869854268016, "grad_norm": 0.1728515625, "learning_rate": 4.999343701445832e-05, "loss": 1.6927599906921387, "step": 463 }, { "epoch": 0.039171406561632705, "grad_norm": 0.1513671875, "learning_rate": 4.999328701491667e-05, "loss": 1.50872802734375, "step": 464 }, { "epoch": 0.03925582769646381, "grad_norm": 0.16796875, "learning_rate": 4.999313532077007e-05, "loss": 1.597665548324585, "step": 465 }, { "epoch": 0.039340248831294916, "grad_norm": 0.1494140625, "learning_rate": 4.999298193202883e-05, "loss": 1.6973309516906738, "step": 466 }, { "epoch": 0.03942466996612602, "grad_norm": 0.197265625, "learning_rate": 4.9992826848703335e-05, "loss": 1.6154022216796875, "step": 467 }, { "epoch": 0.03950909110095713, "grad_norm": 0.2451171875, "learning_rate": 4.9992670070804105e-05, "loss": 1.6378440856933594, "step": 468 }, { "epoch": 0.03959351223578823, "grad_norm": 0.1640625, "learning_rate": 4.999251159834177e-05, "loss": 1.6173133850097656, "step": 469 }, { "epoch": 0.03967793337061933, "grad_norm": 0.173828125, "learning_rate": 4.999235143132708e-05, "loss": 1.6918542385101318, "step": 470 }, { "epoch": 0.03976235450545044, "grad_norm": 0.2138671875, "learning_rate": 4.999218956977088e-05, "loss": 1.617885947227478, "step": 471 }, { "epoch": 0.039846775640281544, "grad_norm": 0.1640625, "learning_rate": 4.9992026013684166e-05, "loss": 1.6793427467346191, "step": 472 }, { "epoch": 0.03993119677511265, "grad_norm": 0.220703125, "learning_rate": 4.9991860763078005e-05, "loss": 1.4857052564620972, "step": 473 }, { "epoch": 0.040015617909943756, "grad_norm": 0.203125, "learning_rate": 4.9991693817963615e-05, "loss": 1.5985982418060303, "step": 474 }, { "epoch": 0.04010003904477486, "grad_norm": 0.1708984375, "learning_rate": 4.9991525178352314e-05, "loss": 1.5973824262619019, "step": 475 }, { "epoch": 0.04018446017960597, "grad_norm": 0.1533203125, "learning_rate": 4.999135484425553e-05, "loss": 1.6387345790863037, "step": 476 }, { "epoch": 0.040268881314437066, "grad_norm": 0.21875, "learning_rate": 4.999118281568482e-05, "loss": 1.5671336650848389, "step": 477 }, { "epoch": 0.04035330244926817, "grad_norm": 0.2216796875, "learning_rate": 4.999100909265184e-05, "loss": 1.647403359413147, "step": 478 }, { "epoch": 0.04043772358409928, "grad_norm": 0.212890625, "learning_rate": 4.999083367516838e-05, "loss": 1.6478052139282227, "step": 479 }, { "epoch": 0.040522144718930384, "grad_norm": 0.1640625, "learning_rate": 4.999065656324632e-05, "loss": 1.5961257219314575, "step": 480 }, { "epoch": 0.04060656585376149, "grad_norm": 0.173828125, "learning_rate": 4.999047775689768e-05, "loss": 1.6769834756851196, "step": 481 }, { "epoch": 0.040690986988592595, "grad_norm": 0.1630859375, "learning_rate": 4.999029725613458e-05, "loss": 1.6079161167144775, "step": 482 }, { "epoch": 0.0407754081234237, "grad_norm": 0.224609375, "learning_rate": 4.999011506096926e-05, "loss": 1.5912724733352661, "step": 483 }, { "epoch": 0.04085982925825481, "grad_norm": 0.212890625, "learning_rate": 4.9989931171414056e-05, "loss": 1.5996240377426147, "step": 484 }, { "epoch": 0.04094425039308591, "grad_norm": 0.1640625, "learning_rate": 4.998974558748146e-05, "loss": 1.587320327758789, "step": 485 }, { "epoch": 0.04102867152791701, "grad_norm": 0.150390625, "learning_rate": 4.9989558309184046e-05, "loss": 1.5694639682769775, "step": 486 }, { "epoch": 0.04111309266274812, "grad_norm": 0.158203125, "learning_rate": 4.9989369336534506e-05, "loss": 1.6364160776138306, "step": 487 }, { "epoch": 0.04119751379757922, "grad_norm": 0.1962890625, "learning_rate": 4.998917866954567e-05, "loss": 1.5209298133850098, "step": 488 }, { "epoch": 0.04128193493241033, "grad_norm": 0.1572265625, "learning_rate": 4.9988986308230445e-05, "loss": 1.5801811218261719, "step": 489 }, { "epoch": 0.041366356067241435, "grad_norm": 0.2177734375, "learning_rate": 4.9988792252601884e-05, "loss": 1.6423038244247437, "step": 490 }, { "epoch": 0.04145077720207254, "grad_norm": 0.158203125, "learning_rate": 4.9988596502673146e-05, "loss": 1.62470281124115, "step": 491 }, { "epoch": 0.041535198336903646, "grad_norm": 0.1767578125, "learning_rate": 4.99883990584575e-05, "loss": 1.6116652488708496, "step": 492 }, { "epoch": 0.04161961947173475, "grad_norm": 0.15234375, "learning_rate": 4.9988199919968326e-05, "loss": 1.5447746515274048, "step": 493 }, { "epoch": 0.04170404060656585, "grad_norm": 0.1796875, "learning_rate": 4.998799908721914e-05, "loss": 1.6105908155441284, "step": 494 }, { "epoch": 0.04178846174139696, "grad_norm": 0.1552734375, "learning_rate": 4.998779656022355e-05, "loss": 1.5833240747451782, "step": 495 }, { "epoch": 0.04187288287622806, "grad_norm": 0.2099609375, "learning_rate": 4.99875923389953e-05, "loss": 1.6046719551086426, "step": 496 }, { "epoch": 0.04195730401105917, "grad_norm": 0.162109375, "learning_rate": 4.9987386423548224e-05, "loss": 1.6445509195327759, "step": 497 }, { "epoch": 0.042041725145890274, "grad_norm": 0.1591796875, "learning_rate": 4.998717881389628e-05, "loss": 1.5743871927261353, "step": 498 }, { "epoch": 0.04212614628072138, "grad_norm": 0.1513671875, "learning_rate": 4.998696951005355e-05, "loss": 1.5873903036117554, "step": 499 }, { "epoch": 0.042210567415552486, "grad_norm": 0.1669921875, "learning_rate": 4.9986758512034235e-05, "loss": 1.623517632484436, "step": 500 }, { "epoch": 0.04229498855038359, "grad_norm": 0.1611328125, "learning_rate": 4.9986545819852625e-05, "loss": 1.6880600452423096, "step": 501 }, { "epoch": 0.04237940968521469, "grad_norm": 0.162109375, "learning_rate": 4.9986331433523156e-05, "loss": 1.5910546779632568, "step": 502 }, { "epoch": 0.042463830820045796, "grad_norm": 0.185546875, "learning_rate": 4.998611535306035e-05, "loss": 1.6281813383102417, "step": 503 }, { "epoch": 0.0425482519548769, "grad_norm": 0.1357421875, "learning_rate": 4.998589757847887e-05, "loss": 1.5819835662841797, "step": 504 }, { "epoch": 0.04263267308970801, "grad_norm": 0.169921875, "learning_rate": 4.9985678109793466e-05, "loss": 1.7049564123153687, "step": 505 }, { "epoch": 0.042717094224539114, "grad_norm": 0.1767578125, "learning_rate": 4.998545694701904e-05, "loss": 1.6109203100204468, "step": 506 }, { "epoch": 0.04280151535937022, "grad_norm": 0.20703125, "learning_rate": 4.998523409017057e-05, "loss": 1.6457691192626953, "step": 507 }, { "epoch": 0.042885936494201325, "grad_norm": 0.1572265625, "learning_rate": 4.9985009539263175e-05, "loss": 1.646790862083435, "step": 508 }, { "epoch": 0.04297035762903243, "grad_norm": 0.162109375, "learning_rate": 4.998478329431208e-05, "loss": 1.6524535417556763, "step": 509 }, { "epoch": 0.04305477876386353, "grad_norm": 0.2578125, "learning_rate": 4.9984555355332604e-05, "loss": 1.6112817525863647, "step": 510 }, { "epoch": 0.043139199898694636, "grad_norm": 0.1962890625, "learning_rate": 4.998432572234024e-05, "loss": 1.6453421115875244, "step": 511 }, { "epoch": 0.04322362103352574, "grad_norm": 0.17578125, "learning_rate": 4.998409439535053e-05, "loss": 1.6371428966522217, "step": 512 }, { "epoch": 0.04330804216835685, "grad_norm": 0.21484375, "learning_rate": 4.998386137437917e-05, "loss": 1.65333890914917, "step": 513 }, { "epoch": 0.04339246330318795, "grad_norm": 0.1787109375, "learning_rate": 4.9983626659441954e-05, "loss": 1.6345890760421753, "step": 514 }, { "epoch": 0.04347688443801906, "grad_norm": 0.166015625, "learning_rate": 4.99833902505548e-05, "loss": 1.5610089302062988, "step": 515 }, { "epoch": 0.043561305572850165, "grad_norm": 0.232421875, "learning_rate": 4.998315214773373e-05, "loss": 1.5980216264724731, "step": 516 }, { "epoch": 0.04364572670768127, "grad_norm": 0.17578125, "learning_rate": 4.9982912350994887e-05, "loss": 1.616779088973999, "step": 517 }, { "epoch": 0.043730147842512376, "grad_norm": 0.1669921875, "learning_rate": 4.998267086035454e-05, "loss": 1.571217656135559, "step": 518 }, { "epoch": 0.043814568977343475, "grad_norm": 0.1572265625, "learning_rate": 4.998242767582907e-05, "loss": 1.643623948097229, "step": 519 }, { "epoch": 0.04389899011217458, "grad_norm": 0.1455078125, "learning_rate": 4.998218279743494e-05, "loss": 1.5300320386886597, "step": 520 }, { "epoch": 0.04398341124700569, "grad_norm": 0.2021484375, "learning_rate": 4.998193622518877e-05, "loss": 1.6066581010818481, "step": 521 }, { "epoch": 0.04406783238183679, "grad_norm": 0.19140625, "learning_rate": 4.998168795910728e-05, "loss": 1.5467736721038818, "step": 522 }, { "epoch": 0.0441522535166679, "grad_norm": 0.1611328125, "learning_rate": 4.998143799920729e-05, "loss": 1.594221830368042, "step": 523 }, { "epoch": 0.044236674651499004, "grad_norm": 0.181640625, "learning_rate": 4.9981186345505766e-05, "loss": 1.6079282760620117, "step": 524 }, { "epoch": 0.04432109578633011, "grad_norm": 0.1748046875, "learning_rate": 4.998093299801976e-05, "loss": 1.6315739154815674, "step": 525 }, { "epoch": 0.044405516921161216, "grad_norm": 0.185546875, "learning_rate": 4.998067795676644e-05, "loss": 1.6526939868927002, "step": 526 }, { "epoch": 0.044489938055992315, "grad_norm": 0.185546875, "learning_rate": 4.9980421221763116e-05, "loss": 1.6944586038589478, "step": 527 }, { "epoch": 0.04457435919082342, "grad_norm": 0.1748046875, "learning_rate": 4.998016279302719e-05, "loss": 1.577286958694458, "step": 528 }, { "epoch": 0.044658780325654526, "grad_norm": 0.1591796875, "learning_rate": 4.997990267057618e-05, "loss": 1.5745923519134521, "step": 529 }, { "epoch": 0.04474320146048563, "grad_norm": 0.1962890625, "learning_rate": 4.997964085442772e-05, "loss": 1.5601844787597656, "step": 530 }, { "epoch": 0.04482762259531674, "grad_norm": 0.1640625, "learning_rate": 4.9979377344599574e-05, "loss": 1.6266376972198486, "step": 531 }, { "epoch": 0.044912043730147844, "grad_norm": 0.20703125, "learning_rate": 4.997911214110961e-05, "loss": 1.6555094718933105, "step": 532 }, { "epoch": 0.04499646486497895, "grad_norm": 0.1826171875, "learning_rate": 4.997884524397578e-05, "loss": 1.601851224899292, "step": 533 }, { "epoch": 0.045080885999810055, "grad_norm": 0.1513671875, "learning_rate": 4.9978576653216214e-05, "loss": 1.6198093891143799, "step": 534 }, { "epoch": 0.045165307134641154, "grad_norm": 0.15234375, "learning_rate": 4.997830636884911e-05, "loss": 1.5800427198410034, "step": 535 }, { "epoch": 0.04524972826947226, "grad_norm": 0.15625, "learning_rate": 4.997803439089279e-05, "loss": 1.6338483095169067, "step": 536 }, { "epoch": 0.045334149404303366, "grad_norm": 0.1484375, "learning_rate": 4.997776071936571e-05, "loss": 1.6084768772125244, "step": 537 }, { "epoch": 0.04541857053913447, "grad_norm": 0.1826171875, "learning_rate": 4.9977485354286404e-05, "loss": 1.7037640810012817, "step": 538 }, { "epoch": 0.04550299167396558, "grad_norm": 0.1806640625, "learning_rate": 4.997720829567355e-05, "loss": 1.6098676919937134, "step": 539 }, { "epoch": 0.04558741280879668, "grad_norm": 0.1806640625, "learning_rate": 4.997692954354594e-05, "loss": 1.4957362413406372, "step": 540 }, { "epoch": 0.04567183394362779, "grad_norm": 0.16015625, "learning_rate": 4.9976649097922476e-05, "loss": 1.5464318990707397, "step": 541 }, { "epoch": 0.045756255078458895, "grad_norm": 0.1689453125, "learning_rate": 4.9976366958822165e-05, "loss": 1.5551670789718628, "step": 542 }, { "epoch": 0.04584067621329, "grad_norm": 0.1640625, "learning_rate": 4.9976083126264136e-05, "loss": 1.5509132146835327, "step": 543 }, { "epoch": 0.0459250973481211, "grad_norm": 0.1630859375, "learning_rate": 4.997579760026764e-05, "loss": 1.5716795921325684, "step": 544 }, { "epoch": 0.046009518482952205, "grad_norm": 0.18359375, "learning_rate": 4.9975510380852024e-05, "loss": 1.619931936264038, "step": 545 }, { "epoch": 0.04609393961778331, "grad_norm": 0.1962890625, "learning_rate": 4.9975221468036776e-05, "loss": 1.6553831100463867, "step": 546 }, { "epoch": 0.04617836075261442, "grad_norm": 0.2041015625, "learning_rate": 4.9974930861841486e-05, "loss": 1.7082645893096924, "step": 547 }, { "epoch": 0.04626278188744552, "grad_norm": 0.2041015625, "learning_rate": 4.997463856228584e-05, "loss": 1.579378366470337, "step": 548 }, { "epoch": 0.04634720302227663, "grad_norm": 0.185546875, "learning_rate": 4.9974344569389676e-05, "loss": 1.5385243892669678, "step": 549 }, { "epoch": 0.046431624157107734, "grad_norm": 0.1865234375, "learning_rate": 4.997404888317292e-05, "loss": 1.6467984914779663, "step": 550 }, { "epoch": 0.04651604529193884, "grad_norm": 0.2001953125, "learning_rate": 4.997375150365562e-05, "loss": 1.638499140739441, "step": 551 }, { "epoch": 0.04660046642676994, "grad_norm": 0.17578125, "learning_rate": 4.997345243085794e-05, "loss": 1.5907526016235352, "step": 552 }, { "epoch": 0.046684887561601045, "grad_norm": 0.1845703125, "learning_rate": 4.9973151664800155e-05, "loss": 1.6034146547317505, "step": 553 }, { "epoch": 0.04676930869643215, "grad_norm": 0.1865234375, "learning_rate": 4.997284920550266e-05, "loss": 1.6385269165039062, "step": 554 }, { "epoch": 0.046853729831263256, "grad_norm": 0.1572265625, "learning_rate": 4.9972545052985956e-05, "loss": 1.6289095878601074, "step": 555 }, { "epoch": 0.04693815096609436, "grad_norm": 0.158203125, "learning_rate": 4.997223920727068e-05, "loss": 1.6038004159927368, "step": 556 }, { "epoch": 0.04702257210092547, "grad_norm": 0.216796875, "learning_rate": 4.997193166837756e-05, "loss": 1.5785092115402222, "step": 557 }, { "epoch": 0.047106993235756574, "grad_norm": 0.216796875, "learning_rate": 4.9971622436327435e-05, "loss": 1.610973834991455, "step": 558 }, { "epoch": 0.04719141437058768, "grad_norm": 0.1650390625, "learning_rate": 4.99713115111413e-05, "loss": 1.6048845052719116, "step": 559 }, { "epoch": 0.04727583550541878, "grad_norm": 0.16796875, "learning_rate": 4.997099889284021e-05, "loss": 1.5659550428390503, "step": 560 }, { "epoch": 0.047360256640249884, "grad_norm": 0.1767578125, "learning_rate": 4.997068458144539e-05, "loss": 1.6416534185409546, "step": 561 }, { "epoch": 0.04744467777508099, "grad_norm": 0.177734375, "learning_rate": 4.997036857697812e-05, "loss": 1.5856825113296509, "step": 562 }, { "epoch": 0.047529098909912096, "grad_norm": 0.1796875, "learning_rate": 4.997005087945984e-05, "loss": 1.5868322849273682, "step": 563 }, { "epoch": 0.0476135200447432, "grad_norm": 0.1611328125, "learning_rate": 4.9969731488912095e-05, "loss": 1.5188250541687012, "step": 564 }, { "epoch": 0.04769794117957431, "grad_norm": 0.1826171875, "learning_rate": 4.996941040535653e-05, "loss": 1.60282564163208, "step": 565 }, { "epoch": 0.04778236231440541, "grad_norm": 0.1572265625, "learning_rate": 4.9969087628814926e-05, "loss": 1.627384066581726, "step": 566 }, { "epoch": 0.04786678344923652, "grad_norm": 0.1611328125, "learning_rate": 4.9968763159309164e-05, "loss": 1.5880156755447388, "step": 567 }, { "epoch": 0.04795120458406762, "grad_norm": 0.1962890625, "learning_rate": 4.9968436996861244e-05, "loss": 1.5902949571609497, "step": 568 }, { "epoch": 0.048035625718898724, "grad_norm": 0.1884765625, "learning_rate": 4.9968109141493274e-05, "loss": 1.5562844276428223, "step": 569 }, { "epoch": 0.04812004685372983, "grad_norm": 0.1630859375, "learning_rate": 4.9967779593227496e-05, "loss": 1.5500397682189941, "step": 570 }, { "epoch": 0.048204467988560935, "grad_norm": 0.1640625, "learning_rate": 4.996744835208623e-05, "loss": 1.6231600046157837, "step": 571 }, { "epoch": 0.04828888912339204, "grad_norm": 0.1533203125, "learning_rate": 4.996711541809197e-05, "loss": 1.583062767982483, "step": 572 }, { "epoch": 0.04837331025822315, "grad_norm": 0.158203125, "learning_rate": 4.996678079126726e-05, "loss": 1.6116145849227905, "step": 573 }, { "epoch": 0.04845773139305425, "grad_norm": 0.16015625, "learning_rate": 4.996644447163481e-05, "loss": 1.5846019983291626, "step": 574 }, { "epoch": 0.04854215252788536, "grad_norm": 0.16796875, "learning_rate": 4.996610645921741e-05, "loss": 1.6875287294387817, "step": 575 }, { "epoch": 0.048626573662716464, "grad_norm": 0.1650390625, "learning_rate": 4.996576675403798e-05, "loss": 1.7041023969650269, "step": 576 }, { "epoch": 0.04871099479754756, "grad_norm": 0.1533203125, "learning_rate": 4.9965425356119556e-05, "loss": 1.5766501426696777, "step": 577 }, { "epoch": 0.04879541593237867, "grad_norm": 0.1455078125, "learning_rate": 4.996508226548528e-05, "loss": 1.5641412734985352, "step": 578 }, { "epoch": 0.048879837067209775, "grad_norm": 0.1689453125, "learning_rate": 4.996473748215842e-05, "loss": 1.7050131559371948, "step": 579 }, { "epoch": 0.04896425820204088, "grad_norm": 0.1640625, "learning_rate": 4.996439100616235e-05, "loss": 1.6410311460494995, "step": 580 }, { "epoch": 0.049048679336871986, "grad_norm": 0.20703125, "learning_rate": 4.9964042837520564e-05, "loss": 1.5548278093338013, "step": 581 }, { "epoch": 0.04913310047170309, "grad_norm": 0.1572265625, "learning_rate": 4.996369297625667e-05, "loss": 1.5862805843353271, "step": 582 }, { "epoch": 0.0492175216065342, "grad_norm": 0.1669921875, "learning_rate": 4.996334142239438e-05, "loss": 1.5494872331619263, "step": 583 }, { "epoch": 0.049301942741365304, "grad_norm": 0.146484375, "learning_rate": 4.9962988175957545e-05, "loss": 1.661067247390747, "step": 584 }, { "epoch": 0.0493863638761964, "grad_norm": 0.1552734375, "learning_rate": 4.996263323697011e-05, "loss": 1.694993019104004, "step": 585 }, { "epoch": 0.04947078501102751, "grad_norm": 0.197265625, "learning_rate": 4.996227660545614e-05, "loss": 1.5963544845581055, "step": 586 }, { "epoch": 0.049555206145858614, "grad_norm": 0.158203125, "learning_rate": 4.996191828143981e-05, "loss": 1.6081085205078125, "step": 587 }, { "epoch": 0.04963962728068972, "grad_norm": 0.166015625, "learning_rate": 4.9961558264945426e-05, "loss": 1.633750319480896, "step": 588 }, { "epoch": 0.049724048415520826, "grad_norm": 0.15234375, "learning_rate": 4.996119655599739e-05, "loss": 1.5155572891235352, "step": 589 }, { "epoch": 0.04980846955035193, "grad_norm": 0.1640625, "learning_rate": 4.996083315462022e-05, "loss": 1.5940085649490356, "step": 590 }, { "epoch": 0.04989289068518304, "grad_norm": 0.1474609375, "learning_rate": 4.996046806083857e-05, "loss": 1.637359619140625, "step": 591 }, { "epoch": 0.04997731182001414, "grad_norm": 0.25390625, "learning_rate": 4.996010127467719e-05, "loss": 1.6361520290374756, "step": 592 }, { "epoch": 0.05006173295484524, "grad_norm": 0.166015625, "learning_rate": 4.9959732796160944e-05, "loss": 1.5755572319030762, "step": 593 }, { "epoch": 0.05014615408967635, "grad_norm": 0.1494140625, "learning_rate": 4.995936262531482e-05, "loss": 1.5762519836425781, "step": 594 }, { "epoch": 0.050230575224507454, "grad_norm": 0.1591796875, "learning_rate": 4.995899076216392e-05, "loss": 1.6167001724243164, "step": 595 }, { "epoch": 0.05031499635933856, "grad_norm": 0.1533203125, "learning_rate": 4.995861720673345e-05, "loss": 1.667899250984192, "step": 596 }, { "epoch": 0.050399417494169665, "grad_norm": 0.171875, "learning_rate": 4.995824195904874e-05, "loss": 1.5446314811706543, "step": 597 }, { "epoch": 0.05048383862900077, "grad_norm": 0.146484375, "learning_rate": 4.9957865019135236e-05, "loss": 1.6241257190704346, "step": 598 }, { "epoch": 0.05056825976383188, "grad_norm": 0.193359375, "learning_rate": 4.9957486387018494e-05, "loss": 1.6467264890670776, "step": 599 }, { "epoch": 0.05065268089866298, "grad_norm": 0.181640625, "learning_rate": 4.995710606272418e-05, "loss": 1.5515860319137573, "step": 600 }, { "epoch": 0.05073710203349409, "grad_norm": 0.16015625, "learning_rate": 4.995672404627809e-05, "loss": 1.6502290964126587, "step": 601 }, { "epoch": 0.05082152316832519, "grad_norm": 0.166015625, "learning_rate": 4.995634033770612e-05, "loss": 1.608381748199463, "step": 602 }, { "epoch": 0.05090594430315629, "grad_norm": 0.1669921875, "learning_rate": 4.9955954937034286e-05, "loss": 1.593355655670166, "step": 603 }, { "epoch": 0.0509903654379874, "grad_norm": 0.1572265625, "learning_rate": 4.995556784428872e-05, "loss": 1.6045453548431396, "step": 604 }, { "epoch": 0.051074786572818505, "grad_norm": 0.150390625, "learning_rate": 4.995517905949567e-05, "loss": 1.529528260231018, "step": 605 }, { "epoch": 0.05115920770764961, "grad_norm": 0.1533203125, "learning_rate": 4.99547885826815e-05, "loss": 1.543692708015442, "step": 606 }, { "epoch": 0.05124362884248072, "grad_norm": 0.17578125, "learning_rate": 4.995439641387267e-05, "loss": 1.5727996826171875, "step": 607 }, { "epoch": 0.05132804997731182, "grad_norm": 0.1689453125, "learning_rate": 4.995400255309579e-05, "loss": 1.650260329246521, "step": 608 }, { "epoch": 0.05141247111214293, "grad_norm": 0.15625, "learning_rate": 4.9953607000377555e-05, "loss": 1.5900590419769287, "step": 609 }, { "epoch": 0.05149689224697403, "grad_norm": 0.2060546875, "learning_rate": 4.9953209755744784e-05, "loss": 1.601644515991211, "step": 610 }, { "epoch": 0.05158131338180513, "grad_norm": 0.166015625, "learning_rate": 4.995281081922441e-05, "loss": 1.595787525177002, "step": 611 }, { "epoch": 0.05166573451663624, "grad_norm": 0.1572265625, "learning_rate": 4.995241019084348e-05, "loss": 1.620141863822937, "step": 612 }, { "epoch": 0.051750155651467344, "grad_norm": 0.154296875, "learning_rate": 4.995200787062917e-05, "loss": 1.5571637153625488, "step": 613 }, { "epoch": 0.05183457678629845, "grad_norm": 0.1513671875, "learning_rate": 4.995160385860875e-05, "loss": 1.5647047758102417, "step": 614 }, { "epoch": 0.051918997921129556, "grad_norm": 0.1943359375, "learning_rate": 4.995119815480961e-05, "loss": 1.6407194137573242, "step": 615 }, { "epoch": 0.05200341905596066, "grad_norm": 0.1630859375, "learning_rate": 4.9950790759259255e-05, "loss": 1.5389293432235718, "step": 616 }, { "epoch": 0.05208784019079177, "grad_norm": 0.15625, "learning_rate": 4.995038167198532e-05, "loss": 1.631372332572937, "step": 617 }, { "epoch": 0.052172261325622867, "grad_norm": 0.1650390625, "learning_rate": 4.994997089301553e-05, "loss": 1.5692945718765259, "step": 618 }, { "epoch": 0.05225668246045397, "grad_norm": 0.197265625, "learning_rate": 4.994955842237774e-05, "loss": 1.5684703588485718, "step": 619 }, { "epoch": 0.05234110359528508, "grad_norm": 0.1572265625, "learning_rate": 4.9949144260099925e-05, "loss": 1.5181894302368164, "step": 620 }, { "epoch": 0.052425524730116184, "grad_norm": 0.1591796875, "learning_rate": 4.9948728406210156e-05, "loss": 1.5687142610549927, "step": 621 }, { "epoch": 0.05250994586494729, "grad_norm": 0.169921875, "learning_rate": 4.994831086073663e-05, "loss": 1.6147935390472412, "step": 622 }, { "epoch": 0.052594366999778396, "grad_norm": 0.16015625, "learning_rate": 4.994789162370767e-05, "loss": 1.5937262773513794, "step": 623 }, { "epoch": 0.0526787881346095, "grad_norm": 0.162109375, "learning_rate": 4.994747069515168e-05, "loss": 1.5212535858154297, "step": 624 }, { "epoch": 0.05276320926944061, "grad_norm": 0.162109375, "learning_rate": 4.994704807509721e-05, "loss": 1.6661145687103271, "step": 625 }, { "epoch": 0.052847630404271706, "grad_norm": 0.1572265625, "learning_rate": 4.994662376357292e-05, "loss": 1.6154965162277222, "step": 626 }, { "epoch": 0.05293205153910281, "grad_norm": 0.1455078125, "learning_rate": 4.994619776060757e-05, "loss": 1.5733472108840942, "step": 627 }, { "epoch": 0.05301647267393392, "grad_norm": 0.1591796875, "learning_rate": 4.994577006623006e-05, "loss": 1.697629451751709, "step": 628 }, { "epoch": 0.05310089380876502, "grad_norm": 0.162109375, "learning_rate": 4.994534068046937e-05, "loss": 1.523598551750183, "step": 629 }, { "epoch": 0.05318531494359613, "grad_norm": 0.140625, "learning_rate": 4.9944909603354614e-05, "loss": 1.5913676023483276, "step": 630 }, { "epoch": 0.053269736078427235, "grad_norm": 0.181640625, "learning_rate": 4.994447683491505e-05, "loss": 1.655526876449585, "step": 631 }, { "epoch": 0.05335415721325834, "grad_norm": 0.1533203125, "learning_rate": 4.994404237517998e-05, "loss": 1.5853296518325806, "step": 632 }, { "epoch": 0.05343857834808945, "grad_norm": 0.17578125, "learning_rate": 4.9943606224178874e-05, "loss": 1.6100014448165894, "step": 633 }, { "epoch": 0.05352299948292055, "grad_norm": 0.1728515625, "learning_rate": 4.994316838194132e-05, "loss": 1.6493096351623535, "step": 634 }, { "epoch": 0.05360742061775165, "grad_norm": 0.1474609375, "learning_rate": 4.9942728848496995e-05, "loss": 1.538409948348999, "step": 635 }, { "epoch": 0.05369184175258276, "grad_norm": 0.1533203125, "learning_rate": 4.9942287623875696e-05, "loss": 1.5832620859146118, "step": 636 }, { "epoch": 0.05377626288741386, "grad_norm": 0.1962890625, "learning_rate": 4.9941844708107344e-05, "loss": 1.5834059715270996, "step": 637 }, { "epoch": 0.05386068402224497, "grad_norm": 0.1640625, "learning_rate": 4.994140010122197e-05, "loss": 1.6195523738861084, "step": 638 }, { "epoch": 0.053945105157076075, "grad_norm": 0.1494140625, "learning_rate": 4.994095380324971e-05, "loss": 1.4997708797454834, "step": 639 }, { "epoch": 0.05402952629190718, "grad_norm": 0.1826171875, "learning_rate": 4.9940505814220843e-05, "loss": 1.6843256950378418, "step": 640 }, { "epoch": 0.054113947426738286, "grad_norm": 0.154296875, "learning_rate": 4.994005613416573e-05, "loss": 1.6339000463485718, "step": 641 }, { "epoch": 0.05419836856156939, "grad_norm": 0.1630859375, "learning_rate": 4.993960476311486e-05, "loss": 1.6087794303894043, "step": 642 }, { "epoch": 0.05428278969640049, "grad_norm": 0.15625, "learning_rate": 4.9939151701098844e-05, "loss": 1.583433747291565, "step": 643 }, { "epoch": 0.0543672108312316, "grad_norm": 0.16015625, "learning_rate": 4.993869694814839e-05, "loss": 1.5689761638641357, "step": 644 }, { "epoch": 0.0544516319660627, "grad_norm": 0.15234375, "learning_rate": 4.9938240504294345e-05, "loss": 1.632717490196228, "step": 645 }, { "epoch": 0.05453605310089381, "grad_norm": 0.1708984375, "learning_rate": 4.993778236956765e-05, "loss": 1.5718660354614258, "step": 646 }, { "epoch": 0.054620474235724914, "grad_norm": 0.166015625, "learning_rate": 4.993732254399936e-05, "loss": 1.6095823049545288, "step": 647 }, { "epoch": 0.05470489537055602, "grad_norm": 0.1484375, "learning_rate": 4.9936861027620667e-05, "loss": 1.5716655254364014, "step": 648 }, { "epoch": 0.054789316505387126, "grad_norm": 0.1630859375, "learning_rate": 4.9936397820462856e-05, "loss": 1.5668543577194214, "step": 649 }, { "epoch": 0.05487373764021823, "grad_norm": 0.1611328125, "learning_rate": 4.993593292255733e-05, "loss": 1.5562334060668945, "step": 650 }, { "epoch": 0.05495815877504933, "grad_norm": 0.1640625, "learning_rate": 4.993546633393562e-05, "loss": 1.5765010118484497, "step": 651 }, { "epoch": 0.055042579909880436, "grad_norm": 0.1513671875, "learning_rate": 4.993499805462935e-05, "loss": 1.5558613538742065, "step": 652 }, { "epoch": 0.05512700104471154, "grad_norm": 0.1494140625, "learning_rate": 4.993452808467027e-05, "loss": 1.6140116453170776, "step": 653 }, { "epoch": 0.05521142217954265, "grad_norm": 0.15625, "learning_rate": 4.993405642409027e-05, "loss": 1.624215006828308, "step": 654 }, { "epoch": 0.055295843314373753, "grad_norm": 0.1748046875, "learning_rate": 4.9933583072921296e-05, "loss": 1.6595280170440674, "step": 655 }, { "epoch": 0.05538026444920486, "grad_norm": 0.1611328125, "learning_rate": 4.9933108031195464e-05, "loss": 1.5326616764068604, "step": 656 }, { "epoch": 0.055464685584035965, "grad_norm": 0.1591796875, "learning_rate": 4.9932631298944966e-05, "loss": 1.676175832748413, "step": 657 }, { "epoch": 0.05554910671886707, "grad_norm": 0.16796875, "learning_rate": 4.9932152876202144e-05, "loss": 1.6377794742584229, "step": 658 }, { "epoch": 0.05563352785369818, "grad_norm": 0.1474609375, "learning_rate": 4.9931672762999424e-05, "loss": 1.572467565536499, "step": 659 }, { "epoch": 0.055717948988529276, "grad_norm": 0.1689453125, "learning_rate": 4.993119095936937e-05, "loss": 1.5958118438720703, "step": 660 }, { "epoch": 0.05580237012336038, "grad_norm": 0.1572265625, "learning_rate": 4.993070746534464e-05, "loss": 1.5777391195297241, "step": 661 }, { "epoch": 0.05588679125819149, "grad_norm": 0.1845703125, "learning_rate": 4.9930222280958015e-05, "loss": 1.5738435983657837, "step": 662 }, { "epoch": 0.05597121239302259, "grad_norm": 0.20703125, "learning_rate": 4.9929735406242395e-05, "loss": 1.6539490222930908, "step": 663 }, { "epoch": 0.0560556335278537, "grad_norm": 0.1640625, "learning_rate": 4.9929246841230794e-05, "loss": 1.6041362285614014, "step": 664 }, { "epoch": 0.056140054662684805, "grad_norm": 0.1904296875, "learning_rate": 4.9928756585956334e-05, "loss": 1.5856208801269531, "step": 665 }, { "epoch": 0.05622447579751591, "grad_norm": 0.1669921875, "learning_rate": 4.9928264640452246e-05, "loss": 1.6221308708190918, "step": 666 }, { "epoch": 0.056308896932347016, "grad_norm": 0.1611328125, "learning_rate": 4.992777100475191e-05, "loss": 1.6622532606124878, "step": 667 }, { "epoch": 0.056393318067178115, "grad_norm": 0.203125, "learning_rate": 4.992727567888878e-05, "loss": 1.5967732667922974, "step": 668 }, { "epoch": 0.05647773920200922, "grad_norm": 0.212890625, "learning_rate": 4.992677866289644e-05, "loss": 1.61140775680542, "step": 669 }, { "epoch": 0.05656216033684033, "grad_norm": 0.177734375, "learning_rate": 4.9926279956808586e-05, "loss": 1.6024420261383057, "step": 670 }, { "epoch": 0.05664658147167143, "grad_norm": 0.166015625, "learning_rate": 4.992577956065904e-05, "loss": 1.6508376598358154, "step": 671 }, { "epoch": 0.05673100260650254, "grad_norm": 0.1533203125, "learning_rate": 4.9925277474481726e-05, "loss": 1.612852692604065, "step": 672 }, { "epoch": 0.056815423741333644, "grad_norm": 0.158203125, "learning_rate": 4.992477369831069e-05, "loss": 1.6076043844223022, "step": 673 }, { "epoch": 0.05689984487616475, "grad_norm": 0.177734375, "learning_rate": 4.9924268232180084e-05, "loss": 1.5173777341842651, "step": 674 }, { "epoch": 0.056984266010995856, "grad_norm": 0.2216796875, "learning_rate": 4.992376107612418e-05, "loss": 1.5410168170928955, "step": 675 }, { "epoch": 0.057068687145826955, "grad_norm": 0.1728515625, "learning_rate": 4.992325223017737e-05, "loss": 1.5897005796432495, "step": 676 }, { "epoch": 0.05715310828065806, "grad_norm": 0.1494140625, "learning_rate": 4.9922741694374145e-05, "loss": 1.7125482559204102, "step": 677 }, { "epoch": 0.057237529415489166, "grad_norm": 0.1826171875, "learning_rate": 4.9922229468749125e-05, "loss": 1.6056625843048096, "step": 678 }, { "epoch": 0.05732195055032027, "grad_norm": 0.1435546875, "learning_rate": 4.992171555333705e-05, "loss": 1.5780582427978516, "step": 679 }, { "epoch": 0.05740637168515138, "grad_norm": 0.201171875, "learning_rate": 4.992119994817275e-05, "loss": 1.620453119277954, "step": 680 }, { "epoch": 0.057490792819982484, "grad_norm": 0.1767578125, "learning_rate": 4.99206826532912e-05, "loss": 1.6043634414672852, "step": 681 }, { "epoch": 0.05757521395481359, "grad_norm": 0.173828125, "learning_rate": 4.9920163668727446e-05, "loss": 1.5759450197219849, "step": 682 }, { "epoch": 0.057659635089644695, "grad_norm": 0.1875, "learning_rate": 4.9919642994516715e-05, "loss": 1.537148356437683, "step": 683 }, { "epoch": 0.057744056224475794, "grad_norm": 0.1552734375, "learning_rate": 4.9919120630694284e-05, "loss": 1.6395654678344727, "step": 684 }, { "epoch": 0.0578284773593069, "grad_norm": 0.1396484375, "learning_rate": 4.991859657729557e-05, "loss": 1.5584957599639893, "step": 685 }, { "epoch": 0.057912898494138006, "grad_norm": 0.1640625, "learning_rate": 4.991807083435612e-05, "loss": 1.5965428352355957, "step": 686 }, { "epoch": 0.05799731962896911, "grad_norm": 0.171875, "learning_rate": 4.9917543401911565e-05, "loss": 1.5047967433929443, "step": 687 }, { "epoch": 0.05808174076380022, "grad_norm": 0.15625, "learning_rate": 4.991701427999768e-05, "loss": 1.6437535285949707, "step": 688 }, { "epoch": 0.05816616189863132, "grad_norm": 0.1748046875, "learning_rate": 4.9916483468650335e-05, "loss": 1.6230201721191406, "step": 689 }, { "epoch": 0.05825058303346243, "grad_norm": 0.1640625, "learning_rate": 4.991595096790551e-05, "loss": 1.7175289392471313, "step": 690 }, { "epoch": 0.058335004168293535, "grad_norm": 0.1474609375, "learning_rate": 4.991541677779933e-05, "loss": 1.5670099258422852, "step": 691 }, { "epoch": 0.05841942530312464, "grad_norm": 0.171875, "learning_rate": 4.991488089836799e-05, "loss": 1.5329668521881104, "step": 692 }, { "epoch": 0.05850384643795574, "grad_norm": 0.17578125, "learning_rate": 4.991434332964785e-05, "loss": 1.5514776706695557, "step": 693 }, { "epoch": 0.058588267572786845, "grad_norm": 0.15625, "learning_rate": 4.991380407167534e-05, "loss": 1.5855871438980103, "step": 694 }, { "epoch": 0.05867268870761795, "grad_norm": 0.1474609375, "learning_rate": 4.991326312448704e-05, "loss": 1.5549472570419312, "step": 695 }, { "epoch": 0.05875710984244906, "grad_norm": 0.162109375, "learning_rate": 4.9912720488119604e-05, "loss": 1.5817338228225708, "step": 696 }, { "epoch": 0.05884153097728016, "grad_norm": 0.16015625, "learning_rate": 4.9912176162609835e-05, "loss": 1.5230989456176758, "step": 697 }, { "epoch": 0.05892595211211127, "grad_norm": 0.1572265625, "learning_rate": 4.9911630147994654e-05, "loss": 1.585750699043274, "step": 698 }, { "epoch": 0.059010373246942374, "grad_norm": 0.14453125, "learning_rate": 4.9911082444311066e-05, "loss": 1.5422899723052979, "step": 699 }, { "epoch": 0.05909479438177348, "grad_norm": 0.15234375, "learning_rate": 4.99105330515962e-05, "loss": 1.5393155813217163, "step": 700 }, { "epoch": 0.05917921551660458, "grad_norm": 0.1767578125, "learning_rate": 4.990998196988732e-05, "loss": 1.565571665763855, "step": 701 }, { "epoch": 0.059263636651435685, "grad_norm": 0.1513671875, "learning_rate": 4.990942919922179e-05, "loss": 1.5120567083358765, "step": 702 }, { "epoch": 0.05934805778626679, "grad_norm": 0.1884765625, "learning_rate": 4.990887473963709e-05, "loss": 1.620524525642395, "step": 703 }, { "epoch": 0.059432478921097896, "grad_norm": 0.1611328125, "learning_rate": 4.9908318591170796e-05, "loss": 1.5774177312850952, "step": 704 }, { "epoch": 0.059516900055929, "grad_norm": 0.138671875, "learning_rate": 4.9907760753860645e-05, "loss": 1.6243704557418823, "step": 705 }, { "epoch": 0.05960132119076011, "grad_norm": 0.1669921875, "learning_rate": 4.990720122774444e-05, "loss": 1.683653473854065, "step": 706 }, { "epoch": 0.059685742325591214, "grad_norm": 0.1455078125, "learning_rate": 4.990664001286012e-05, "loss": 1.5025489330291748, "step": 707 }, { "epoch": 0.05977016346042232, "grad_norm": 0.1455078125, "learning_rate": 4.990607710924574e-05, "loss": 1.6191861629486084, "step": 708 }, { "epoch": 0.05985458459525342, "grad_norm": 0.1484375, "learning_rate": 4.990551251693946e-05, "loss": 1.6455694437026978, "step": 709 }, { "epoch": 0.059939005730084524, "grad_norm": 0.1416015625, "learning_rate": 4.9904946235979574e-05, "loss": 1.5674538612365723, "step": 710 }, { "epoch": 0.06002342686491563, "grad_norm": 0.1689453125, "learning_rate": 4.9904378266404475e-05, "loss": 1.5876362323760986, "step": 711 }, { "epoch": 0.060107847999746736, "grad_norm": 0.150390625, "learning_rate": 4.9903808608252655e-05, "loss": 1.6776857376098633, "step": 712 }, { "epoch": 0.06019226913457784, "grad_norm": 0.138671875, "learning_rate": 4.990323726156275e-05, "loss": 1.5125263929367065, "step": 713 }, { "epoch": 0.06027669026940895, "grad_norm": 0.1484375, "learning_rate": 4.9902664226373506e-05, "loss": 1.6371386051177979, "step": 714 }, { "epoch": 0.06036111140424005, "grad_norm": 0.1669921875, "learning_rate": 4.990208950272377e-05, "loss": 1.6448794603347778, "step": 715 }, { "epoch": 0.06044553253907116, "grad_norm": 0.1669921875, "learning_rate": 4.990151309065251e-05, "loss": 1.5787657499313354, "step": 716 }, { "epoch": 0.060529953673902265, "grad_norm": 0.169921875, "learning_rate": 4.99009349901988e-05, "loss": 1.592373251914978, "step": 717 }, { "epoch": 0.060614374808733364, "grad_norm": 0.1630859375, "learning_rate": 4.990035520140185e-05, "loss": 1.667327642440796, "step": 718 }, { "epoch": 0.06069879594356447, "grad_norm": 0.1591796875, "learning_rate": 4.989977372430096e-05, "loss": 1.5910874605178833, "step": 719 }, { "epoch": 0.060783217078395575, "grad_norm": 0.166015625, "learning_rate": 4.9899190558935565e-05, "loss": 1.7205394506454468, "step": 720 }, { "epoch": 0.06086763821322668, "grad_norm": 0.15234375, "learning_rate": 4.9898605705345197e-05, "loss": 1.656476616859436, "step": 721 }, { "epoch": 0.06095205934805779, "grad_norm": 0.1474609375, "learning_rate": 4.989801916356952e-05, "loss": 1.6092019081115723, "step": 722 }, { "epoch": 0.06103648048288889, "grad_norm": 0.17578125, "learning_rate": 4.989743093364829e-05, "loss": 1.5741610527038574, "step": 723 }, { "epoch": 0.06112090161772, "grad_norm": 0.1572265625, "learning_rate": 4.98968410156214e-05, "loss": 1.6421408653259277, "step": 724 }, { "epoch": 0.061205322752551104, "grad_norm": 0.16015625, "learning_rate": 4.989624940952884e-05, "loss": 1.6553239822387695, "step": 725 }, { "epoch": 0.0612897438873822, "grad_norm": 0.1484375, "learning_rate": 4.989565611541073e-05, "loss": 1.582601547241211, "step": 726 }, { "epoch": 0.06137416502221331, "grad_norm": 0.15234375, "learning_rate": 4.9895061133307295e-05, "loss": 1.67678964138031, "step": 727 }, { "epoch": 0.061458586157044415, "grad_norm": 0.1552734375, "learning_rate": 4.9894464463258876e-05, "loss": 1.6871241331100464, "step": 728 }, { "epoch": 0.06154300729187552, "grad_norm": 0.1630859375, "learning_rate": 4.989386610530593e-05, "loss": 1.689056158065796, "step": 729 }, { "epoch": 0.061627428426706626, "grad_norm": 0.1572265625, "learning_rate": 4.989326605948902e-05, "loss": 1.6245583295822144, "step": 730 }, { "epoch": 0.06171184956153773, "grad_norm": 0.14453125, "learning_rate": 4.989266432584884e-05, "loss": 1.5304181575775146, "step": 731 }, { "epoch": 0.06179627069636884, "grad_norm": 0.154296875, "learning_rate": 4.9892060904426186e-05, "loss": 1.645117998123169, "step": 732 }, { "epoch": 0.061880691831199944, "grad_norm": 0.146484375, "learning_rate": 4.989145579526197e-05, "loss": 1.5164378881454468, "step": 733 }, { "epoch": 0.06196511296603104, "grad_norm": 0.158203125, "learning_rate": 4.989084899839721e-05, "loss": 1.5720356702804565, "step": 734 }, { "epoch": 0.06204953410086215, "grad_norm": 0.1669921875, "learning_rate": 4.9890240513873064e-05, "loss": 1.5607081651687622, "step": 735 }, { "epoch": 0.062133955235693254, "grad_norm": 0.1552734375, "learning_rate": 4.988963034173079e-05, "loss": 1.5777839422225952, "step": 736 }, { "epoch": 0.06221837637052436, "grad_norm": 0.158203125, "learning_rate": 4.988901848201174e-05, "loss": 1.5798395872116089, "step": 737 }, { "epoch": 0.062302797505355466, "grad_norm": 0.1552734375, "learning_rate": 4.988840493475742e-05, "loss": 1.5393118858337402, "step": 738 }, { "epoch": 0.06238721864018657, "grad_norm": 0.140625, "learning_rate": 4.988778970000942e-05, "loss": 1.5366668701171875, "step": 739 }, { "epoch": 0.06247163977501768, "grad_norm": 0.1552734375, "learning_rate": 4.988717277780945e-05, "loss": 1.6536136865615845, "step": 740 }, { "epoch": 0.06255606090984878, "grad_norm": 0.15625, "learning_rate": 4.988655416819935e-05, "loss": 1.554735541343689, "step": 741 }, { "epoch": 0.06264048204467988, "grad_norm": 0.140625, "learning_rate": 4.9885933871221064e-05, "loss": 1.5781807899475098, "step": 742 }, { "epoch": 0.06272490317951099, "grad_norm": 0.1669921875, "learning_rate": 4.988531188691664e-05, "loss": 1.544344425201416, "step": 743 }, { "epoch": 0.0628093243143421, "grad_norm": 0.146484375, "learning_rate": 4.9884688215328244e-05, "loss": 1.6536489725112915, "step": 744 }, { "epoch": 0.0628937454491732, "grad_norm": 0.158203125, "learning_rate": 4.988406285649818e-05, "loss": 1.62677800655365, "step": 745 }, { "epoch": 0.0629781665840043, "grad_norm": 0.169921875, "learning_rate": 4.9883435810468846e-05, "loss": 1.5174858570098877, "step": 746 }, { "epoch": 0.06306258771883541, "grad_norm": 0.150390625, "learning_rate": 4.9882807077282746e-05, "loss": 1.5307406187057495, "step": 747 }, { "epoch": 0.06314700885366652, "grad_norm": 0.1806640625, "learning_rate": 4.9882176656982514e-05, "loss": 1.4522676467895508, "step": 748 }, { "epoch": 0.06323142998849762, "grad_norm": 0.154296875, "learning_rate": 4.98815445496109e-05, "loss": 1.607223629951477, "step": 749 }, { "epoch": 0.06331585112332873, "grad_norm": 0.146484375, "learning_rate": 4.9880910755210753e-05, "loss": 1.6233800649642944, "step": 750 }, { "epoch": 0.06340027225815983, "grad_norm": 0.150390625, "learning_rate": 4.988027527382505e-05, "loss": 1.5773872137069702, "step": 751 }, { "epoch": 0.06348469339299094, "grad_norm": 0.1552734375, "learning_rate": 4.987963810549688e-05, "loss": 1.5744261741638184, "step": 752 }, { "epoch": 0.06356911452782205, "grad_norm": 0.1630859375, "learning_rate": 4.9878999250269456e-05, "loss": 1.445959210395813, "step": 753 }, { "epoch": 0.06365353566265315, "grad_norm": 0.14453125, "learning_rate": 4.9878358708186065e-05, "loss": 1.6022957563400269, "step": 754 }, { "epoch": 0.06373795679748424, "grad_norm": 0.1435546875, "learning_rate": 4.9877716479290174e-05, "loss": 1.6193228960037231, "step": 755 }, { "epoch": 0.06382237793231535, "grad_norm": 0.1630859375, "learning_rate": 4.9877072563625285e-05, "loss": 1.5455536842346191, "step": 756 }, { "epoch": 0.06390679906714646, "grad_norm": 0.14453125, "learning_rate": 4.987642696123509e-05, "loss": 1.5797549486160278, "step": 757 }, { "epoch": 0.06399122020197756, "grad_norm": 0.146484375, "learning_rate": 4.987577967216335e-05, "loss": 1.6201740503311157, "step": 758 }, { "epoch": 0.06407564133680867, "grad_norm": 0.1474609375, "learning_rate": 4.987513069645396e-05, "loss": 1.5993059873580933, "step": 759 }, { "epoch": 0.06416006247163977, "grad_norm": 0.14453125, "learning_rate": 4.9874480034150915e-05, "loss": 1.5566504001617432, "step": 760 }, { "epoch": 0.06424448360647088, "grad_norm": 0.1513671875, "learning_rate": 4.987382768529833e-05, "loss": 1.5636488199234009, "step": 761 }, { "epoch": 0.06432890474130198, "grad_norm": 0.154296875, "learning_rate": 4.9873173649940444e-05, "loss": 1.5777477025985718, "step": 762 }, { "epoch": 0.06441332587613309, "grad_norm": 0.166015625, "learning_rate": 4.987251792812159e-05, "loss": 1.502740740776062, "step": 763 }, { "epoch": 0.0644977470109642, "grad_norm": 0.1552734375, "learning_rate": 4.9871860519886234e-05, "loss": 1.4975149631500244, "step": 764 }, { "epoch": 0.0645821681457953, "grad_norm": 0.1484375, "learning_rate": 4.987120142527896e-05, "loss": 1.5578696727752686, "step": 765 }, { "epoch": 0.06466658928062641, "grad_norm": 0.212890625, "learning_rate": 4.987054064434444e-05, "loss": 1.6040722131729126, "step": 766 }, { "epoch": 0.06475101041545751, "grad_norm": 0.158203125, "learning_rate": 4.986987817712748e-05, "loss": 1.5802072286605835, "step": 767 }, { "epoch": 0.06483543155028862, "grad_norm": 0.1552734375, "learning_rate": 4.986921402367301e-05, "loss": 1.6024343967437744, "step": 768 }, { "epoch": 0.06491985268511972, "grad_norm": 0.1669921875, "learning_rate": 4.986854818402605e-05, "loss": 1.627449870109558, "step": 769 }, { "epoch": 0.06500427381995083, "grad_norm": 0.1455078125, "learning_rate": 4.9867880658231745e-05, "loss": 1.5894228219985962, "step": 770 }, { "epoch": 0.06508869495478194, "grad_norm": 0.1435546875, "learning_rate": 4.986721144633536e-05, "loss": 1.6410901546478271, "step": 771 }, { "epoch": 0.06517311608961303, "grad_norm": 0.1572265625, "learning_rate": 4.986654054838226e-05, "loss": 1.5870797634124756, "step": 772 }, { "epoch": 0.06525753722444413, "grad_norm": 0.1435546875, "learning_rate": 4.986586796441794e-05, "loss": 1.6254043579101562, "step": 773 }, { "epoch": 0.06534195835927524, "grad_norm": 0.1533203125, "learning_rate": 4.9865193694488e-05, "loss": 1.6735769510269165, "step": 774 }, { "epoch": 0.06542637949410635, "grad_norm": 0.154296875, "learning_rate": 4.9864517738638165e-05, "loss": 1.6863441467285156, "step": 775 }, { "epoch": 0.06551080062893745, "grad_norm": 0.166015625, "learning_rate": 4.986384009691426e-05, "loss": 1.539546251296997, "step": 776 }, { "epoch": 0.06559522176376856, "grad_norm": 0.13671875, "learning_rate": 4.986316076936223e-05, "loss": 1.6846110820770264, "step": 777 }, { "epoch": 0.06567964289859966, "grad_norm": 0.177734375, "learning_rate": 4.9862479756028136e-05, "loss": 1.6126331090927124, "step": 778 }, { "epoch": 0.06576406403343077, "grad_norm": 0.16015625, "learning_rate": 4.986179705695816e-05, "loss": 1.5691187381744385, "step": 779 }, { "epoch": 0.06584848516826187, "grad_norm": 0.154296875, "learning_rate": 4.986111267219857e-05, "loss": 1.5435012578964233, "step": 780 }, { "epoch": 0.06593290630309298, "grad_norm": 0.1630859375, "learning_rate": 4.986042660179579e-05, "loss": 1.575346827507019, "step": 781 }, { "epoch": 0.06601732743792409, "grad_norm": 0.173828125, "learning_rate": 4.985973884579634e-05, "loss": 1.5887644290924072, "step": 782 }, { "epoch": 0.06610174857275519, "grad_norm": 0.1728515625, "learning_rate": 4.9859049404246825e-05, "loss": 1.5859471559524536, "step": 783 }, { "epoch": 0.0661861697075863, "grad_norm": 0.140625, "learning_rate": 4.9858358277194014e-05, "loss": 1.6175484657287598, "step": 784 }, { "epoch": 0.0662705908424174, "grad_norm": 0.162109375, "learning_rate": 4.985766546468477e-05, "loss": 1.556715726852417, "step": 785 }, { "epoch": 0.06635501197724851, "grad_norm": 0.1640625, "learning_rate": 4.985697096676604e-05, "loss": 1.645336627960205, "step": 786 }, { "epoch": 0.06643943311207962, "grad_norm": 0.1533203125, "learning_rate": 4.985627478348494e-05, "loss": 1.572736144065857, "step": 787 }, { "epoch": 0.06652385424691071, "grad_norm": 0.158203125, "learning_rate": 4.985557691488866e-05, "loss": 1.6193807125091553, "step": 788 }, { "epoch": 0.06660827538174181, "grad_norm": 0.16015625, "learning_rate": 4.9854877361024524e-05, "loss": 1.5906057357788086, "step": 789 }, { "epoch": 0.06669269651657292, "grad_norm": 0.15625, "learning_rate": 4.9854176121939956e-05, "loss": 1.5870742797851562, "step": 790 }, { "epoch": 0.06677711765140402, "grad_norm": 0.1630859375, "learning_rate": 4.985347319768251e-05, "loss": 1.6311438083648682, "step": 791 }, { "epoch": 0.06686153878623513, "grad_norm": 0.16015625, "learning_rate": 4.985276858829984e-05, "loss": 1.5688424110412598, "step": 792 }, { "epoch": 0.06694595992106624, "grad_norm": 0.14453125, "learning_rate": 4.985206229383971e-05, "loss": 1.562387466430664, "step": 793 }, { "epoch": 0.06703038105589734, "grad_norm": 0.15234375, "learning_rate": 4.985135431435003e-05, "loss": 1.6465171575546265, "step": 794 }, { "epoch": 0.06711480219072845, "grad_norm": 0.142578125, "learning_rate": 4.98506446498788e-05, "loss": 1.6103321313858032, "step": 795 }, { "epoch": 0.06719922332555955, "grad_norm": 0.15625, "learning_rate": 4.984993330047412e-05, "loss": 1.6036887168884277, "step": 796 }, { "epoch": 0.06728364446039066, "grad_norm": 0.1640625, "learning_rate": 4.984922026618423e-05, "loss": 1.6367055177688599, "step": 797 }, { "epoch": 0.06736806559522177, "grad_norm": 0.142578125, "learning_rate": 4.984850554705748e-05, "loss": 1.6071406602859497, "step": 798 }, { "epoch": 0.06745248673005287, "grad_norm": 0.16796875, "learning_rate": 4.984778914314232e-05, "loss": 1.594648003578186, "step": 799 }, { "epoch": 0.06753690786488398, "grad_norm": 0.1572265625, "learning_rate": 4.984707105448734e-05, "loss": 1.6235123872756958, "step": 800 }, { "epoch": 0.06762132899971508, "grad_norm": 0.1552734375, "learning_rate": 4.984635128114121e-05, "loss": 1.554120659828186, "step": 801 }, { "epoch": 0.06770575013454619, "grad_norm": 0.154296875, "learning_rate": 4.984562982315274e-05, "loss": 1.6473053693771362, "step": 802 }, { "epoch": 0.0677901712693773, "grad_norm": 0.1826171875, "learning_rate": 4.9844906680570845e-05, "loss": 1.5653772354125977, "step": 803 }, { "epoch": 0.0678745924042084, "grad_norm": 0.1650390625, "learning_rate": 4.9844181853444574e-05, "loss": 1.6586716175079346, "step": 804 }, { "epoch": 0.06795901353903949, "grad_norm": 0.1416015625, "learning_rate": 4.984345534182304e-05, "loss": 1.5953484773635864, "step": 805 }, { "epoch": 0.0680434346738706, "grad_norm": 0.1552734375, "learning_rate": 4.984272714575552e-05, "loss": 1.6143605709075928, "step": 806 }, { "epoch": 0.0681278558087017, "grad_norm": 0.150390625, "learning_rate": 4.984199726529138e-05, "loss": 1.496361255645752, "step": 807 }, { "epoch": 0.06821227694353281, "grad_norm": 0.1806640625, "learning_rate": 4.984126570048013e-05, "loss": 1.587442398071289, "step": 808 }, { "epoch": 0.06829669807836392, "grad_norm": 0.1552734375, "learning_rate": 4.984053245137135e-05, "loss": 1.5303995609283447, "step": 809 }, { "epoch": 0.06838111921319502, "grad_norm": 0.1572265625, "learning_rate": 4.983979751801475e-05, "loss": 1.5745149850845337, "step": 810 }, { "epoch": 0.06846554034802613, "grad_norm": 0.1611328125, "learning_rate": 4.983906090046018e-05, "loss": 1.613297700881958, "step": 811 }, { "epoch": 0.06854996148285723, "grad_norm": 0.142578125, "learning_rate": 4.9838322598757575e-05, "loss": 1.6143231391906738, "step": 812 }, { "epoch": 0.06863438261768834, "grad_norm": 0.1953125, "learning_rate": 4.983758261295699e-05, "loss": 1.589606523513794, "step": 813 }, { "epoch": 0.06871880375251944, "grad_norm": 0.1572265625, "learning_rate": 4.983684094310861e-05, "loss": 1.6058388948440552, "step": 814 }, { "epoch": 0.06880322488735055, "grad_norm": 0.1357421875, "learning_rate": 4.983609758926271e-05, "loss": 1.54656183719635, "step": 815 }, { "epoch": 0.06888764602218166, "grad_norm": 0.1591796875, "learning_rate": 4.9835352551469693e-05, "loss": 1.6308456659317017, "step": 816 }, { "epoch": 0.06897206715701276, "grad_norm": 0.15625, "learning_rate": 4.983460582978008e-05, "loss": 1.5696568489074707, "step": 817 }, { "epoch": 0.06905648829184387, "grad_norm": 0.150390625, "learning_rate": 4.983385742424449e-05, "loss": 1.5771981477737427, "step": 818 }, { "epoch": 0.06914090942667497, "grad_norm": 0.189453125, "learning_rate": 4.9833107334913685e-05, "loss": 1.60326087474823, "step": 819 }, { "epoch": 0.06922533056150608, "grad_norm": 0.1826171875, "learning_rate": 4.98323555618385e-05, "loss": 1.580567717552185, "step": 820 }, { "epoch": 0.06930975169633717, "grad_norm": 0.189453125, "learning_rate": 4.983160210506993e-05, "loss": 1.5235404968261719, "step": 821 }, { "epoch": 0.06939417283116828, "grad_norm": 0.1943359375, "learning_rate": 4.983084696465905e-05, "loss": 1.6180061101913452, "step": 822 }, { "epoch": 0.06947859396599938, "grad_norm": 0.166015625, "learning_rate": 4.9830090140657046e-05, "loss": 1.5494519472122192, "step": 823 }, { "epoch": 0.06956301510083049, "grad_norm": 0.1435546875, "learning_rate": 4.982933163311526e-05, "loss": 1.5858838558197021, "step": 824 }, { "epoch": 0.0696474362356616, "grad_norm": 0.1591796875, "learning_rate": 4.98285714420851e-05, "loss": 1.66102135181427, "step": 825 }, { "epoch": 0.0697318573704927, "grad_norm": 0.1806640625, "learning_rate": 4.9827809567618125e-05, "loss": 1.6283265352249146, "step": 826 }, { "epoch": 0.0698162785053238, "grad_norm": 0.1943359375, "learning_rate": 4.982704600976597e-05, "loss": 1.536479115486145, "step": 827 }, { "epoch": 0.06990069964015491, "grad_norm": 0.224609375, "learning_rate": 4.982628076858044e-05, "loss": 1.695186734199524, "step": 828 }, { "epoch": 0.06998512077498602, "grad_norm": 0.150390625, "learning_rate": 4.982551384411338e-05, "loss": 1.5930124521255493, "step": 829 }, { "epoch": 0.07006954190981712, "grad_norm": 0.1435546875, "learning_rate": 4.982474523641682e-05, "loss": 1.5582013130187988, "step": 830 }, { "epoch": 0.07015396304464823, "grad_norm": 0.15625, "learning_rate": 4.982397494554285e-05, "loss": 1.6196134090423584, "step": 831 }, { "epoch": 0.07023838417947934, "grad_norm": 0.166015625, "learning_rate": 4.982320297154372e-05, "loss": 1.6558994054794312, "step": 832 }, { "epoch": 0.07032280531431044, "grad_norm": 0.185546875, "learning_rate": 4.982242931447176e-05, "loss": 1.5539685487747192, "step": 833 }, { "epoch": 0.07040722644914155, "grad_norm": 0.1552734375, "learning_rate": 4.982165397437942e-05, "loss": 1.5616856813430786, "step": 834 }, { "epoch": 0.07049164758397265, "grad_norm": 0.255859375, "learning_rate": 4.982087695131928e-05, "loss": 1.546697735786438, "step": 835 }, { "epoch": 0.07057606871880376, "grad_norm": 0.1484375, "learning_rate": 4.982009824534403e-05, "loss": 1.497623085975647, "step": 836 }, { "epoch": 0.07066048985363486, "grad_norm": 0.1494140625, "learning_rate": 4.9819317856506454e-05, "loss": 1.5423433780670166, "step": 837 }, { "epoch": 0.07074491098846596, "grad_norm": 0.1552734375, "learning_rate": 4.981853578485947e-05, "loss": 1.6218332052230835, "step": 838 }, { "epoch": 0.07082933212329706, "grad_norm": 0.1396484375, "learning_rate": 4.98177520304561e-05, "loss": 1.554701566696167, "step": 839 }, { "epoch": 0.07091375325812817, "grad_norm": 0.1982421875, "learning_rate": 4.981696659334949e-05, "loss": 1.6399028301239014, "step": 840 }, { "epoch": 0.07099817439295927, "grad_norm": 0.1513671875, "learning_rate": 4.9816179473592894e-05, "loss": 1.5419455766677856, "step": 841 }, { "epoch": 0.07108259552779038, "grad_norm": 0.1552734375, "learning_rate": 4.981539067123968e-05, "loss": 1.572737693786621, "step": 842 }, { "epoch": 0.07116701666262149, "grad_norm": 0.166015625, "learning_rate": 4.981460018634333e-05, "loss": 1.6312193870544434, "step": 843 }, { "epoch": 0.07125143779745259, "grad_norm": 0.162109375, "learning_rate": 4.981380801895744e-05, "loss": 1.596800684928894, "step": 844 }, { "epoch": 0.0713358589322837, "grad_norm": 0.1669921875, "learning_rate": 4.9813014169135726e-05, "loss": 1.5650520324707031, "step": 845 }, { "epoch": 0.0714202800671148, "grad_norm": 0.1533203125, "learning_rate": 4.981221863693201e-05, "loss": 1.5460387468338013, "step": 846 }, { "epoch": 0.07150470120194591, "grad_norm": 0.146484375, "learning_rate": 4.981142142240022e-05, "loss": 1.617356300354004, "step": 847 }, { "epoch": 0.07158912233677701, "grad_norm": 0.1494140625, "learning_rate": 4.981062252559442e-05, "loss": 1.5785149335861206, "step": 848 }, { "epoch": 0.07167354347160812, "grad_norm": 0.185546875, "learning_rate": 4.980982194656878e-05, "loss": 1.6970611810684204, "step": 849 }, { "epoch": 0.07175796460643923, "grad_norm": 0.1494140625, "learning_rate": 4.980901968537758e-05, "loss": 1.6016675233840942, "step": 850 }, { "epoch": 0.07184238574127033, "grad_norm": 0.1669921875, "learning_rate": 4.98082157420752e-05, "loss": 1.6424320936203003, "step": 851 }, { "epoch": 0.07192680687610144, "grad_norm": 0.1357421875, "learning_rate": 4.980741011671618e-05, "loss": 1.4996325969696045, "step": 852 }, { "epoch": 0.07201122801093254, "grad_norm": 0.1484375, "learning_rate": 4.980660280935511e-05, "loss": 1.5900036096572876, "step": 853 }, { "epoch": 0.07209564914576364, "grad_norm": 0.1435546875, "learning_rate": 4.980579382004675e-05, "loss": 1.5715168714523315, "step": 854 }, { "epoch": 0.07218007028059474, "grad_norm": 0.1552734375, "learning_rate": 4.9804983148845944e-05, "loss": 1.6243343353271484, "step": 855 }, { "epoch": 0.07226449141542585, "grad_norm": 0.1640625, "learning_rate": 4.9804170795807645e-05, "loss": 1.5213226079940796, "step": 856 }, { "epoch": 0.07234891255025695, "grad_norm": 0.142578125, "learning_rate": 4.980335676098696e-05, "loss": 1.6540623903274536, "step": 857 }, { "epoch": 0.07243333368508806, "grad_norm": 0.162109375, "learning_rate": 4.9802541044439064e-05, "loss": 1.514367938041687, "step": 858 }, { "epoch": 0.07251775481991916, "grad_norm": 0.1611328125, "learning_rate": 4.980172364621926e-05, "loss": 1.603034496307373, "step": 859 }, { "epoch": 0.07260217595475027, "grad_norm": 0.1455078125, "learning_rate": 4.9800904566382984e-05, "loss": 1.6057888269424438, "step": 860 }, { "epoch": 0.07268659708958138, "grad_norm": 0.1494140625, "learning_rate": 4.980008380498576e-05, "loss": 1.5810801982879639, "step": 861 }, { "epoch": 0.07277101822441248, "grad_norm": 0.146484375, "learning_rate": 4.979926136208325e-05, "loss": 1.6083580255508423, "step": 862 }, { "epoch": 0.07285543935924359, "grad_norm": 0.1552734375, "learning_rate": 4.97984372377312e-05, "loss": 1.6156439781188965, "step": 863 }, { "epoch": 0.0729398604940747, "grad_norm": 0.146484375, "learning_rate": 4.979761143198551e-05, "loss": 1.5867253541946411, "step": 864 }, { "epoch": 0.0730242816289058, "grad_norm": 0.1435546875, "learning_rate": 4.979678394490215e-05, "loss": 1.490647792816162, "step": 865 }, { "epoch": 0.0731087027637369, "grad_norm": 0.1611328125, "learning_rate": 4.979595477653724e-05, "loss": 1.679516077041626, "step": 866 }, { "epoch": 0.07319312389856801, "grad_norm": 0.16015625, "learning_rate": 4.979512392694699e-05, "loss": 1.6414821147918701, "step": 867 }, { "epoch": 0.07327754503339912, "grad_norm": 0.1396484375, "learning_rate": 4.979429139618774e-05, "loss": 1.4869240522384644, "step": 868 }, { "epoch": 0.07336196616823022, "grad_norm": 0.146484375, "learning_rate": 4.979345718431594e-05, "loss": 1.6441841125488281, "step": 869 }, { "epoch": 0.07344638730306133, "grad_norm": 0.1484375, "learning_rate": 4.979262129138814e-05, "loss": 1.514360785484314, "step": 870 }, { "epoch": 0.07353080843789242, "grad_norm": 0.15234375, "learning_rate": 4.979178371746103e-05, "loss": 1.5812935829162598, "step": 871 }, { "epoch": 0.07361522957272353, "grad_norm": 0.1435546875, "learning_rate": 4.979094446259138e-05, "loss": 1.5810726881027222, "step": 872 }, { "epoch": 0.07369965070755463, "grad_norm": 0.1748046875, "learning_rate": 4.979010352683612e-05, "loss": 1.6829882860183716, "step": 873 }, { "epoch": 0.07378407184238574, "grad_norm": 0.1474609375, "learning_rate": 4.9789260910252246e-05, "loss": 1.533240556716919, "step": 874 }, { "epoch": 0.07386849297721684, "grad_norm": 0.1533203125, "learning_rate": 4.9788416612896896e-05, "loss": 1.6407995223999023, "step": 875 }, { "epoch": 0.07395291411204795, "grad_norm": 0.1484375, "learning_rate": 4.9787570634827317e-05, "loss": 1.6221240758895874, "step": 876 }, { "epoch": 0.07403733524687905, "grad_norm": 0.1435546875, "learning_rate": 4.9786722976100876e-05, "loss": 1.557322382926941, "step": 877 }, { "epoch": 0.07412175638171016, "grad_norm": 0.1416015625, "learning_rate": 4.978587363677503e-05, "loss": 1.6873465776443481, "step": 878 }, { "epoch": 0.07420617751654127, "grad_norm": 0.14453125, "learning_rate": 4.9785022616907376e-05, "loss": 1.5385369062423706, "step": 879 }, { "epoch": 0.07429059865137237, "grad_norm": 0.140625, "learning_rate": 4.978416991655561e-05, "loss": 1.567862629890442, "step": 880 }, { "epoch": 0.07437501978620348, "grad_norm": 0.140625, "learning_rate": 4.9783315535777554e-05, "loss": 1.5841679573059082, "step": 881 }, { "epoch": 0.07445944092103458, "grad_norm": 0.142578125, "learning_rate": 4.9782459474631125e-05, "loss": 1.6543951034545898, "step": 882 }, { "epoch": 0.07454386205586569, "grad_norm": 0.134765625, "learning_rate": 4.978160173317438e-05, "loss": 1.5499844551086426, "step": 883 }, { "epoch": 0.0746282831906968, "grad_norm": 0.1591796875, "learning_rate": 4.978074231146548e-05, "loss": 1.6929930448532104, "step": 884 }, { "epoch": 0.0747127043255279, "grad_norm": 0.1533203125, "learning_rate": 4.9779881209562675e-05, "loss": 1.6487072706222534, "step": 885 }, { "epoch": 0.074797125460359, "grad_norm": 0.14453125, "learning_rate": 4.977901842752436e-05, "loss": 1.6180661916732788, "step": 886 }, { "epoch": 0.07488154659519011, "grad_norm": 0.14453125, "learning_rate": 4.9778153965409036e-05, "loss": 1.5343701839447021, "step": 887 }, { "epoch": 0.0749659677300212, "grad_norm": 0.1455078125, "learning_rate": 4.977728782327532e-05, "loss": 1.599949836730957, "step": 888 }, { "epoch": 0.07505038886485231, "grad_norm": 0.177734375, "learning_rate": 4.977642000118193e-05, "loss": 1.5265077352523804, "step": 889 }, { "epoch": 0.07513480999968342, "grad_norm": 0.1552734375, "learning_rate": 4.977555049918771e-05, "loss": 1.6038569211959839, "step": 890 }, { "epoch": 0.07521923113451452, "grad_norm": 0.1533203125, "learning_rate": 4.977467931735161e-05, "loss": 1.4691592454910278, "step": 891 }, { "epoch": 0.07530365226934563, "grad_norm": 0.14453125, "learning_rate": 4.9773806455732705e-05, "loss": 1.5818487405776978, "step": 892 }, { "epoch": 0.07538807340417673, "grad_norm": 0.1435546875, "learning_rate": 4.977293191439018e-05, "loss": 1.62671959400177, "step": 893 }, { "epoch": 0.07547249453900784, "grad_norm": 0.140625, "learning_rate": 4.977205569338331e-05, "loss": 1.6087015867233276, "step": 894 }, { "epoch": 0.07555691567383895, "grad_norm": 0.142578125, "learning_rate": 4.977117779277153e-05, "loss": 1.515254020690918, "step": 895 }, { "epoch": 0.07564133680867005, "grad_norm": 0.138671875, "learning_rate": 4.977029821261435e-05, "loss": 1.5619091987609863, "step": 896 }, { "epoch": 0.07572575794350116, "grad_norm": 0.15234375, "learning_rate": 4.9769416952971414e-05, "loss": 1.5967223644256592, "step": 897 }, { "epoch": 0.07581017907833226, "grad_norm": 0.1552734375, "learning_rate": 4.976853401390247e-05, "loss": 1.595138430595398, "step": 898 }, { "epoch": 0.07589460021316337, "grad_norm": 0.1708984375, "learning_rate": 4.976764939546738e-05, "loss": 1.6713165044784546, "step": 899 }, { "epoch": 0.07597902134799447, "grad_norm": 0.1533203125, "learning_rate": 4.976676309772613e-05, "loss": 1.639660120010376, "step": 900 }, { "epoch": 0.07606344248282558, "grad_norm": 0.15625, "learning_rate": 4.9765875120738816e-05, "loss": 1.5563740730285645, "step": 901 }, { "epoch": 0.07614786361765669, "grad_norm": 0.1552734375, "learning_rate": 4.9764985464565636e-05, "loss": 1.6493149995803833, "step": 902 }, { "epoch": 0.07623228475248779, "grad_norm": 0.1591796875, "learning_rate": 4.9764094129266915e-05, "loss": 1.5375117063522339, "step": 903 }, { "epoch": 0.07631670588731888, "grad_norm": 0.1640625, "learning_rate": 4.9763201114903076e-05, "loss": 1.4590237140655518, "step": 904 }, { "epoch": 0.07640112702214999, "grad_norm": 0.166015625, "learning_rate": 4.9762306421534694e-05, "loss": 1.6607824563980103, "step": 905 }, { "epoch": 0.0764855481569811, "grad_norm": 0.138671875, "learning_rate": 4.976141004922241e-05, "loss": 1.5296324491500854, "step": 906 }, { "epoch": 0.0765699692918122, "grad_norm": 0.1650390625, "learning_rate": 4.9760511998027e-05, "loss": 1.5479099750518799, "step": 907 }, { "epoch": 0.0766543904266433, "grad_norm": 0.146484375, "learning_rate": 4.975961226800937e-05, "loss": 1.5083847045898438, "step": 908 }, { "epoch": 0.07673881156147441, "grad_norm": 0.150390625, "learning_rate": 4.975871085923051e-05, "loss": 1.5619466304779053, "step": 909 }, { "epoch": 0.07682323269630552, "grad_norm": 0.150390625, "learning_rate": 4.975780777175154e-05, "loss": 1.6030278205871582, "step": 910 }, { "epoch": 0.07690765383113662, "grad_norm": 0.15625, "learning_rate": 4.975690300563369e-05, "loss": 1.5437612533569336, "step": 911 }, { "epoch": 0.07699207496596773, "grad_norm": 0.1494140625, "learning_rate": 4.975599656093832e-05, "loss": 1.585343599319458, "step": 912 }, { "epoch": 0.07707649610079884, "grad_norm": 0.1796875, "learning_rate": 4.975508843772687e-05, "loss": 1.6136850118637085, "step": 913 }, { "epoch": 0.07716091723562994, "grad_norm": 0.1748046875, "learning_rate": 4.9754178636060925e-05, "loss": 1.5867538452148438, "step": 914 }, { "epoch": 0.07724533837046105, "grad_norm": 0.1552734375, "learning_rate": 4.975326715600216e-05, "loss": 1.5565069913864136, "step": 915 }, { "epoch": 0.07732975950529215, "grad_norm": 0.16015625, "learning_rate": 4.9752353997612386e-05, "loss": 1.6309503316879272, "step": 916 }, { "epoch": 0.07741418064012326, "grad_norm": 0.1572265625, "learning_rate": 4.975143916095351e-05, "loss": 1.6348800659179688, "step": 917 }, { "epoch": 0.07749860177495436, "grad_norm": 0.1455078125, "learning_rate": 4.975052264608757e-05, "loss": 1.6898605823516846, "step": 918 }, { "epoch": 0.07758302290978547, "grad_norm": 0.15234375, "learning_rate": 4.9749604453076704e-05, "loss": 1.6067336797714233, "step": 919 }, { "epoch": 0.07766744404461658, "grad_norm": 0.1455078125, "learning_rate": 4.974868458198316e-05, "loss": 1.6294509172439575, "step": 920 }, { "epoch": 0.07775186517944767, "grad_norm": 0.1494140625, "learning_rate": 4.9747763032869314e-05, "loss": 1.614424228668213, "step": 921 }, { "epoch": 0.07783628631427877, "grad_norm": 0.1689453125, "learning_rate": 4.974683980579765e-05, "loss": 1.5634151697158813, "step": 922 }, { "epoch": 0.07792070744910988, "grad_norm": 0.1474609375, "learning_rate": 4.974591490083077e-05, "loss": 1.5811766386032104, "step": 923 }, { "epoch": 0.07800512858394099, "grad_norm": 0.140625, "learning_rate": 4.9744988318031374e-05, "loss": 1.5754756927490234, "step": 924 }, { "epoch": 0.07808954971877209, "grad_norm": 0.150390625, "learning_rate": 4.974406005746228e-05, "loss": 1.5678222179412842, "step": 925 }, { "epoch": 0.0781739708536032, "grad_norm": 0.1640625, "learning_rate": 4.974313011918646e-05, "loss": 1.6481801271438599, "step": 926 }, { "epoch": 0.0782583919884343, "grad_norm": 0.2197265625, "learning_rate": 4.9742198503266924e-05, "loss": 1.6108219623565674, "step": 927 }, { "epoch": 0.07834281312326541, "grad_norm": 0.1494140625, "learning_rate": 4.9741265209766864e-05, "loss": 1.5231777429580688, "step": 928 }, { "epoch": 0.07842723425809651, "grad_norm": 0.1611328125, "learning_rate": 4.974033023874954e-05, "loss": 1.670398473739624, "step": 929 }, { "epoch": 0.07851165539292762, "grad_norm": 0.1572265625, "learning_rate": 4.9739393590278377e-05, "loss": 1.6213018894195557, "step": 930 }, { "epoch": 0.07859607652775873, "grad_norm": 0.1513671875, "learning_rate": 4.9738455264416854e-05, "loss": 1.5716791152954102, "step": 931 }, { "epoch": 0.07868049766258983, "grad_norm": 0.173828125, "learning_rate": 4.9737515261228604e-05, "loss": 1.5812113285064697, "step": 932 }, { "epoch": 0.07876491879742094, "grad_norm": 0.1572265625, "learning_rate": 4.9736573580777356e-05, "loss": 1.5772775411605835, "step": 933 }, { "epoch": 0.07884933993225204, "grad_norm": 0.1708984375, "learning_rate": 4.973563022312696e-05, "loss": 1.6714390516281128, "step": 934 }, { "epoch": 0.07893376106708315, "grad_norm": 0.15625, "learning_rate": 4.9734685188341376e-05, "loss": 1.5231332778930664, "step": 935 }, { "epoch": 0.07901818220191426, "grad_norm": 0.1748046875, "learning_rate": 4.973373847648469e-05, "loss": 1.6182622909545898, "step": 936 }, { "epoch": 0.07910260333674535, "grad_norm": 0.1552734375, "learning_rate": 4.973279008762107e-05, "loss": 1.5738674402236938, "step": 937 }, { "epoch": 0.07918702447157645, "grad_norm": 0.1611328125, "learning_rate": 4.9731840021814846e-05, "loss": 1.5647940635681152, "step": 938 }, { "epoch": 0.07927144560640756, "grad_norm": 0.142578125, "learning_rate": 4.973088827913041e-05, "loss": 1.5947407484054565, "step": 939 }, { "epoch": 0.07935586674123866, "grad_norm": 0.142578125, "learning_rate": 4.972993485963231e-05, "loss": 1.4649159908294678, "step": 940 }, { "epoch": 0.07944028787606977, "grad_norm": 0.1630859375, "learning_rate": 4.9728979763385185e-05, "loss": 1.610262393951416, "step": 941 }, { "epoch": 0.07952470901090088, "grad_norm": 0.150390625, "learning_rate": 4.972802299045379e-05, "loss": 1.6130998134613037, "step": 942 }, { "epoch": 0.07960913014573198, "grad_norm": 0.134765625, "learning_rate": 4.9727064540903e-05, "loss": 1.590061902999878, "step": 943 }, { "epoch": 0.07969355128056309, "grad_norm": 0.1552734375, "learning_rate": 4.972610441479779e-05, "loss": 1.5877292156219482, "step": 944 }, { "epoch": 0.0797779724153942, "grad_norm": 0.1494140625, "learning_rate": 4.9725142612203265e-05, "loss": 1.6421570777893066, "step": 945 }, { "epoch": 0.0798623935502253, "grad_norm": 0.1416015625, "learning_rate": 4.972417913318465e-05, "loss": 1.5701134204864502, "step": 946 }, { "epoch": 0.0799468146850564, "grad_norm": 0.1513671875, "learning_rate": 4.972321397780726e-05, "loss": 1.5858527421951294, "step": 947 }, { "epoch": 0.08003123581988751, "grad_norm": 0.1474609375, "learning_rate": 4.972224714613653e-05, "loss": 1.576418399810791, "step": 948 }, { "epoch": 0.08011565695471862, "grad_norm": 0.1455078125, "learning_rate": 4.9721278638238026e-05, "loss": 1.5765786170959473, "step": 949 }, { "epoch": 0.08020007808954972, "grad_norm": 0.14453125, "learning_rate": 4.97203084541774e-05, "loss": 1.5415277481079102, "step": 950 }, { "epoch": 0.08028449922438083, "grad_norm": 0.1484375, "learning_rate": 4.971933659402044e-05, "loss": 1.5668679475784302, "step": 951 }, { "epoch": 0.08036892035921193, "grad_norm": 0.1416015625, "learning_rate": 4.971836305783305e-05, "loss": 1.5934967994689941, "step": 952 }, { "epoch": 0.08045334149404304, "grad_norm": 0.1533203125, "learning_rate": 4.971738784568122e-05, "loss": 1.504536509513855, "step": 953 }, { "epoch": 0.08053776262887413, "grad_norm": 0.185546875, "learning_rate": 4.971641095763109e-05, "loss": 1.6751377582550049, "step": 954 }, { "epoch": 0.08062218376370524, "grad_norm": 0.1611328125, "learning_rate": 4.9715432393748886e-05, "loss": 1.5554847717285156, "step": 955 }, { "epoch": 0.08070660489853634, "grad_norm": 0.146484375, "learning_rate": 4.971445215410096e-05, "loss": 1.582876443862915, "step": 956 }, { "epoch": 0.08079102603336745, "grad_norm": 0.1455078125, "learning_rate": 4.9713470238753755e-05, "loss": 1.5517175197601318, "step": 957 }, { "epoch": 0.08087544716819856, "grad_norm": 0.142578125, "learning_rate": 4.9712486647773885e-05, "loss": 1.5629459619522095, "step": 958 }, { "epoch": 0.08095986830302966, "grad_norm": 0.1455078125, "learning_rate": 4.971150138122801e-05, "loss": 1.621368646621704, "step": 959 }, { "epoch": 0.08104428943786077, "grad_norm": 0.16015625, "learning_rate": 4.971051443918294e-05, "loss": 1.5534815788269043, "step": 960 }, { "epoch": 0.08112871057269187, "grad_norm": 0.14453125, "learning_rate": 4.97095258217056e-05, "loss": 1.5914332866668701, "step": 961 }, { "epoch": 0.08121313170752298, "grad_norm": 0.1494140625, "learning_rate": 4.970853552886301e-05, "loss": 1.5443124771118164, "step": 962 }, { "epoch": 0.08129755284235408, "grad_norm": 0.146484375, "learning_rate": 4.970754356072232e-05, "loss": 1.6102588176727295, "step": 963 }, { "epoch": 0.08138197397718519, "grad_norm": 0.140625, "learning_rate": 4.97065499173508e-05, "loss": 1.5940548181533813, "step": 964 }, { "epoch": 0.0814663951120163, "grad_norm": 0.140625, "learning_rate": 4.97055545988158e-05, "loss": 1.5734665393829346, "step": 965 }, { "epoch": 0.0815508162468474, "grad_norm": 0.150390625, "learning_rate": 4.970455760518481e-05, "loss": 1.4956315755844116, "step": 966 }, { "epoch": 0.08163523738167851, "grad_norm": 0.15625, "learning_rate": 4.970355893652544e-05, "loss": 1.5538274049758911, "step": 967 }, { "epoch": 0.08171965851650961, "grad_norm": 0.166015625, "learning_rate": 4.970255859290539e-05, "loss": 1.7022795677185059, "step": 968 }, { "epoch": 0.08180407965134072, "grad_norm": 0.14453125, "learning_rate": 4.970155657439249e-05, "loss": 1.6248104572296143, "step": 969 }, { "epoch": 0.08188850078617183, "grad_norm": 0.14453125, "learning_rate": 4.970055288105468e-05, "loss": 1.5717110633850098, "step": 970 }, { "epoch": 0.08197292192100292, "grad_norm": 0.1435546875, "learning_rate": 4.969954751296001e-05, "loss": 1.6417186260223389, "step": 971 }, { "epoch": 0.08205734305583402, "grad_norm": 0.1474609375, "learning_rate": 4.969854047017666e-05, "loss": 1.6804938316345215, "step": 972 }, { "epoch": 0.08214176419066513, "grad_norm": 0.1748046875, "learning_rate": 4.9697531752772886e-05, "loss": 1.519451379776001, "step": 973 }, { "epoch": 0.08222618532549623, "grad_norm": 0.1650390625, "learning_rate": 4.9696521360817094e-05, "loss": 1.584751844406128, "step": 974 }, { "epoch": 0.08231060646032734, "grad_norm": 0.1396484375, "learning_rate": 4.969550929437779e-05, "loss": 1.5693778991699219, "step": 975 }, { "epoch": 0.08239502759515845, "grad_norm": 0.1435546875, "learning_rate": 4.969449555352361e-05, "loss": 1.6455631256103516, "step": 976 }, { "epoch": 0.08247944872998955, "grad_norm": 0.154296875, "learning_rate": 4.9693480138323265e-05, "loss": 1.578500509262085, "step": 977 }, { "epoch": 0.08256386986482066, "grad_norm": 0.158203125, "learning_rate": 4.96924630488456e-05, "loss": 1.577634572982788, "step": 978 }, { "epoch": 0.08264829099965176, "grad_norm": 0.1611328125, "learning_rate": 4.969144428515961e-05, "loss": 1.5605370998382568, "step": 979 }, { "epoch": 0.08273271213448287, "grad_norm": 0.140625, "learning_rate": 4.969042384733433e-05, "loss": 1.61066472530365, "step": 980 }, { "epoch": 0.08281713326931398, "grad_norm": 0.1376953125, "learning_rate": 4.968940173543898e-05, "loss": 1.5319035053253174, "step": 981 }, { "epoch": 0.08290155440414508, "grad_norm": 0.138671875, "learning_rate": 4.9688377949542833e-05, "loss": 1.587929606437683, "step": 982 }, { "epoch": 0.08298597553897619, "grad_norm": 0.1640625, "learning_rate": 4.968735248971532e-05, "loss": 1.5737502574920654, "step": 983 }, { "epoch": 0.08307039667380729, "grad_norm": 0.1689453125, "learning_rate": 4.968632535602597e-05, "loss": 1.6500221490859985, "step": 984 }, { "epoch": 0.0831548178086384, "grad_norm": 0.1416015625, "learning_rate": 4.9685296548544424e-05, "loss": 1.4996622800827026, "step": 985 }, { "epoch": 0.0832392389434695, "grad_norm": 0.1474609375, "learning_rate": 4.9684266067340436e-05, "loss": 1.5302091836929321, "step": 986 }, { "epoch": 0.0833236600783006, "grad_norm": 0.1416015625, "learning_rate": 4.968323391248387e-05, "loss": 1.4335404634475708, "step": 987 }, { "epoch": 0.0834080812131317, "grad_norm": 0.15625, "learning_rate": 4.968220008404473e-05, "loss": 1.6115388870239258, "step": 988 }, { "epoch": 0.08349250234796281, "grad_norm": 0.15234375, "learning_rate": 4.968116458209308e-05, "loss": 1.6169239282608032, "step": 989 }, { "epoch": 0.08357692348279391, "grad_norm": 0.15625, "learning_rate": 4.968012740669915e-05, "loss": 1.5316150188446045, "step": 990 }, { "epoch": 0.08366134461762502, "grad_norm": 0.14453125, "learning_rate": 4.967908855793326e-05, "loss": 1.6119734048843384, "step": 991 }, { "epoch": 0.08374576575245612, "grad_norm": 0.158203125, "learning_rate": 4.967804803586584e-05, "loss": 1.650734782218933, "step": 992 }, { "epoch": 0.08383018688728723, "grad_norm": 0.14453125, "learning_rate": 4.967700584056745e-05, "loss": 1.6237361431121826, "step": 993 }, { "epoch": 0.08391460802211834, "grad_norm": 0.166015625, "learning_rate": 4.967596197210875e-05, "loss": 1.619134783744812, "step": 994 }, { "epoch": 0.08399902915694944, "grad_norm": 0.142578125, "learning_rate": 4.967491643056051e-05, "loss": 1.468575358390808, "step": 995 }, { "epoch": 0.08408345029178055, "grad_norm": 0.1611328125, "learning_rate": 4.9673869215993626e-05, "loss": 1.5606331825256348, "step": 996 }, { "epoch": 0.08416787142661165, "grad_norm": 0.1416015625, "learning_rate": 4.967282032847911e-05, "loss": 1.5830302238464355, "step": 997 }, { "epoch": 0.08425229256144276, "grad_norm": 0.1748046875, "learning_rate": 4.967176976808806e-05, "loss": 1.706465244293213, "step": 998 }, { "epoch": 0.08433671369627387, "grad_norm": 0.140625, "learning_rate": 4.967071753489172e-05, "loss": 1.602945327758789, "step": 999 }, { "epoch": 0.08442113483110497, "grad_norm": 0.146484375, "learning_rate": 4.966966362896143e-05, "loss": 1.581222653388977, "step": 1000 }, { "epoch": 0.08450555596593608, "grad_norm": 0.1533203125, "learning_rate": 4.966860805036865e-05, "loss": 1.555198073387146, "step": 1001 }, { "epoch": 0.08458997710076718, "grad_norm": 0.1474609375, "learning_rate": 4.9667550799184946e-05, "loss": 1.5960700511932373, "step": 1002 }, { "epoch": 0.08467439823559829, "grad_norm": 0.1484375, "learning_rate": 4.9666491875482004e-05, "loss": 1.5005416870117188, "step": 1003 }, { "epoch": 0.08475881937042938, "grad_norm": 0.15234375, "learning_rate": 4.966543127933162e-05, "loss": 1.6120591163635254, "step": 1004 }, { "epoch": 0.08484324050526049, "grad_norm": 0.1455078125, "learning_rate": 4.966436901080571e-05, "loss": 1.6278706789016724, "step": 1005 }, { "epoch": 0.08492766164009159, "grad_norm": 0.1396484375, "learning_rate": 4.96633050699763e-05, "loss": 1.6118887662887573, "step": 1006 }, { "epoch": 0.0850120827749227, "grad_norm": 0.1552734375, "learning_rate": 4.966223945691552e-05, "loss": 1.6120095252990723, "step": 1007 }, { "epoch": 0.0850965039097538, "grad_norm": 0.142578125, "learning_rate": 4.9661172171695626e-05, "loss": 1.5598992109298706, "step": 1008 }, { "epoch": 0.08518092504458491, "grad_norm": 0.13671875, "learning_rate": 4.966010321438898e-05, "loss": 1.5049943923950195, "step": 1009 }, { "epoch": 0.08526534617941602, "grad_norm": 0.177734375, "learning_rate": 4.965903258506806e-05, "loss": 1.5519638061523438, "step": 1010 }, { "epoch": 0.08534976731424712, "grad_norm": 0.1650390625, "learning_rate": 4.965796028380546e-05, "loss": 1.6481916904449463, "step": 1011 }, { "epoch": 0.08543418844907823, "grad_norm": 0.158203125, "learning_rate": 4.965688631067388e-05, "loss": 1.6035791635513306, "step": 1012 }, { "epoch": 0.08551860958390933, "grad_norm": 0.16015625, "learning_rate": 4.965581066574615e-05, "loss": 1.5598320960998535, "step": 1013 }, { "epoch": 0.08560303071874044, "grad_norm": 0.1513671875, "learning_rate": 4.9654733349095184e-05, "loss": 1.672532081604004, "step": 1014 }, { "epoch": 0.08568745185357154, "grad_norm": 0.15625, "learning_rate": 4.965365436079403e-05, "loss": 1.553385615348816, "step": 1015 }, { "epoch": 0.08577187298840265, "grad_norm": 0.1708984375, "learning_rate": 4.965257370091586e-05, "loss": 1.5514403581619263, "step": 1016 }, { "epoch": 0.08585629412323376, "grad_norm": 0.1435546875, "learning_rate": 4.965149136953393e-05, "loss": 1.492621898651123, "step": 1017 }, { "epoch": 0.08594071525806486, "grad_norm": 0.169921875, "learning_rate": 4.9650407366721634e-05, "loss": 1.4701204299926758, "step": 1018 }, { "epoch": 0.08602513639289597, "grad_norm": 0.1455078125, "learning_rate": 4.9649321692552464e-05, "loss": 1.596268653869629, "step": 1019 }, { "epoch": 0.08610955752772706, "grad_norm": 0.1884765625, "learning_rate": 4.9648234347100044e-05, "loss": 1.4899026155471802, "step": 1020 }, { "epoch": 0.08619397866255817, "grad_norm": 0.15234375, "learning_rate": 4.964714533043808e-05, "loss": 1.6352088451385498, "step": 1021 }, { "epoch": 0.08627839979738927, "grad_norm": 0.1572265625, "learning_rate": 4.9646054642640414e-05, "loss": 1.5801454782485962, "step": 1022 }, { "epoch": 0.08636282093222038, "grad_norm": 0.1513671875, "learning_rate": 4.964496228378101e-05, "loss": 1.5583409070968628, "step": 1023 }, { "epoch": 0.08644724206705148, "grad_norm": 0.1552734375, "learning_rate": 4.9643868253933925e-05, "loss": 1.6750340461730957, "step": 1024 }, { "epoch": 0.08653166320188259, "grad_norm": 0.154296875, "learning_rate": 4.9642772553173333e-05, "loss": 1.5714560747146606, "step": 1025 }, { "epoch": 0.0866160843367137, "grad_norm": 0.14453125, "learning_rate": 4.964167518157353e-05, "loss": 1.6154370307922363, "step": 1026 }, { "epoch": 0.0867005054715448, "grad_norm": 0.1474609375, "learning_rate": 4.964057613920892e-05, "loss": 1.4642243385314941, "step": 1027 }, { "epoch": 0.0867849266063759, "grad_norm": 0.1455078125, "learning_rate": 4.9639475426154015e-05, "loss": 1.515283226966858, "step": 1028 }, { "epoch": 0.08686934774120701, "grad_norm": 0.1474609375, "learning_rate": 4.963837304248345e-05, "loss": 1.5758662223815918, "step": 1029 }, { "epoch": 0.08695376887603812, "grad_norm": 0.1494140625, "learning_rate": 4.963726898827197e-05, "loss": 1.5497000217437744, "step": 1030 }, { "epoch": 0.08703819001086922, "grad_norm": 0.1513671875, "learning_rate": 4.963616326359444e-05, "loss": 1.5640968084335327, "step": 1031 }, { "epoch": 0.08712261114570033, "grad_norm": 0.1591796875, "learning_rate": 4.963505586852582e-05, "loss": 1.5189164876937866, "step": 1032 }, { "epoch": 0.08720703228053144, "grad_norm": 0.1494140625, "learning_rate": 4.963394680314119e-05, "loss": 1.5838544368743896, "step": 1033 }, { "epoch": 0.08729145341536254, "grad_norm": 0.146484375, "learning_rate": 4.9632836067515765e-05, "loss": 1.568235158920288, "step": 1034 }, { "epoch": 0.08737587455019365, "grad_norm": 0.15234375, "learning_rate": 4.9631723661724836e-05, "loss": 1.6196975708007812, "step": 1035 }, { "epoch": 0.08746029568502475, "grad_norm": 0.1845703125, "learning_rate": 4.963060958584384e-05, "loss": 1.646034836769104, "step": 1036 }, { "epoch": 0.08754471681985584, "grad_norm": 0.16796875, "learning_rate": 4.962949383994831e-05, "loss": 1.6564253568649292, "step": 1037 }, { "epoch": 0.08762913795468695, "grad_norm": 0.1328125, "learning_rate": 4.96283764241139e-05, "loss": 1.5167640447616577, "step": 1038 }, { "epoch": 0.08771355908951806, "grad_norm": 0.1376953125, "learning_rate": 4.962725733841637e-05, "loss": 1.614194631576538, "step": 1039 }, { "epoch": 0.08779798022434916, "grad_norm": 0.16015625, "learning_rate": 4.962613658293158e-05, "loss": 1.4977456331253052, "step": 1040 }, { "epoch": 0.08788240135918027, "grad_norm": 0.1513671875, "learning_rate": 4.962501415773555e-05, "loss": 1.5008068084716797, "step": 1041 }, { "epoch": 0.08796682249401137, "grad_norm": 0.1455078125, "learning_rate": 4.962389006290437e-05, "loss": 1.5394437313079834, "step": 1042 }, { "epoch": 0.08805124362884248, "grad_norm": 0.1513671875, "learning_rate": 4.9622764298514255e-05, "loss": 1.619840383529663, "step": 1043 }, { "epoch": 0.08813566476367359, "grad_norm": 0.1357421875, "learning_rate": 4.962163686464153e-05, "loss": 1.5852782726287842, "step": 1044 }, { "epoch": 0.08822008589850469, "grad_norm": 0.1630859375, "learning_rate": 4.962050776136265e-05, "loss": 1.6190227270126343, "step": 1045 }, { "epoch": 0.0883045070333358, "grad_norm": 0.1533203125, "learning_rate": 4.9619376988754166e-05, "loss": 1.6506011486053467, "step": 1046 }, { "epoch": 0.0883889281681669, "grad_norm": 0.140625, "learning_rate": 4.961824454689273e-05, "loss": 1.5067732334136963, "step": 1047 }, { "epoch": 0.08847334930299801, "grad_norm": 0.142578125, "learning_rate": 4.961711043585515e-05, "loss": 1.61312997341156, "step": 1048 }, { "epoch": 0.08855777043782911, "grad_norm": 0.1416015625, "learning_rate": 4.9615974655718314e-05, "loss": 1.5709991455078125, "step": 1049 }, { "epoch": 0.08864219157266022, "grad_norm": 0.13671875, "learning_rate": 4.9614837206559216e-05, "loss": 1.579270601272583, "step": 1050 }, { "epoch": 0.08872661270749133, "grad_norm": 0.1513671875, "learning_rate": 4.9613698088455e-05, "loss": 1.5932791233062744, "step": 1051 }, { "epoch": 0.08881103384232243, "grad_norm": 0.1572265625, "learning_rate": 4.961255730148289e-05, "loss": 1.5840497016906738, "step": 1052 }, { "epoch": 0.08889545497715352, "grad_norm": 0.146484375, "learning_rate": 4.9611414845720225e-05, "loss": 1.4361931085586548, "step": 1053 }, { "epoch": 0.08897987611198463, "grad_norm": 0.169921875, "learning_rate": 4.961027072124448e-05, "loss": 1.540065050125122, "step": 1054 }, { "epoch": 0.08906429724681574, "grad_norm": 0.1416015625, "learning_rate": 4.9609124928133226e-05, "loss": 1.569807767868042, "step": 1055 }, { "epoch": 0.08914871838164684, "grad_norm": 0.14453125, "learning_rate": 4.960797746646415e-05, "loss": 1.6138501167297363, "step": 1056 }, { "epoch": 0.08923313951647795, "grad_norm": 0.15625, "learning_rate": 4.9606828336315046e-05, "loss": 1.4712516069412231, "step": 1057 }, { "epoch": 0.08931756065130905, "grad_norm": 0.138671875, "learning_rate": 4.960567753776384e-05, "loss": 1.4918692111968994, "step": 1058 }, { "epoch": 0.08940198178614016, "grad_norm": 0.166015625, "learning_rate": 4.960452507088855e-05, "loss": 1.5758073329925537, "step": 1059 }, { "epoch": 0.08948640292097126, "grad_norm": 0.16015625, "learning_rate": 4.9603370935767324e-05, "loss": 1.6193264722824097, "step": 1060 }, { "epoch": 0.08957082405580237, "grad_norm": 0.166015625, "learning_rate": 4.9602215132478405e-05, "loss": 1.5881681442260742, "step": 1061 }, { "epoch": 0.08965524519063348, "grad_norm": 0.146484375, "learning_rate": 4.9601057661100167e-05, "loss": 1.602967619895935, "step": 1062 }, { "epoch": 0.08973966632546458, "grad_norm": 0.15625, "learning_rate": 4.9599898521711086e-05, "loss": 1.5741441249847412, "step": 1063 }, { "epoch": 0.08982408746029569, "grad_norm": 0.15234375, "learning_rate": 4.959873771438975e-05, "loss": 1.5900341272354126, "step": 1064 }, { "epoch": 0.0899085085951268, "grad_norm": 0.126953125, "learning_rate": 4.959757523921487e-05, "loss": 1.5587823390960693, "step": 1065 }, { "epoch": 0.0899929297299579, "grad_norm": 0.1611328125, "learning_rate": 4.959641109626527e-05, "loss": 1.605702519416809, "step": 1066 }, { "epoch": 0.090077350864789, "grad_norm": 0.166015625, "learning_rate": 4.959524528561987e-05, "loss": 1.535705327987671, "step": 1067 }, { "epoch": 0.09016177199962011, "grad_norm": 0.1787109375, "learning_rate": 4.959407780735772e-05, "loss": 1.5170420408248901, "step": 1068 }, { "epoch": 0.09024619313445122, "grad_norm": 0.1513671875, "learning_rate": 4.959290866155798e-05, "loss": 1.5739306211471558, "step": 1069 }, { "epoch": 0.09033061426928231, "grad_norm": 0.14453125, "learning_rate": 4.959173784829992e-05, "loss": 1.613591194152832, "step": 1070 }, { "epoch": 0.09041503540411341, "grad_norm": 0.1630859375, "learning_rate": 4.959056536766292e-05, "loss": 1.6369960308074951, "step": 1071 }, { "epoch": 0.09049945653894452, "grad_norm": 0.1474609375, "learning_rate": 4.958939121972649e-05, "loss": 1.5646097660064697, "step": 1072 }, { "epoch": 0.09058387767377563, "grad_norm": 0.1396484375, "learning_rate": 4.958821540457022e-05, "loss": 1.6003310680389404, "step": 1073 }, { "epoch": 0.09066829880860673, "grad_norm": 0.158203125, "learning_rate": 4.9587037922273846e-05, "loss": 1.5857038497924805, "step": 1074 }, { "epoch": 0.09075271994343784, "grad_norm": 0.158203125, "learning_rate": 4.9585858772917206e-05, "loss": 1.530789852142334, "step": 1075 }, { "epoch": 0.09083714107826894, "grad_norm": 0.15234375, "learning_rate": 4.958467795658024e-05, "loss": 1.5620501041412354, "step": 1076 }, { "epoch": 0.09092156221310005, "grad_norm": 0.150390625, "learning_rate": 4.9583495473343014e-05, "loss": 1.5608181953430176, "step": 1077 }, { "epoch": 0.09100598334793115, "grad_norm": 0.13671875, "learning_rate": 4.958231132328571e-05, "loss": 1.6119650602340698, "step": 1078 }, { "epoch": 0.09109040448276226, "grad_norm": 0.166015625, "learning_rate": 4.95811255064886e-05, "loss": 1.5785363912582397, "step": 1079 }, { "epoch": 0.09117482561759337, "grad_norm": 0.1650390625, "learning_rate": 4.95799380230321e-05, "loss": 1.5271719694137573, "step": 1080 }, { "epoch": 0.09125924675242447, "grad_norm": 0.1474609375, "learning_rate": 4.957874887299672e-05, "loss": 1.5537375211715698, "step": 1081 }, { "epoch": 0.09134366788725558, "grad_norm": 0.1865234375, "learning_rate": 4.957755805646309e-05, "loss": 1.55873441696167, "step": 1082 }, { "epoch": 0.09142808902208668, "grad_norm": 0.17578125, "learning_rate": 4.957636557351195e-05, "loss": 1.6179969310760498, "step": 1083 }, { "epoch": 0.09151251015691779, "grad_norm": 0.1376953125, "learning_rate": 4.9575171424224146e-05, "loss": 1.5659689903259277, "step": 1084 }, { "epoch": 0.0915969312917489, "grad_norm": 0.1494140625, "learning_rate": 4.957397560868064e-05, "loss": 1.6657699346542358, "step": 1085 }, { "epoch": 0.09168135242658, "grad_norm": 0.1630859375, "learning_rate": 4.957277812696253e-05, "loss": 1.624552845954895, "step": 1086 }, { "epoch": 0.0917657735614111, "grad_norm": 0.1611328125, "learning_rate": 4.957157897915099e-05, "loss": 1.566788911819458, "step": 1087 }, { "epoch": 0.0918501946962422, "grad_norm": 0.166015625, "learning_rate": 4.957037816532734e-05, "loss": 1.5563817024230957, "step": 1088 }, { "epoch": 0.0919346158310733, "grad_norm": 0.1630859375, "learning_rate": 4.956917568557299e-05, "loss": 1.550632119178772, "step": 1089 }, { "epoch": 0.09201903696590441, "grad_norm": 0.1552734375, "learning_rate": 4.956797153996947e-05, "loss": 1.5978050231933594, "step": 1090 }, { "epoch": 0.09210345810073552, "grad_norm": 0.1455078125, "learning_rate": 4.956676572859843e-05, "loss": 1.5438714027404785, "step": 1091 }, { "epoch": 0.09218787923556662, "grad_norm": 0.1640625, "learning_rate": 4.9565558251541616e-05, "loss": 1.530635952949524, "step": 1092 }, { "epoch": 0.09227230037039773, "grad_norm": 0.169921875, "learning_rate": 4.956434910888091e-05, "loss": 1.5542387962341309, "step": 1093 }, { "epoch": 0.09235672150522883, "grad_norm": 0.1796875, "learning_rate": 4.9563138300698286e-05, "loss": 1.647200107574463, "step": 1094 }, { "epoch": 0.09244114264005994, "grad_norm": 0.1611328125, "learning_rate": 4.956192582707585e-05, "loss": 1.6115326881408691, "step": 1095 }, { "epoch": 0.09252556377489105, "grad_norm": 0.1513671875, "learning_rate": 4.95607116880958e-05, "loss": 1.6363095045089722, "step": 1096 }, { "epoch": 0.09260998490972215, "grad_norm": 0.1416015625, "learning_rate": 4.955949588384046e-05, "loss": 1.5551118850708008, "step": 1097 }, { "epoch": 0.09269440604455326, "grad_norm": 0.1552734375, "learning_rate": 4.9558278414392265e-05, "loss": 1.5138428211212158, "step": 1098 }, { "epoch": 0.09277882717938436, "grad_norm": 0.1455078125, "learning_rate": 4.955705927983376e-05, "loss": 1.5687265396118164, "step": 1099 }, { "epoch": 0.09286324831421547, "grad_norm": 0.1650390625, "learning_rate": 4.955583848024761e-05, "loss": 1.642451286315918, "step": 1100 }, { "epoch": 0.09294766944904657, "grad_norm": 0.154296875, "learning_rate": 4.955461601571659e-05, "loss": 1.5805939435958862, "step": 1101 }, { "epoch": 0.09303209058387768, "grad_norm": 0.13671875, "learning_rate": 4.955339188632359e-05, "loss": 1.5886597633361816, "step": 1102 }, { "epoch": 0.09311651171870877, "grad_norm": 0.15234375, "learning_rate": 4.9552166092151584e-05, "loss": 1.4796905517578125, "step": 1103 }, { "epoch": 0.09320093285353988, "grad_norm": 0.146484375, "learning_rate": 4.955093863328372e-05, "loss": 1.5359755754470825, "step": 1104 }, { "epoch": 0.09328535398837098, "grad_norm": 0.177734375, "learning_rate": 4.954970950980319e-05, "loss": 1.611934781074524, "step": 1105 }, { "epoch": 0.09336977512320209, "grad_norm": 0.1484375, "learning_rate": 4.954847872179335e-05, "loss": 1.512021541595459, "step": 1106 }, { "epoch": 0.0934541962580332, "grad_norm": 0.1689453125, "learning_rate": 4.9547246269337644e-05, "loss": 1.5388455390930176, "step": 1107 }, { "epoch": 0.0935386173928643, "grad_norm": 0.1611328125, "learning_rate": 4.954601215251964e-05, "loss": 1.610199213027954, "step": 1108 }, { "epoch": 0.0936230385276954, "grad_norm": 0.17578125, "learning_rate": 4.954477637142301e-05, "loss": 1.6508188247680664, "step": 1109 }, { "epoch": 0.09370745966252651, "grad_norm": 0.1494140625, "learning_rate": 4.954353892613154e-05, "loss": 1.536607027053833, "step": 1110 }, { "epoch": 0.09379188079735762, "grad_norm": 0.14453125, "learning_rate": 4.954229981672914e-05, "loss": 1.5587977170944214, "step": 1111 }, { "epoch": 0.09387630193218872, "grad_norm": 0.14453125, "learning_rate": 4.954105904329982e-05, "loss": 1.491629958152771, "step": 1112 }, { "epoch": 0.09396072306701983, "grad_norm": 0.1513671875, "learning_rate": 4.9539816605927716e-05, "loss": 1.5800856351852417, "step": 1113 }, { "epoch": 0.09404514420185094, "grad_norm": 0.158203125, "learning_rate": 4.953857250469706e-05, "loss": 1.5993802547454834, "step": 1114 }, { "epoch": 0.09412956533668204, "grad_norm": 0.154296875, "learning_rate": 4.953732673969219e-05, "loss": 1.6013774871826172, "step": 1115 }, { "epoch": 0.09421398647151315, "grad_norm": 0.1455078125, "learning_rate": 4.95360793109976e-05, "loss": 1.5404835939407349, "step": 1116 }, { "epoch": 0.09429840760634425, "grad_norm": 0.1572265625, "learning_rate": 4.953483021869785e-05, "loss": 1.6115339994430542, "step": 1117 }, { "epoch": 0.09438282874117536, "grad_norm": 0.146484375, "learning_rate": 4.953357946287763e-05, "loss": 1.5674808025360107, "step": 1118 }, { "epoch": 0.09446724987600646, "grad_norm": 0.1533203125, "learning_rate": 4.9532327043621764e-05, "loss": 1.5278860330581665, "step": 1119 }, { "epoch": 0.09455167101083756, "grad_norm": 0.1650390625, "learning_rate": 4.9531072961015156e-05, "loss": 1.686423897743225, "step": 1120 }, { "epoch": 0.09463609214566866, "grad_norm": 0.15625, "learning_rate": 4.9529817215142826e-05, "loss": 1.5812933444976807, "step": 1121 }, { "epoch": 0.09472051328049977, "grad_norm": 0.234375, "learning_rate": 4.9528559806089936e-05, "loss": 1.5967988967895508, "step": 1122 }, { "epoch": 0.09480493441533087, "grad_norm": 0.1357421875, "learning_rate": 4.9527300733941725e-05, "loss": 1.5344598293304443, "step": 1123 }, { "epoch": 0.09488935555016198, "grad_norm": 0.1591796875, "learning_rate": 4.952603999878358e-05, "loss": 1.5734471082687378, "step": 1124 }, { "epoch": 0.09497377668499309, "grad_norm": 0.1455078125, "learning_rate": 4.952477760070096e-05, "loss": 1.5974299907684326, "step": 1125 }, { "epoch": 0.09505819781982419, "grad_norm": 0.1396484375, "learning_rate": 4.9523513539779474e-05, "loss": 1.5897560119628906, "step": 1126 }, { "epoch": 0.0951426189546553, "grad_norm": 0.1611328125, "learning_rate": 4.952224781610482e-05, "loss": 1.5235847234725952, "step": 1127 }, { "epoch": 0.0952270400894864, "grad_norm": 0.13671875, "learning_rate": 4.952098042976282e-05, "loss": 1.573582410812378, "step": 1128 }, { "epoch": 0.09531146122431751, "grad_norm": 0.150390625, "learning_rate": 4.951971138083941e-05, "loss": 1.5627623796463013, "step": 1129 }, { "epoch": 0.09539588235914861, "grad_norm": 0.146484375, "learning_rate": 4.951844066942063e-05, "loss": 1.6006829738616943, "step": 1130 }, { "epoch": 0.09548030349397972, "grad_norm": 0.1474609375, "learning_rate": 4.951716829559264e-05, "loss": 1.6238690614700317, "step": 1131 }, { "epoch": 0.09556472462881083, "grad_norm": 0.1357421875, "learning_rate": 4.95158942594417e-05, "loss": 1.5593698024749756, "step": 1132 }, { "epoch": 0.09564914576364193, "grad_norm": 0.224609375, "learning_rate": 4.9514618561054205e-05, "loss": 1.5958350896835327, "step": 1133 }, { "epoch": 0.09573356689847304, "grad_norm": 0.15234375, "learning_rate": 4.951334120051665e-05, "loss": 1.5278546810150146, "step": 1134 }, { "epoch": 0.09581798803330414, "grad_norm": 0.1689453125, "learning_rate": 4.951206217791564e-05, "loss": 1.602634072303772, "step": 1135 }, { "epoch": 0.09590240916813524, "grad_norm": 0.1455078125, "learning_rate": 4.951078149333789e-05, "loss": 1.570521354675293, "step": 1136 }, { "epoch": 0.09598683030296634, "grad_norm": 0.140625, "learning_rate": 4.9509499146870236e-05, "loss": 1.4936254024505615, "step": 1137 }, { "epoch": 0.09607125143779745, "grad_norm": 0.15625, "learning_rate": 4.950821513859963e-05, "loss": 1.5931661128997803, "step": 1138 }, { "epoch": 0.09615567257262855, "grad_norm": 0.1630859375, "learning_rate": 4.950692946861313e-05, "loss": 1.5785425901412964, "step": 1139 }, { "epoch": 0.09624009370745966, "grad_norm": 0.162109375, "learning_rate": 4.95056421369979e-05, "loss": 1.6368576288223267, "step": 1140 }, { "epoch": 0.09632451484229076, "grad_norm": 0.1513671875, "learning_rate": 4.950435314384123e-05, "loss": 1.532509207725525, "step": 1141 }, { "epoch": 0.09640893597712187, "grad_norm": 0.1494140625, "learning_rate": 4.950306248923052e-05, "loss": 1.647567868232727, "step": 1142 }, { "epoch": 0.09649335711195298, "grad_norm": 0.1455078125, "learning_rate": 4.9501770173253283e-05, "loss": 1.7072246074676514, "step": 1143 }, { "epoch": 0.09657777824678408, "grad_norm": 0.15234375, "learning_rate": 4.950047619599712e-05, "loss": 1.595790147781372, "step": 1144 }, { "epoch": 0.09666219938161519, "grad_norm": 0.150390625, "learning_rate": 4.949918055754978e-05, "loss": 1.544264793395996, "step": 1145 }, { "epoch": 0.0967466205164463, "grad_norm": 0.1611328125, "learning_rate": 4.949788325799912e-05, "loss": 1.6314494609832764, "step": 1146 }, { "epoch": 0.0968310416512774, "grad_norm": 0.14453125, "learning_rate": 4.949658429743308e-05, "loss": 1.5657110214233398, "step": 1147 }, { "epoch": 0.0969154627861085, "grad_norm": 0.16015625, "learning_rate": 4.949528367593975e-05, "loss": 1.5692499876022339, "step": 1148 }, { "epoch": 0.09699988392093961, "grad_norm": 0.150390625, "learning_rate": 4.9493981393607305e-05, "loss": 1.5758543014526367, "step": 1149 }, { "epoch": 0.09708430505577072, "grad_norm": 0.1357421875, "learning_rate": 4.949267745052405e-05, "loss": 1.6260167360305786, "step": 1150 }, { "epoch": 0.09716872619060182, "grad_norm": 0.1513671875, "learning_rate": 4.949137184677838e-05, "loss": 1.6124608516693115, "step": 1151 }, { "epoch": 0.09725314732543293, "grad_norm": 0.15234375, "learning_rate": 4.949006458245884e-05, "loss": 1.6067126989364624, "step": 1152 }, { "epoch": 0.09733756846026402, "grad_norm": 0.1572265625, "learning_rate": 4.948875565765405e-05, "loss": 1.5086840391159058, "step": 1153 }, { "epoch": 0.09742198959509513, "grad_norm": 0.1435546875, "learning_rate": 4.9487445072452765e-05, "loss": 1.5954065322875977, "step": 1154 }, { "epoch": 0.09750641072992623, "grad_norm": 0.150390625, "learning_rate": 4.948613282694384e-05, "loss": 1.6042380332946777, "step": 1155 }, { "epoch": 0.09759083186475734, "grad_norm": 0.1669921875, "learning_rate": 4.9484818921216256e-05, "loss": 1.611860752105713, "step": 1156 }, { "epoch": 0.09767525299958844, "grad_norm": 0.1640625, "learning_rate": 4.9483503355359096e-05, "loss": 1.5524133443832397, "step": 1157 }, { "epoch": 0.09775967413441955, "grad_norm": 0.1875, "learning_rate": 4.948218612946156e-05, "loss": 1.5110622644424438, "step": 1158 }, { "epoch": 0.09784409526925066, "grad_norm": 0.15234375, "learning_rate": 4.948086724361295e-05, "loss": 1.4779006242752075, "step": 1159 }, { "epoch": 0.09792851640408176, "grad_norm": 0.150390625, "learning_rate": 4.94795466979027e-05, "loss": 1.5677398443222046, "step": 1160 }, { "epoch": 0.09801293753891287, "grad_norm": 0.1494140625, "learning_rate": 4.947822449242034e-05, "loss": 1.5295389890670776, "step": 1161 }, { "epoch": 0.09809735867374397, "grad_norm": 0.13671875, "learning_rate": 4.947690062725553e-05, "loss": 1.6195895671844482, "step": 1162 }, { "epoch": 0.09818177980857508, "grad_norm": 0.162109375, "learning_rate": 4.9475575102498016e-05, "loss": 1.552922248840332, "step": 1163 }, { "epoch": 0.09826620094340618, "grad_norm": 0.1533203125, "learning_rate": 4.9474247918237684e-05, "loss": 1.501480221748352, "step": 1164 }, { "epoch": 0.09835062207823729, "grad_norm": 0.1572265625, "learning_rate": 4.947291907456451e-05, "loss": 1.5911405086517334, "step": 1165 }, { "epoch": 0.0984350432130684, "grad_norm": 0.1943359375, "learning_rate": 4.947158857156859e-05, "loss": 1.6295015811920166, "step": 1166 }, { "epoch": 0.0985194643478995, "grad_norm": 0.1611328125, "learning_rate": 4.947025640934016e-05, "loss": 1.628625750541687, "step": 1167 }, { "epoch": 0.09860388548273061, "grad_norm": 0.1640625, "learning_rate": 4.9468922587969516e-05, "loss": 1.603043556213379, "step": 1168 }, { "epoch": 0.0986883066175617, "grad_norm": 0.1416015625, "learning_rate": 4.946758710754711e-05, "loss": 1.594895362854004, "step": 1169 }, { "epoch": 0.0987727277523928, "grad_norm": 0.15625, "learning_rate": 4.946624996816348e-05, "loss": 1.6059985160827637, "step": 1170 }, { "epoch": 0.09885714888722391, "grad_norm": 0.154296875, "learning_rate": 4.94649111699093e-05, "loss": 1.6526817083358765, "step": 1171 }, { "epoch": 0.09894157002205502, "grad_norm": 0.14453125, "learning_rate": 4.946357071287533e-05, "loss": 1.645193338394165, "step": 1172 }, { "epoch": 0.09902599115688612, "grad_norm": 0.1533203125, "learning_rate": 4.946222859715247e-05, "loss": 1.5580109357833862, "step": 1173 }, { "epoch": 0.09911041229171723, "grad_norm": 0.140625, "learning_rate": 4.946088482283171e-05, "loss": 1.4789832830429077, "step": 1174 }, { "epoch": 0.09919483342654833, "grad_norm": 0.1533203125, "learning_rate": 4.9459539390004153e-05, "loss": 1.5866878032684326, "step": 1175 }, { "epoch": 0.09927925456137944, "grad_norm": 0.171875, "learning_rate": 4.945819229876104e-05, "loss": 1.62095308303833, "step": 1176 }, { "epoch": 0.09936367569621055, "grad_norm": 0.1455078125, "learning_rate": 4.94568435491937e-05, "loss": 1.5903619527816772, "step": 1177 }, { "epoch": 0.09944809683104165, "grad_norm": 0.158203125, "learning_rate": 4.9455493141393586e-05, "loss": 1.5549026727676392, "step": 1178 }, { "epoch": 0.09953251796587276, "grad_norm": 0.146484375, "learning_rate": 4.945414107545224e-05, "loss": 1.5831973552703857, "step": 1179 }, { "epoch": 0.09961693910070386, "grad_norm": 0.181640625, "learning_rate": 4.945278735146136e-05, "loss": 1.5897198915481567, "step": 1180 }, { "epoch": 0.09970136023553497, "grad_norm": 0.1455078125, "learning_rate": 4.9451431969512716e-05, "loss": 1.5049457550048828, "step": 1181 }, { "epoch": 0.09978578137036608, "grad_norm": 0.1533203125, "learning_rate": 4.945007492969821e-05, "loss": 1.5716215372085571, "step": 1182 }, { "epoch": 0.09987020250519718, "grad_norm": 0.166015625, "learning_rate": 4.944871623210986e-05, "loss": 1.5180470943450928, "step": 1183 }, { "epoch": 0.09995462364002829, "grad_norm": 0.1708984375, "learning_rate": 4.944735587683977e-05, "loss": 1.5892754793167114, "step": 1184 }, { "epoch": 0.10003904477485939, "grad_norm": 0.162109375, "learning_rate": 4.94459938639802e-05, "loss": 1.5569028854370117, "step": 1185 }, { "epoch": 0.10012346590969048, "grad_norm": 0.1494140625, "learning_rate": 4.9444630193623485e-05, "loss": 1.525275707244873, "step": 1186 }, { "epoch": 0.10020788704452159, "grad_norm": 0.1591796875, "learning_rate": 4.944326486586208e-05, "loss": 1.6772162914276123, "step": 1187 }, { "epoch": 0.1002923081793527, "grad_norm": 0.1455078125, "learning_rate": 4.944189788078857e-05, "loss": 1.537657618522644, "step": 1188 }, { "epoch": 0.1003767293141838, "grad_norm": 0.1484375, "learning_rate": 4.9440529238495626e-05, "loss": 1.5722020864486694, "step": 1189 }, { "epoch": 0.10046115044901491, "grad_norm": 0.1474609375, "learning_rate": 4.943915893907606e-05, "loss": 1.5355985164642334, "step": 1190 }, { "epoch": 0.10054557158384601, "grad_norm": 0.1484375, "learning_rate": 4.943778698262276e-05, "loss": 1.6124498844146729, "step": 1191 }, { "epoch": 0.10062999271867712, "grad_norm": 0.1474609375, "learning_rate": 4.943641336922877e-05, "loss": 1.5958611965179443, "step": 1192 }, { "epoch": 0.10071441385350823, "grad_norm": 0.15625, "learning_rate": 4.943503809898722e-05, "loss": 1.4816551208496094, "step": 1193 }, { "epoch": 0.10079883498833933, "grad_norm": 0.142578125, "learning_rate": 4.9433661171991355e-05, "loss": 1.5667823553085327, "step": 1194 }, { "epoch": 0.10088325612317044, "grad_norm": 0.158203125, "learning_rate": 4.9432282588334525e-05, "loss": 1.5568194389343262, "step": 1195 }, { "epoch": 0.10096767725800154, "grad_norm": 0.1396484375, "learning_rate": 4.9430902348110206e-05, "loss": 1.5633097887039185, "step": 1196 }, { "epoch": 0.10105209839283265, "grad_norm": 0.1572265625, "learning_rate": 4.942952045141199e-05, "loss": 1.6951076984405518, "step": 1197 }, { "epoch": 0.10113651952766375, "grad_norm": 0.1416015625, "learning_rate": 4.9428136898333566e-05, "loss": 1.557917594909668, "step": 1198 }, { "epoch": 0.10122094066249486, "grad_norm": 0.146484375, "learning_rate": 4.9426751688968744e-05, "loss": 1.5618938207626343, "step": 1199 }, { "epoch": 0.10130536179732597, "grad_norm": 0.158203125, "learning_rate": 4.942536482341143e-05, "loss": 1.5673084259033203, "step": 1200 }, { "epoch": 0.10138978293215707, "grad_norm": 0.1591796875, "learning_rate": 4.942397630175568e-05, "loss": 1.6963694095611572, "step": 1201 }, { "epoch": 0.10147420406698818, "grad_norm": 0.15234375, "learning_rate": 4.942258612409564e-05, "loss": 1.6757537126541138, "step": 1202 }, { "epoch": 0.10155862520181927, "grad_norm": 0.13671875, "learning_rate": 4.942119429052554e-05, "loss": 1.5346548557281494, "step": 1203 }, { "epoch": 0.10164304633665038, "grad_norm": 0.1416015625, "learning_rate": 4.941980080113977e-05, "loss": 1.5361634492874146, "step": 1204 }, { "epoch": 0.10172746747148148, "grad_norm": 0.1435546875, "learning_rate": 4.941840565603281e-05, "loss": 1.5919830799102783, "step": 1205 }, { "epoch": 0.10181188860631259, "grad_norm": 0.1552734375, "learning_rate": 4.941700885529926e-05, "loss": 1.6122361421585083, "step": 1206 }, { "epoch": 0.10189630974114369, "grad_norm": 0.14453125, "learning_rate": 4.941561039903381e-05, "loss": 1.5515491962432861, "step": 1207 }, { "epoch": 0.1019807308759748, "grad_norm": 0.1513671875, "learning_rate": 4.941421028733129e-05, "loss": 1.577235221862793, "step": 1208 }, { "epoch": 0.1020651520108059, "grad_norm": 0.146484375, "learning_rate": 4.9412808520286624e-05, "loss": 1.459924578666687, "step": 1209 }, { "epoch": 0.10214957314563701, "grad_norm": 0.1494140625, "learning_rate": 4.941140509799487e-05, "loss": 1.5832527875900269, "step": 1210 }, { "epoch": 0.10223399428046812, "grad_norm": 0.1689453125, "learning_rate": 4.9410000020551164e-05, "loss": 1.5481539964675903, "step": 1211 }, { "epoch": 0.10231841541529922, "grad_norm": 0.1474609375, "learning_rate": 4.9408593288050787e-05, "loss": 1.6134848594665527, "step": 1212 }, { "epoch": 0.10240283655013033, "grad_norm": 0.1455078125, "learning_rate": 4.940718490058911e-05, "loss": 1.555649995803833, "step": 1213 }, { "epoch": 0.10248725768496143, "grad_norm": 0.1552734375, "learning_rate": 4.940577485826163e-05, "loss": 1.6901071071624756, "step": 1214 }, { "epoch": 0.10257167881979254, "grad_norm": 0.1767578125, "learning_rate": 4.940436316116395e-05, "loss": 1.611746907234192, "step": 1215 }, { "epoch": 0.10265609995462364, "grad_norm": 0.17578125, "learning_rate": 4.9402949809391794e-05, "loss": 1.5243459939956665, "step": 1216 }, { "epoch": 0.10274052108945475, "grad_norm": 0.16796875, "learning_rate": 4.940153480304098e-05, "loss": 1.5551137924194336, "step": 1217 }, { "epoch": 0.10282494222428586, "grad_norm": 0.1650390625, "learning_rate": 4.940011814220745e-05, "loss": 1.5505210161209106, "step": 1218 }, { "epoch": 0.10290936335911695, "grad_norm": 0.146484375, "learning_rate": 4.9398699826987265e-05, "loss": 1.5751901865005493, "step": 1219 }, { "epoch": 0.10299378449394805, "grad_norm": 0.1474609375, "learning_rate": 4.9397279857476584e-05, "loss": 1.5489009618759155, "step": 1220 }, { "epoch": 0.10307820562877916, "grad_norm": 0.1865234375, "learning_rate": 4.9395858233771686e-05, "loss": 1.6965444087982178, "step": 1221 }, { "epoch": 0.10316262676361027, "grad_norm": 0.1474609375, "learning_rate": 4.939443495596896e-05, "loss": 1.5244529247283936, "step": 1222 }, { "epoch": 0.10324704789844137, "grad_norm": 0.1591796875, "learning_rate": 4.93930100241649e-05, "loss": 1.6082983016967773, "step": 1223 }, { "epoch": 0.10333146903327248, "grad_norm": 0.1640625, "learning_rate": 4.939158343845613e-05, "loss": 1.6299713850021362, "step": 1224 }, { "epoch": 0.10341589016810358, "grad_norm": 0.1396484375, "learning_rate": 4.939015519893938e-05, "loss": 1.5550769567489624, "step": 1225 }, { "epoch": 0.10350031130293469, "grad_norm": 0.1357421875, "learning_rate": 4.938872530571148e-05, "loss": 1.5565154552459717, "step": 1226 }, { "epoch": 0.1035847324377658, "grad_norm": 0.1416015625, "learning_rate": 4.938729375886938e-05, "loss": 1.5415356159210205, "step": 1227 }, { "epoch": 0.1036691535725969, "grad_norm": 0.154296875, "learning_rate": 4.938586055851014e-05, "loss": 1.5420254468917847, "step": 1228 }, { "epoch": 0.103753574707428, "grad_norm": 0.1708984375, "learning_rate": 4.938442570473094e-05, "loss": 1.5881208181381226, "step": 1229 }, { "epoch": 0.10383799584225911, "grad_norm": 0.1533203125, "learning_rate": 4.938298919762907e-05, "loss": 1.5371357202529907, "step": 1230 }, { "epoch": 0.10392241697709022, "grad_norm": 0.1845703125, "learning_rate": 4.938155103730192e-05, "loss": 1.6099700927734375, "step": 1231 }, { "epoch": 0.10400683811192132, "grad_norm": 0.1435546875, "learning_rate": 4.9380111223847005e-05, "loss": 1.5723334550857544, "step": 1232 }, { "epoch": 0.10409125924675243, "grad_norm": 0.16796875, "learning_rate": 4.937866975736194e-05, "loss": 1.6919546127319336, "step": 1233 }, { "epoch": 0.10417568038158354, "grad_norm": 0.1552734375, "learning_rate": 4.9377226637944474e-05, "loss": 1.67641019821167, "step": 1234 }, { "epoch": 0.10426010151641464, "grad_norm": 0.1416015625, "learning_rate": 4.937578186569244e-05, "loss": 1.6453735828399658, "step": 1235 }, { "epoch": 0.10434452265124573, "grad_norm": 0.154296875, "learning_rate": 4.937433544070381e-05, "loss": 1.5493730306625366, "step": 1236 }, { "epoch": 0.10442894378607684, "grad_norm": 0.154296875, "learning_rate": 4.937288736307665e-05, "loss": 1.5847190618515015, "step": 1237 }, { "epoch": 0.10451336492090794, "grad_norm": 0.16796875, "learning_rate": 4.937143763290914e-05, "loss": 1.5498998165130615, "step": 1238 }, { "epoch": 0.10459778605573905, "grad_norm": 0.1435546875, "learning_rate": 4.9369986250299576e-05, "loss": 1.4915891885757446, "step": 1239 }, { "epoch": 0.10468220719057016, "grad_norm": 0.15234375, "learning_rate": 4.936853321534637e-05, "loss": 1.615307092666626, "step": 1240 }, { "epoch": 0.10476662832540126, "grad_norm": 0.1494140625, "learning_rate": 4.936707852814804e-05, "loss": 1.5787434577941895, "step": 1241 }, { "epoch": 0.10485104946023237, "grad_norm": 0.1396484375, "learning_rate": 4.9365622188803204e-05, "loss": 1.5770654678344727, "step": 1242 }, { "epoch": 0.10493547059506347, "grad_norm": 0.1416015625, "learning_rate": 4.936416419741062e-05, "loss": 1.6028845310211182, "step": 1243 }, { "epoch": 0.10501989172989458, "grad_norm": 0.1484375, "learning_rate": 4.9362704554069145e-05, "loss": 1.5878270864486694, "step": 1244 }, { "epoch": 0.10510431286472569, "grad_norm": 0.146484375, "learning_rate": 4.936124325887774e-05, "loss": 1.4776298999786377, "step": 1245 }, { "epoch": 0.10518873399955679, "grad_norm": 0.140625, "learning_rate": 4.935978031193548e-05, "loss": 1.5097705125808716, "step": 1246 }, { "epoch": 0.1052731551343879, "grad_norm": 0.140625, "learning_rate": 4.935831571334157e-05, "loss": 1.56532621383667, "step": 1247 }, { "epoch": 0.105357576269219, "grad_norm": 0.1455078125, "learning_rate": 4.93568494631953e-05, "loss": 1.5839262008666992, "step": 1248 }, { "epoch": 0.10544199740405011, "grad_norm": 0.166015625, "learning_rate": 4.935538156159609e-05, "loss": 1.5862903594970703, "step": 1249 }, { "epoch": 0.10552641853888121, "grad_norm": 0.1474609375, "learning_rate": 4.9353912008643464e-05, "loss": 1.5486226081848145, "step": 1250 }, { "epoch": 0.10561083967371232, "grad_norm": 0.1416015625, "learning_rate": 4.935244080443707e-05, "loss": 1.6118236780166626, "step": 1251 }, { "epoch": 0.10569526080854341, "grad_norm": 0.138671875, "learning_rate": 4.935096794907665e-05, "loss": 1.5697178840637207, "step": 1252 }, { "epoch": 0.10577968194337452, "grad_norm": 0.150390625, "learning_rate": 4.9349493442662074e-05, "loss": 1.5429937839508057, "step": 1253 }, { "epoch": 0.10586410307820562, "grad_norm": 0.146484375, "learning_rate": 4.9348017285293316e-05, "loss": 1.6556727886199951, "step": 1254 }, { "epoch": 0.10594852421303673, "grad_norm": 0.13671875, "learning_rate": 4.934653947707046e-05, "loss": 1.5794644355773926, "step": 1255 }, { "epoch": 0.10603294534786784, "grad_norm": 0.1572265625, "learning_rate": 4.93450600180937e-05, "loss": 1.5184943675994873, "step": 1256 }, { "epoch": 0.10611736648269894, "grad_norm": 0.142578125, "learning_rate": 4.934357890846336e-05, "loss": 1.5755865573883057, "step": 1257 }, { "epoch": 0.10620178761753005, "grad_norm": 0.1767578125, "learning_rate": 4.934209614827986e-05, "loss": 1.6060444116592407, "step": 1258 }, { "epoch": 0.10628620875236115, "grad_norm": 0.1630859375, "learning_rate": 4.934061173764372e-05, "loss": 1.6031934022903442, "step": 1259 }, { "epoch": 0.10637062988719226, "grad_norm": 0.1494140625, "learning_rate": 4.933912567665561e-05, "loss": 1.5381027460098267, "step": 1260 }, { "epoch": 0.10645505102202336, "grad_norm": 0.1552734375, "learning_rate": 4.933763796541626e-05, "loss": 1.544348120689392, "step": 1261 }, { "epoch": 0.10653947215685447, "grad_norm": 0.14453125, "learning_rate": 4.933614860402657e-05, "loss": 1.5734930038452148, "step": 1262 }, { "epoch": 0.10662389329168558, "grad_norm": 0.1572265625, "learning_rate": 4.93346575925875e-05, "loss": 1.6127238273620605, "step": 1263 }, { "epoch": 0.10670831442651668, "grad_norm": 0.138671875, "learning_rate": 4.933316493120015e-05, "loss": 1.6115820407867432, "step": 1264 }, { "epoch": 0.10679273556134779, "grad_norm": 0.1513671875, "learning_rate": 4.9331670619965734e-05, "loss": 1.6169395446777344, "step": 1265 }, { "epoch": 0.1068771566961789, "grad_norm": 0.1484375, "learning_rate": 4.933017465898556e-05, "loss": 1.6429109573364258, "step": 1266 }, { "epoch": 0.10696157783101, "grad_norm": 0.15625, "learning_rate": 4.932867704836106e-05, "loss": 1.5547666549682617, "step": 1267 }, { "epoch": 0.1070459989658411, "grad_norm": 0.1396484375, "learning_rate": 4.9327177788193785e-05, "loss": 1.6042988300323486, "step": 1268 }, { "epoch": 0.1071304201006722, "grad_norm": 0.1298828125, "learning_rate": 4.932567687858538e-05, "loss": 1.5748622417449951, "step": 1269 }, { "epoch": 0.1072148412355033, "grad_norm": 0.138671875, "learning_rate": 4.932417431963761e-05, "loss": 1.5407711267471313, "step": 1270 }, { "epoch": 0.10729926237033441, "grad_norm": 0.142578125, "learning_rate": 4.932267011145235e-05, "loss": 1.538536787033081, "step": 1271 }, { "epoch": 0.10738368350516551, "grad_norm": 0.150390625, "learning_rate": 4.9321164254131595e-05, "loss": 1.63173508644104, "step": 1272 }, { "epoch": 0.10746810463999662, "grad_norm": 0.138671875, "learning_rate": 4.9319656747777445e-05, "loss": 1.609519124031067, "step": 1273 }, { "epoch": 0.10755252577482773, "grad_norm": 0.138671875, "learning_rate": 4.9318147592492106e-05, "loss": 1.54145348072052, "step": 1274 }, { "epoch": 0.10763694690965883, "grad_norm": 0.1533203125, "learning_rate": 4.9316636788377915e-05, "loss": 1.500044345855713, "step": 1275 }, { "epoch": 0.10772136804448994, "grad_norm": 0.1474609375, "learning_rate": 4.931512433553729e-05, "loss": 1.5197014808654785, "step": 1276 }, { "epoch": 0.10780578917932104, "grad_norm": 0.140625, "learning_rate": 4.93136102340728e-05, "loss": 1.5827479362487793, "step": 1277 }, { "epoch": 0.10789021031415215, "grad_norm": 0.1728515625, "learning_rate": 4.931209448408709e-05, "loss": 1.5706337690353394, "step": 1278 }, { "epoch": 0.10797463144898325, "grad_norm": 0.150390625, "learning_rate": 4.931057708568293e-05, "loss": 1.5710324048995972, "step": 1279 }, { "epoch": 0.10805905258381436, "grad_norm": 0.14453125, "learning_rate": 4.930905803896322e-05, "loss": 1.5165836811065674, "step": 1280 }, { "epoch": 0.10814347371864547, "grad_norm": 0.15625, "learning_rate": 4.930753734403093e-05, "loss": 1.6007541418075562, "step": 1281 }, { "epoch": 0.10822789485347657, "grad_norm": 0.1435546875, "learning_rate": 4.930601500098919e-05, "loss": 1.5302681922912598, "step": 1282 }, { "epoch": 0.10831231598830768, "grad_norm": 0.173828125, "learning_rate": 4.93044910099412e-05, "loss": 1.6334125995635986, "step": 1283 }, { "epoch": 0.10839673712313878, "grad_norm": 0.1484375, "learning_rate": 4.9302965370990303e-05, "loss": 1.5150710344314575, "step": 1284 }, { "epoch": 0.10848115825796989, "grad_norm": 0.1474609375, "learning_rate": 4.930143808423995e-05, "loss": 1.4639887809753418, "step": 1285 }, { "epoch": 0.10856557939280098, "grad_norm": 0.15234375, "learning_rate": 4.929990914979367e-05, "loss": 1.5813275575637817, "step": 1286 }, { "epoch": 0.10865000052763209, "grad_norm": 0.14453125, "learning_rate": 4.929837856775514e-05, "loss": 1.574223518371582, "step": 1287 }, { "epoch": 0.1087344216624632, "grad_norm": 0.1513671875, "learning_rate": 4.929684633822814e-05, "loss": 1.649957299232483, "step": 1288 }, { "epoch": 0.1088188427972943, "grad_norm": 0.15234375, "learning_rate": 4.9295312461316554e-05, "loss": 1.5782175064086914, "step": 1289 }, { "epoch": 0.1089032639321254, "grad_norm": 0.1484375, "learning_rate": 4.929377693712439e-05, "loss": 1.6383167505264282, "step": 1290 }, { "epoch": 0.10898768506695651, "grad_norm": 0.146484375, "learning_rate": 4.929223976575575e-05, "loss": 1.5826759338378906, "step": 1291 }, { "epoch": 0.10907210620178762, "grad_norm": 0.1474609375, "learning_rate": 4.9290700947314864e-05, "loss": 1.5542329549789429, "step": 1292 }, { "epoch": 0.10915652733661872, "grad_norm": 0.1376953125, "learning_rate": 4.9289160481906066e-05, "loss": 1.5461441278457642, "step": 1293 }, { "epoch": 0.10924094847144983, "grad_norm": 0.142578125, "learning_rate": 4.92876183696338e-05, "loss": 1.5967063903808594, "step": 1294 }, { "epoch": 0.10932536960628093, "grad_norm": 0.1396484375, "learning_rate": 4.928607461060264e-05, "loss": 1.5291666984558105, "step": 1295 }, { "epoch": 0.10940979074111204, "grad_norm": 0.1572265625, "learning_rate": 4.928452920491724e-05, "loss": 1.6228692531585693, "step": 1296 }, { "epoch": 0.10949421187594315, "grad_norm": 0.15234375, "learning_rate": 4.9282982152682384e-05, "loss": 1.5093940496444702, "step": 1297 }, { "epoch": 0.10957863301077425, "grad_norm": 0.154296875, "learning_rate": 4.9281433454002974e-05, "loss": 1.5817738771438599, "step": 1298 }, { "epoch": 0.10966305414560536, "grad_norm": 0.1708984375, "learning_rate": 4.9279883108984005e-05, "loss": 1.5591678619384766, "step": 1299 }, { "epoch": 0.10974747528043646, "grad_norm": 0.1611328125, "learning_rate": 4.927833111773061e-05, "loss": 1.6466014385223389, "step": 1300 }, { "epoch": 0.10983189641526757, "grad_norm": 0.1357421875, "learning_rate": 4.9276777480348e-05, "loss": 1.471158742904663, "step": 1301 }, { "epoch": 0.10991631755009866, "grad_norm": 0.154296875, "learning_rate": 4.927522219694153e-05, "loss": 1.5034712553024292, "step": 1302 }, { "epoch": 0.11000073868492977, "grad_norm": 0.1650390625, "learning_rate": 4.927366526761663e-05, "loss": 1.5647281408309937, "step": 1303 }, { "epoch": 0.11008515981976087, "grad_norm": 0.1484375, "learning_rate": 4.927210669247889e-05, "loss": 1.4688128232955933, "step": 1304 }, { "epoch": 0.11016958095459198, "grad_norm": 0.1396484375, "learning_rate": 4.927054647163398e-05, "loss": 1.5838103294372559, "step": 1305 }, { "epoch": 0.11025400208942308, "grad_norm": 0.1533203125, "learning_rate": 4.926898460518767e-05, "loss": 1.5171775817871094, "step": 1306 }, { "epoch": 0.11033842322425419, "grad_norm": 0.169921875, "learning_rate": 4.926742109324587e-05, "loss": 1.575232744216919, "step": 1307 }, { "epoch": 0.1104228443590853, "grad_norm": 0.1484375, "learning_rate": 4.92658559359146e-05, "loss": 1.5591957569122314, "step": 1308 }, { "epoch": 0.1105072654939164, "grad_norm": 0.16015625, "learning_rate": 4.926428913329996e-05, "loss": 1.584563136100769, "step": 1309 }, { "epoch": 0.11059168662874751, "grad_norm": 0.15625, "learning_rate": 4.926272068550819e-05, "loss": 1.554900050163269, "step": 1310 }, { "epoch": 0.11067610776357861, "grad_norm": 0.14453125, "learning_rate": 4.926115059264564e-05, "loss": 1.60682213306427, "step": 1311 }, { "epoch": 0.11076052889840972, "grad_norm": 0.1611328125, "learning_rate": 4.9259578854818764e-05, "loss": 1.6101146936416626, "step": 1312 }, { "epoch": 0.11084495003324082, "grad_norm": 0.1806640625, "learning_rate": 4.925800547213413e-05, "loss": 1.6017857789993286, "step": 1313 }, { "epoch": 0.11092937116807193, "grad_norm": 0.162109375, "learning_rate": 4.925643044469842e-05, "loss": 1.61378812789917, "step": 1314 }, { "epoch": 0.11101379230290304, "grad_norm": 0.15234375, "learning_rate": 4.925485377261841e-05, "loss": 1.6446746587753296, "step": 1315 }, { "epoch": 0.11109821343773414, "grad_norm": 0.1484375, "learning_rate": 4.9253275456001024e-05, "loss": 1.6102268695831299, "step": 1316 }, { "epoch": 0.11118263457256525, "grad_norm": 0.1376953125, "learning_rate": 4.925169549495326e-05, "loss": 1.571045160293579, "step": 1317 }, { "epoch": 0.11126705570739635, "grad_norm": 0.1513671875, "learning_rate": 4.925011388958226e-05, "loss": 1.6127419471740723, "step": 1318 }, { "epoch": 0.11135147684222745, "grad_norm": 0.1552734375, "learning_rate": 4.9248530639995235e-05, "loss": 1.5276448726654053, "step": 1319 }, { "epoch": 0.11143589797705855, "grad_norm": 0.146484375, "learning_rate": 4.924694574629955e-05, "loss": 1.5684692859649658, "step": 1320 }, { "epoch": 0.11152031911188966, "grad_norm": 0.1484375, "learning_rate": 4.924535920860266e-05, "loss": 1.61451256275177, "step": 1321 }, { "epoch": 0.11160474024672076, "grad_norm": 0.1357421875, "learning_rate": 4.924377102701214e-05, "loss": 1.5156983137130737, "step": 1322 }, { "epoch": 0.11168916138155187, "grad_norm": 0.1572265625, "learning_rate": 4.9242181201635674e-05, "loss": 1.673735499382019, "step": 1323 }, { "epoch": 0.11177358251638297, "grad_norm": 0.1630859375, "learning_rate": 4.924058973258104e-05, "loss": 1.5911961793899536, "step": 1324 }, { "epoch": 0.11185800365121408, "grad_norm": 0.154296875, "learning_rate": 4.923899661995617e-05, "loss": 1.5697189569473267, "step": 1325 }, { "epoch": 0.11194242478604519, "grad_norm": 0.1484375, "learning_rate": 4.923740186386906e-05, "loss": 1.6126656532287598, "step": 1326 }, { "epoch": 0.11202684592087629, "grad_norm": 0.1513671875, "learning_rate": 4.923580546442784e-05, "loss": 1.5599323511123657, "step": 1327 }, { "epoch": 0.1121112670557074, "grad_norm": 0.14453125, "learning_rate": 4.923420742174076e-05, "loss": 1.5351808071136475, "step": 1328 }, { "epoch": 0.1121956881905385, "grad_norm": 0.1650390625, "learning_rate": 4.9232607735916156e-05, "loss": 1.611683964729309, "step": 1329 }, { "epoch": 0.11228010932536961, "grad_norm": 0.1494140625, "learning_rate": 4.923100640706251e-05, "loss": 1.4965497255325317, "step": 1330 }, { "epoch": 0.11236453046020072, "grad_norm": 0.15234375, "learning_rate": 4.922940343528839e-05, "loss": 1.4797807931900024, "step": 1331 }, { "epoch": 0.11244895159503182, "grad_norm": 0.150390625, "learning_rate": 4.9227798820702465e-05, "loss": 1.6290721893310547, "step": 1332 }, { "epoch": 0.11253337272986293, "grad_norm": 0.1474609375, "learning_rate": 4.922619256341355e-05, "loss": 1.5409425497055054, "step": 1333 }, { "epoch": 0.11261779386469403, "grad_norm": 0.1416015625, "learning_rate": 4.922458466353055e-05, "loss": 1.5112552642822266, "step": 1334 }, { "epoch": 0.11270221499952512, "grad_norm": 0.1357421875, "learning_rate": 4.922297512116248e-05, "loss": 1.5286753177642822, "step": 1335 }, { "epoch": 0.11278663613435623, "grad_norm": 0.1474609375, "learning_rate": 4.9221363936418465e-05, "loss": 1.564696192741394, "step": 1336 }, { "epoch": 0.11287105726918734, "grad_norm": 0.1552734375, "learning_rate": 4.921975110940776e-05, "loss": 1.5686900615692139, "step": 1337 }, { "epoch": 0.11295547840401844, "grad_norm": 0.15234375, "learning_rate": 4.921813664023972e-05, "loss": 1.601433515548706, "step": 1338 }, { "epoch": 0.11303989953884955, "grad_norm": 0.1357421875, "learning_rate": 4.921652052902379e-05, "loss": 1.6793524026870728, "step": 1339 }, { "epoch": 0.11312432067368065, "grad_norm": 0.1416015625, "learning_rate": 4.921490277586957e-05, "loss": 1.5699999332427979, "step": 1340 }, { "epoch": 0.11320874180851176, "grad_norm": 0.1279296875, "learning_rate": 4.9213283380886734e-05, "loss": 1.5319290161132812, "step": 1341 }, { "epoch": 0.11329316294334286, "grad_norm": 0.16015625, "learning_rate": 4.921166234418508e-05, "loss": 1.7047789096832275, "step": 1342 }, { "epoch": 0.11337758407817397, "grad_norm": 0.146484375, "learning_rate": 4.921003966587453e-05, "loss": 1.5735679864883423, "step": 1343 }, { "epoch": 0.11346200521300508, "grad_norm": 0.15234375, "learning_rate": 4.9208415346065084e-05, "loss": 1.5170552730560303, "step": 1344 }, { "epoch": 0.11354642634783618, "grad_norm": 0.1513671875, "learning_rate": 4.9206789384866904e-05, "loss": 1.6251944303512573, "step": 1345 }, { "epoch": 0.11363084748266729, "grad_norm": 0.1474609375, "learning_rate": 4.9205161782390206e-05, "loss": 1.5583317279815674, "step": 1346 }, { "epoch": 0.1137152686174984, "grad_norm": 0.16015625, "learning_rate": 4.9203532538745364e-05, "loss": 1.5891584157943726, "step": 1347 }, { "epoch": 0.1137996897523295, "grad_norm": 0.1591796875, "learning_rate": 4.9201901654042836e-05, "loss": 1.5413933992385864, "step": 1348 }, { "epoch": 0.1138841108871606, "grad_norm": 0.146484375, "learning_rate": 4.92002691283932e-05, "loss": 1.5529067516326904, "step": 1349 }, { "epoch": 0.11396853202199171, "grad_norm": 0.1611328125, "learning_rate": 4.9198634961907156e-05, "loss": 1.5698425769805908, "step": 1350 }, { "epoch": 0.11405295315682282, "grad_norm": 0.146484375, "learning_rate": 4.9196999154695485e-05, "loss": 1.5525351762771606, "step": 1351 }, { "epoch": 0.11413737429165391, "grad_norm": 0.181640625, "learning_rate": 4.919536170686911e-05, "loss": 1.5645416975021362, "step": 1352 }, { "epoch": 0.11422179542648501, "grad_norm": 0.1484375, "learning_rate": 4.9193722618539064e-05, "loss": 1.6197509765625, "step": 1353 }, { "epoch": 0.11430621656131612, "grad_norm": 0.1328125, "learning_rate": 4.9192081889816454e-05, "loss": 1.6072185039520264, "step": 1354 }, { "epoch": 0.11439063769614723, "grad_norm": 0.158203125, "learning_rate": 4.919043952081256e-05, "loss": 1.60439133644104, "step": 1355 }, { "epoch": 0.11447505883097833, "grad_norm": 0.15234375, "learning_rate": 4.918879551163871e-05, "loss": 1.5620983839035034, "step": 1356 }, { "epoch": 0.11455947996580944, "grad_norm": 0.146484375, "learning_rate": 4.918714986240638e-05, "loss": 1.4545835256576538, "step": 1357 }, { "epoch": 0.11464390110064054, "grad_norm": 0.14453125, "learning_rate": 4.918550257322715e-05, "loss": 1.5686612129211426, "step": 1358 }, { "epoch": 0.11472832223547165, "grad_norm": 0.140625, "learning_rate": 4.918385364421272e-05, "loss": 1.597298264503479, "step": 1359 }, { "epoch": 0.11481274337030276, "grad_norm": 0.177734375, "learning_rate": 4.9182203075474884e-05, "loss": 1.5153069496154785, "step": 1360 }, { "epoch": 0.11489716450513386, "grad_norm": 0.142578125, "learning_rate": 4.918055086712554e-05, "loss": 1.5708270072937012, "step": 1361 }, { "epoch": 0.11498158563996497, "grad_norm": 0.142578125, "learning_rate": 4.917889701927674e-05, "loss": 1.5879926681518555, "step": 1362 }, { "epoch": 0.11506600677479607, "grad_norm": 0.15234375, "learning_rate": 4.917724153204059e-05, "loss": 1.6651703119277954, "step": 1363 }, { "epoch": 0.11515042790962718, "grad_norm": 0.15234375, "learning_rate": 4.9175584405529356e-05, "loss": 1.6100382804870605, "step": 1364 }, { "epoch": 0.11523484904445828, "grad_norm": 0.14453125, "learning_rate": 4.917392563985539e-05, "loss": 1.595951795578003, "step": 1365 }, { "epoch": 0.11531927017928939, "grad_norm": 0.1435546875, "learning_rate": 4.917226523513116e-05, "loss": 1.5931620597839355, "step": 1366 }, { "epoch": 0.1154036913141205, "grad_norm": 0.185546875, "learning_rate": 4.9170603191469244e-05, "loss": 1.6065236330032349, "step": 1367 }, { "epoch": 0.11548811244895159, "grad_norm": 0.1455078125, "learning_rate": 4.9168939508982324e-05, "loss": 1.5936858654022217, "step": 1368 }, { "epoch": 0.1155725335837827, "grad_norm": 0.154296875, "learning_rate": 4.916727418778322e-05, "loss": 1.574998378753662, "step": 1369 }, { "epoch": 0.1156569547186138, "grad_norm": 0.1435546875, "learning_rate": 4.9165607227984835e-05, "loss": 1.5341953039169312, "step": 1370 }, { "epoch": 0.1157413758534449, "grad_norm": 0.140625, "learning_rate": 4.916393862970019e-05, "loss": 1.582316517829895, "step": 1371 }, { "epoch": 0.11582579698827601, "grad_norm": 0.15234375, "learning_rate": 4.916226839304243e-05, "loss": 1.6105026006698608, "step": 1372 }, { "epoch": 0.11591021812310712, "grad_norm": 0.1357421875, "learning_rate": 4.916059651812479e-05, "loss": 1.5574591159820557, "step": 1373 }, { "epoch": 0.11599463925793822, "grad_norm": 0.1552734375, "learning_rate": 4.915892300506063e-05, "loss": 1.5452638864517212, "step": 1374 }, { "epoch": 0.11607906039276933, "grad_norm": 0.13671875, "learning_rate": 4.9157247853963424e-05, "loss": 1.5453053712844849, "step": 1375 }, { "epoch": 0.11616348152760043, "grad_norm": 0.1357421875, "learning_rate": 4.915557106494675e-05, "loss": 1.4961192607879639, "step": 1376 }, { "epoch": 0.11624790266243154, "grad_norm": 0.1748046875, "learning_rate": 4.915389263812429e-05, "loss": 1.5731927156448364, "step": 1377 }, { "epoch": 0.11633232379726265, "grad_norm": 0.14453125, "learning_rate": 4.9152212573609844e-05, "loss": 1.5847749710083008, "step": 1378 }, { "epoch": 0.11641674493209375, "grad_norm": 0.154296875, "learning_rate": 4.915053087151734e-05, "loss": 1.5598156452178955, "step": 1379 }, { "epoch": 0.11650116606692486, "grad_norm": 0.1552734375, "learning_rate": 4.9148847531960795e-05, "loss": 1.5675901174545288, "step": 1380 }, { "epoch": 0.11658558720175596, "grad_norm": 0.1552734375, "learning_rate": 4.914716255505434e-05, "loss": 1.5659734010696411, "step": 1381 }, { "epoch": 0.11667000833658707, "grad_norm": 0.1484375, "learning_rate": 4.914547594091221e-05, "loss": 1.6038693189620972, "step": 1382 }, { "epoch": 0.11675442947141818, "grad_norm": 0.1376953125, "learning_rate": 4.9143787689648784e-05, "loss": 1.4196391105651855, "step": 1383 }, { "epoch": 0.11683885060624928, "grad_norm": 0.1396484375, "learning_rate": 4.914209780137852e-05, "loss": 1.620425820350647, "step": 1384 }, { "epoch": 0.11692327174108037, "grad_norm": 0.1591796875, "learning_rate": 4.914040627621599e-05, "loss": 1.5982425212860107, "step": 1385 }, { "epoch": 0.11700769287591148, "grad_norm": 0.1416015625, "learning_rate": 4.913871311427589e-05, "loss": 1.535482406616211, "step": 1386 }, { "epoch": 0.11709211401074258, "grad_norm": 0.146484375, "learning_rate": 4.913701831567302e-05, "loss": 1.5309085845947266, "step": 1387 }, { "epoch": 0.11717653514557369, "grad_norm": 0.17578125, "learning_rate": 4.9135321880522287e-05, "loss": 1.5833656787872314, "step": 1388 }, { "epoch": 0.1172609562804048, "grad_norm": 0.1640625, "learning_rate": 4.913362380893872e-05, "loss": 1.5258110761642456, "step": 1389 }, { "epoch": 0.1173453774152359, "grad_norm": 0.142578125, "learning_rate": 4.913192410103745e-05, "loss": 1.5628185272216797, "step": 1390 }, { "epoch": 0.11742979855006701, "grad_norm": 0.1796875, "learning_rate": 4.913022275693372e-05, "loss": 1.5719926357269287, "step": 1391 }, { "epoch": 0.11751421968489811, "grad_norm": 0.1474609375, "learning_rate": 4.912851977674289e-05, "loss": 1.575455665588379, "step": 1392 }, { "epoch": 0.11759864081972922, "grad_norm": 0.140625, "learning_rate": 4.912681516058041e-05, "loss": 1.563199520111084, "step": 1393 }, { "epoch": 0.11768306195456033, "grad_norm": 0.169921875, "learning_rate": 4.912510890856188e-05, "loss": 1.6706916093826294, "step": 1394 }, { "epoch": 0.11776748308939143, "grad_norm": 0.138671875, "learning_rate": 4.9123401020802974e-05, "loss": 1.4954906702041626, "step": 1395 }, { "epoch": 0.11785190422422254, "grad_norm": 0.142578125, "learning_rate": 4.9121691497419485e-05, "loss": 1.5883949995040894, "step": 1396 }, { "epoch": 0.11793632535905364, "grad_norm": 0.134765625, "learning_rate": 4.911998033852734e-05, "loss": 1.5186786651611328, "step": 1397 }, { "epoch": 0.11802074649388475, "grad_norm": 0.13671875, "learning_rate": 4.911826754424255e-05, "loss": 1.4764958620071411, "step": 1398 }, { "epoch": 0.11810516762871585, "grad_norm": 0.1923828125, "learning_rate": 4.911655311468125e-05, "loss": 1.5714792013168335, "step": 1399 }, { "epoch": 0.11818958876354696, "grad_norm": 0.1552734375, "learning_rate": 4.911483704995968e-05, "loss": 1.620301365852356, "step": 1400 }, { "epoch": 0.11827400989837807, "grad_norm": 0.1552734375, "learning_rate": 4.911311935019419e-05, "loss": 1.5977178812026978, "step": 1401 }, { "epoch": 0.11835843103320916, "grad_norm": 0.1572265625, "learning_rate": 4.911140001550125e-05, "loss": 1.6046440601348877, "step": 1402 }, { "epoch": 0.11844285216804026, "grad_norm": 0.1416015625, "learning_rate": 4.910967904599743e-05, "loss": 1.5854542255401611, "step": 1403 }, { "epoch": 0.11852727330287137, "grad_norm": 0.1328125, "learning_rate": 4.910795644179942e-05, "loss": 1.4908759593963623, "step": 1404 }, { "epoch": 0.11861169443770248, "grad_norm": 0.1357421875, "learning_rate": 4.9106232203024014e-05, "loss": 1.5450584888458252, "step": 1405 }, { "epoch": 0.11869611557253358, "grad_norm": 0.162109375, "learning_rate": 4.9104506329788124e-05, "loss": 1.651362419128418, "step": 1406 }, { "epoch": 0.11878053670736469, "grad_norm": 0.150390625, "learning_rate": 4.910277882220877e-05, "loss": 1.6152138710021973, "step": 1407 }, { "epoch": 0.11886495784219579, "grad_norm": 0.1455078125, "learning_rate": 4.9101049680403064e-05, "loss": 1.584620714187622, "step": 1408 }, { "epoch": 0.1189493789770269, "grad_norm": 0.1552734375, "learning_rate": 4.9099318904488265e-05, "loss": 1.5850114822387695, "step": 1409 }, { "epoch": 0.119033800111858, "grad_norm": 0.1572265625, "learning_rate": 4.909758649458172e-05, "loss": 1.709367036819458, "step": 1410 }, { "epoch": 0.11911822124668911, "grad_norm": 0.171875, "learning_rate": 4.909585245080088e-05, "loss": 1.6845283508300781, "step": 1411 }, { "epoch": 0.11920264238152022, "grad_norm": 0.1484375, "learning_rate": 4.9094116773263335e-05, "loss": 1.5516842603683472, "step": 1412 }, { "epoch": 0.11928706351635132, "grad_norm": 0.1640625, "learning_rate": 4.9092379462086756e-05, "loss": 1.6803674697875977, "step": 1413 }, { "epoch": 0.11937148465118243, "grad_norm": 0.1552734375, "learning_rate": 4.909064051738893e-05, "loss": 1.529933214187622, "step": 1414 }, { "epoch": 0.11945590578601353, "grad_norm": 0.1474609375, "learning_rate": 4.908889993928778e-05, "loss": 1.5279641151428223, "step": 1415 }, { "epoch": 0.11954032692084464, "grad_norm": 0.1396484375, "learning_rate": 4.908715772790131e-05, "loss": 1.558773159980774, "step": 1416 }, { "epoch": 0.11962474805567574, "grad_norm": 0.138671875, "learning_rate": 4.908541388334765e-05, "loss": 1.5712971687316895, "step": 1417 }, { "epoch": 0.11970916919050684, "grad_norm": 0.1357421875, "learning_rate": 4.908366840574503e-05, "loss": 1.555100679397583, "step": 1418 }, { "epoch": 0.11979359032533794, "grad_norm": 0.1962890625, "learning_rate": 4.9081921295211805e-05, "loss": 1.6004775762557983, "step": 1419 }, { "epoch": 0.11987801146016905, "grad_norm": 0.173828125, "learning_rate": 4.908017255186643e-05, "loss": 1.71947181224823, "step": 1420 }, { "epoch": 0.11996243259500015, "grad_norm": 0.150390625, "learning_rate": 4.907842217582748e-05, "loss": 1.4829893112182617, "step": 1421 }, { "epoch": 0.12004685372983126, "grad_norm": 0.20703125, "learning_rate": 4.9076670167213616e-05, "loss": 1.6297732591629028, "step": 1422 }, { "epoch": 0.12013127486466237, "grad_norm": 0.1669921875, "learning_rate": 4.9074916526143653e-05, "loss": 1.570002555847168, "step": 1423 }, { "epoch": 0.12021569599949347, "grad_norm": 0.1826171875, "learning_rate": 4.9073161252736474e-05, "loss": 1.6551793813705444, "step": 1424 }, { "epoch": 0.12030011713432458, "grad_norm": 0.173828125, "learning_rate": 4.90714043471111e-05, "loss": 1.521382451057434, "step": 1425 }, { "epoch": 0.12038453826915568, "grad_norm": 0.1826171875, "learning_rate": 4.906964580938667e-05, "loss": 1.5316988229751587, "step": 1426 }, { "epoch": 0.12046895940398679, "grad_norm": 0.1533203125, "learning_rate": 4.9067885639682376e-05, "loss": 1.5901329517364502, "step": 1427 }, { "epoch": 0.1205533805388179, "grad_norm": 0.1748046875, "learning_rate": 4.906612383811759e-05, "loss": 1.5688354969024658, "step": 1428 }, { "epoch": 0.120637801673649, "grad_norm": 0.1806640625, "learning_rate": 4.906436040481176e-05, "loss": 1.570517659187317, "step": 1429 }, { "epoch": 0.1207222228084801, "grad_norm": 0.1689453125, "learning_rate": 4.906259533988445e-05, "loss": 1.5729737281799316, "step": 1430 }, { "epoch": 0.12080664394331121, "grad_norm": 0.1484375, "learning_rate": 4.9060828643455334e-05, "loss": 1.642932653427124, "step": 1431 }, { "epoch": 0.12089106507814232, "grad_norm": 0.142578125, "learning_rate": 4.905906031564421e-05, "loss": 1.5789315700531006, "step": 1432 }, { "epoch": 0.12097548621297342, "grad_norm": 0.1591796875, "learning_rate": 4.905729035657097e-05, "loss": 1.5250803232192993, "step": 1433 }, { "epoch": 0.12105990734780453, "grad_norm": 0.15234375, "learning_rate": 4.905551876635561e-05, "loss": 1.5084314346313477, "step": 1434 }, { "epoch": 0.12114432848263562, "grad_norm": 0.1494140625, "learning_rate": 4.905374554511825e-05, "loss": 1.6086212396621704, "step": 1435 }, { "epoch": 0.12122874961746673, "grad_norm": 0.16015625, "learning_rate": 4.905197069297913e-05, "loss": 1.565629482269287, "step": 1436 }, { "epoch": 0.12131317075229783, "grad_norm": 0.1533203125, "learning_rate": 4.9050194210058584e-05, "loss": 1.5182478427886963, "step": 1437 }, { "epoch": 0.12139759188712894, "grad_norm": 0.1357421875, "learning_rate": 4.9048416096477066e-05, "loss": 1.4481887817382812, "step": 1438 }, { "epoch": 0.12148201302196004, "grad_norm": 0.158203125, "learning_rate": 4.9046636352355126e-05, "loss": 1.6732350587844849, "step": 1439 }, { "epoch": 0.12156643415679115, "grad_norm": 0.1748046875, "learning_rate": 4.904485497781345e-05, "loss": 1.6247808933258057, "step": 1440 }, { "epoch": 0.12165085529162226, "grad_norm": 0.1484375, "learning_rate": 4.90430719729728e-05, "loss": 1.6151690483093262, "step": 1441 }, { "epoch": 0.12173527642645336, "grad_norm": 0.166015625, "learning_rate": 4.9041287337954076e-05, "loss": 1.6778324842453003, "step": 1442 }, { "epoch": 0.12181969756128447, "grad_norm": 0.146484375, "learning_rate": 4.9039501072878294e-05, "loss": 1.6357684135437012, "step": 1443 }, { "epoch": 0.12190411869611557, "grad_norm": 0.169921875, "learning_rate": 4.9037713177866546e-05, "loss": 1.5218141078948975, "step": 1444 }, { "epoch": 0.12198853983094668, "grad_norm": 0.1669921875, "learning_rate": 4.903592365304007e-05, "loss": 1.5567357540130615, "step": 1445 }, { "epoch": 0.12207296096577779, "grad_norm": 0.158203125, "learning_rate": 4.90341324985202e-05, "loss": 1.541542887687683, "step": 1446 }, { "epoch": 0.12215738210060889, "grad_norm": 0.1455078125, "learning_rate": 4.903233971442837e-05, "loss": 1.5667365789413452, "step": 1447 }, { "epoch": 0.12224180323544, "grad_norm": 0.1552734375, "learning_rate": 4.903054530088614e-05, "loss": 1.6663354635238647, "step": 1448 }, { "epoch": 0.1223262243702711, "grad_norm": 0.150390625, "learning_rate": 4.9028749258015175e-05, "loss": 1.544370412826538, "step": 1449 }, { "epoch": 0.12241064550510221, "grad_norm": 0.1513671875, "learning_rate": 4.9026951585937267e-05, "loss": 1.6657160520553589, "step": 1450 }, { "epoch": 0.1224950666399333, "grad_norm": 0.150390625, "learning_rate": 4.902515228477427e-05, "loss": 1.5708839893341064, "step": 1451 }, { "epoch": 0.1225794877747644, "grad_norm": 0.162109375, "learning_rate": 4.9023351354648204e-05, "loss": 1.516056776046753, "step": 1452 }, { "epoch": 0.12266390890959551, "grad_norm": 0.1572265625, "learning_rate": 4.9021548795681185e-05, "loss": 1.4261225461959839, "step": 1453 }, { "epoch": 0.12274833004442662, "grad_norm": 0.1376953125, "learning_rate": 4.90197446079954e-05, "loss": 1.5922422409057617, "step": 1454 }, { "epoch": 0.12283275117925772, "grad_norm": 0.150390625, "learning_rate": 4.90179387917132e-05, "loss": 1.5440268516540527, "step": 1455 }, { "epoch": 0.12291717231408883, "grad_norm": 0.1572265625, "learning_rate": 4.9016131346957026e-05, "loss": 1.5596026182174683, "step": 1456 }, { "epoch": 0.12300159344891994, "grad_norm": 0.146484375, "learning_rate": 4.9014322273849414e-05, "loss": 1.569815754890442, "step": 1457 }, { "epoch": 0.12308601458375104, "grad_norm": 0.1494140625, "learning_rate": 4.9012511572513034e-05, "loss": 1.5379934310913086, "step": 1458 }, { "epoch": 0.12317043571858215, "grad_norm": 0.1435546875, "learning_rate": 4.901069924307064e-05, "loss": 1.5978996753692627, "step": 1459 }, { "epoch": 0.12325485685341325, "grad_norm": 0.158203125, "learning_rate": 4.9008885285645134e-05, "loss": 1.5666124820709229, "step": 1460 }, { "epoch": 0.12333927798824436, "grad_norm": 0.1572265625, "learning_rate": 4.9007069700359484e-05, "loss": 1.6096376180648804, "step": 1461 }, { "epoch": 0.12342369912307546, "grad_norm": 0.1533203125, "learning_rate": 4.900525248733682e-05, "loss": 1.629467248916626, "step": 1462 }, { "epoch": 0.12350812025790657, "grad_norm": 0.1376953125, "learning_rate": 4.900343364670032e-05, "loss": 1.5182805061340332, "step": 1463 }, { "epoch": 0.12359254139273768, "grad_norm": 0.1455078125, "learning_rate": 4.9001613178573326e-05, "loss": 1.5514777898788452, "step": 1464 }, { "epoch": 0.12367696252756878, "grad_norm": 0.1357421875, "learning_rate": 4.899979108307927e-05, "loss": 1.551185131072998, "step": 1465 }, { "epoch": 0.12376138366239989, "grad_norm": 0.1533203125, "learning_rate": 4.899796736034169e-05, "loss": 1.5661139488220215, "step": 1466 }, { "epoch": 0.123845804797231, "grad_norm": 0.1376953125, "learning_rate": 4.899614201048423e-05, "loss": 1.4870394468307495, "step": 1467 }, { "epoch": 0.12393022593206209, "grad_norm": 0.1640625, "learning_rate": 4.899431503363068e-05, "loss": 1.6274763345718384, "step": 1468 }, { "epoch": 0.12401464706689319, "grad_norm": 0.150390625, "learning_rate": 4.899248642990489e-05, "loss": 1.5620934963226318, "step": 1469 }, { "epoch": 0.1240990682017243, "grad_norm": 0.146484375, "learning_rate": 4.899065619943084e-05, "loss": 1.5051394701004028, "step": 1470 }, { "epoch": 0.1241834893365554, "grad_norm": 0.1455078125, "learning_rate": 4.898882434233265e-05, "loss": 1.5797427892684937, "step": 1471 }, { "epoch": 0.12426791047138651, "grad_norm": 0.15625, "learning_rate": 4.8986990858734494e-05, "loss": 1.551324486732483, "step": 1472 }, { "epoch": 0.12435233160621761, "grad_norm": 0.1708984375, "learning_rate": 4.89851557487607e-05, "loss": 1.5508707761764526, "step": 1473 }, { "epoch": 0.12443675274104872, "grad_norm": 0.162109375, "learning_rate": 4.89833190125357e-05, "loss": 1.5817756652832031, "step": 1474 }, { "epoch": 0.12452117387587983, "grad_norm": 0.1591796875, "learning_rate": 4.898148065018403e-05, "loss": 1.5748255252838135, "step": 1475 }, { "epoch": 0.12460559501071093, "grad_norm": 0.1357421875, "learning_rate": 4.8979640661830315e-05, "loss": 1.5241166353225708, "step": 1476 }, { "epoch": 0.12469001614554204, "grad_norm": 0.1416015625, "learning_rate": 4.897779904759933e-05, "loss": 1.5472779273986816, "step": 1477 }, { "epoch": 0.12477443728037314, "grad_norm": 0.1806640625, "learning_rate": 4.8975955807615934e-05, "loss": 1.56446373462677, "step": 1478 }, { "epoch": 0.12485885841520425, "grad_norm": 0.1591796875, "learning_rate": 4.8974110942005104e-05, "loss": 1.6823064088821411, "step": 1479 }, { "epoch": 0.12494327955003535, "grad_norm": 0.162109375, "learning_rate": 4.897226445089193e-05, "loss": 1.5454561710357666, "step": 1480 }, { "epoch": 0.12502770068486646, "grad_norm": 0.1845703125, "learning_rate": 4.897041633440159e-05, "loss": 1.6434730291366577, "step": 1481 }, { "epoch": 0.12511212181969755, "grad_norm": 0.1552734375, "learning_rate": 4.896856659265942e-05, "loss": 1.6153327226638794, "step": 1482 }, { "epoch": 0.12519654295452867, "grad_norm": 0.162109375, "learning_rate": 4.8966715225790816e-05, "loss": 1.580686330795288, "step": 1483 }, { "epoch": 0.12528096408935976, "grad_norm": 0.228515625, "learning_rate": 4.896486223392131e-05, "loss": 1.5943100452423096, "step": 1484 }, { "epoch": 0.12536538522419088, "grad_norm": 0.1728515625, "learning_rate": 4.8963007617176535e-05, "loss": 1.605948567390442, "step": 1485 }, { "epoch": 0.12544980635902198, "grad_norm": 0.158203125, "learning_rate": 4.8961151375682254e-05, "loss": 1.55374014377594, "step": 1486 }, { "epoch": 0.1255342274938531, "grad_norm": 0.1416015625, "learning_rate": 4.895929350956431e-05, "loss": 1.6460001468658447, "step": 1487 }, { "epoch": 0.1256186486286842, "grad_norm": 0.17578125, "learning_rate": 4.8957434018948675e-05, "loss": 1.6449549198150635, "step": 1488 }, { "epoch": 0.1257030697635153, "grad_norm": 0.1611328125, "learning_rate": 4.8955572903961435e-05, "loss": 1.7256759405136108, "step": 1489 }, { "epoch": 0.1257874908983464, "grad_norm": 0.1767578125, "learning_rate": 4.8953710164728765e-05, "loss": 1.6062498092651367, "step": 1490 }, { "epoch": 0.12587191203317752, "grad_norm": 0.1474609375, "learning_rate": 4.8951845801376974e-05, "loss": 1.5168333053588867, "step": 1491 }, { "epoch": 0.1259563331680086, "grad_norm": 0.14453125, "learning_rate": 4.8949979814032455e-05, "loss": 1.4995940923690796, "step": 1492 }, { "epoch": 0.1260407543028397, "grad_norm": 0.1669921875, "learning_rate": 4.894811220282175e-05, "loss": 1.6079843044281006, "step": 1493 }, { "epoch": 0.12612517543767082, "grad_norm": 0.1669921875, "learning_rate": 4.894624296787146e-05, "loss": 1.5414135456085205, "step": 1494 }, { "epoch": 0.12620959657250191, "grad_norm": 0.2314453125, "learning_rate": 4.8944372109308343e-05, "loss": 1.5204417705535889, "step": 1495 }, { "epoch": 0.12629401770733303, "grad_norm": 0.1533203125, "learning_rate": 4.894249962725924e-05, "loss": 1.5474050045013428, "step": 1496 }, { "epoch": 0.12637843884216413, "grad_norm": 0.142578125, "learning_rate": 4.8940625521851116e-05, "loss": 1.5464391708374023, "step": 1497 }, { "epoch": 0.12646285997699525, "grad_norm": 0.1435546875, "learning_rate": 4.893874979321104e-05, "loss": 1.5853023529052734, "step": 1498 }, { "epoch": 0.12654728111182634, "grad_norm": 0.146484375, "learning_rate": 4.893687244146618e-05, "loss": 1.6234502792358398, "step": 1499 }, { "epoch": 0.12663170224665746, "grad_norm": 0.1572265625, "learning_rate": 4.893499346674383e-05, "loss": 1.6265147924423218, "step": 1500 }, { "epoch": 0.12671612338148855, "grad_norm": 0.1611328125, "learning_rate": 4.8933112869171394e-05, "loss": 1.5312403440475464, "step": 1501 }, { "epoch": 0.12680054451631967, "grad_norm": 0.150390625, "learning_rate": 4.893123064887638e-05, "loss": 1.560545802116394, "step": 1502 }, { "epoch": 0.12688496565115076, "grad_norm": 0.1748046875, "learning_rate": 4.89293468059864e-05, "loss": 1.5519657135009766, "step": 1503 }, { "epoch": 0.12696938678598188, "grad_norm": 0.1396484375, "learning_rate": 4.8927461340629186e-05, "loss": 1.5895323753356934, "step": 1504 }, { "epoch": 0.12705380792081297, "grad_norm": 0.1357421875, "learning_rate": 4.892557425293259e-05, "loss": 1.5180543661117554, "step": 1505 }, { "epoch": 0.1271382290556441, "grad_norm": 0.158203125, "learning_rate": 4.892368554302454e-05, "loss": 1.617601990699768, "step": 1506 }, { "epoch": 0.12722265019047518, "grad_norm": 0.140625, "learning_rate": 4.892179521103311e-05, "loss": 1.566053032875061, "step": 1507 }, { "epoch": 0.1273070713253063, "grad_norm": 0.138671875, "learning_rate": 4.891990325708646e-05, "loss": 1.5596973896026611, "step": 1508 }, { "epoch": 0.1273914924601374, "grad_norm": 0.1435546875, "learning_rate": 4.891800968131288e-05, "loss": 1.5555732250213623, "step": 1509 }, { "epoch": 0.1274759135949685, "grad_norm": 0.150390625, "learning_rate": 4.8916114483840746e-05, "loss": 1.484452486038208, "step": 1510 }, { "epoch": 0.1275603347297996, "grad_norm": 0.1484375, "learning_rate": 4.8914217664798565e-05, "loss": 1.5741115808486938, "step": 1511 }, { "epoch": 0.1276447558646307, "grad_norm": 0.15234375, "learning_rate": 4.891231922431495e-05, "loss": 1.6000642776489258, "step": 1512 }, { "epoch": 0.12772917699946182, "grad_norm": 0.138671875, "learning_rate": 4.891041916251861e-05, "loss": 1.5463569164276123, "step": 1513 }, { "epoch": 0.1278135981342929, "grad_norm": 0.1435546875, "learning_rate": 4.890851747953837e-05, "loss": 1.5432697534561157, "step": 1514 }, { "epoch": 0.12789801926912403, "grad_norm": 0.171875, "learning_rate": 4.890661417550319e-05, "loss": 1.6308988332748413, "step": 1515 }, { "epoch": 0.12798244040395512, "grad_norm": 0.169921875, "learning_rate": 4.8904709250542104e-05, "loss": 1.5601962804794312, "step": 1516 }, { "epoch": 0.12806686153878624, "grad_norm": 0.1416015625, "learning_rate": 4.8902802704784254e-05, "loss": 1.453061819076538, "step": 1517 }, { "epoch": 0.12815128267361733, "grad_norm": 0.1669921875, "learning_rate": 4.8900894538358944e-05, "loss": 1.4673254489898682, "step": 1518 }, { "epoch": 0.12823570380844845, "grad_norm": 0.146484375, "learning_rate": 4.8898984751395525e-05, "loss": 1.5620781183242798, "step": 1519 }, { "epoch": 0.12832012494327955, "grad_norm": 0.1689453125, "learning_rate": 4.8897073344023505e-05, "loss": 1.6525150537490845, "step": 1520 }, { "epoch": 0.12840454607811067, "grad_norm": 0.1455078125, "learning_rate": 4.889516031637246e-05, "loss": 1.6064225435256958, "step": 1521 }, { "epoch": 0.12848896721294176, "grad_norm": 0.1904296875, "learning_rate": 4.889324566857211e-05, "loss": 1.5667465925216675, "step": 1522 }, { "epoch": 0.12857338834777288, "grad_norm": 0.1533203125, "learning_rate": 4.889132940075227e-05, "loss": 1.512059211730957, "step": 1523 }, { "epoch": 0.12865780948260397, "grad_norm": 0.1611328125, "learning_rate": 4.888941151304288e-05, "loss": 1.5250128507614136, "step": 1524 }, { "epoch": 0.1287422306174351, "grad_norm": 0.1494140625, "learning_rate": 4.888749200557396e-05, "loss": 1.5981990098953247, "step": 1525 }, { "epoch": 0.12882665175226618, "grad_norm": 0.1484375, "learning_rate": 4.888557087847566e-05, "loss": 1.558314323425293, "step": 1526 }, { "epoch": 0.12891107288709727, "grad_norm": 0.1640625, "learning_rate": 4.8883648131878244e-05, "loss": 1.5519461631774902, "step": 1527 }, { "epoch": 0.1289954940219284, "grad_norm": 0.1826171875, "learning_rate": 4.888172376591208e-05, "loss": 1.5678374767303467, "step": 1528 }, { "epoch": 0.12907991515675948, "grad_norm": 0.14453125, "learning_rate": 4.8879797780707636e-05, "loss": 1.5711122751235962, "step": 1529 }, { "epoch": 0.1291643362915906, "grad_norm": 0.1455078125, "learning_rate": 4.887787017639551e-05, "loss": 1.5594981908798218, "step": 1530 }, { "epoch": 0.1292487574264217, "grad_norm": 0.1435546875, "learning_rate": 4.887594095310639e-05, "loss": 1.4606518745422363, "step": 1531 }, { "epoch": 0.12933317856125282, "grad_norm": 0.1484375, "learning_rate": 4.8874010110971075e-05, "loss": 1.4921462535858154, "step": 1532 }, { "epoch": 0.1294175996960839, "grad_norm": 0.1513671875, "learning_rate": 4.8872077650120494e-05, "loss": 1.5455515384674072, "step": 1533 }, { "epoch": 0.12950202083091503, "grad_norm": 0.14453125, "learning_rate": 4.8870143570685666e-05, "loss": 1.5714261531829834, "step": 1534 }, { "epoch": 0.12958644196574612, "grad_norm": 0.15234375, "learning_rate": 4.886820787279773e-05, "loss": 1.5271351337432861, "step": 1535 }, { "epoch": 0.12967086310057724, "grad_norm": 0.1611328125, "learning_rate": 4.8866270556587926e-05, "loss": 1.5987460613250732, "step": 1536 }, { "epoch": 0.12975528423540833, "grad_norm": 0.1357421875, "learning_rate": 4.886433162218761e-05, "loss": 1.602429747581482, "step": 1537 }, { "epoch": 0.12983970537023945, "grad_norm": 0.142578125, "learning_rate": 4.886239106972825e-05, "loss": 1.576725959777832, "step": 1538 }, { "epoch": 0.12992412650507054, "grad_norm": 0.18359375, "learning_rate": 4.8860448899341415e-05, "loss": 1.524839997291565, "step": 1539 }, { "epoch": 0.13000854763990166, "grad_norm": 0.1640625, "learning_rate": 4.8858505111158804e-05, "loss": 1.5144044160842896, "step": 1540 }, { "epoch": 0.13009296877473275, "grad_norm": 0.1494140625, "learning_rate": 4.885655970531219e-05, "loss": 1.5785971879959106, "step": 1541 }, { "epoch": 0.13017738990956387, "grad_norm": 0.134765625, "learning_rate": 4.885461268193348e-05, "loss": 1.4991990327835083, "step": 1542 }, { "epoch": 0.13026181104439497, "grad_norm": 0.1591796875, "learning_rate": 4.88526640411547e-05, "loss": 1.4846675395965576, "step": 1543 }, { "epoch": 0.13034623217922606, "grad_norm": 0.15625, "learning_rate": 4.8850713783107945e-05, "loss": 1.5458866357803345, "step": 1544 }, { "epoch": 0.13043065331405718, "grad_norm": 0.1552734375, "learning_rate": 4.884876190792548e-05, "loss": 1.5901620388031006, "step": 1545 }, { "epoch": 0.13051507444888827, "grad_norm": 0.1494140625, "learning_rate": 4.884680841573964e-05, "loss": 1.4481935501098633, "step": 1546 }, { "epoch": 0.1305994955837194, "grad_norm": 0.1552734375, "learning_rate": 4.8844853306682856e-05, "loss": 1.6294457912445068, "step": 1547 }, { "epoch": 0.13068391671855048, "grad_norm": 0.1318359375, "learning_rate": 4.884289658088771e-05, "loss": 1.4966809749603271, "step": 1548 }, { "epoch": 0.1307683378533816, "grad_norm": 0.14453125, "learning_rate": 4.884093823848686e-05, "loss": 1.604305386543274, "step": 1549 }, { "epoch": 0.1308527589882127, "grad_norm": 0.15625, "learning_rate": 4.883897827961309e-05, "loss": 1.614500880241394, "step": 1550 }, { "epoch": 0.1309371801230438, "grad_norm": 0.1337890625, "learning_rate": 4.88370167043993e-05, "loss": 1.5409194231033325, "step": 1551 }, { "epoch": 0.1310216012578749, "grad_norm": 0.1484375, "learning_rate": 4.8835053512978475e-05, "loss": 1.6170616149902344, "step": 1552 }, { "epoch": 0.13110602239270602, "grad_norm": 0.1435546875, "learning_rate": 4.883308870548373e-05, "loss": 1.553998351097107, "step": 1553 }, { "epoch": 0.13119044352753712, "grad_norm": 0.1572265625, "learning_rate": 4.883112228204828e-05, "loss": 1.61740243434906, "step": 1554 }, { "epoch": 0.13127486466236823, "grad_norm": 0.1494140625, "learning_rate": 4.882915424280546e-05, "loss": 1.5674560070037842, "step": 1555 }, { "epoch": 0.13135928579719933, "grad_norm": 0.1474609375, "learning_rate": 4.882718458788871e-05, "loss": 1.5233744382858276, "step": 1556 }, { "epoch": 0.13144370693203045, "grad_norm": 0.1484375, "learning_rate": 4.882521331743157e-05, "loss": 1.505447268486023, "step": 1557 }, { "epoch": 0.13152812806686154, "grad_norm": 0.14453125, "learning_rate": 4.88232404315677e-05, "loss": 1.5687015056610107, "step": 1558 }, { "epoch": 0.13161254920169263, "grad_norm": 0.14453125, "learning_rate": 4.882126593043086e-05, "loss": 1.5698907375335693, "step": 1559 }, { "epoch": 0.13169697033652375, "grad_norm": 0.154296875, "learning_rate": 4.8819289814154935e-05, "loss": 1.553745150566101, "step": 1560 }, { "epoch": 0.13178139147135484, "grad_norm": 0.1357421875, "learning_rate": 4.8817312082873904e-05, "loss": 1.5440614223480225, "step": 1561 }, { "epoch": 0.13186581260618596, "grad_norm": 0.13671875, "learning_rate": 4.881533273672186e-05, "loss": 1.5457406044006348, "step": 1562 }, { "epoch": 0.13195023374101705, "grad_norm": 0.146484375, "learning_rate": 4.881335177583301e-05, "loss": 1.5837661027908325, "step": 1563 }, { "epoch": 0.13203465487584817, "grad_norm": 0.1513671875, "learning_rate": 4.881136920034168e-05, "loss": 1.5345100164413452, "step": 1564 }, { "epoch": 0.13211907601067926, "grad_norm": 0.13671875, "learning_rate": 4.880938501038228e-05, "loss": 1.5217176675796509, "step": 1565 }, { "epoch": 0.13220349714551038, "grad_norm": 0.1455078125, "learning_rate": 4.880739920608935e-05, "loss": 1.5359771251678467, "step": 1566 }, { "epoch": 0.13228791828034148, "grad_norm": 0.140625, "learning_rate": 4.880541178759752e-05, "loss": 1.5707626342773438, "step": 1567 }, { "epoch": 0.1323723394151726, "grad_norm": 0.13671875, "learning_rate": 4.880342275504156e-05, "loss": 1.550718069076538, "step": 1568 }, { "epoch": 0.1324567605500037, "grad_norm": 0.1435546875, "learning_rate": 4.880143210855631e-05, "loss": 1.5804505348205566, "step": 1569 }, { "epoch": 0.1325411816848348, "grad_norm": 0.1376953125, "learning_rate": 4.879943984827676e-05, "loss": 1.5133870840072632, "step": 1570 }, { "epoch": 0.1326256028196659, "grad_norm": 0.154296875, "learning_rate": 4.879744597433798e-05, "loss": 1.5858279466629028, "step": 1571 }, { "epoch": 0.13271002395449702, "grad_norm": 0.1474609375, "learning_rate": 4.879545048687516e-05, "loss": 1.639333724975586, "step": 1572 }, { "epoch": 0.1327944450893281, "grad_norm": 0.16015625, "learning_rate": 4.87934533860236e-05, "loss": 1.5317217111587524, "step": 1573 }, { "epoch": 0.13287886622415923, "grad_norm": 0.1416015625, "learning_rate": 4.8791454671918714e-05, "loss": 1.568875789642334, "step": 1574 }, { "epoch": 0.13296328735899032, "grad_norm": 0.13671875, "learning_rate": 4.8789454344696004e-05, "loss": 1.5308244228363037, "step": 1575 }, { "epoch": 0.13304770849382141, "grad_norm": 0.142578125, "learning_rate": 4.878745240449112e-05, "loss": 1.5302220582962036, "step": 1576 }, { "epoch": 0.13313212962865253, "grad_norm": 0.14453125, "learning_rate": 4.8785448851439775e-05, "loss": 1.5449347496032715, "step": 1577 }, { "epoch": 0.13321655076348363, "grad_norm": 0.13671875, "learning_rate": 4.8783443685677835e-05, "loss": 1.6081516742706299, "step": 1578 }, { "epoch": 0.13330097189831475, "grad_norm": 0.138671875, "learning_rate": 4.878143690734123e-05, "loss": 1.5317999124526978, "step": 1579 }, { "epoch": 0.13338539303314584, "grad_norm": 0.154296875, "learning_rate": 4.877942851656605e-05, "loss": 1.5266363620758057, "step": 1580 }, { "epoch": 0.13346981416797696, "grad_norm": 0.140625, "learning_rate": 4.877741851348846e-05, "loss": 1.5941509008407593, "step": 1581 }, { "epoch": 0.13355423530280805, "grad_norm": 0.16015625, "learning_rate": 4.877540689824473e-05, "loss": 1.5739288330078125, "step": 1582 }, { "epoch": 0.13363865643763917, "grad_norm": 0.162109375, "learning_rate": 4.877339367097128e-05, "loss": 1.6158264875411987, "step": 1583 }, { "epoch": 0.13372307757247026, "grad_norm": 0.142578125, "learning_rate": 4.877137883180459e-05, "loss": 1.6401176452636719, "step": 1584 }, { "epoch": 0.13380749870730138, "grad_norm": 0.1435546875, "learning_rate": 4.876936238088127e-05, "loss": 1.5517024993896484, "step": 1585 }, { "epoch": 0.13389191984213247, "grad_norm": 0.1357421875, "learning_rate": 4.876734431833805e-05, "loss": 1.4934613704681396, "step": 1586 }, { "epoch": 0.1339763409769636, "grad_norm": 0.1455078125, "learning_rate": 4.876532464431176e-05, "loss": 1.6388726234436035, "step": 1587 }, { "epoch": 0.13406076211179468, "grad_norm": 0.158203125, "learning_rate": 4.876330335893933e-05, "loss": 1.6442383527755737, "step": 1588 }, { "epoch": 0.1341451832466258, "grad_norm": 0.154296875, "learning_rate": 4.876128046235781e-05, "loss": 1.643612027168274, "step": 1589 }, { "epoch": 0.1342296043814569, "grad_norm": 0.1689453125, "learning_rate": 4.875925595470436e-05, "loss": 1.6283760070800781, "step": 1590 }, { "epoch": 0.13431402551628802, "grad_norm": 0.138671875, "learning_rate": 4.875722983611626e-05, "loss": 1.4887688159942627, "step": 1591 }, { "epoch": 0.1343984466511191, "grad_norm": 0.13671875, "learning_rate": 4.8755202106730857e-05, "loss": 1.5186043977737427, "step": 1592 }, { "epoch": 0.1344828677859502, "grad_norm": 0.1376953125, "learning_rate": 4.875317276668566e-05, "loss": 1.5932652950286865, "step": 1593 }, { "epoch": 0.13456728892078132, "grad_norm": 0.146484375, "learning_rate": 4.875114181611825e-05, "loss": 1.620898723602295, "step": 1594 }, { "epoch": 0.1346517100556124, "grad_norm": 0.1435546875, "learning_rate": 4.874910925516634e-05, "loss": 1.647580623626709, "step": 1595 }, { "epoch": 0.13473613119044353, "grad_norm": 0.1689453125, "learning_rate": 4.874707508396773e-05, "loss": 1.6436104774475098, "step": 1596 }, { "epoch": 0.13482055232527462, "grad_norm": 0.1435546875, "learning_rate": 4.874503930266035e-05, "loss": 1.5740541219711304, "step": 1597 }, { "epoch": 0.13490497346010574, "grad_norm": 0.142578125, "learning_rate": 4.874300191138224e-05, "loss": 1.5480284690856934, "step": 1598 }, { "epoch": 0.13498939459493683, "grad_norm": 0.1337890625, "learning_rate": 4.8740962910271515e-05, "loss": 1.5967217683792114, "step": 1599 }, { "epoch": 0.13507381572976795, "grad_norm": 0.134765625, "learning_rate": 4.873892229946645e-05, "loss": 1.5402497053146362, "step": 1600 }, { "epoch": 0.13515823686459905, "grad_norm": 0.1474609375, "learning_rate": 4.8736880079105386e-05, "loss": 1.525488257408142, "step": 1601 }, { "epoch": 0.13524265799943017, "grad_norm": 0.1640625, "learning_rate": 4.8734836249326796e-05, "loss": 1.5537159442901611, "step": 1602 }, { "epoch": 0.13532707913426126, "grad_norm": 0.1357421875, "learning_rate": 4.873279081026926e-05, "loss": 1.5277875661849976, "step": 1603 }, { "epoch": 0.13541150026909238, "grad_norm": 0.1455078125, "learning_rate": 4.873074376207146e-05, "loss": 1.6102138757705688, "step": 1604 }, { "epoch": 0.13549592140392347, "grad_norm": 0.138671875, "learning_rate": 4.872869510487219e-05, "loss": 1.5554484128952026, "step": 1605 }, { "epoch": 0.1355803425387546, "grad_norm": 0.1455078125, "learning_rate": 4.8726644838810354e-05, "loss": 1.6261547803878784, "step": 1606 }, { "epoch": 0.13566476367358568, "grad_norm": 0.138671875, "learning_rate": 4.872459296402497e-05, "loss": 1.6797655820846558, "step": 1607 }, { "epoch": 0.1357491848084168, "grad_norm": 0.1513671875, "learning_rate": 4.872253948065516e-05, "loss": 1.464200496673584, "step": 1608 }, { "epoch": 0.1358336059432479, "grad_norm": 0.1484375, "learning_rate": 4.872048438884015e-05, "loss": 1.548805594444275, "step": 1609 }, { "epoch": 0.13591802707807898, "grad_norm": 0.1455078125, "learning_rate": 4.871842768871928e-05, "loss": 1.5564279556274414, "step": 1610 }, { "epoch": 0.1360024482129101, "grad_norm": 0.1455078125, "learning_rate": 4.8716369380432e-05, "loss": 1.6053401231765747, "step": 1611 }, { "epoch": 0.1360868693477412, "grad_norm": 0.13671875, "learning_rate": 4.871430946411787e-05, "loss": 1.592158555984497, "step": 1612 }, { "epoch": 0.13617129048257232, "grad_norm": 0.134765625, "learning_rate": 4.871224793991656e-05, "loss": 1.4874478578567505, "step": 1613 }, { "epoch": 0.1362557116174034, "grad_norm": 0.1435546875, "learning_rate": 4.871018480796784e-05, "loss": 1.5617852210998535, "step": 1614 }, { "epoch": 0.13634013275223453, "grad_norm": 0.138671875, "learning_rate": 4.87081200684116e-05, "loss": 1.5675394535064697, "step": 1615 }, { "epoch": 0.13642455388706562, "grad_norm": 0.1474609375, "learning_rate": 4.8706053721387836e-05, "loss": 1.5847543478012085, "step": 1616 }, { "epoch": 0.13650897502189674, "grad_norm": 0.1572265625, "learning_rate": 4.870398576703664e-05, "loss": 1.533252239227295, "step": 1617 }, { "epoch": 0.13659339615672783, "grad_norm": 0.1484375, "learning_rate": 4.8701916205498236e-05, "loss": 1.5469331741333008, "step": 1618 }, { "epoch": 0.13667781729155895, "grad_norm": 0.1630859375, "learning_rate": 4.869984503691294e-05, "loss": 1.5625205039978027, "step": 1619 }, { "epoch": 0.13676223842639004, "grad_norm": 0.140625, "learning_rate": 4.8697772261421185e-05, "loss": 1.5665394067764282, "step": 1620 }, { "epoch": 0.13684665956122116, "grad_norm": 0.134765625, "learning_rate": 4.86956978791635e-05, "loss": 1.568131446838379, "step": 1621 }, { "epoch": 0.13693108069605225, "grad_norm": 0.1357421875, "learning_rate": 4.869362189028056e-05, "loss": 1.527104139328003, "step": 1622 }, { "epoch": 0.13701550183088337, "grad_norm": 0.1357421875, "learning_rate": 4.8691544294913094e-05, "loss": 1.4477158784866333, "step": 1623 }, { "epoch": 0.13709992296571447, "grad_norm": 0.1328125, "learning_rate": 4.8689465093201976e-05, "loss": 1.5008938312530518, "step": 1624 }, { "epoch": 0.13718434410054556, "grad_norm": 0.13671875, "learning_rate": 4.8687384285288185e-05, "loss": 1.555943250656128, "step": 1625 }, { "epoch": 0.13726876523537668, "grad_norm": 0.1552734375, "learning_rate": 4.86853018713128e-05, "loss": 1.664305329322815, "step": 1626 }, { "epoch": 0.13735318637020777, "grad_norm": 0.1396484375, "learning_rate": 4.8683217851417015e-05, "loss": 1.5689358711242676, "step": 1627 }, { "epoch": 0.1374376075050389, "grad_norm": 0.146484375, "learning_rate": 4.868113222574214e-05, "loss": 1.5964959859848022, "step": 1628 }, { "epoch": 0.13752202863986998, "grad_norm": 0.1357421875, "learning_rate": 4.8679044994429575e-05, "loss": 1.5371919870376587, "step": 1629 }, { "epoch": 0.1376064497747011, "grad_norm": 0.1416015625, "learning_rate": 4.867695615762084e-05, "loss": 1.5418365001678467, "step": 1630 }, { "epoch": 0.1376908709095322, "grad_norm": 0.1455078125, "learning_rate": 4.867486571545756e-05, "loss": 1.5345516204833984, "step": 1631 }, { "epoch": 0.1377752920443633, "grad_norm": 0.1328125, "learning_rate": 4.867277366808149e-05, "loss": 1.4523402452468872, "step": 1632 }, { "epoch": 0.1378597131791944, "grad_norm": 0.158203125, "learning_rate": 4.867068001563446e-05, "loss": 1.5009597539901733, "step": 1633 }, { "epoch": 0.13794413431402552, "grad_norm": 0.1572265625, "learning_rate": 4.8668584758258426e-05, "loss": 1.5561801195144653, "step": 1634 }, { "epoch": 0.13802855544885662, "grad_norm": 0.13671875, "learning_rate": 4.866648789609545e-05, "loss": 1.5216126441955566, "step": 1635 }, { "epoch": 0.13811297658368774, "grad_norm": 0.1376953125, "learning_rate": 4.866438942928771e-05, "loss": 1.5032384395599365, "step": 1636 }, { "epoch": 0.13819739771851883, "grad_norm": 0.1865234375, "learning_rate": 4.866228935797749e-05, "loss": 1.6293696165084839, "step": 1637 }, { "epoch": 0.13828181885334995, "grad_norm": 0.1435546875, "learning_rate": 4.866018768230717e-05, "loss": 1.5990771055221558, "step": 1638 }, { "epoch": 0.13836623998818104, "grad_norm": 0.1494140625, "learning_rate": 4.865808440241926e-05, "loss": 1.563735842704773, "step": 1639 }, { "epoch": 0.13845066112301216, "grad_norm": 0.1474609375, "learning_rate": 4.865597951845635e-05, "loss": 1.549803614616394, "step": 1640 }, { "epoch": 0.13853508225784325, "grad_norm": 0.13671875, "learning_rate": 4.865387303056118e-05, "loss": 1.6063745021820068, "step": 1641 }, { "epoch": 0.13861950339267434, "grad_norm": 0.158203125, "learning_rate": 4.8651764938876556e-05, "loss": 1.6279296875, "step": 1642 }, { "epoch": 0.13870392452750546, "grad_norm": 0.1455078125, "learning_rate": 4.864965524354541e-05, "loss": 1.5502190589904785, "step": 1643 }, { "epoch": 0.13878834566233655, "grad_norm": 0.142578125, "learning_rate": 4.86475439447108e-05, "loss": 1.5297821760177612, "step": 1644 }, { "epoch": 0.13887276679716767, "grad_norm": 0.134765625, "learning_rate": 4.864543104251587e-05, "loss": 1.5519723892211914, "step": 1645 }, { "epoch": 0.13895718793199877, "grad_norm": 0.1376953125, "learning_rate": 4.8643316537103876e-05, "loss": 1.5004717111587524, "step": 1646 }, { "epoch": 0.13904160906682989, "grad_norm": 0.154296875, "learning_rate": 4.864120042861819e-05, "loss": 1.5744582414627075, "step": 1647 }, { "epoch": 0.13912603020166098, "grad_norm": 0.134765625, "learning_rate": 4.863908271720229e-05, "loss": 1.4884365797042847, "step": 1648 }, { "epoch": 0.1392104513364921, "grad_norm": 0.1474609375, "learning_rate": 4.8636963402999764e-05, "loss": 1.5953130722045898, "step": 1649 }, { "epoch": 0.1392948724713232, "grad_norm": 0.1416015625, "learning_rate": 4.8634842486154295e-05, "loss": 1.5932445526123047, "step": 1650 }, { "epoch": 0.1393792936061543, "grad_norm": 0.1357421875, "learning_rate": 4.8632719966809706e-05, "loss": 1.5439555644989014, "step": 1651 }, { "epoch": 0.1394637147409854, "grad_norm": 0.1611328125, "learning_rate": 4.863059584510989e-05, "loss": 1.6524977684020996, "step": 1652 }, { "epoch": 0.13954813587581652, "grad_norm": 0.138671875, "learning_rate": 4.8628470121198876e-05, "loss": 1.6168866157531738, "step": 1653 }, { "epoch": 0.1396325570106476, "grad_norm": 0.1484375, "learning_rate": 4.8626342795220796e-05, "loss": 1.5327068567276, "step": 1654 }, { "epoch": 0.13971697814547873, "grad_norm": 0.13671875, "learning_rate": 4.8624213867319884e-05, "loss": 1.5882904529571533, "step": 1655 }, { "epoch": 0.13980139928030982, "grad_norm": 0.1416015625, "learning_rate": 4.862208333764049e-05, "loss": 1.5407888889312744, "step": 1656 }, { "epoch": 0.13988582041514094, "grad_norm": 0.130859375, "learning_rate": 4.861995120632705e-05, "loss": 1.5339500904083252, "step": 1657 }, { "epoch": 0.13997024154997204, "grad_norm": 0.140625, "learning_rate": 4.861781747352416e-05, "loss": 1.4980545043945312, "step": 1658 }, { "epoch": 0.14005466268480313, "grad_norm": 0.1494140625, "learning_rate": 4.861568213937647e-05, "loss": 1.5958211421966553, "step": 1659 }, { "epoch": 0.14013908381963425, "grad_norm": 0.1494140625, "learning_rate": 4.8613545204028764e-05, "loss": 1.4890192747116089, "step": 1660 }, { "epoch": 0.14022350495446534, "grad_norm": 0.1484375, "learning_rate": 4.861140666762594e-05, "loss": 1.5666061639785767, "step": 1661 }, { "epoch": 0.14030792608929646, "grad_norm": 0.1396484375, "learning_rate": 4.860926653031298e-05, "loss": 1.5759570598602295, "step": 1662 }, { "epoch": 0.14039234722412755, "grad_norm": 0.1396484375, "learning_rate": 4.8607124792235e-05, "loss": 1.5411829948425293, "step": 1663 }, { "epoch": 0.14047676835895867, "grad_norm": 0.1435546875, "learning_rate": 4.8604981453537226e-05, "loss": 1.6465167999267578, "step": 1664 }, { "epoch": 0.14056118949378976, "grad_norm": 0.146484375, "learning_rate": 4.8602836514364965e-05, "loss": 1.5118961334228516, "step": 1665 }, { "epoch": 0.14064561062862088, "grad_norm": 0.17578125, "learning_rate": 4.860068997486366e-05, "loss": 1.5334519147872925, "step": 1666 }, { "epoch": 0.14073003176345197, "grad_norm": 0.1474609375, "learning_rate": 4.8598541835178834e-05, "loss": 1.5838903188705444, "step": 1667 }, { "epoch": 0.1408144528982831, "grad_norm": 0.146484375, "learning_rate": 4.8596392095456154e-05, "loss": 1.537990689277649, "step": 1668 }, { "epoch": 0.14089887403311419, "grad_norm": 0.1474609375, "learning_rate": 4.859424075584137e-05, "loss": 1.5407538414001465, "step": 1669 }, { "epoch": 0.1409832951679453, "grad_norm": 0.1455078125, "learning_rate": 4.859208781648036e-05, "loss": 1.5337586402893066, "step": 1670 }, { "epoch": 0.1410677163027764, "grad_norm": 0.138671875, "learning_rate": 4.8589933277519074e-05, "loss": 1.5489764213562012, "step": 1671 }, { "epoch": 0.14115213743760752, "grad_norm": 0.146484375, "learning_rate": 4.858777713910362e-05, "loss": 1.6022619009017944, "step": 1672 }, { "epoch": 0.1412365585724386, "grad_norm": 0.150390625, "learning_rate": 4.8585619401380165e-05, "loss": 1.5061169862747192, "step": 1673 }, { "epoch": 0.14132097970726973, "grad_norm": 0.1513671875, "learning_rate": 4.858346006449504e-05, "loss": 1.5318392515182495, "step": 1674 }, { "epoch": 0.14140540084210082, "grad_norm": 0.138671875, "learning_rate": 4.8581299128594623e-05, "loss": 1.5963023900985718, "step": 1675 }, { "epoch": 0.1414898219769319, "grad_norm": 0.1484375, "learning_rate": 4.857913659382545e-05, "loss": 1.5170575380325317, "step": 1676 }, { "epoch": 0.14157424311176303, "grad_norm": 0.1484375, "learning_rate": 4.8576972460334125e-05, "loss": 1.5134004354476929, "step": 1677 }, { "epoch": 0.14165866424659412, "grad_norm": 0.1357421875, "learning_rate": 4.8574806728267406e-05, "loss": 1.5509672164916992, "step": 1678 }, { "epoch": 0.14174308538142524, "grad_norm": 0.1611328125, "learning_rate": 4.857263939777212e-05, "loss": 1.52232027053833, "step": 1679 }, { "epoch": 0.14182750651625634, "grad_norm": 0.189453125, "learning_rate": 4.8570470468995234e-05, "loss": 1.5469391345977783, "step": 1680 }, { "epoch": 0.14191192765108745, "grad_norm": 0.1396484375, "learning_rate": 4.8568299942083784e-05, "loss": 1.5456295013427734, "step": 1681 }, { "epoch": 0.14199634878591855, "grad_norm": 0.1396484375, "learning_rate": 4.8566127817184946e-05, "loss": 1.5092543363571167, "step": 1682 }, { "epoch": 0.14208076992074967, "grad_norm": 0.140625, "learning_rate": 4.856395409444601e-05, "loss": 1.5664420127868652, "step": 1683 }, { "epoch": 0.14216519105558076, "grad_norm": 0.1552734375, "learning_rate": 4.856177877401433e-05, "loss": 1.607832670211792, "step": 1684 }, { "epoch": 0.14224961219041188, "grad_norm": 0.1474609375, "learning_rate": 4.855960185603742e-05, "loss": 1.590164065361023, "step": 1685 }, { "epoch": 0.14233403332524297, "grad_norm": 0.1552734375, "learning_rate": 4.8557423340662875e-05, "loss": 1.6596556901931763, "step": 1686 }, { "epoch": 0.1424184544600741, "grad_norm": 0.1396484375, "learning_rate": 4.85552432280384e-05, "loss": 1.5664340257644653, "step": 1687 }, { "epoch": 0.14250287559490518, "grad_norm": 0.1416015625, "learning_rate": 4.855306151831182e-05, "loss": 1.5526779890060425, "step": 1688 }, { "epoch": 0.1425872967297363, "grad_norm": 0.15234375, "learning_rate": 4.8550878211631056e-05, "loss": 1.5987626314163208, "step": 1689 }, { "epoch": 0.1426717178645674, "grad_norm": 0.1513671875, "learning_rate": 4.8548693308144134e-05, "loss": 1.6470893621444702, "step": 1690 }, { "epoch": 0.1427561389993985, "grad_norm": 0.140625, "learning_rate": 4.8546506807999206e-05, "loss": 1.571912169456482, "step": 1691 }, { "epoch": 0.1428405601342296, "grad_norm": 0.14453125, "learning_rate": 4.8544318711344515e-05, "loss": 1.5851213932037354, "step": 1692 }, { "epoch": 0.1429249812690607, "grad_norm": 0.14453125, "learning_rate": 4.854212901832842e-05, "loss": 1.491511583328247, "step": 1693 }, { "epoch": 0.14300940240389182, "grad_norm": 0.154296875, "learning_rate": 4.853993772909939e-05, "loss": 1.559273362159729, "step": 1694 }, { "epoch": 0.1430938235387229, "grad_norm": 0.1630859375, "learning_rate": 4.853774484380601e-05, "loss": 1.5475282669067383, "step": 1695 }, { "epoch": 0.14317824467355403, "grad_norm": 0.134765625, "learning_rate": 4.853555036259695e-05, "loss": 1.5831050872802734, "step": 1696 }, { "epoch": 0.14326266580838512, "grad_norm": 0.15234375, "learning_rate": 4.853335428562099e-05, "loss": 1.5364574193954468, "step": 1697 }, { "epoch": 0.14334708694321624, "grad_norm": 0.1806640625, "learning_rate": 4.853115661302706e-05, "loss": 1.506678581237793, "step": 1698 }, { "epoch": 0.14343150807804733, "grad_norm": 0.1650390625, "learning_rate": 4.852895734496414e-05, "loss": 1.6453176736831665, "step": 1699 }, { "epoch": 0.14351592921287845, "grad_norm": 0.15625, "learning_rate": 4.852675648158135e-05, "loss": 1.5735585689544678, "step": 1700 }, { "epoch": 0.14360035034770954, "grad_norm": 0.1533203125, "learning_rate": 4.852455402302793e-05, "loss": 1.5884054899215698, "step": 1701 }, { "epoch": 0.14368477148254066, "grad_norm": 0.150390625, "learning_rate": 4.85223499694532e-05, "loss": 1.5598690509796143, "step": 1702 }, { "epoch": 0.14376919261737175, "grad_norm": 0.1669921875, "learning_rate": 4.85201443210066e-05, "loss": 1.6071256399154663, "step": 1703 }, { "epoch": 0.14385361375220287, "grad_norm": 0.1396484375, "learning_rate": 4.8517937077837686e-05, "loss": 1.5939784049987793, "step": 1704 }, { "epoch": 0.14393803488703397, "grad_norm": 0.1513671875, "learning_rate": 4.85157282400961e-05, "loss": 1.4841172695159912, "step": 1705 }, { "epoch": 0.1440224560218651, "grad_norm": 0.1484375, "learning_rate": 4.851351780793162e-05, "loss": 1.549564003944397, "step": 1706 }, { "epoch": 0.14410687715669618, "grad_norm": 0.138671875, "learning_rate": 4.851130578149411e-05, "loss": 1.5266528129577637, "step": 1707 }, { "epoch": 0.14419129829152727, "grad_norm": 0.138671875, "learning_rate": 4.8509092160933554e-05, "loss": 1.5378942489624023, "step": 1708 }, { "epoch": 0.1442757194263584, "grad_norm": 0.134765625, "learning_rate": 4.8506876946400045e-05, "loss": 1.5712400674819946, "step": 1709 }, { "epoch": 0.14436014056118948, "grad_norm": 0.1474609375, "learning_rate": 4.850466013804377e-05, "loss": 1.6038501262664795, "step": 1710 }, { "epoch": 0.1444445616960206, "grad_norm": 0.14453125, "learning_rate": 4.8502441736015046e-05, "loss": 1.5035169124603271, "step": 1711 }, { "epoch": 0.1445289828308517, "grad_norm": 0.14453125, "learning_rate": 4.850022174046428e-05, "loss": 1.5596688985824585, "step": 1712 }, { "epoch": 0.1446134039656828, "grad_norm": 0.142578125, "learning_rate": 4.849800015154199e-05, "loss": 1.5116829872131348, "step": 1713 }, { "epoch": 0.1446978251005139, "grad_norm": 0.138671875, "learning_rate": 4.849577696939881e-05, "loss": 1.5346367359161377, "step": 1714 }, { "epoch": 0.14478224623534502, "grad_norm": 0.1591796875, "learning_rate": 4.849355219418547e-05, "loss": 1.5308022499084473, "step": 1715 }, { "epoch": 0.14486666737017612, "grad_norm": 0.146484375, "learning_rate": 4.8491325826052825e-05, "loss": 1.5815128087997437, "step": 1716 }, { "epoch": 0.14495108850500724, "grad_norm": 0.1435546875, "learning_rate": 4.8489097865151824e-05, "loss": 1.591718316078186, "step": 1717 }, { "epoch": 0.14503550963983833, "grad_norm": 0.1455078125, "learning_rate": 4.848686831163353e-05, "loss": 1.586348533630371, "step": 1718 }, { "epoch": 0.14511993077466945, "grad_norm": 0.13671875, "learning_rate": 4.84846371656491e-05, "loss": 1.5297573804855347, "step": 1719 }, { "epoch": 0.14520435190950054, "grad_norm": 2.9375, "learning_rate": 4.8482404427349826e-05, "loss": 1.6725549697875977, "step": 1720 }, { "epoch": 0.14528877304433166, "grad_norm": 0.2158203125, "learning_rate": 4.8480170096887086e-05, "loss": 1.5425466299057007, "step": 1721 }, { "epoch": 0.14537319417916275, "grad_norm": 0.1396484375, "learning_rate": 4.8477934174412376e-05, "loss": 1.6153396368026733, "step": 1722 }, { "epoch": 0.14545761531399387, "grad_norm": 0.140625, "learning_rate": 4.8475696660077295e-05, "loss": 1.5681535005569458, "step": 1723 }, { "epoch": 0.14554203644882496, "grad_norm": 0.142578125, "learning_rate": 4.847345755403355e-05, "loss": 1.5183672904968262, "step": 1724 }, { "epoch": 0.14562645758365605, "grad_norm": 0.1484375, "learning_rate": 4.847121685643297e-05, "loss": 1.5748701095581055, "step": 1725 }, { "epoch": 0.14571087871848717, "grad_norm": 0.154296875, "learning_rate": 4.8468974567427455e-05, "loss": 1.5549170970916748, "step": 1726 }, { "epoch": 0.14579529985331827, "grad_norm": 0.1435546875, "learning_rate": 4.846673068716906e-05, "loss": 1.5440917015075684, "step": 1727 }, { "epoch": 0.1458797209881494, "grad_norm": 0.140625, "learning_rate": 4.8464485215809916e-05, "loss": 1.563909649848938, "step": 1728 }, { "epoch": 0.14596414212298048, "grad_norm": 0.146484375, "learning_rate": 4.8462238153502274e-05, "loss": 1.541308879852295, "step": 1729 }, { "epoch": 0.1460485632578116, "grad_norm": 0.15234375, "learning_rate": 4.845998950039849e-05, "loss": 1.5052063465118408, "step": 1730 }, { "epoch": 0.1461329843926427, "grad_norm": 0.13671875, "learning_rate": 4.845773925665103e-05, "loss": 1.5335874557495117, "step": 1731 }, { "epoch": 0.1462174055274738, "grad_norm": 0.142578125, "learning_rate": 4.845548742241246e-05, "loss": 1.5554934740066528, "step": 1732 }, { "epoch": 0.1463018266623049, "grad_norm": 0.1416015625, "learning_rate": 4.845323399783547e-05, "loss": 1.5712915658950806, "step": 1733 }, { "epoch": 0.14638624779713602, "grad_norm": 0.14453125, "learning_rate": 4.845097898307282e-05, "loss": 1.5496419668197632, "step": 1734 }, { "epoch": 0.1464706689319671, "grad_norm": 0.158203125, "learning_rate": 4.844872237827745e-05, "loss": 1.5223758220672607, "step": 1735 }, { "epoch": 0.14655509006679823, "grad_norm": 0.1435546875, "learning_rate": 4.844646418360233e-05, "loss": 1.5368365049362183, "step": 1736 }, { "epoch": 0.14663951120162932, "grad_norm": 0.1669921875, "learning_rate": 4.8444204399200574e-05, "loss": 1.57246732711792, "step": 1737 }, { "epoch": 0.14672393233646044, "grad_norm": 0.13671875, "learning_rate": 4.844194302522542e-05, "loss": 1.5573010444641113, "step": 1738 }, { "epoch": 0.14680835347129154, "grad_norm": 0.146484375, "learning_rate": 4.843968006183018e-05, "loss": 1.6803606748580933, "step": 1739 }, { "epoch": 0.14689277460612266, "grad_norm": 0.1435546875, "learning_rate": 4.843741550916828e-05, "loss": 1.5286755561828613, "step": 1740 }, { "epoch": 0.14697719574095375, "grad_norm": 0.1572265625, "learning_rate": 4.8435149367393284e-05, "loss": 1.5364419221878052, "step": 1741 }, { "epoch": 0.14706161687578484, "grad_norm": 0.1494140625, "learning_rate": 4.843288163665882e-05, "loss": 1.5598276853561401, "step": 1742 }, { "epoch": 0.14714603801061596, "grad_norm": 0.1572265625, "learning_rate": 4.843061231711866e-05, "loss": 1.556052803993225, "step": 1743 }, { "epoch": 0.14723045914544705, "grad_norm": 0.1376953125, "learning_rate": 4.842834140892667e-05, "loss": 1.5758237838745117, "step": 1744 }, { "epoch": 0.14731488028027817, "grad_norm": 0.1416015625, "learning_rate": 4.842606891223681e-05, "loss": 1.6058354377746582, "step": 1745 }, { "epoch": 0.14739930141510926, "grad_norm": 0.166015625, "learning_rate": 4.842379482720317e-05, "loss": 1.556838870048523, "step": 1746 }, { "epoch": 0.14748372254994038, "grad_norm": 0.1416015625, "learning_rate": 4.842151915397995e-05, "loss": 1.592481255531311, "step": 1747 }, { "epoch": 0.14756814368477147, "grad_norm": 0.138671875, "learning_rate": 4.841924189272142e-05, "loss": 1.5351009368896484, "step": 1748 }, { "epoch": 0.1476525648196026, "grad_norm": 0.15234375, "learning_rate": 4.8416963043582e-05, "loss": 1.6119754314422607, "step": 1749 }, { "epoch": 0.14773698595443369, "grad_norm": 0.1708984375, "learning_rate": 4.84146826067162e-05, "loss": 1.6244796514511108, "step": 1750 }, { "epoch": 0.1478214070892648, "grad_norm": 0.14453125, "learning_rate": 4.841240058227864e-05, "loss": 1.5567854642868042, "step": 1751 }, { "epoch": 0.1479058282240959, "grad_norm": 0.142578125, "learning_rate": 4.8410116970424034e-05, "loss": 1.5486587285995483, "step": 1752 }, { "epoch": 0.14799024935892702, "grad_norm": 0.1494140625, "learning_rate": 4.8407831771307245e-05, "loss": 1.5718438625335693, "step": 1753 }, { "epoch": 0.1480746704937581, "grad_norm": 0.1484375, "learning_rate": 4.8405544985083186e-05, "loss": 1.6047558784484863, "step": 1754 }, { "epoch": 0.14815909162858923, "grad_norm": 0.140625, "learning_rate": 4.840325661190691e-05, "loss": 1.5650873184204102, "step": 1755 }, { "epoch": 0.14824351276342032, "grad_norm": 0.138671875, "learning_rate": 4.840096665193359e-05, "loss": 1.6470775604248047, "step": 1756 }, { "epoch": 0.14832793389825144, "grad_norm": 0.1484375, "learning_rate": 4.8398675105318484e-05, "loss": 1.5192724466323853, "step": 1757 }, { "epoch": 0.14841235503308253, "grad_norm": 0.1435546875, "learning_rate": 4.839638197221697e-05, "loss": 1.4774531126022339, "step": 1758 }, { "epoch": 0.14849677616791362, "grad_norm": 0.154296875, "learning_rate": 4.8394087252784504e-05, "loss": 1.5209746360778809, "step": 1759 }, { "epoch": 0.14858119730274474, "grad_norm": 0.1396484375, "learning_rate": 4.8391790947176696e-05, "loss": 1.5509706735610962, "step": 1760 }, { "epoch": 0.14866561843757584, "grad_norm": 0.130859375, "learning_rate": 4.838949305554924e-05, "loss": 1.4667836427688599, "step": 1761 }, { "epoch": 0.14875003957240696, "grad_norm": 0.1396484375, "learning_rate": 4.838719357805793e-05, "loss": 1.5665887594223022, "step": 1762 }, { "epoch": 0.14883446070723805, "grad_norm": 0.1416015625, "learning_rate": 4.838489251485868e-05, "loss": 1.5003432035446167, "step": 1763 }, { "epoch": 0.14891888184206917, "grad_norm": 0.140625, "learning_rate": 4.838258986610751e-05, "loss": 1.6080536842346191, "step": 1764 }, { "epoch": 0.14900330297690026, "grad_norm": 0.146484375, "learning_rate": 4.838028563196054e-05, "loss": 1.556040644645691, "step": 1765 }, { "epoch": 0.14908772411173138, "grad_norm": 0.146484375, "learning_rate": 4.837797981257401e-05, "loss": 1.60652494430542, "step": 1766 }, { "epoch": 0.14917214524656247, "grad_norm": 0.154296875, "learning_rate": 4.837567240810426e-05, "loss": 1.492244839668274, "step": 1767 }, { "epoch": 0.1492565663813936, "grad_norm": 0.158203125, "learning_rate": 4.837336341870772e-05, "loss": 1.5446133613586426, "step": 1768 }, { "epoch": 0.14934098751622468, "grad_norm": 0.134765625, "learning_rate": 4.837105284454097e-05, "loss": 1.5328232049942017, "step": 1769 }, { "epoch": 0.1494254086510558, "grad_norm": 0.12890625, "learning_rate": 4.836874068576065e-05, "loss": 1.5612335205078125, "step": 1770 }, { "epoch": 0.1495098297858869, "grad_norm": 0.1396484375, "learning_rate": 4.836642694252354e-05, "loss": 1.5198452472686768, "step": 1771 }, { "epoch": 0.149594250920718, "grad_norm": 0.14453125, "learning_rate": 4.8364111614986527e-05, "loss": 1.5506532192230225, "step": 1772 }, { "epoch": 0.1496786720555491, "grad_norm": 0.1416015625, "learning_rate": 4.836179470330658e-05, "loss": 1.5904886722564697, "step": 1773 }, { "epoch": 0.14976309319038023, "grad_norm": 0.14453125, "learning_rate": 4.8359476207640794e-05, "loss": 1.6291420459747314, "step": 1774 }, { "epoch": 0.14984751432521132, "grad_norm": 0.154296875, "learning_rate": 4.8357156128146386e-05, "loss": 1.5386388301849365, "step": 1775 }, { "epoch": 0.1499319354600424, "grad_norm": 0.1552734375, "learning_rate": 4.835483446498063e-05, "loss": 1.6143362522125244, "step": 1776 }, { "epoch": 0.15001635659487353, "grad_norm": 0.15234375, "learning_rate": 4.8352511218300975e-05, "loss": 1.5883439779281616, "step": 1777 }, { "epoch": 0.15010077772970462, "grad_norm": 0.1689453125, "learning_rate": 4.8350186388264926e-05, "loss": 1.5820841789245605, "step": 1778 }, { "epoch": 0.15018519886453574, "grad_norm": 0.1484375, "learning_rate": 4.8347859975030115e-05, "loss": 1.5250093936920166, "step": 1779 }, { "epoch": 0.15026961999936683, "grad_norm": 0.1533203125, "learning_rate": 4.8345531978754266e-05, "loss": 1.5689767599105835, "step": 1780 }, { "epoch": 0.15035404113419795, "grad_norm": 0.1328125, "learning_rate": 4.834320239959525e-05, "loss": 1.5593047142028809, "step": 1781 }, { "epoch": 0.15043846226902904, "grad_norm": 0.1650390625, "learning_rate": 4.8340871237710985e-05, "loss": 1.5504440069198608, "step": 1782 }, { "epoch": 0.15052288340386016, "grad_norm": 0.1416015625, "learning_rate": 4.8338538493259556e-05, "loss": 1.4661601781845093, "step": 1783 }, { "epoch": 0.15060730453869126, "grad_norm": 0.1455078125, "learning_rate": 4.833620416639911e-05, "loss": 1.6086825132369995, "step": 1784 }, { "epoch": 0.15069172567352238, "grad_norm": 0.1396484375, "learning_rate": 4.833386825728794e-05, "loss": 1.6137468814849854, "step": 1785 }, { "epoch": 0.15077614680835347, "grad_norm": 0.1416015625, "learning_rate": 4.833153076608441e-05, "loss": 1.5672607421875, "step": 1786 }, { "epoch": 0.1508605679431846, "grad_norm": 0.1552734375, "learning_rate": 4.832919169294701e-05, "loss": 1.4725518226623535, "step": 1787 }, { "epoch": 0.15094498907801568, "grad_norm": 0.1357421875, "learning_rate": 4.832685103803434e-05, "loss": 1.590743064880371, "step": 1788 }, { "epoch": 0.1510294102128468, "grad_norm": 0.1337890625, "learning_rate": 4.83245088015051e-05, "loss": 1.5216981172561646, "step": 1789 }, { "epoch": 0.1511138313476779, "grad_norm": 0.142578125, "learning_rate": 4.8322164983518095e-05, "loss": 1.5594369173049927, "step": 1790 }, { "epoch": 0.15119825248250898, "grad_norm": 0.142578125, "learning_rate": 4.831981958423224e-05, "loss": 1.5436904430389404, "step": 1791 }, { "epoch": 0.1512826736173401, "grad_norm": 0.14453125, "learning_rate": 4.831747260380657e-05, "loss": 1.5176867246627808, "step": 1792 }, { "epoch": 0.1513670947521712, "grad_norm": 0.169921875, "learning_rate": 4.831512404240021e-05, "loss": 1.5154036283493042, "step": 1793 }, { "epoch": 0.1514515158870023, "grad_norm": 0.158203125, "learning_rate": 4.83127739001724e-05, "loss": 1.592873454093933, "step": 1794 }, { "epoch": 0.1515359370218334, "grad_norm": 0.140625, "learning_rate": 4.8310422177282476e-05, "loss": 1.5499147176742554, "step": 1795 }, { "epoch": 0.15162035815666453, "grad_norm": 0.150390625, "learning_rate": 4.830806887388991e-05, "loss": 1.5523003339767456, "step": 1796 }, { "epoch": 0.15170477929149562, "grad_norm": 0.1494140625, "learning_rate": 4.830571399015424e-05, "loss": 1.6555384397506714, "step": 1797 }, { "epoch": 0.15178920042632674, "grad_norm": 0.158203125, "learning_rate": 4.830335752623514e-05, "loss": 1.5784525871276855, "step": 1798 }, { "epoch": 0.15187362156115783, "grad_norm": 0.1533203125, "learning_rate": 4.830099948229239e-05, "loss": 1.5936208963394165, "step": 1799 }, { "epoch": 0.15195804269598895, "grad_norm": 0.1376953125, "learning_rate": 4.829863985848587e-05, "loss": 1.5061613321304321, "step": 1800 }, { "epoch": 0.15204246383082004, "grad_norm": 0.1484375, "learning_rate": 4.829627865497556e-05, "loss": 1.5477641820907593, "step": 1801 }, { "epoch": 0.15212688496565116, "grad_norm": 0.1591796875, "learning_rate": 4.8293915871921556e-05, "loss": 1.536116123199463, "step": 1802 }, { "epoch": 0.15221130610048225, "grad_norm": 0.1455078125, "learning_rate": 4.829155150948407e-05, "loss": 1.4483592510223389, "step": 1803 }, { "epoch": 0.15229572723531337, "grad_norm": 0.1552734375, "learning_rate": 4.828918556782341e-05, "loss": 1.6156387329101562, "step": 1804 }, { "epoch": 0.15238014837014446, "grad_norm": 0.1494140625, "learning_rate": 4.828681804709998e-05, "loss": 1.4922096729278564, "step": 1805 }, { "epoch": 0.15246456950497558, "grad_norm": 0.1416015625, "learning_rate": 4.828444894747432e-05, "loss": 1.5581706762313843, "step": 1806 }, { "epoch": 0.15254899063980668, "grad_norm": 0.158203125, "learning_rate": 4.828207826910705e-05, "loss": 1.6745011806488037, "step": 1807 }, { "epoch": 0.15263341177463777, "grad_norm": 0.1416015625, "learning_rate": 4.827970601215891e-05, "loss": 1.5777947902679443, "step": 1808 }, { "epoch": 0.1527178329094689, "grad_norm": 0.138671875, "learning_rate": 4.8277332176790745e-05, "loss": 1.5303925275802612, "step": 1809 }, { "epoch": 0.15280225404429998, "grad_norm": 0.1455078125, "learning_rate": 4.8274956763163506e-05, "loss": 1.5795161724090576, "step": 1810 }, { "epoch": 0.1528866751791311, "grad_norm": 0.140625, "learning_rate": 4.827257977143826e-05, "loss": 1.5311987400054932, "step": 1811 }, { "epoch": 0.1529710963139622, "grad_norm": 0.1650390625, "learning_rate": 4.827020120177616e-05, "loss": 1.5655165910720825, "step": 1812 }, { "epoch": 0.1530555174487933, "grad_norm": 0.1455078125, "learning_rate": 4.826782105433848e-05, "loss": 1.472798466682434, "step": 1813 }, { "epoch": 0.1531399385836244, "grad_norm": 0.1474609375, "learning_rate": 4.826543932928661e-05, "loss": 1.5572941303253174, "step": 1814 }, { "epoch": 0.15322435971845552, "grad_norm": 0.1552734375, "learning_rate": 4.826305602678203e-05, "loss": 1.6305458545684814, "step": 1815 }, { "epoch": 0.1533087808532866, "grad_norm": 0.150390625, "learning_rate": 4.8260671146986336e-05, "loss": 1.632872223854065, "step": 1816 }, { "epoch": 0.15339320198811773, "grad_norm": 0.1435546875, "learning_rate": 4.825828469006123e-05, "loss": 1.5583422183990479, "step": 1817 }, { "epoch": 0.15347762312294883, "grad_norm": 0.1474609375, "learning_rate": 4.825589665616851e-05, "loss": 1.5543371438980103, "step": 1818 }, { "epoch": 0.15356204425777994, "grad_norm": 0.134765625, "learning_rate": 4.825350704547009e-05, "loss": 1.5311576128005981, "step": 1819 }, { "epoch": 0.15364646539261104, "grad_norm": 0.1474609375, "learning_rate": 4.825111585812801e-05, "loss": 1.5385799407958984, "step": 1820 }, { "epoch": 0.15373088652744216, "grad_norm": 0.1416015625, "learning_rate": 4.824872309430438e-05, "loss": 1.5878220796585083, "step": 1821 }, { "epoch": 0.15381530766227325, "grad_norm": 0.1591796875, "learning_rate": 4.824632875416145e-05, "loss": 1.5470287799835205, "step": 1822 }, { "epoch": 0.15389972879710437, "grad_norm": 0.1591796875, "learning_rate": 4.824393283786155e-05, "loss": 1.6195749044418335, "step": 1823 }, { "epoch": 0.15398414993193546, "grad_norm": 0.15625, "learning_rate": 4.8241535345567126e-05, "loss": 1.5866612195968628, "step": 1824 }, { "epoch": 0.15406857106676655, "grad_norm": 0.1435546875, "learning_rate": 4.8239136277440745e-05, "loss": 1.5251082181930542, "step": 1825 }, { "epoch": 0.15415299220159767, "grad_norm": 0.1474609375, "learning_rate": 4.823673563364507e-05, "loss": 1.4976167678833008, "step": 1826 }, { "epoch": 0.15423741333642876, "grad_norm": 0.1396484375, "learning_rate": 4.823433341434286e-05, "loss": 1.5487889051437378, "step": 1827 }, { "epoch": 0.15432183447125988, "grad_norm": 0.1396484375, "learning_rate": 4.823192961969699e-05, "loss": 1.4849517345428467, "step": 1828 }, { "epoch": 0.15440625560609098, "grad_norm": 0.1328125, "learning_rate": 4.822952424987046e-05, "loss": 1.5176808834075928, "step": 1829 }, { "epoch": 0.1544906767409221, "grad_norm": 0.14453125, "learning_rate": 4.822711730502634e-05, "loss": 1.5616047382354736, "step": 1830 }, { "epoch": 0.1545750978757532, "grad_norm": 0.142578125, "learning_rate": 4.8224708785327845e-05, "loss": 1.5632731914520264, "step": 1831 }, { "epoch": 0.1546595190105843, "grad_norm": 0.1455078125, "learning_rate": 4.822229869093827e-05, "loss": 1.5732817649841309, "step": 1832 }, { "epoch": 0.1547439401454154, "grad_norm": 0.1357421875, "learning_rate": 4.8219887022021013e-05, "loss": 1.502690315246582, "step": 1833 }, { "epoch": 0.15482836128024652, "grad_norm": 0.1474609375, "learning_rate": 4.821747377873962e-05, "loss": 1.5799407958984375, "step": 1834 }, { "epoch": 0.1549127824150776, "grad_norm": 0.1552734375, "learning_rate": 4.821505896125769e-05, "loss": 1.5975781679153442, "step": 1835 }, { "epoch": 0.15499720354990873, "grad_norm": 0.14453125, "learning_rate": 4.821264256973895e-05, "loss": 1.5673445463180542, "step": 1836 }, { "epoch": 0.15508162468473982, "grad_norm": 0.134765625, "learning_rate": 4.821022460434726e-05, "loss": 1.6050184965133667, "step": 1837 }, { "epoch": 0.15516604581957094, "grad_norm": 0.1640625, "learning_rate": 4.8207805065246545e-05, "loss": 1.5134586095809937, "step": 1838 }, { "epoch": 0.15525046695440203, "grad_norm": 0.1630859375, "learning_rate": 4.820538395260087e-05, "loss": 1.5868496894836426, "step": 1839 }, { "epoch": 0.15533488808923315, "grad_norm": 0.14453125, "learning_rate": 4.820296126657437e-05, "loss": 1.5712192058563232, "step": 1840 }, { "epoch": 0.15541930922406424, "grad_norm": 0.146484375, "learning_rate": 4.820053700733134e-05, "loss": 1.546459436416626, "step": 1841 }, { "epoch": 0.15550373035889534, "grad_norm": 0.1494140625, "learning_rate": 4.819811117503613e-05, "loss": 1.5163072347640991, "step": 1842 }, { "epoch": 0.15558815149372646, "grad_norm": 0.1533203125, "learning_rate": 4.819568376985322e-05, "loss": 1.5364030599594116, "step": 1843 }, { "epoch": 0.15567257262855755, "grad_norm": 0.1494140625, "learning_rate": 4.8193254791947195e-05, "loss": 1.5073429346084595, "step": 1844 }, { "epoch": 0.15575699376338867, "grad_norm": 0.1552734375, "learning_rate": 4.819082424148275e-05, "loss": 1.6190470457077026, "step": 1845 }, { "epoch": 0.15584141489821976, "grad_norm": 0.1396484375, "learning_rate": 4.818839211862467e-05, "loss": 1.555841326713562, "step": 1846 }, { "epoch": 0.15592583603305088, "grad_norm": 0.130859375, "learning_rate": 4.818595842353787e-05, "loss": 1.505096435546875, "step": 1847 }, { "epoch": 0.15601025716788197, "grad_norm": 0.1455078125, "learning_rate": 4.8183523156387354e-05, "loss": 1.5553340911865234, "step": 1848 }, { "epoch": 0.1560946783027131, "grad_norm": 0.1435546875, "learning_rate": 4.8181086317338244e-05, "loss": 1.550831913948059, "step": 1849 }, { "epoch": 0.15617909943754418, "grad_norm": 0.1416015625, "learning_rate": 4.817864790655577e-05, "loss": 1.5845637321472168, "step": 1850 }, { "epoch": 0.1562635205723753, "grad_norm": 0.1455078125, "learning_rate": 4.8176207924205245e-05, "loss": 1.548147201538086, "step": 1851 }, { "epoch": 0.1563479417072064, "grad_norm": 0.1318359375, "learning_rate": 4.817376637045212e-05, "loss": 1.5028903484344482, "step": 1852 }, { "epoch": 0.15643236284203751, "grad_norm": 0.1396484375, "learning_rate": 4.817132324546193e-05, "loss": 1.5066571235656738, "step": 1853 }, { "epoch": 0.1565167839768686, "grad_norm": 0.1435546875, "learning_rate": 4.816887854940032e-05, "loss": 1.6345614194869995, "step": 1854 }, { "epoch": 0.15660120511169973, "grad_norm": 0.14453125, "learning_rate": 4.816643228243307e-05, "loss": 1.569209337234497, "step": 1855 }, { "epoch": 0.15668562624653082, "grad_norm": 0.15625, "learning_rate": 4.8163984444726014e-05, "loss": 1.491801381111145, "step": 1856 }, { "epoch": 0.15677004738136194, "grad_norm": 0.1357421875, "learning_rate": 4.8161535036445136e-05, "loss": 1.6236083507537842, "step": 1857 }, { "epoch": 0.15685446851619303, "grad_norm": 0.138671875, "learning_rate": 4.815908405775651e-05, "loss": 1.5456211566925049, "step": 1858 }, { "epoch": 0.15693888965102412, "grad_norm": 0.146484375, "learning_rate": 4.8156631508826316e-05, "loss": 1.6230127811431885, "step": 1859 }, { "epoch": 0.15702331078585524, "grad_norm": 0.1640625, "learning_rate": 4.815417738982085e-05, "loss": 1.5963612794876099, "step": 1860 }, { "epoch": 0.15710773192068633, "grad_norm": 0.1513671875, "learning_rate": 4.8151721700906495e-05, "loss": 1.6020982265472412, "step": 1861 }, { "epoch": 0.15719215305551745, "grad_norm": 0.1416015625, "learning_rate": 4.8149264442249764e-05, "loss": 1.6034088134765625, "step": 1862 }, { "epoch": 0.15727657419034854, "grad_norm": 0.166015625, "learning_rate": 4.814680561401726e-05, "loss": 1.5707508325576782, "step": 1863 }, { "epoch": 0.15736099532517966, "grad_norm": 0.142578125, "learning_rate": 4.81443452163757e-05, "loss": 1.554071068763733, "step": 1864 }, { "epoch": 0.15744541646001076, "grad_norm": 0.1611328125, "learning_rate": 4.8141883249491895e-05, "loss": 1.57026207447052, "step": 1865 }, { "epoch": 0.15752983759484188, "grad_norm": 0.1455078125, "learning_rate": 4.813941971353278e-05, "loss": 1.5202385187149048, "step": 1866 }, { "epoch": 0.15761425872967297, "grad_norm": 0.15625, "learning_rate": 4.81369546086654e-05, "loss": 1.517987847328186, "step": 1867 }, { "epoch": 0.1576986798645041, "grad_norm": 0.1337890625, "learning_rate": 4.813448793505687e-05, "loss": 1.5222835540771484, "step": 1868 }, { "epoch": 0.15778310099933518, "grad_norm": 0.146484375, "learning_rate": 4.813201969287446e-05, "loss": 1.5669503211975098, "step": 1869 }, { "epoch": 0.1578675221341663, "grad_norm": 0.142578125, "learning_rate": 4.8129549882285504e-05, "loss": 1.5267066955566406, "step": 1870 }, { "epoch": 0.1579519432689974, "grad_norm": 0.138671875, "learning_rate": 4.812707850345748e-05, "loss": 1.4995023012161255, "step": 1871 }, { "epoch": 0.1580363644038285, "grad_norm": 0.1376953125, "learning_rate": 4.8124605556557937e-05, "loss": 1.5506603717803955, "step": 1872 }, { "epoch": 0.1581207855386596, "grad_norm": 0.1376953125, "learning_rate": 4.812213104175456e-05, "loss": 1.5455963611602783, "step": 1873 }, { "epoch": 0.1582052066734907, "grad_norm": 0.17578125, "learning_rate": 4.811965495921511e-05, "loss": 1.6207035779953003, "step": 1874 }, { "epoch": 0.15828962780832181, "grad_norm": 0.1669921875, "learning_rate": 4.811717730910749e-05, "loss": 1.664159893989563, "step": 1875 }, { "epoch": 0.1583740489431529, "grad_norm": 0.1533203125, "learning_rate": 4.811469809159968e-05, "loss": 1.5816549062728882, "step": 1876 }, { "epoch": 0.15845847007798403, "grad_norm": 0.150390625, "learning_rate": 4.811221730685977e-05, "loss": 1.5373663902282715, "step": 1877 }, { "epoch": 0.15854289121281512, "grad_norm": 0.150390625, "learning_rate": 4.810973495505598e-05, "loss": 1.5414901971817017, "step": 1878 }, { "epoch": 0.15862731234764624, "grad_norm": 0.150390625, "learning_rate": 4.810725103635661e-05, "loss": 1.6182938814163208, "step": 1879 }, { "epoch": 0.15871173348247733, "grad_norm": 0.1552734375, "learning_rate": 4.8104765550930075e-05, "loss": 1.5495336055755615, "step": 1880 }, { "epoch": 0.15879615461730845, "grad_norm": 0.1455078125, "learning_rate": 4.810227849894491e-05, "loss": 1.623075008392334, "step": 1881 }, { "epoch": 0.15888057575213954, "grad_norm": 0.1435546875, "learning_rate": 4.8099789880569726e-05, "loss": 1.5812232494354248, "step": 1882 }, { "epoch": 0.15896499688697066, "grad_norm": 0.1552734375, "learning_rate": 4.8097299695973256e-05, "loss": 1.5007047653198242, "step": 1883 }, { "epoch": 0.15904941802180175, "grad_norm": 0.1650390625, "learning_rate": 4.809480794532435e-05, "loss": 1.6127856969833374, "step": 1884 }, { "epoch": 0.15913383915663287, "grad_norm": 0.1552734375, "learning_rate": 4.809231462879196e-05, "loss": 1.5502936840057373, "step": 1885 }, { "epoch": 0.15921826029146396, "grad_norm": 0.1435546875, "learning_rate": 4.8089819746545126e-05, "loss": 1.6110610961914062, "step": 1886 }, { "epoch": 0.15930268142629508, "grad_norm": 0.146484375, "learning_rate": 4.808732329875302e-05, "loss": 1.4646577835083008, "step": 1887 }, { "epoch": 0.15938710256112618, "grad_norm": 0.1337890625, "learning_rate": 4.808482528558489e-05, "loss": 1.5076868534088135, "step": 1888 }, { "epoch": 0.1594715236959573, "grad_norm": 0.1416015625, "learning_rate": 4.8082325707210116e-05, "loss": 1.5767101049423218, "step": 1889 }, { "epoch": 0.1595559448307884, "grad_norm": 0.1328125, "learning_rate": 4.8079824563798187e-05, "loss": 1.5286110639572144, "step": 1890 }, { "epoch": 0.15964036596561948, "grad_norm": 0.146484375, "learning_rate": 4.807732185551867e-05, "loss": 1.5824503898620605, "step": 1891 }, { "epoch": 0.1597247871004506, "grad_norm": 0.1513671875, "learning_rate": 4.807481758254127e-05, "loss": 1.6859431266784668, "step": 1892 }, { "epoch": 0.1598092082352817, "grad_norm": 0.13671875, "learning_rate": 4.807231174503576e-05, "loss": 1.509676456451416, "step": 1893 }, { "epoch": 0.1598936293701128, "grad_norm": 0.140625, "learning_rate": 4.8069804343172054e-05, "loss": 1.5817139148712158, "step": 1894 }, { "epoch": 0.1599780505049439, "grad_norm": 0.1513671875, "learning_rate": 4.806729537712017e-05, "loss": 1.575016975402832, "step": 1895 }, { "epoch": 0.16006247163977502, "grad_norm": 0.1552734375, "learning_rate": 4.806478484705021e-05, "loss": 1.5777860879898071, "step": 1896 }, { "epoch": 0.16014689277460611, "grad_norm": 0.1513671875, "learning_rate": 4.80622727531324e-05, "loss": 1.5133744478225708, "step": 1897 }, { "epoch": 0.16023131390943723, "grad_norm": 0.1455078125, "learning_rate": 4.8059759095537054e-05, "loss": 1.4742212295532227, "step": 1898 }, { "epoch": 0.16031573504426833, "grad_norm": 0.1416015625, "learning_rate": 4.805724387443462e-05, "loss": 1.6133474111557007, "step": 1899 }, { "epoch": 0.16040015617909945, "grad_norm": 0.14453125, "learning_rate": 4.8054727089995624e-05, "loss": 1.5799065828323364, "step": 1900 }, { "epoch": 0.16048457731393054, "grad_norm": 0.1416015625, "learning_rate": 4.805220874239072e-05, "loss": 1.5346925258636475, "step": 1901 }, { "epoch": 0.16056899844876166, "grad_norm": 0.1513671875, "learning_rate": 4.804968883179065e-05, "loss": 1.545093059539795, "step": 1902 }, { "epoch": 0.16065341958359275, "grad_norm": 0.14453125, "learning_rate": 4.8047167358366277e-05, "loss": 1.5346200466156006, "step": 1903 }, { "epoch": 0.16073784071842387, "grad_norm": 0.1591796875, "learning_rate": 4.804464432228856e-05, "loss": 1.5530871152877808, "step": 1904 }, { "epoch": 0.16082226185325496, "grad_norm": 0.142578125, "learning_rate": 4.804211972372856e-05, "loss": 1.5849392414093018, "step": 1905 }, { "epoch": 0.16090668298808608, "grad_norm": 0.1484375, "learning_rate": 4.803959356285746e-05, "loss": 1.5583990812301636, "step": 1906 }, { "epoch": 0.16099110412291717, "grad_norm": 0.1416015625, "learning_rate": 4.803706583984654e-05, "loss": 1.5166834592819214, "step": 1907 }, { "epoch": 0.16107552525774826, "grad_norm": 0.181640625, "learning_rate": 4.803453655486717e-05, "loss": 1.487786054611206, "step": 1908 }, { "epoch": 0.16115994639257938, "grad_norm": 0.1357421875, "learning_rate": 4.8032005708090864e-05, "loss": 1.5308042764663696, "step": 1909 }, { "epoch": 0.16124436752741048, "grad_norm": 0.142578125, "learning_rate": 4.802947329968921e-05, "loss": 1.5758885145187378, "step": 1910 }, { "epoch": 0.1613287886622416, "grad_norm": 0.1533203125, "learning_rate": 4.802693932983391e-05, "loss": 1.5244669914245605, "step": 1911 }, { "epoch": 0.1614132097970727, "grad_norm": 0.1689453125, "learning_rate": 4.802440379869677e-05, "loss": 1.5788710117340088, "step": 1912 }, { "epoch": 0.1614976309319038, "grad_norm": 0.1435546875, "learning_rate": 4.802186670644971e-05, "loss": 1.519598126411438, "step": 1913 }, { "epoch": 0.1615820520667349, "grad_norm": 0.142578125, "learning_rate": 4.801932805326476e-05, "loss": 1.5726574659347534, "step": 1914 }, { "epoch": 0.16166647320156602, "grad_norm": 0.1416015625, "learning_rate": 4.801678783931402e-05, "loss": 1.5175988674163818, "step": 1915 }, { "epoch": 0.1617508943363971, "grad_norm": 0.154296875, "learning_rate": 4.8014246064769754e-05, "loss": 1.5778547525405884, "step": 1916 }, { "epoch": 0.16183531547122823, "grad_norm": 0.1337890625, "learning_rate": 4.801170272980428e-05, "loss": 1.516188144683838, "step": 1917 }, { "epoch": 0.16191973660605932, "grad_norm": 0.1337890625, "learning_rate": 4.8009157834590044e-05, "loss": 1.592103123664856, "step": 1918 }, { "epoch": 0.16200415774089044, "grad_norm": 0.1435546875, "learning_rate": 4.8006611379299604e-05, "loss": 1.5289511680603027, "step": 1919 }, { "epoch": 0.16208857887572153, "grad_norm": 0.1455078125, "learning_rate": 4.800406336410561e-05, "loss": 1.552725911140442, "step": 1920 }, { "epoch": 0.16217300001055265, "grad_norm": 0.16796875, "learning_rate": 4.800151378918083e-05, "loss": 1.5468494892120361, "step": 1921 }, { "epoch": 0.16225742114538375, "grad_norm": 0.169921875, "learning_rate": 4.799896265469812e-05, "loss": 1.6184653043746948, "step": 1922 }, { "epoch": 0.16234184228021487, "grad_norm": 0.17578125, "learning_rate": 4.799640996083046e-05, "loss": 1.5973728895187378, "step": 1923 }, { "epoch": 0.16242626341504596, "grad_norm": 0.173828125, "learning_rate": 4.7993855707750934e-05, "loss": 1.5903435945510864, "step": 1924 }, { "epoch": 0.16251068454987705, "grad_norm": 0.1494140625, "learning_rate": 4.7991299895632716e-05, "loss": 1.5069626569747925, "step": 1925 }, { "epoch": 0.16259510568470817, "grad_norm": 0.150390625, "learning_rate": 4.79887425246491e-05, "loss": 1.5854945182800293, "step": 1926 }, { "epoch": 0.16267952681953926, "grad_norm": 0.1416015625, "learning_rate": 4.798618359497349e-05, "loss": 1.6047813892364502, "step": 1927 }, { "epoch": 0.16276394795437038, "grad_norm": 0.1533203125, "learning_rate": 4.798362310677939e-05, "loss": 1.5437155961990356, "step": 1928 }, { "epoch": 0.16284836908920147, "grad_norm": 0.138671875, "learning_rate": 4.798106106024038e-05, "loss": 1.6394466161727905, "step": 1929 }, { "epoch": 0.1629327902240326, "grad_norm": 0.1474609375, "learning_rate": 4.797849745553019e-05, "loss": 1.628232717514038, "step": 1930 }, { "epoch": 0.16301721135886368, "grad_norm": 0.1708984375, "learning_rate": 4.797593229282265e-05, "loss": 1.523317813873291, "step": 1931 }, { "epoch": 0.1631016324936948, "grad_norm": 0.13671875, "learning_rate": 4.797336557229167e-05, "loss": 1.490416407585144, "step": 1932 }, { "epoch": 0.1631860536285259, "grad_norm": 0.1484375, "learning_rate": 4.797079729411128e-05, "loss": 1.5907236337661743, "step": 1933 }, { "epoch": 0.16327047476335702, "grad_norm": 0.1494140625, "learning_rate": 4.796822745845563e-05, "loss": 1.5640686750411987, "step": 1934 }, { "epoch": 0.1633548958981881, "grad_norm": 0.1494140625, "learning_rate": 4.7965656065498944e-05, "loss": 1.4597432613372803, "step": 1935 }, { "epoch": 0.16343931703301923, "grad_norm": 0.15625, "learning_rate": 4.7963083115415566e-05, "loss": 1.5743842124938965, "step": 1936 }, { "epoch": 0.16352373816785032, "grad_norm": 0.1484375, "learning_rate": 4.796050860837997e-05, "loss": 1.593737244606018, "step": 1937 }, { "epoch": 0.16360815930268144, "grad_norm": 0.1337890625, "learning_rate": 4.795793254456669e-05, "loss": 1.4794996976852417, "step": 1938 }, { "epoch": 0.16369258043751253, "grad_norm": 0.1513671875, "learning_rate": 4.795535492415041e-05, "loss": 1.5185555219650269, "step": 1939 }, { "epoch": 0.16377700157234365, "grad_norm": 0.138671875, "learning_rate": 4.795277574730588e-05, "loss": 1.5599113702774048, "step": 1940 }, { "epoch": 0.16386142270717474, "grad_norm": 0.1552734375, "learning_rate": 4.795019501420799e-05, "loss": 1.562304139137268, "step": 1941 }, { "epoch": 0.16394584384200583, "grad_norm": 0.1494140625, "learning_rate": 4.79476127250317e-05, "loss": 1.5385627746582031, "step": 1942 }, { "epoch": 0.16403026497683695, "grad_norm": 0.1455078125, "learning_rate": 4.794502887995212e-05, "loss": 1.586653232574463, "step": 1943 }, { "epoch": 0.16411468611166805, "grad_norm": 0.13671875, "learning_rate": 4.794244347914443e-05, "loss": 1.5186707973480225, "step": 1944 }, { "epoch": 0.16419910724649917, "grad_norm": 0.14453125, "learning_rate": 4.793985652278392e-05, "loss": 1.5890498161315918, "step": 1945 }, { "epoch": 0.16428352838133026, "grad_norm": 0.1572265625, "learning_rate": 4.7937268011046e-05, "loss": 1.536623239517212, "step": 1946 }, { "epoch": 0.16436794951616138, "grad_norm": 0.1572265625, "learning_rate": 4.793467794410618e-05, "loss": 1.611007809638977, "step": 1947 }, { "epoch": 0.16445237065099247, "grad_norm": 0.1533203125, "learning_rate": 4.793208632214006e-05, "loss": 1.563693881034851, "step": 1948 }, { "epoch": 0.1645367917858236, "grad_norm": 0.138671875, "learning_rate": 4.7929493145323366e-05, "loss": 1.5493743419647217, "step": 1949 }, { "epoch": 0.16462121292065468, "grad_norm": 0.1650390625, "learning_rate": 4.792689841383193e-05, "loss": 1.5038301944732666, "step": 1950 }, { "epoch": 0.1647056340554858, "grad_norm": 0.1552734375, "learning_rate": 4.792430212784166e-05, "loss": 1.486590027809143, "step": 1951 }, { "epoch": 0.1647900551903169, "grad_norm": 0.1484375, "learning_rate": 4.792170428752861e-05, "loss": 1.637108325958252, "step": 1952 }, { "epoch": 0.164874476325148, "grad_norm": 0.1669921875, "learning_rate": 4.7919104893068914e-05, "loss": 1.5666170120239258, "step": 1953 }, { "epoch": 0.1649588974599791, "grad_norm": 0.1494140625, "learning_rate": 4.791650394463882e-05, "loss": 1.5538548231124878, "step": 1954 }, { "epoch": 0.16504331859481022, "grad_norm": 0.138671875, "learning_rate": 4.7913901442414665e-05, "loss": 1.5413525104522705, "step": 1955 }, { "epoch": 0.16512773972964132, "grad_norm": 0.16015625, "learning_rate": 4.7911297386572916e-05, "loss": 1.4927525520324707, "step": 1956 }, { "epoch": 0.1652121608644724, "grad_norm": 0.1494140625, "learning_rate": 4.790869177729014e-05, "loss": 1.5071430206298828, "step": 1957 }, { "epoch": 0.16529658199930353, "grad_norm": 0.1474609375, "learning_rate": 4.790608461474299e-05, "loss": 1.6348267793655396, "step": 1958 }, { "epoch": 0.16538100313413462, "grad_norm": 0.1376953125, "learning_rate": 4.7903475899108246e-05, "loss": 1.5658376216888428, "step": 1959 }, { "epoch": 0.16546542426896574, "grad_norm": 0.1416015625, "learning_rate": 4.7900865630562786e-05, "loss": 1.5515638589859009, "step": 1960 }, { "epoch": 0.16554984540379683, "grad_norm": 0.146484375, "learning_rate": 4.789825380928358e-05, "loss": 1.5700123310089111, "step": 1961 }, { "epoch": 0.16563426653862795, "grad_norm": 0.14453125, "learning_rate": 4.789564043544774e-05, "loss": 1.4950692653656006, "step": 1962 }, { "epoch": 0.16571868767345904, "grad_norm": 0.1572265625, "learning_rate": 4.789302550923244e-05, "loss": 1.5674089193344116, "step": 1963 }, { "epoch": 0.16580310880829016, "grad_norm": 0.1357421875, "learning_rate": 4.789040903081497e-05, "loss": 1.519379734992981, "step": 1964 }, { "epoch": 0.16588752994312125, "grad_norm": 0.150390625, "learning_rate": 4.7887791000372763e-05, "loss": 1.5414644479751587, "step": 1965 }, { "epoch": 0.16597195107795237, "grad_norm": 0.162109375, "learning_rate": 4.78851714180833e-05, "loss": 1.568934440612793, "step": 1966 }, { "epoch": 0.16605637221278347, "grad_norm": 0.150390625, "learning_rate": 4.788255028412421e-05, "loss": 1.5035459995269775, "step": 1967 }, { "epoch": 0.16614079334761458, "grad_norm": 0.14453125, "learning_rate": 4.787992759867321e-05, "loss": 1.5912747383117676, "step": 1968 }, { "epoch": 0.16622521448244568, "grad_norm": 0.146484375, "learning_rate": 4.787730336190812e-05, "loss": 1.5484603643417358, "step": 1969 }, { "epoch": 0.1663096356172768, "grad_norm": 0.1396484375, "learning_rate": 4.7874677574006874e-05, "loss": 1.5236009359359741, "step": 1970 }, { "epoch": 0.1663940567521079, "grad_norm": 0.1337890625, "learning_rate": 4.787205023514751e-05, "loss": 1.5341756343841553, "step": 1971 }, { "epoch": 0.166478477886939, "grad_norm": 0.13671875, "learning_rate": 4.786942134550816e-05, "loss": 1.539247751235962, "step": 1972 }, { "epoch": 0.1665628990217701, "grad_norm": 0.1318359375, "learning_rate": 4.7866790905267065e-05, "loss": 1.5245583057403564, "step": 1973 }, { "epoch": 0.1666473201566012, "grad_norm": 0.150390625, "learning_rate": 4.786415891460259e-05, "loss": 1.560536503791809, "step": 1974 }, { "epoch": 0.1667317412914323, "grad_norm": 0.15234375, "learning_rate": 4.786152537369317e-05, "loss": 1.5991944074630737, "step": 1975 }, { "epoch": 0.1668161624262634, "grad_norm": 0.1494140625, "learning_rate": 4.7858890282717395e-05, "loss": 1.531635046005249, "step": 1976 }, { "epoch": 0.16690058356109452, "grad_norm": 0.150390625, "learning_rate": 4.78562536418539e-05, "loss": 1.5281720161437988, "step": 1977 }, { "epoch": 0.16698500469592562, "grad_norm": 0.146484375, "learning_rate": 4.7853615451281475e-05, "loss": 1.556789517402649, "step": 1978 }, { "epoch": 0.16706942583075673, "grad_norm": 0.1357421875, "learning_rate": 4.785097571117899e-05, "loss": 1.5067274570465088, "step": 1979 }, { "epoch": 0.16715384696558783, "grad_norm": 0.146484375, "learning_rate": 4.7848334421725426e-05, "loss": 1.6176942586898804, "step": 1980 }, { "epoch": 0.16723826810041895, "grad_norm": 0.1416015625, "learning_rate": 4.784569158309986e-05, "loss": 1.5829054117202759, "step": 1981 }, { "epoch": 0.16732268923525004, "grad_norm": 0.1396484375, "learning_rate": 4.784304719548151e-05, "loss": 1.5973684787750244, "step": 1982 }, { "epoch": 0.16740711037008116, "grad_norm": 0.1708984375, "learning_rate": 4.784040125904963e-05, "loss": 1.6021867990493774, "step": 1983 }, { "epoch": 0.16749153150491225, "grad_norm": 0.1533203125, "learning_rate": 4.783775377398365e-05, "loss": 1.5238388776779175, "step": 1984 }, { "epoch": 0.16757595263974337, "grad_norm": 0.150390625, "learning_rate": 4.783510474046308e-05, "loss": 1.6330938339233398, "step": 1985 }, { "epoch": 0.16766037377457446, "grad_norm": 0.146484375, "learning_rate": 4.7832454158667513e-05, "loss": 1.5353906154632568, "step": 1986 }, { "epoch": 0.16774479490940558, "grad_norm": 0.1435546875, "learning_rate": 4.782980202877667e-05, "loss": 1.553264856338501, "step": 1987 }, { "epoch": 0.16782921604423667, "grad_norm": 0.142578125, "learning_rate": 4.782714835097037e-05, "loss": 1.5051567554473877, "step": 1988 }, { "epoch": 0.1679136371790678, "grad_norm": 0.146484375, "learning_rate": 4.782449312542855e-05, "loss": 1.510542631149292, "step": 1989 }, { "epoch": 0.16799805831389888, "grad_norm": 0.13671875, "learning_rate": 4.782183635233124e-05, "loss": 1.4705991744995117, "step": 1990 }, { "epoch": 0.16808247944872998, "grad_norm": 0.134765625, "learning_rate": 4.781917803185856e-05, "loss": 1.5702213048934937, "step": 1991 }, { "epoch": 0.1681669005835611, "grad_norm": 0.1376953125, "learning_rate": 4.781651816419075e-05, "loss": 1.5662615299224854, "step": 1992 }, { "epoch": 0.1682513217183922, "grad_norm": 0.1455078125, "learning_rate": 4.781385674950818e-05, "loss": 1.5405980348587036, "step": 1993 }, { "epoch": 0.1683357428532233, "grad_norm": 0.13671875, "learning_rate": 4.781119378799128e-05, "loss": 1.5383247137069702, "step": 1994 }, { "epoch": 0.1684201639880544, "grad_norm": 0.146484375, "learning_rate": 4.780852927982061e-05, "loss": 1.5253350734710693, "step": 1995 }, { "epoch": 0.16850458512288552, "grad_norm": 0.1474609375, "learning_rate": 4.7805863225176826e-05, "loss": 1.5981414318084717, "step": 1996 }, { "epoch": 0.1685890062577166, "grad_norm": 0.1474609375, "learning_rate": 4.780319562424071e-05, "loss": 1.5901777744293213, "step": 1997 }, { "epoch": 0.16867342739254773, "grad_norm": 0.1376953125, "learning_rate": 4.78005264771931e-05, "loss": 1.5884482860565186, "step": 1998 }, { "epoch": 0.16875784852737882, "grad_norm": 0.13671875, "learning_rate": 4.779785578421501e-05, "loss": 1.5199047327041626, "step": 1999 }, { "epoch": 0.16884226966220994, "grad_norm": 0.1494140625, "learning_rate": 4.779518354548748e-05, "loss": 1.632900595664978, "step": 2000 }, { "epoch": 0.16892669079704103, "grad_norm": 0.1376953125, "learning_rate": 4.7792509761191726e-05, "loss": 1.5922707319259644, "step": 2001 }, { "epoch": 0.16901111193187215, "grad_norm": 0.142578125, "learning_rate": 4.7789834431509016e-05, "loss": 1.5673284530639648, "step": 2002 }, { "epoch": 0.16909553306670325, "grad_norm": 0.150390625, "learning_rate": 4.778715755662076e-05, "loss": 1.5600394010543823, "step": 2003 }, { "epoch": 0.16917995420153437, "grad_norm": 0.13671875, "learning_rate": 4.778447913670844e-05, "loss": 1.443041205406189, "step": 2004 }, { "epoch": 0.16926437533636546, "grad_norm": 0.14453125, "learning_rate": 4.778179917195368e-05, "loss": 1.688056230545044, "step": 2005 }, { "epoch": 0.16934879647119658, "grad_norm": 0.1396484375, "learning_rate": 4.7779117662538164e-05, "loss": 1.6220219135284424, "step": 2006 }, { "epoch": 0.16943321760602767, "grad_norm": 0.1591796875, "learning_rate": 4.777643460864373e-05, "loss": 1.6376714706420898, "step": 2007 }, { "epoch": 0.16951763874085876, "grad_norm": 0.1494140625, "learning_rate": 4.777375001045227e-05, "loss": 1.5734078884124756, "step": 2008 }, { "epoch": 0.16960205987568988, "grad_norm": 0.146484375, "learning_rate": 4.777106386814582e-05, "loss": 1.5646486282348633, "step": 2009 }, { "epoch": 0.16968648101052097, "grad_norm": 0.1376953125, "learning_rate": 4.77683761819065e-05, "loss": 1.5617069005966187, "step": 2010 }, { "epoch": 0.1697709021453521, "grad_norm": 0.15234375, "learning_rate": 4.776568695191656e-05, "loss": 1.6191524267196655, "step": 2011 }, { "epoch": 0.16985532328018318, "grad_norm": 0.1533203125, "learning_rate": 4.7762996178358324e-05, "loss": 1.5757417678833008, "step": 2012 }, { "epoch": 0.1699397444150143, "grad_norm": 0.154296875, "learning_rate": 4.776030386141422e-05, "loss": 1.6776195764541626, "step": 2013 }, { "epoch": 0.1700241655498454, "grad_norm": 0.1484375, "learning_rate": 4.7757610001266815e-05, "loss": 1.5664277076721191, "step": 2014 }, { "epoch": 0.17010858668467652, "grad_norm": 0.1376953125, "learning_rate": 4.7754914598098743e-05, "loss": 1.598163366317749, "step": 2015 }, { "epoch": 0.1701930078195076, "grad_norm": 0.1416015625, "learning_rate": 4.7752217652092766e-05, "loss": 1.6031601428985596, "step": 2016 }, { "epoch": 0.17027742895433873, "grad_norm": 0.1357421875, "learning_rate": 4.774951916343175e-05, "loss": 1.574711561203003, "step": 2017 }, { "epoch": 0.17036185008916982, "grad_norm": 0.146484375, "learning_rate": 4.7746819132298646e-05, "loss": 1.5104538202285767, "step": 2018 }, { "epoch": 0.17044627122400094, "grad_norm": 0.1455078125, "learning_rate": 4.774411755887653e-05, "loss": 1.470955491065979, "step": 2019 }, { "epoch": 0.17053069235883203, "grad_norm": 0.14453125, "learning_rate": 4.774141444334857e-05, "loss": 1.676771640777588, "step": 2020 }, { "epoch": 0.17061511349366315, "grad_norm": 0.138671875, "learning_rate": 4.7738709785898055e-05, "loss": 1.5383049249649048, "step": 2021 }, { "epoch": 0.17069953462849424, "grad_norm": 0.14453125, "learning_rate": 4.7736003586708355e-05, "loss": 1.5506612062454224, "step": 2022 }, { "epoch": 0.17078395576332533, "grad_norm": 0.146484375, "learning_rate": 4.773329584596297e-05, "loss": 1.614864706993103, "step": 2023 }, { "epoch": 0.17086837689815645, "grad_norm": 0.1435546875, "learning_rate": 4.773058656384547e-05, "loss": 1.5187883377075195, "step": 2024 }, { "epoch": 0.17095279803298755, "grad_norm": 0.1455078125, "learning_rate": 4.772787574053957e-05, "loss": 1.5502005815505981, "step": 2025 }, { "epoch": 0.17103721916781867, "grad_norm": 0.1513671875, "learning_rate": 4.7725163376229064e-05, "loss": 1.5708171129226685, "step": 2026 }, { "epoch": 0.17112164030264976, "grad_norm": 0.1796875, "learning_rate": 4.7722449471097855e-05, "loss": 1.5326249599456787, "step": 2027 }, { "epoch": 0.17120606143748088, "grad_norm": 0.1435546875, "learning_rate": 4.771973402532996e-05, "loss": 1.5287768840789795, "step": 2028 }, { "epoch": 0.17129048257231197, "grad_norm": 0.150390625, "learning_rate": 4.771701703910948e-05, "loss": 1.5443224906921387, "step": 2029 }, { "epoch": 0.1713749037071431, "grad_norm": 0.1572265625, "learning_rate": 4.7714298512620646e-05, "loss": 1.5432865619659424, "step": 2030 }, { "epoch": 0.17145932484197418, "grad_norm": 0.150390625, "learning_rate": 4.771157844604778e-05, "loss": 1.4478380680084229, "step": 2031 }, { "epoch": 0.1715437459768053, "grad_norm": 0.1474609375, "learning_rate": 4.770885683957529e-05, "loss": 1.5553723573684692, "step": 2032 }, { "epoch": 0.1716281671116364, "grad_norm": 0.134765625, "learning_rate": 4.770613369338773e-05, "loss": 1.5618250370025635, "step": 2033 }, { "epoch": 0.1717125882464675, "grad_norm": 0.14453125, "learning_rate": 4.770340900766973e-05, "loss": 1.6487306356430054, "step": 2034 }, { "epoch": 0.1717970093812986, "grad_norm": 0.14453125, "learning_rate": 4.7700682782606015e-05, "loss": 1.5927854776382446, "step": 2035 }, { "epoch": 0.17188143051612972, "grad_norm": 0.140625, "learning_rate": 4.769795501838145e-05, "loss": 1.579351544380188, "step": 2036 }, { "epoch": 0.17196585165096082, "grad_norm": 0.1591796875, "learning_rate": 4.769522571518098e-05, "loss": 1.453666090965271, "step": 2037 }, { "epoch": 0.17205027278579194, "grad_norm": 0.14453125, "learning_rate": 4.7692494873189645e-05, "loss": 1.5564357042312622, "step": 2038 }, { "epoch": 0.17213469392062303, "grad_norm": 0.1494140625, "learning_rate": 4.768976249259262e-05, "loss": 1.620945930480957, "step": 2039 }, { "epoch": 0.17221911505545412, "grad_norm": 0.1474609375, "learning_rate": 4.768702857357515e-05, "loss": 1.61033296585083, "step": 2040 }, { "epoch": 0.17230353619028524, "grad_norm": 0.1474609375, "learning_rate": 4.768429311632262e-05, "loss": 1.543076753616333, "step": 2041 }, { "epoch": 0.17238795732511633, "grad_norm": 0.1376953125, "learning_rate": 4.768155612102049e-05, "loss": 1.4782482385635376, "step": 2042 }, { "epoch": 0.17247237845994745, "grad_norm": 0.140625, "learning_rate": 4.767881758785433e-05, "loss": 1.4844509363174438, "step": 2043 }, { "epoch": 0.17255679959477854, "grad_norm": 0.13671875, "learning_rate": 4.767607751700983e-05, "loss": 1.561711311340332, "step": 2044 }, { "epoch": 0.17264122072960966, "grad_norm": 0.1328125, "learning_rate": 4.767333590867277e-05, "loss": 1.5738933086395264, "step": 2045 }, { "epoch": 0.17272564186444075, "grad_norm": 0.140625, "learning_rate": 4.767059276302903e-05, "loss": 1.574850082397461, "step": 2046 }, { "epoch": 0.17281006299927187, "grad_norm": 0.1474609375, "learning_rate": 4.766784808026461e-05, "loss": 1.6239893436431885, "step": 2047 }, { "epoch": 0.17289448413410297, "grad_norm": 0.1474609375, "learning_rate": 4.7665101860565594e-05, "loss": 1.5602309703826904, "step": 2048 }, { "epoch": 0.17297890526893409, "grad_norm": 0.130859375, "learning_rate": 4.766235410411821e-05, "loss": 1.5247278213500977, "step": 2049 }, { "epoch": 0.17306332640376518, "grad_norm": 0.15625, "learning_rate": 4.765960481110874e-05, "loss": 1.639088749885559, "step": 2050 }, { "epoch": 0.1731477475385963, "grad_norm": 0.142578125, "learning_rate": 4.765685398172359e-05, "loss": 1.4268826246261597, "step": 2051 }, { "epoch": 0.1732321686734274, "grad_norm": 0.169921875, "learning_rate": 4.765410161614928e-05, "loss": 1.439247965812683, "step": 2052 }, { "epoch": 0.1733165898082585, "grad_norm": 0.1435546875, "learning_rate": 4.7651347714572435e-05, "loss": 1.616236686706543, "step": 2053 }, { "epoch": 0.1734010109430896, "grad_norm": 0.1533203125, "learning_rate": 4.764859227717976e-05, "loss": 1.5462898015975952, "step": 2054 }, { "epoch": 0.17348543207792072, "grad_norm": 0.1416015625, "learning_rate": 4.764583530415809e-05, "loss": 1.563820242881775, "step": 2055 }, { "epoch": 0.1735698532127518, "grad_norm": 0.1552734375, "learning_rate": 4.764307679569436e-05, "loss": 1.5593490600585938, "step": 2056 }, { "epoch": 0.1736542743475829, "grad_norm": 0.1533203125, "learning_rate": 4.764031675197559e-05, "loss": 1.5472012758255005, "step": 2057 }, { "epoch": 0.17373869548241402, "grad_norm": 0.15625, "learning_rate": 4.7637555173188933e-05, "loss": 1.5567312240600586, "step": 2058 }, { "epoch": 0.17382311661724512, "grad_norm": 0.1376953125, "learning_rate": 4.763479205952161e-05, "loss": 1.4767472743988037, "step": 2059 }, { "epoch": 0.17390753775207624, "grad_norm": 0.1474609375, "learning_rate": 4.763202741116098e-05, "loss": 1.5579044818878174, "step": 2060 }, { "epoch": 0.17399195888690733, "grad_norm": 0.146484375, "learning_rate": 4.76292612282945e-05, "loss": 1.5238896608352661, "step": 2061 }, { "epoch": 0.17407638002173845, "grad_norm": 0.1455078125, "learning_rate": 4.762649351110971e-05, "loss": 1.5550477504730225, "step": 2062 }, { "epoch": 0.17416080115656954, "grad_norm": 0.1337890625, "learning_rate": 4.762372425979427e-05, "loss": 1.5245932340621948, "step": 2063 }, { "epoch": 0.17424522229140066, "grad_norm": 0.146484375, "learning_rate": 4.762095347453595e-05, "loss": 1.5221577882766724, "step": 2064 }, { "epoch": 0.17432964342623175, "grad_norm": 0.13671875, "learning_rate": 4.7618181155522614e-05, "loss": 1.4908841848373413, "step": 2065 }, { "epoch": 0.17441406456106287, "grad_norm": 0.140625, "learning_rate": 4.761540730294222e-05, "loss": 1.5616023540496826, "step": 2066 }, { "epoch": 0.17449848569589396, "grad_norm": 0.1611328125, "learning_rate": 4.761263191698285e-05, "loss": 1.5253074169158936, "step": 2067 }, { "epoch": 0.17458290683072508, "grad_norm": 0.1474609375, "learning_rate": 4.760985499783269e-05, "loss": 1.6144381761550903, "step": 2068 }, { "epoch": 0.17466732796555617, "grad_norm": 0.15234375, "learning_rate": 4.7607076545680005e-05, "loss": 1.5661373138427734, "step": 2069 }, { "epoch": 0.1747517491003873, "grad_norm": 0.1396484375, "learning_rate": 4.76042965607132e-05, "loss": 1.533756136894226, "step": 2070 }, { "epoch": 0.17483617023521839, "grad_norm": 0.13671875, "learning_rate": 4.760151504312075e-05, "loss": 1.537079095840454, "step": 2071 }, { "epoch": 0.1749205913700495, "grad_norm": 0.14453125, "learning_rate": 4.759873199309125e-05, "loss": 1.4873759746551514, "step": 2072 }, { "epoch": 0.1750050125048806, "grad_norm": 0.146484375, "learning_rate": 4.75959474108134e-05, "loss": 1.498805046081543, "step": 2073 }, { "epoch": 0.1750894336397117, "grad_norm": 0.1474609375, "learning_rate": 4.759316129647601e-05, "loss": 1.5868620872497559, "step": 2074 }, { "epoch": 0.1751738547745428, "grad_norm": 0.1435546875, "learning_rate": 4.759037365026797e-05, "loss": 1.5251425504684448, "step": 2075 }, { "epoch": 0.1752582759093739, "grad_norm": 0.1474609375, "learning_rate": 4.75875844723783e-05, "loss": 1.574047327041626, "step": 2076 }, { "epoch": 0.17534269704420502, "grad_norm": 0.1435546875, "learning_rate": 4.758479376299612e-05, "loss": 1.5908622741699219, "step": 2077 }, { "epoch": 0.1754271181790361, "grad_norm": 0.1513671875, "learning_rate": 4.758200152231062e-05, "loss": 1.5791560411453247, "step": 2078 }, { "epoch": 0.17551153931386723, "grad_norm": 0.14453125, "learning_rate": 4.757920775051114e-05, "loss": 1.536508321762085, "step": 2079 }, { "epoch": 0.17559596044869832, "grad_norm": 0.1376953125, "learning_rate": 4.75764124477871e-05, "loss": 1.4921410083770752, "step": 2080 }, { "epoch": 0.17568038158352944, "grad_norm": 0.1376953125, "learning_rate": 4.7573615614328035e-05, "loss": 1.5691694021224976, "step": 2081 }, { "epoch": 0.17576480271836054, "grad_norm": 0.1435546875, "learning_rate": 4.7570817250323574e-05, "loss": 1.5126136541366577, "step": 2082 }, { "epoch": 0.17584922385319166, "grad_norm": 0.1357421875, "learning_rate": 4.7568017355963444e-05, "loss": 1.531757116317749, "step": 2083 }, { "epoch": 0.17593364498802275, "grad_norm": 0.1474609375, "learning_rate": 4.756521593143749e-05, "loss": 1.5674424171447754, "step": 2084 }, { "epoch": 0.17601806612285387, "grad_norm": 0.15234375, "learning_rate": 4.756241297693566e-05, "loss": 1.6882569789886475, "step": 2085 }, { "epoch": 0.17610248725768496, "grad_norm": 0.1455078125, "learning_rate": 4.7559608492647996e-05, "loss": 1.518796682357788, "step": 2086 }, { "epoch": 0.17618690839251608, "grad_norm": 0.142578125, "learning_rate": 4.755680247876465e-05, "loss": 1.5950679779052734, "step": 2087 }, { "epoch": 0.17627132952734717, "grad_norm": 0.1318359375, "learning_rate": 4.7553994935475875e-05, "loss": 1.4918723106384277, "step": 2088 }, { "epoch": 0.1763557506621783, "grad_norm": 0.1396484375, "learning_rate": 4.755118586297204e-05, "loss": 1.5786515474319458, "step": 2089 }, { "epoch": 0.17644017179700938, "grad_norm": 0.169921875, "learning_rate": 4.754837526144358e-05, "loss": 1.5564192533493042, "step": 2090 }, { "epoch": 0.17652459293184047, "grad_norm": 0.130859375, "learning_rate": 4.754556313108109e-05, "loss": 1.5550636053085327, "step": 2091 }, { "epoch": 0.1766090140666716, "grad_norm": 0.1376953125, "learning_rate": 4.754274947207523e-05, "loss": 1.6197643280029297, "step": 2092 }, { "epoch": 0.17669343520150269, "grad_norm": 0.142578125, "learning_rate": 4.753993428461676e-05, "loss": 1.5826449394226074, "step": 2093 }, { "epoch": 0.1767778563363338, "grad_norm": 0.1435546875, "learning_rate": 4.753711756889657e-05, "loss": 1.6008481979370117, "step": 2094 }, { "epoch": 0.1768622774711649, "grad_norm": 0.14453125, "learning_rate": 4.753429932510564e-05, "loss": 1.5756627321243286, "step": 2095 }, { "epoch": 0.17694669860599602, "grad_norm": 0.146484375, "learning_rate": 4.753147955343506e-05, "loss": 1.5208834409713745, "step": 2096 }, { "epoch": 0.1770311197408271, "grad_norm": 0.13671875, "learning_rate": 4.7528658254075986e-05, "loss": 1.5910441875457764, "step": 2097 }, { "epoch": 0.17711554087565823, "grad_norm": 0.1455078125, "learning_rate": 4.752583542721974e-05, "loss": 1.6050492525100708, "step": 2098 }, { "epoch": 0.17719996201048932, "grad_norm": 0.142578125, "learning_rate": 4.752301107305771e-05, "loss": 1.5894197225570679, "step": 2099 }, { "epoch": 0.17728438314532044, "grad_norm": 0.140625, "learning_rate": 4.752018519178139e-05, "loss": 1.5485552549362183, "step": 2100 }, { "epoch": 0.17736880428015153, "grad_norm": 0.1513671875, "learning_rate": 4.751735778358238e-05, "loss": 1.64976167678833, "step": 2101 }, { "epoch": 0.17745322541498265, "grad_norm": 0.1513671875, "learning_rate": 4.75145288486524e-05, "loss": 1.6977970600128174, "step": 2102 }, { "epoch": 0.17753764654981374, "grad_norm": 0.14453125, "learning_rate": 4.751169838718323e-05, "loss": 1.5164798498153687, "step": 2103 }, { "epoch": 0.17762206768464486, "grad_norm": 0.15625, "learning_rate": 4.75088663993668e-05, "loss": 1.5582668781280518, "step": 2104 }, { "epoch": 0.17770648881947596, "grad_norm": 0.1376953125, "learning_rate": 4.7506032885395134e-05, "loss": 1.5709075927734375, "step": 2105 }, { "epoch": 0.17779090995430705, "grad_norm": 0.1376953125, "learning_rate": 4.7503197845460334e-05, "loss": 1.543847918510437, "step": 2106 }, { "epoch": 0.17787533108913817, "grad_norm": 0.1416015625, "learning_rate": 4.750036127975464e-05, "loss": 1.54268479347229, "step": 2107 }, { "epoch": 0.17795975222396926, "grad_norm": 0.15234375, "learning_rate": 4.749752318847035e-05, "loss": 1.648959755897522, "step": 2108 }, { "epoch": 0.17804417335880038, "grad_norm": 0.154296875, "learning_rate": 4.749468357179992e-05, "loss": 1.5836493968963623, "step": 2109 }, { "epoch": 0.17812859449363147, "grad_norm": 0.134765625, "learning_rate": 4.749184242993587e-05, "loss": 1.4906823635101318, "step": 2110 }, { "epoch": 0.1782130156284626, "grad_norm": 0.13671875, "learning_rate": 4.748899976307084e-05, "loss": 1.5021251440048218, "step": 2111 }, { "epoch": 0.17829743676329368, "grad_norm": 0.150390625, "learning_rate": 4.748615557139758e-05, "loss": 1.6246650218963623, "step": 2112 }, { "epoch": 0.1783818578981248, "grad_norm": 0.138671875, "learning_rate": 4.7483309855108916e-05, "loss": 1.530889868736267, "step": 2113 }, { "epoch": 0.1784662790329559, "grad_norm": 0.142578125, "learning_rate": 4.74804626143978e-05, "loss": 1.5550295114517212, "step": 2114 }, { "epoch": 0.178550700167787, "grad_norm": 0.1376953125, "learning_rate": 4.747761384945728e-05, "loss": 1.5177667140960693, "step": 2115 }, { "epoch": 0.1786351213026181, "grad_norm": 0.1328125, "learning_rate": 4.7474763560480516e-05, "loss": 1.526268482208252, "step": 2116 }, { "epoch": 0.17871954243744922, "grad_norm": 0.1650390625, "learning_rate": 4.7471911747660755e-05, "loss": 1.5784674882888794, "step": 2117 }, { "epoch": 0.17880396357228032, "grad_norm": 0.1337890625, "learning_rate": 4.746905841119137e-05, "loss": 1.559259295463562, "step": 2118 }, { "epoch": 0.17888838470711144, "grad_norm": 0.1416015625, "learning_rate": 4.746620355126581e-05, "loss": 1.4998345375061035, "step": 2119 }, { "epoch": 0.17897280584194253, "grad_norm": 0.1455078125, "learning_rate": 4.7463347168077654e-05, "loss": 1.5493407249450684, "step": 2120 }, { "epoch": 0.17905722697677365, "grad_norm": 0.1396484375, "learning_rate": 4.746048926182056e-05, "loss": 1.6333613395690918, "step": 2121 }, { "epoch": 0.17914164811160474, "grad_norm": 0.1572265625, "learning_rate": 4.745762983268831e-05, "loss": 1.6257914304733276, "step": 2122 }, { "epoch": 0.17922606924643583, "grad_norm": 0.13671875, "learning_rate": 4.745476888087478e-05, "loss": 1.6032963991165161, "step": 2123 }, { "epoch": 0.17931049038126695, "grad_norm": 0.1416015625, "learning_rate": 4.745190640657393e-05, "loss": 1.5468111038208008, "step": 2124 }, { "epoch": 0.17939491151609804, "grad_norm": 0.142578125, "learning_rate": 4.744904240997987e-05, "loss": 1.572190523147583, "step": 2125 }, { "epoch": 0.17947933265092916, "grad_norm": 0.14453125, "learning_rate": 4.7446176891286774e-05, "loss": 1.5476995706558228, "step": 2126 }, { "epoch": 0.17956375378576026, "grad_norm": 0.13671875, "learning_rate": 4.7443309850688936e-05, "loss": 1.5354678630828857, "step": 2127 }, { "epoch": 0.17964817492059137, "grad_norm": 0.1494140625, "learning_rate": 4.7440441288380735e-05, "loss": 1.5185372829437256, "step": 2128 }, { "epoch": 0.17973259605542247, "grad_norm": 0.140625, "learning_rate": 4.7437571204556677e-05, "loss": 1.6339137554168701, "step": 2129 }, { "epoch": 0.1798170171902536, "grad_norm": 0.1552734375, "learning_rate": 4.743469959941136e-05, "loss": 1.5148993730545044, "step": 2130 }, { "epoch": 0.17990143832508468, "grad_norm": 0.1484375, "learning_rate": 4.743182647313948e-05, "loss": 1.6234533786773682, "step": 2131 }, { "epoch": 0.1799858594599158, "grad_norm": 0.1396484375, "learning_rate": 4.742895182593585e-05, "loss": 1.580324649810791, "step": 2132 }, { "epoch": 0.1800702805947469, "grad_norm": 0.142578125, "learning_rate": 4.7426075657995375e-05, "loss": 1.5908681154251099, "step": 2133 }, { "epoch": 0.180154701729578, "grad_norm": 0.13671875, "learning_rate": 4.742319796951305e-05, "loss": 1.518674612045288, "step": 2134 }, { "epoch": 0.1802391228644091, "grad_norm": 0.1396484375, "learning_rate": 4.742031876068402e-05, "loss": 1.562605619430542, "step": 2135 }, { "epoch": 0.18032354399924022, "grad_norm": 0.134765625, "learning_rate": 4.741743803170349e-05, "loss": 1.5509071350097656, "step": 2136 }, { "epoch": 0.1804079651340713, "grad_norm": 0.1435546875, "learning_rate": 4.741455578276677e-05, "loss": 1.5474803447723389, "step": 2137 }, { "epoch": 0.18049238626890243, "grad_norm": 0.1884765625, "learning_rate": 4.7411672014069294e-05, "loss": 1.5526859760284424, "step": 2138 }, { "epoch": 0.18057680740373352, "grad_norm": 0.1904296875, "learning_rate": 4.740878672580659e-05, "loss": 1.5600616931915283, "step": 2139 }, { "epoch": 0.18066122853856462, "grad_norm": 0.1533203125, "learning_rate": 4.7405899918174266e-05, "loss": 1.6569825410842896, "step": 2140 }, { "epoch": 0.18074564967339574, "grad_norm": 0.130859375, "learning_rate": 4.7403011591368083e-05, "loss": 1.533414363861084, "step": 2141 }, { "epoch": 0.18083007080822683, "grad_norm": 0.138671875, "learning_rate": 4.7400121745583856e-05, "loss": 1.5895862579345703, "step": 2142 }, { "epoch": 0.18091449194305795, "grad_norm": 0.1435546875, "learning_rate": 4.739723038101754e-05, "loss": 1.557408094406128, "step": 2143 }, { "epoch": 0.18099891307788904, "grad_norm": 0.1494140625, "learning_rate": 4.739433749786517e-05, "loss": 1.5803266763687134, "step": 2144 }, { "epoch": 0.18108333421272016, "grad_norm": 0.14453125, "learning_rate": 4.7391443096322885e-05, "loss": 1.5511882305145264, "step": 2145 }, { "epoch": 0.18116775534755125, "grad_norm": 0.140625, "learning_rate": 4.738854717658693e-05, "loss": 1.4794842004776, "step": 2146 }, { "epoch": 0.18125217648238237, "grad_norm": 0.1494140625, "learning_rate": 4.738564973885366e-05, "loss": 1.5924513339996338, "step": 2147 }, { "epoch": 0.18133659761721346, "grad_norm": 0.166015625, "learning_rate": 4.738275078331955e-05, "loss": 1.5431278944015503, "step": 2148 }, { "epoch": 0.18142101875204458, "grad_norm": 0.142578125, "learning_rate": 4.737985031018112e-05, "loss": 1.5626710653305054, "step": 2149 }, { "epoch": 0.18150543988687567, "grad_norm": 0.1455078125, "learning_rate": 4.737694831963505e-05, "loss": 1.4667518138885498, "step": 2150 }, { "epoch": 0.1815898610217068, "grad_norm": 0.154296875, "learning_rate": 4.737404481187809e-05, "loss": 1.5579235553741455, "step": 2151 }, { "epoch": 0.1816742821565379, "grad_norm": 0.1640625, "learning_rate": 4.737113978710711e-05, "loss": 1.509600281715393, "step": 2152 }, { "epoch": 0.181758703291369, "grad_norm": 0.130859375, "learning_rate": 4.736823324551909e-05, "loss": 1.4623908996582031, "step": 2153 }, { "epoch": 0.1818431244262001, "grad_norm": 0.1513671875, "learning_rate": 4.7365325187311084e-05, "loss": 1.5280965566635132, "step": 2154 }, { "epoch": 0.18192754556103122, "grad_norm": 0.1533203125, "learning_rate": 4.736241561268027e-05, "loss": 1.6170958280563354, "step": 2155 }, { "epoch": 0.1820119666958623, "grad_norm": 0.154296875, "learning_rate": 4.735950452182393e-05, "loss": 1.5683245658874512, "step": 2156 }, { "epoch": 0.1820963878306934, "grad_norm": 0.1474609375, "learning_rate": 4.735659191493944e-05, "loss": 1.5547159910202026, "step": 2157 }, { "epoch": 0.18218080896552452, "grad_norm": 0.15234375, "learning_rate": 4.735367779222427e-05, "loss": 1.6291723251342773, "step": 2158 }, { "epoch": 0.1822652301003556, "grad_norm": 0.1376953125, "learning_rate": 4.7350762153876013e-05, "loss": 1.5232534408569336, "step": 2159 }, { "epoch": 0.18234965123518673, "grad_norm": 0.162109375, "learning_rate": 4.734784500009237e-05, "loss": 1.5372977256774902, "step": 2160 }, { "epoch": 0.18243407237001782, "grad_norm": 0.1396484375, "learning_rate": 4.7344926331071114e-05, "loss": 1.539218783378601, "step": 2161 }, { "epoch": 0.18251849350484894, "grad_norm": 0.1396484375, "learning_rate": 4.734200614701014e-05, "loss": 1.4922224283218384, "step": 2162 }, { "epoch": 0.18260291463968004, "grad_norm": 0.13671875, "learning_rate": 4.733908444810745e-05, "loss": 1.5951944589614868, "step": 2163 }, { "epoch": 0.18268733577451116, "grad_norm": 0.1357421875, "learning_rate": 4.733616123456114e-05, "loss": 1.5841009616851807, "step": 2164 }, { "epoch": 0.18277175690934225, "grad_norm": 0.150390625, "learning_rate": 4.7333236506569404e-05, "loss": 1.6140648126602173, "step": 2165 }, { "epoch": 0.18285617804417337, "grad_norm": 0.14453125, "learning_rate": 4.733031026433056e-05, "loss": 1.5683541297912598, "step": 2166 }, { "epoch": 0.18294059917900446, "grad_norm": 0.1474609375, "learning_rate": 4.7327382508043e-05, "loss": 1.5764098167419434, "step": 2167 }, { "epoch": 0.18302502031383558, "grad_norm": 0.1416015625, "learning_rate": 4.732445323790523e-05, "loss": 1.4651908874511719, "step": 2168 }, { "epoch": 0.18310944144866667, "grad_norm": 0.1435546875, "learning_rate": 4.7321522454115875e-05, "loss": 1.4753814935684204, "step": 2169 }, { "epoch": 0.1831938625834978, "grad_norm": 0.1435546875, "learning_rate": 4.731859015687364e-05, "loss": 1.5093177556991577, "step": 2170 }, { "epoch": 0.18327828371832888, "grad_norm": 0.138671875, "learning_rate": 4.731565634637735e-05, "loss": 1.5759289264678955, "step": 2171 }, { "epoch": 0.18336270485316, "grad_norm": 0.150390625, "learning_rate": 4.731272102282592e-05, "loss": 1.5863336324691772, "step": 2172 }, { "epoch": 0.1834471259879911, "grad_norm": 0.169921875, "learning_rate": 4.7309784186418374e-05, "loss": 1.6042077541351318, "step": 2173 }, { "epoch": 0.1835315471228222, "grad_norm": 0.1416015625, "learning_rate": 4.730684583735383e-05, "loss": 1.5883150100708008, "step": 2174 }, { "epoch": 0.1836159682576533, "grad_norm": 0.1435546875, "learning_rate": 4.730390597583152e-05, "loss": 1.5478087663650513, "step": 2175 }, { "epoch": 0.1837003893924844, "grad_norm": 0.1357421875, "learning_rate": 4.730096460205078e-05, "loss": 1.5268229246139526, "step": 2176 }, { "epoch": 0.18378481052731552, "grad_norm": 0.146484375, "learning_rate": 4.729802171621103e-05, "loss": 1.5389683246612549, "step": 2177 }, { "epoch": 0.1838692316621466, "grad_norm": 0.1435546875, "learning_rate": 4.72950773185118e-05, "loss": 1.5350927114486694, "step": 2178 }, { "epoch": 0.18395365279697773, "grad_norm": 0.1494140625, "learning_rate": 4.729213140915276e-05, "loss": 1.5899938344955444, "step": 2179 }, { "epoch": 0.18403807393180882, "grad_norm": 0.158203125, "learning_rate": 4.728918398833361e-05, "loss": 1.5233021974563599, "step": 2180 }, { "epoch": 0.18412249506663994, "grad_norm": 0.1396484375, "learning_rate": 4.728623505625421e-05, "loss": 1.523815393447876, "step": 2181 }, { "epoch": 0.18420691620147103, "grad_norm": 0.138671875, "learning_rate": 4.728328461311452e-05, "loss": 1.5471142530441284, "step": 2182 }, { "epoch": 0.18429133733630215, "grad_norm": 0.1630859375, "learning_rate": 4.728033265911456e-05, "loss": 1.5377624034881592, "step": 2183 }, { "epoch": 0.18437575847113324, "grad_norm": 0.1533203125, "learning_rate": 4.7277379194454484e-05, "loss": 1.5560933351516724, "step": 2184 }, { "epoch": 0.18446017960596436, "grad_norm": 0.13671875, "learning_rate": 4.727442421933456e-05, "loss": 1.556131362915039, "step": 2185 }, { "epoch": 0.18454460074079546, "grad_norm": 0.1435546875, "learning_rate": 4.727146773395513e-05, "loss": 1.5792930126190186, "step": 2186 }, { "epoch": 0.18462902187562658, "grad_norm": 0.1552734375, "learning_rate": 4.726850973851665e-05, "loss": 1.6478915214538574, "step": 2187 }, { "epoch": 0.18471344301045767, "grad_norm": 0.1474609375, "learning_rate": 4.7265550233219694e-05, "loss": 1.5955047607421875, "step": 2188 }, { "epoch": 0.18479786414528876, "grad_norm": 0.150390625, "learning_rate": 4.726258921826491e-05, "loss": 1.579500675201416, "step": 2189 }, { "epoch": 0.18488228528011988, "grad_norm": 0.1533203125, "learning_rate": 4.7259626693853065e-05, "loss": 1.5734752416610718, "step": 2190 }, { "epoch": 0.18496670641495097, "grad_norm": 0.1513671875, "learning_rate": 4.725666266018502e-05, "loss": 1.6602187156677246, "step": 2191 }, { "epoch": 0.1850511275497821, "grad_norm": 0.1328125, "learning_rate": 4.725369711746175e-05, "loss": 1.5202107429504395, "step": 2192 }, { "epoch": 0.18513554868461318, "grad_norm": 0.150390625, "learning_rate": 4.725073006588433e-05, "loss": 1.6547677516937256, "step": 2193 }, { "epoch": 0.1852199698194443, "grad_norm": 0.1455078125, "learning_rate": 4.724776150565392e-05, "loss": 1.5844529867172241, "step": 2194 }, { "epoch": 0.1853043909542754, "grad_norm": 0.1455078125, "learning_rate": 4.72447914369718e-05, "loss": 1.594730019569397, "step": 2195 }, { "epoch": 0.18538881208910651, "grad_norm": 0.138671875, "learning_rate": 4.724181986003936e-05, "loss": 1.630993366241455, "step": 2196 }, { "epoch": 0.1854732332239376, "grad_norm": 0.140625, "learning_rate": 4.7238846775058076e-05, "loss": 1.5296499729156494, "step": 2197 }, { "epoch": 0.18555765435876873, "grad_norm": 0.1474609375, "learning_rate": 4.723587218222951e-05, "loss": 1.6048277616500854, "step": 2198 }, { "epoch": 0.18564207549359982, "grad_norm": 0.140625, "learning_rate": 4.723289608175537e-05, "loss": 1.5235880613327026, "step": 2199 }, { "epoch": 0.18572649662843094, "grad_norm": 0.142578125, "learning_rate": 4.722991847383744e-05, "loss": 1.5786280632019043, "step": 2200 }, { "epoch": 0.18581091776326203, "grad_norm": 0.1474609375, "learning_rate": 4.72269393586776e-05, "loss": 1.6492611169815063, "step": 2201 }, { "epoch": 0.18589533889809315, "grad_norm": 0.1552734375, "learning_rate": 4.722395873647785e-05, "loss": 1.5640919208526611, "step": 2202 }, { "epoch": 0.18597976003292424, "grad_norm": 0.140625, "learning_rate": 4.722097660744027e-05, "loss": 1.5661540031433105, "step": 2203 }, { "epoch": 0.18606418116775536, "grad_norm": 0.142578125, "learning_rate": 4.7217992971767065e-05, "loss": 1.5485475063323975, "step": 2204 }, { "epoch": 0.18614860230258645, "grad_norm": 0.1376953125, "learning_rate": 4.721500782966053e-05, "loss": 1.4807660579681396, "step": 2205 }, { "epoch": 0.18623302343741754, "grad_norm": 0.1328125, "learning_rate": 4.7212021181323075e-05, "loss": 1.5230534076690674, "step": 2206 }, { "epoch": 0.18631744457224866, "grad_norm": 0.1435546875, "learning_rate": 4.720903302695718e-05, "loss": 1.538728952407837, "step": 2207 }, { "epoch": 0.18640186570707976, "grad_norm": 0.1611328125, "learning_rate": 4.7206043366765476e-05, "loss": 1.5581238269805908, "step": 2208 }, { "epoch": 0.18648628684191088, "grad_norm": 0.16015625, "learning_rate": 4.720305220095065e-05, "loss": 1.6228444576263428, "step": 2209 }, { "epoch": 0.18657070797674197, "grad_norm": 0.1552734375, "learning_rate": 4.720005952971551e-05, "loss": 1.6572808027267456, "step": 2210 }, { "epoch": 0.1866551291115731, "grad_norm": 0.1396484375, "learning_rate": 4.719706535326298e-05, "loss": 1.5488898754119873, "step": 2211 }, { "epoch": 0.18673955024640418, "grad_norm": 0.1357421875, "learning_rate": 4.719406967179606e-05, "loss": 1.5410728454589844, "step": 2212 }, { "epoch": 0.1868239713812353, "grad_norm": 0.1494140625, "learning_rate": 4.719107248551787e-05, "loss": 1.6099549531936646, "step": 2213 }, { "epoch": 0.1869083925160664, "grad_norm": 0.1376953125, "learning_rate": 4.718807379463162e-05, "loss": 1.5537919998168945, "step": 2214 }, { "epoch": 0.1869928136508975, "grad_norm": 0.1396484375, "learning_rate": 4.718507359934064e-05, "loss": 1.5363478660583496, "step": 2215 }, { "epoch": 0.1870772347857286, "grad_norm": 0.14453125, "learning_rate": 4.718207189984834e-05, "loss": 1.555479884147644, "step": 2216 }, { "epoch": 0.18716165592055972, "grad_norm": 0.15234375, "learning_rate": 4.717906869635825e-05, "loss": 1.5398449897766113, "step": 2217 }, { "epoch": 0.1872460770553908, "grad_norm": 0.1552734375, "learning_rate": 4.717606398907399e-05, "loss": 1.5768312215805054, "step": 2218 }, { "epoch": 0.18733049819022193, "grad_norm": 0.1484375, "learning_rate": 4.717305777819929e-05, "loss": 1.5098366737365723, "step": 2219 }, { "epoch": 0.18741491932505303, "grad_norm": 0.1513671875, "learning_rate": 4.717005006393798e-05, "loss": 1.582203984260559, "step": 2220 }, { "epoch": 0.18749934045988415, "grad_norm": 0.1533203125, "learning_rate": 4.716704084649397e-05, "loss": 1.5364326238632202, "step": 2221 }, { "epoch": 0.18758376159471524, "grad_norm": 0.1435546875, "learning_rate": 4.716403012607132e-05, "loss": 1.5928620100021362, "step": 2222 }, { "epoch": 0.18766818272954633, "grad_norm": 0.1484375, "learning_rate": 4.716101790287415e-05, "loss": 1.6033830642700195, "step": 2223 }, { "epoch": 0.18775260386437745, "grad_norm": 0.1416015625, "learning_rate": 4.71580041771067e-05, "loss": 1.4983843564987183, "step": 2224 }, { "epoch": 0.18783702499920854, "grad_norm": 0.134765625, "learning_rate": 4.71549889489733e-05, "loss": 1.4849486351013184, "step": 2225 }, { "epoch": 0.18792144613403966, "grad_norm": 0.158203125, "learning_rate": 4.7151972218678396e-05, "loss": 1.4983441829681396, "step": 2226 }, { "epoch": 0.18800586726887075, "grad_norm": 0.1455078125, "learning_rate": 4.7148953986426534e-05, "loss": 1.5567898750305176, "step": 2227 }, { "epoch": 0.18809028840370187, "grad_norm": 0.1611328125, "learning_rate": 4.7145934252422356e-05, "loss": 1.5850622653961182, "step": 2228 }, { "epoch": 0.18817470953853296, "grad_norm": 0.14453125, "learning_rate": 4.7142913016870594e-05, "loss": 1.635312795639038, "step": 2229 }, { "epoch": 0.18825913067336408, "grad_norm": 0.142578125, "learning_rate": 4.713989027997611e-05, "loss": 1.5511369705200195, "step": 2230 }, { "epoch": 0.18834355180819518, "grad_norm": 0.158203125, "learning_rate": 4.7136866041943845e-05, "loss": 1.6188443899154663, "step": 2231 }, { "epoch": 0.1884279729430263, "grad_norm": 0.158203125, "learning_rate": 4.7133840302978856e-05, "loss": 1.5800172090530396, "step": 2232 }, { "epoch": 0.1885123940778574, "grad_norm": 0.142578125, "learning_rate": 4.713081306328629e-05, "loss": 1.5755932331085205, "step": 2233 }, { "epoch": 0.1885968152126885, "grad_norm": 0.15625, "learning_rate": 4.71277843230714e-05, "loss": 1.612611174583435, "step": 2234 }, { "epoch": 0.1886812363475196, "grad_norm": 0.1455078125, "learning_rate": 4.7124754082539546e-05, "loss": 1.5091967582702637, "step": 2235 }, { "epoch": 0.18876565748235072, "grad_norm": 0.1416015625, "learning_rate": 4.712172234189619e-05, "loss": 1.6154975891113281, "step": 2236 }, { "epoch": 0.1888500786171818, "grad_norm": 0.177734375, "learning_rate": 4.711868910134688e-05, "loss": 1.4736875295639038, "step": 2237 }, { "epoch": 0.18893449975201293, "grad_norm": 0.14453125, "learning_rate": 4.711565436109728e-05, "loss": 1.6388529539108276, "step": 2238 }, { "epoch": 0.18901892088684402, "grad_norm": 0.1416015625, "learning_rate": 4.7112618121353166e-05, "loss": 1.4830403327941895, "step": 2239 }, { "epoch": 0.1891033420216751, "grad_norm": 0.1513671875, "learning_rate": 4.710958038232038e-05, "loss": 1.5894663333892822, "step": 2240 }, { "epoch": 0.18918776315650623, "grad_norm": 0.1396484375, "learning_rate": 4.7106541144204905e-05, "loss": 1.4744350910186768, "step": 2241 }, { "epoch": 0.18927218429133733, "grad_norm": 0.138671875, "learning_rate": 4.710350040721281e-05, "loss": 1.581407070159912, "step": 2242 }, { "epoch": 0.18935660542616845, "grad_norm": 0.142578125, "learning_rate": 4.7100458171550246e-05, "loss": 1.601474404335022, "step": 2243 }, { "epoch": 0.18944102656099954, "grad_norm": 0.1435546875, "learning_rate": 4.709741443742351e-05, "loss": 1.507683515548706, "step": 2244 }, { "epoch": 0.18952544769583066, "grad_norm": 0.138671875, "learning_rate": 4.709436920503894e-05, "loss": 1.5247864723205566, "step": 2245 }, { "epoch": 0.18960986883066175, "grad_norm": 0.1396484375, "learning_rate": 4.709132247460304e-05, "loss": 1.558261513710022, "step": 2246 }, { "epoch": 0.18969428996549287, "grad_norm": 0.14453125, "learning_rate": 4.7088274246322375e-05, "loss": 1.580621361732483, "step": 2247 }, { "epoch": 0.18977871110032396, "grad_norm": 0.146484375, "learning_rate": 4.7085224520403626e-05, "loss": 1.562495470046997, "step": 2248 }, { "epoch": 0.18986313223515508, "grad_norm": 0.1416015625, "learning_rate": 4.708217329705357e-05, "loss": 1.5387303829193115, "step": 2249 }, { "epoch": 0.18994755336998617, "grad_norm": 0.1640625, "learning_rate": 4.707912057647908e-05, "loss": 1.661500096321106, "step": 2250 }, { "epoch": 0.1900319745048173, "grad_norm": 0.154296875, "learning_rate": 4.707606635888714e-05, "loss": 1.614595890045166, "step": 2251 }, { "epoch": 0.19011639563964838, "grad_norm": 0.1416015625, "learning_rate": 4.707301064448485e-05, "loss": 1.487162709236145, "step": 2252 }, { "epoch": 0.1902008167744795, "grad_norm": 0.1455078125, "learning_rate": 4.7069953433479377e-05, "loss": 1.5225472450256348, "step": 2253 }, { "epoch": 0.1902852379093106, "grad_norm": 0.140625, "learning_rate": 4.7066894726078e-05, "loss": 1.5463253259658813, "step": 2254 }, { "epoch": 0.19036965904414171, "grad_norm": 0.1552734375, "learning_rate": 4.7063834522488134e-05, "loss": 1.536361813545227, "step": 2255 }, { "epoch": 0.1904540801789728, "grad_norm": 0.142578125, "learning_rate": 4.706077282291724e-05, "loss": 1.5084925889968872, "step": 2256 }, { "epoch": 0.1905385013138039, "grad_norm": 0.1416015625, "learning_rate": 4.705770962757293e-05, "loss": 1.5474237203598022, "step": 2257 }, { "epoch": 0.19062292244863502, "grad_norm": 0.140625, "learning_rate": 4.705464493666289e-05, "loss": 1.5984963178634644, "step": 2258 }, { "epoch": 0.1907073435834661, "grad_norm": 0.138671875, "learning_rate": 4.7051578750394906e-05, "loss": 1.552381992340088, "step": 2259 }, { "epoch": 0.19079176471829723, "grad_norm": 0.15234375, "learning_rate": 4.704851106897689e-05, "loss": 1.573160171508789, "step": 2260 }, { "epoch": 0.19087618585312832, "grad_norm": 0.1357421875, "learning_rate": 4.7045441892616805e-05, "loss": 1.48264479637146, "step": 2261 }, { "epoch": 0.19096060698795944, "grad_norm": 0.1513671875, "learning_rate": 4.704237122152279e-05, "loss": 1.6519732475280762, "step": 2262 }, { "epoch": 0.19104502812279053, "grad_norm": 0.1416015625, "learning_rate": 4.703929905590301e-05, "loss": 1.5351759195327759, "step": 2263 }, { "epoch": 0.19112944925762165, "grad_norm": 0.14453125, "learning_rate": 4.703622539596577e-05, "loss": 1.641156554222107, "step": 2264 }, { "epoch": 0.19121387039245274, "grad_norm": 0.140625, "learning_rate": 4.70331502419195e-05, "loss": 1.6021567583084106, "step": 2265 }, { "epoch": 0.19129829152728386, "grad_norm": 0.1474609375, "learning_rate": 4.703007359397267e-05, "loss": 1.5382990837097168, "step": 2266 }, { "epoch": 0.19138271266211496, "grad_norm": 0.1455078125, "learning_rate": 4.70269954523339e-05, "loss": 1.569337010383606, "step": 2267 }, { "epoch": 0.19146713379694608, "grad_norm": 0.1494140625, "learning_rate": 4.7023915817211895e-05, "loss": 1.5825611352920532, "step": 2268 }, { "epoch": 0.19155155493177717, "grad_norm": 0.146484375, "learning_rate": 4.7020834688815455e-05, "loss": 1.599116325378418, "step": 2269 }, { "epoch": 0.1916359760666083, "grad_norm": 0.146484375, "learning_rate": 4.7017752067353496e-05, "loss": 1.6824843883514404, "step": 2270 }, { "epoch": 0.19172039720143938, "grad_norm": 0.1474609375, "learning_rate": 4.701466795303502e-05, "loss": 1.612403392791748, "step": 2271 }, { "epoch": 0.19180481833627047, "grad_norm": 0.1484375, "learning_rate": 4.701158234606914e-05, "loss": 1.5795801877975464, "step": 2272 }, { "epoch": 0.1918892394711016, "grad_norm": 0.138671875, "learning_rate": 4.7008495246665076e-05, "loss": 1.566747784614563, "step": 2273 }, { "epoch": 0.19197366060593268, "grad_norm": 0.142578125, "learning_rate": 4.7005406655032125e-05, "loss": 1.5195300579071045, "step": 2274 }, { "epoch": 0.1920580817407638, "grad_norm": 0.1591796875, "learning_rate": 4.7002316571379715e-05, "loss": 1.5420253276824951, "step": 2275 }, { "epoch": 0.1921425028755949, "grad_norm": 0.158203125, "learning_rate": 4.6999224995917346e-05, "loss": 1.618879795074463, "step": 2276 }, { "epoch": 0.19222692401042601, "grad_norm": 0.1494140625, "learning_rate": 4.699613192885465e-05, "loss": 1.5581072568893433, "step": 2277 }, { "epoch": 0.1923113451452571, "grad_norm": 0.16015625, "learning_rate": 4.699303737040133e-05, "loss": 1.4471790790557861, "step": 2278 }, { "epoch": 0.19239576628008823, "grad_norm": 0.14453125, "learning_rate": 4.698994132076722e-05, "loss": 1.6164742708206177, "step": 2279 }, { "epoch": 0.19248018741491932, "grad_norm": 0.1396484375, "learning_rate": 4.698684378016222e-05, "loss": 1.5907795429229736, "step": 2280 }, { "epoch": 0.19256460854975044, "grad_norm": 0.1484375, "learning_rate": 4.698374474879638e-05, "loss": 1.4907429218292236, "step": 2281 }, { "epoch": 0.19264902968458153, "grad_norm": 0.150390625, "learning_rate": 4.69806442268798e-05, "loss": 1.556503415107727, "step": 2282 }, { "epoch": 0.19273345081941265, "grad_norm": 0.1552734375, "learning_rate": 4.6977542214622696e-05, "loss": 1.4936552047729492, "step": 2283 }, { "epoch": 0.19281787195424374, "grad_norm": 0.150390625, "learning_rate": 4.697443871223541e-05, "loss": 1.5426723957061768, "step": 2284 }, { "epoch": 0.19290229308907486, "grad_norm": 0.1337890625, "learning_rate": 4.6971333719928354e-05, "loss": 1.5237371921539307, "step": 2285 }, { "epoch": 0.19298671422390595, "grad_norm": 0.1484375, "learning_rate": 4.696822723791207e-05, "loss": 1.6365735530853271, "step": 2286 }, { "epoch": 0.19307113535873707, "grad_norm": 0.1484375, "learning_rate": 4.696511926639717e-05, "loss": 1.4801056385040283, "step": 2287 }, { "epoch": 0.19315555649356816, "grad_norm": 0.1435546875, "learning_rate": 4.696200980559438e-05, "loss": 1.5306950807571411, "step": 2288 }, { "epoch": 0.19323997762839926, "grad_norm": 0.150390625, "learning_rate": 4.6958898855714543e-05, "loss": 1.552082896232605, "step": 2289 }, { "epoch": 0.19332439876323038, "grad_norm": 0.15234375, "learning_rate": 4.695578641696858e-05, "loss": 1.5869977474212646, "step": 2290 }, { "epoch": 0.19340881989806147, "grad_norm": 0.166015625, "learning_rate": 4.6952672489567526e-05, "loss": 1.6025103330612183, "step": 2291 }, { "epoch": 0.1934932410328926, "grad_norm": 0.1435546875, "learning_rate": 4.6949557073722506e-05, "loss": 1.5561243295669556, "step": 2292 }, { "epoch": 0.19357766216772368, "grad_norm": 0.1474609375, "learning_rate": 4.694644016964476e-05, "loss": 1.521194577217102, "step": 2293 }, { "epoch": 0.1936620833025548, "grad_norm": 0.142578125, "learning_rate": 4.694332177754561e-05, "loss": 1.5065287351608276, "step": 2294 }, { "epoch": 0.1937465044373859, "grad_norm": 0.14453125, "learning_rate": 4.69402018976365e-05, "loss": 1.6447052955627441, "step": 2295 }, { "epoch": 0.193830925572217, "grad_norm": 0.1416015625, "learning_rate": 4.693708053012897e-05, "loss": 1.5269414186477661, "step": 2296 }, { "epoch": 0.1939153467070481, "grad_norm": 0.1416015625, "learning_rate": 4.6933957675234646e-05, "loss": 1.5345007181167603, "step": 2297 }, { "epoch": 0.19399976784187922, "grad_norm": 0.150390625, "learning_rate": 4.693083333316527e-05, "loss": 1.5474963188171387, "step": 2298 }, { "epoch": 0.19408418897671031, "grad_norm": 0.162109375, "learning_rate": 4.6927707504132686e-05, "loss": 1.582406997680664, "step": 2299 }, { "epoch": 0.19416861011154143, "grad_norm": 0.1796875, "learning_rate": 4.692458018834882e-05, "loss": 1.6403268575668335, "step": 2300 }, { "epoch": 0.19425303124637253, "grad_norm": 0.1435546875, "learning_rate": 4.692145138602572e-05, "loss": 1.5161631107330322, "step": 2301 }, { "epoch": 0.19433745238120365, "grad_norm": 0.1455078125, "learning_rate": 4.6918321097375516e-05, "loss": 1.5785809755325317, "step": 2302 }, { "epoch": 0.19442187351603474, "grad_norm": 0.1435546875, "learning_rate": 4.6915189322610466e-05, "loss": 1.597416639328003, "step": 2303 }, { "epoch": 0.19450629465086586, "grad_norm": 0.130859375, "learning_rate": 4.69120560619429e-05, "loss": 1.5294902324676514, "step": 2304 }, { "epoch": 0.19459071578569695, "grad_norm": 0.142578125, "learning_rate": 4.6908921315585264e-05, "loss": 1.5442718267440796, "step": 2305 }, { "epoch": 0.19467513692052804, "grad_norm": 0.142578125, "learning_rate": 4.69057850837501e-05, "loss": 1.6714818477630615, "step": 2306 }, { "epoch": 0.19475955805535916, "grad_norm": 0.1435546875, "learning_rate": 4.690264736665005e-05, "loss": 1.6138415336608887, "step": 2307 }, { "epoch": 0.19484397919019025, "grad_norm": 0.1435546875, "learning_rate": 4.689950816449786e-05, "loss": 1.5439426898956299, "step": 2308 }, { "epoch": 0.19492840032502137, "grad_norm": 0.16015625, "learning_rate": 4.6896367477506384e-05, "loss": 1.529693365097046, "step": 2309 }, { "epoch": 0.19501282145985246, "grad_norm": 0.1552734375, "learning_rate": 4.6893225305888556e-05, "loss": 1.5661473274230957, "step": 2310 }, { "epoch": 0.19509724259468358, "grad_norm": 0.134765625, "learning_rate": 4.6890081649857435e-05, "loss": 1.5974647998809814, "step": 2311 }, { "epoch": 0.19518166372951468, "grad_norm": 0.1640625, "learning_rate": 4.688693650962615e-05, "loss": 1.5730407238006592, "step": 2312 }, { "epoch": 0.1952660848643458, "grad_norm": 0.1337890625, "learning_rate": 4.688378988540797e-05, "loss": 1.556639313697815, "step": 2313 }, { "epoch": 0.1953505059991769, "grad_norm": 0.173828125, "learning_rate": 4.688064177741622e-05, "loss": 1.5153164863586426, "step": 2314 }, { "epoch": 0.195434927134008, "grad_norm": 0.134765625, "learning_rate": 4.687749218586438e-05, "loss": 1.5184710025787354, "step": 2315 }, { "epoch": 0.1955193482688391, "grad_norm": 0.1474609375, "learning_rate": 4.687434111096598e-05, "loss": 1.585716962814331, "step": 2316 }, { "epoch": 0.19560376940367022, "grad_norm": 0.1435546875, "learning_rate": 4.687118855293467e-05, "loss": 1.6001737117767334, "step": 2317 }, { "epoch": 0.1956881905385013, "grad_norm": 0.1611328125, "learning_rate": 4.6868034511984205e-05, "loss": 1.526794672012329, "step": 2318 }, { "epoch": 0.19577261167333243, "grad_norm": 0.1552734375, "learning_rate": 4.686487898832843e-05, "loss": 1.555947184562683, "step": 2319 }, { "epoch": 0.19585703280816352, "grad_norm": 0.146484375, "learning_rate": 4.686172198218132e-05, "loss": 1.567470908164978, "step": 2320 }, { "epoch": 0.19594145394299464, "grad_norm": 0.1396484375, "learning_rate": 4.6858563493756895e-05, "loss": 1.553735375404358, "step": 2321 }, { "epoch": 0.19602587507782573, "grad_norm": 0.1376953125, "learning_rate": 4.685540352326933e-05, "loss": 1.5496560335159302, "step": 2322 }, { "epoch": 0.19611029621265683, "grad_norm": 0.140625, "learning_rate": 4.685224207093287e-05, "loss": 1.577527642250061, "step": 2323 }, { "epoch": 0.19619471734748795, "grad_norm": 0.181640625, "learning_rate": 4.684907913696188e-05, "loss": 1.5639184713363647, "step": 2324 }, { "epoch": 0.19627913848231904, "grad_norm": 0.140625, "learning_rate": 4.6845914721570796e-05, "loss": 1.5380051136016846, "step": 2325 }, { "epoch": 0.19636355961715016, "grad_norm": 0.1455078125, "learning_rate": 4.684274882497419e-05, "loss": 1.5671802759170532, "step": 2326 }, { "epoch": 0.19644798075198125, "grad_norm": 0.1357421875, "learning_rate": 4.683958144738671e-05, "loss": 1.4459314346313477, "step": 2327 }, { "epoch": 0.19653240188681237, "grad_norm": 0.1328125, "learning_rate": 4.683641258902311e-05, "loss": 1.5840040445327759, "step": 2328 }, { "epoch": 0.19661682302164346, "grad_norm": 0.146484375, "learning_rate": 4.6833242250098254e-05, "loss": 1.5278360843658447, "step": 2329 }, { "epoch": 0.19670124415647458, "grad_norm": 0.15234375, "learning_rate": 4.683007043082709e-05, "loss": 1.5711300373077393, "step": 2330 }, { "epoch": 0.19678566529130567, "grad_norm": 0.1484375, "learning_rate": 4.682689713142467e-05, "loss": 1.5490362644195557, "step": 2331 }, { "epoch": 0.1968700864261368, "grad_norm": 0.140625, "learning_rate": 4.682372235210617e-05, "loss": 1.5462377071380615, "step": 2332 }, { "epoch": 0.19695450756096788, "grad_norm": 0.140625, "learning_rate": 4.682054609308683e-05, "loss": 1.5352356433868408, "step": 2333 }, { "epoch": 0.197038928695799, "grad_norm": 0.1396484375, "learning_rate": 4.681736835458203e-05, "loss": 1.6036171913146973, "step": 2334 }, { "epoch": 0.1971233498306301, "grad_norm": 0.15234375, "learning_rate": 4.68141891368072e-05, "loss": 1.5305596590042114, "step": 2335 }, { "epoch": 0.19720777096546122, "grad_norm": 0.1787109375, "learning_rate": 4.681100843997791e-05, "loss": 1.4777768850326538, "step": 2336 }, { "epoch": 0.1972921921002923, "grad_norm": 0.1396484375, "learning_rate": 4.680782626430982e-05, "loss": 1.528956651687622, "step": 2337 }, { "epoch": 0.1973766132351234, "grad_norm": 0.1396484375, "learning_rate": 4.68046426100187e-05, "loss": 1.6064280271530151, "step": 2338 }, { "epoch": 0.19746103436995452, "grad_norm": 0.1435546875, "learning_rate": 4.680145747732039e-05, "loss": 1.5061287879943848, "step": 2339 }, { "epoch": 0.1975454555047856, "grad_norm": 0.1455078125, "learning_rate": 4.679827086643087e-05, "loss": 1.5622828006744385, "step": 2340 }, { "epoch": 0.19762987663961673, "grad_norm": 0.138671875, "learning_rate": 4.679508277756618e-05, "loss": 1.58157479763031, "step": 2341 }, { "epoch": 0.19771429777444782, "grad_norm": 0.1474609375, "learning_rate": 4.679189321094249e-05, "loss": 1.4539501667022705, "step": 2342 }, { "epoch": 0.19779871890927894, "grad_norm": 0.1552734375, "learning_rate": 4.6788702166776065e-05, "loss": 1.6309059858322144, "step": 2343 }, { "epoch": 0.19788314004411003, "grad_norm": 0.1435546875, "learning_rate": 4.678550964528326e-05, "loss": 1.5464657545089722, "step": 2344 }, { "epoch": 0.19796756117894115, "grad_norm": 0.14453125, "learning_rate": 4.678231564668053e-05, "loss": 1.5525119304656982, "step": 2345 }, { "epoch": 0.19805198231377225, "grad_norm": 0.1337890625, "learning_rate": 4.6779120171184446e-05, "loss": 1.558740496635437, "step": 2346 }, { "epoch": 0.19813640344860337, "grad_norm": 0.140625, "learning_rate": 4.677592321901166e-05, "loss": 1.484794020652771, "step": 2347 }, { "epoch": 0.19822082458343446, "grad_norm": 0.1376953125, "learning_rate": 4.6772724790378945e-05, "loss": 1.585705041885376, "step": 2348 }, { "epoch": 0.19830524571826558, "grad_norm": 0.134765625, "learning_rate": 4.676952488550315e-05, "loss": 1.5846774578094482, "step": 2349 }, { "epoch": 0.19838966685309667, "grad_norm": 0.140625, "learning_rate": 4.676632350460124e-05, "loss": 1.4878544807434082, "step": 2350 }, { "epoch": 0.1984740879879278, "grad_norm": 0.16015625, "learning_rate": 4.676312064789027e-05, "loss": 1.532244324684143, "step": 2351 }, { "epoch": 0.19855850912275888, "grad_norm": 0.15234375, "learning_rate": 4.675991631558742e-05, "loss": 1.623406171798706, "step": 2352 }, { "epoch": 0.19864293025759, "grad_norm": 0.138671875, "learning_rate": 4.675671050790994e-05, "loss": 1.5584843158721924, "step": 2353 }, { "epoch": 0.1987273513924211, "grad_norm": 0.1435546875, "learning_rate": 4.675350322507518e-05, "loss": 1.4984263181686401, "step": 2354 }, { "epoch": 0.19881177252725218, "grad_norm": 0.1435546875, "learning_rate": 4.675029446730062e-05, "loss": 1.6224843263626099, "step": 2355 }, { "epoch": 0.1988961936620833, "grad_norm": 0.1650390625, "learning_rate": 4.6747084234803816e-05, "loss": 1.604074239730835, "step": 2356 }, { "epoch": 0.1989806147969144, "grad_norm": 0.1484375, "learning_rate": 4.6743872527802426e-05, "loss": 1.5453237295150757, "step": 2357 }, { "epoch": 0.19906503593174552, "grad_norm": 0.16796875, "learning_rate": 4.674065934651421e-05, "loss": 1.668739676475525, "step": 2358 }, { "epoch": 0.1991494570665766, "grad_norm": 0.1376953125, "learning_rate": 4.673744469115704e-05, "loss": 1.451710820198059, "step": 2359 }, { "epoch": 0.19923387820140773, "grad_norm": 0.14453125, "learning_rate": 4.6734228561948864e-05, "loss": 1.5547943115234375, "step": 2360 }, { "epoch": 0.19931829933623882, "grad_norm": 0.1435546875, "learning_rate": 4.673101095910774e-05, "loss": 1.5524898767471313, "step": 2361 }, { "epoch": 0.19940272047106994, "grad_norm": 0.142578125, "learning_rate": 4.6727791882851855e-05, "loss": 1.4217476844787598, "step": 2362 }, { "epoch": 0.19948714160590103, "grad_norm": 0.1611328125, "learning_rate": 4.672457133339945e-05, "loss": 1.5634677410125732, "step": 2363 }, { "epoch": 0.19957156274073215, "grad_norm": 0.15234375, "learning_rate": 4.6721349310968885e-05, "loss": 1.5763381719589233, "step": 2364 }, { "epoch": 0.19965598387556324, "grad_norm": 0.142578125, "learning_rate": 4.671812581577863e-05, "loss": 1.5586680173873901, "step": 2365 }, { "epoch": 0.19974040501039436, "grad_norm": 0.150390625, "learning_rate": 4.671490084804724e-05, "loss": 1.5709856748580933, "step": 2366 }, { "epoch": 0.19982482614522545, "grad_norm": 0.1435546875, "learning_rate": 4.671167440799338e-05, "loss": 1.5409657955169678, "step": 2367 }, { "epoch": 0.19990924728005657, "grad_norm": 0.1376953125, "learning_rate": 4.67084464958358e-05, "loss": 1.5598242282867432, "step": 2368 }, { "epoch": 0.19999366841488767, "grad_norm": 0.14453125, "learning_rate": 4.670521711179337e-05, "loss": 1.5634928941726685, "step": 2369 }, { "epoch": 0.20007808954971879, "grad_norm": 0.130859375, "learning_rate": 4.6701986256085046e-05, "loss": 1.586333990097046, "step": 2370 }, { "epoch": 0.20016251068454988, "grad_norm": 0.154296875, "learning_rate": 4.669875392892989e-05, "loss": 1.6035852432250977, "step": 2371 }, { "epoch": 0.20024693181938097, "grad_norm": 0.1396484375, "learning_rate": 4.669552013054706e-05, "loss": 1.5842812061309814, "step": 2372 }, { "epoch": 0.2003313529542121, "grad_norm": 0.138671875, "learning_rate": 4.669228486115582e-05, "loss": 1.5221631526947021, "step": 2373 }, { "epoch": 0.20041577408904318, "grad_norm": 0.1416015625, "learning_rate": 4.668904812097552e-05, "loss": 1.4917134046554565, "step": 2374 }, { "epoch": 0.2005001952238743, "grad_norm": 0.142578125, "learning_rate": 4.668580991022563e-05, "loss": 1.5377521514892578, "step": 2375 }, { "epoch": 0.2005846163587054, "grad_norm": 0.1357421875, "learning_rate": 4.66825702291257e-05, "loss": 1.6131360530853271, "step": 2376 }, { "epoch": 0.2006690374935365, "grad_norm": 0.12890625, "learning_rate": 4.6679329077895384e-05, "loss": 1.5633383989334106, "step": 2377 }, { "epoch": 0.2007534586283676, "grad_norm": 0.154296875, "learning_rate": 4.667608645675445e-05, "loss": 1.5488985776901245, "step": 2378 }, { "epoch": 0.20083787976319872, "grad_norm": 0.1455078125, "learning_rate": 4.667284236592275e-05, "loss": 1.6196141242980957, "step": 2379 }, { "epoch": 0.20092230089802982, "grad_norm": 0.158203125, "learning_rate": 4.666959680562025e-05, "loss": 1.5689829587936401, "step": 2380 }, { "epoch": 0.20100672203286093, "grad_norm": 0.1494140625, "learning_rate": 4.6666349776067e-05, "loss": 1.5823867321014404, "step": 2381 }, { "epoch": 0.20109114316769203, "grad_norm": 0.1494140625, "learning_rate": 4.666310127748315e-05, "loss": 1.5926969051361084, "step": 2382 }, { "epoch": 0.20117556430252315, "grad_norm": 0.1591796875, "learning_rate": 4.6659851310088966e-05, "loss": 1.5258965492248535, "step": 2383 }, { "epoch": 0.20125998543735424, "grad_norm": 0.1357421875, "learning_rate": 4.66565998741048e-05, "loss": 1.4955838918685913, "step": 2384 }, { "epoch": 0.20134440657218536, "grad_norm": 0.150390625, "learning_rate": 4.6653346969751096e-05, "loss": 1.6493384838104248, "step": 2385 }, { "epoch": 0.20142882770701645, "grad_norm": 0.15625, "learning_rate": 4.665009259724843e-05, "loss": 1.5105443000793457, "step": 2386 }, { "epoch": 0.20151324884184757, "grad_norm": 0.1396484375, "learning_rate": 4.664683675681745e-05, "loss": 1.4882714748382568, "step": 2387 }, { "epoch": 0.20159766997667866, "grad_norm": 0.1552734375, "learning_rate": 4.66435794486789e-05, "loss": 1.5483304262161255, "step": 2388 }, { "epoch": 0.20168209111150975, "grad_norm": 0.1513671875, "learning_rate": 4.6640320673053636e-05, "loss": 1.5251953601837158, "step": 2389 }, { "epoch": 0.20176651224634087, "grad_norm": 0.1796875, "learning_rate": 4.663706043016262e-05, "loss": 1.6153874397277832, "step": 2390 }, { "epoch": 0.20185093338117197, "grad_norm": 0.1376953125, "learning_rate": 4.663379872022689e-05, "loss": 1.545154094696045, "step": 2391 }, { "epoch": 0.20193535451600308, "grad_norm": 0.1630859375, "learning_rate": 4.663053554346761e-05, "loss": 1.5615904331207275, "step": 2392 }, { "epoch": 0.20201977565083418, "grad_norm": 0.1572265625, "learning_rate": 4.662727090010603e-05, "loss": 1.5840808153152466, "step": 2393 }, { "epoch": 0.2021041967856653, "grad_norm": 0.220703125, "learning_rate": 4.662400479036349e-05, "loss": 1.587990164756775, "step": 2394 }, { "epoch": 0.2021886179204964, "grad_norm": 0.14453125, "learning_rate": 4.6620737214461465e-05, "loss": 1.497719407081604, "step": 2395 }, { "epoch": 0.2022730390553275, "grad_norm": 0.1640625, "learning_rate": 4.661746817262147e-05, "loss": 1.4477537870407104, "step": 2396 }, { "epoch": 0.2023574601901586, "grad_norm": 0.1435546875, "learning_rate": 4.6614197665065174e-05, "loss": 1.5301306247711182, "step": 2397 }, { "epoch": 0.20244188132498972, "grad_norm": 0.154296875, "learning_rate": 4.661092569201433e-05, "loss": 1.5330109596252441, "step": 2398 }, { "epoch": 0.2025263024598208, "grad_norm": 0.1455078125, "learning_rate": 4.660765225369078e-05, "loss": 1.514633059501648, "step": 2399 }, { "epoch": 0.20261072359465193, "grad_norm": 0.1416015625, "learning_rate": 4.6604377350316457e-05, "loss": 1.5154671669006348, "step": 2400 }, { "epoch": 0.20269514472948302, "grad_norm": 0.1494140625, "learning_rate": 4.6601100982113435e-05, "loss": 1.5606523752212524, "step": 2401 }, { "epoch": 0.20277956586431414, "grad_norm": 0.1416015625, "learning_rate": 4.6597823149303834e-05, "loss": 1.60616934299469, "step": 2402 }, { "epoch": 0.20286398699914523, "grad_norm": 0.142578125, "learning_rate": 4.659454385210991e-05, "loss": 1.529294729232788, "step": 2403 }, { "epoch": 0.20294840813397635, "grad_norm": 0.146484375, "learning_rate": 4.6591263090754e-05, "loss": 1.6676667928695679, "step": 2404 }, { "epoch": 0.20303282926880745, "grad_norm": 0.1416015625, "learning_rate": 4.658798086545857e-05, "loss": 1.6269164085388184, "step": 2405 }, { "epoch": 0.20311725040363854, "grad_norm": 0.16015625, "learning_rate": 4.658469717644614e-05, "loss": 1.4723539352416992, "step": 2406 }, { "epoch": 0.20320167153846966, "grad_norm": 0.150390625, "learning_rate": 4.6581412023939354e-05, "loss": 1.5634241104125977, "step": 2407 }, { "epoch": 0.20328609267330075, "grad_norm": 0.140625, "learning_rate": 4.6578125408160954e-05, "loss": 1.6260864734649658, "step": 2408 }, { "epoch": 0.20337051380813187, "grad_norm": 0.166015625, "learning_rate": 4.657483732933379e-05, "loss": 1.5136207342147827, "step": 2409 }, { "epoch": 0.20345493494296296, "grad_norm": 0.1796875, "learning_rate": 4.65715477876808e-05, "loss": 1.5393438339233398, "step": 2410 }, { "epoch": 0.20353935607779408, "grad_norm": 0.1552734375, "learning_rate": 4.6568256783425014e-05, "loss": 1.5339250564575195, "step": 2411 }, { "epoch": 0.20362377721262517, "grad_norm": 0.1533203125, "learning_rate": 4.656496431678958e-05, "loss": 1.5607249736785889, "step": 2412 }, { "epoch": 0.2037081983474563, "grad_norm": 0.146484375, "learning_rate": 4.656167038799772e-05, "loss": 1.5630409717559814, "step": 2413 }, { "epoch": 0.20379261948228738, "grad_norm": 0.1337890625, "learning_rate": 4.6558374997272794e-05, "loss": 1.552112340927124, "step": 2414 }, { "epoch": 0.2038770406171185, "grad_norm": 0.142578125, "learning_rate": 4.655507814483821e-05, "loss": 1.5449336767196655, "step": 2415 }, { "epoch": 0.2039614617519496, "grad_norm": 0.1396484375, "learning_rate": 4.655177983091752e-05, "loss": 1.4949699640274048, "step": 2416 }, { "epoch": 0.20404588288678072, "grad_norm": 0.1396484375, "learning_rate": 4.6548480055734357e-05, "loss": 1.5564067363739014, "step": 2417 }, { "epoch": 0.2041303040216118, "grad_norm": 0.1455078125, "learning_rate": 4.654517881951245e-05, "loss": 1.6148481369018555, "step": 2418 }, { "epoch": 0.20421472515644293, "grad_norm": 0.154296875, "learning_rate": 4.6541876122475635e-05, "loss": 1.5973306894302368, "step": 2419 }, { "epoch": 0.20429914629127402, "grad_norm": 0.1435546875, "learning_rate": 4.653857196484783e-05, "loss": 1.4891414642333984, "step": 2420 }, { "epoch": 0.2043835674261051, "grad_norm": 0.1494140625, "learning_rate": 4.653526634685308e-05, "loss": 1.560670018196106, "step": 2421 }, { "epoch": 0.20446798856093623, "grad_norm": 0.138671875, "learning_rate": 4.6531959268715506e-05, "loss": 1.481328010559082, "step": 2422 }, { "epoch": 0.20455240969576732, "grad_norm": 0.1455078125, "learning_rate": 4.652865073065934e-05, "loss": 1.5722436904907227, "step": 2423 }, { "epoch": 0.20463683083059844, "grad_norm": 0.140625, "learning_rate": 4.652534073290891e-05, "loss": 1.5141422748565674, "step": 2424 }, { "epoch": 0.20472125196542953, "grad_norm": 0.1572265625, "learning_rate": 4.652202927568863e-05, "loss": 1.620058536529541, "step": 2425 }, { "epoch": 0.20480567310026065, "grad_norm": 0.1474609375, "learning_rate": 4.651871635922304e-05, "loss": 1.5665521621704102, "step": 2426 }, { "epoch": 0.20489009423509175, "grad_norm": 0.146484375, "learning_rate": 4.651540198373675e-05, "loss": 1.5209684371948242, "step": 2427 }, { "epoch": 0.20497451536992287, "grad_norm": 0.1416015625, "learning_rate": 4.6512086149454484e-05, "loss": 1.5831851959228516, "step": 2428 }, { "epoch": 0.20505893650475396, "grad_norm": 0.1318359375, "learning_rate": 4.650876885660108e-05, "loss": 1.4864721298217773, "step": 2429 }, { "epoch": 0.20514335763958508, "grad_norm": 0.154296875, "learning_rate": 4.6505450105401446e-05, "loss": 1.4975343942642212, "step": 2430 }, { "epoch": 0.20522777877441617, "grad_norm": 0.1513671875, "learning_rate": 4.6502129896080596e-05, "loss": 1.614087462425232, "step": 2431 }, { "epoch": 0.2053121999092473, "grad_norm": 0.14453125, "learning_rate": 4.649880822886366e-05, "loss": 1.614099383354187, "step": 2432 }, { "epoch": 0.20539662104407838, "grad_norm": 0.154296875, "learning_rate": 4.649548510397585e-05, "loss": 1.599697232246399, "step": 2433 }, { "epoch": 0.2054810421789095, "grad_norm": 0.142578125, "learning_rate": 4.649216052164248e-05, "loss": 1.4934567213058472, "step": 2434 }, { "epoch": 0.2055654633137406, "grad_norm": 0.150390625, "learning_rate": 4.6488834482088965e-05, "loss": 1.6097221374511719, "step": 2435 }, { "epoch": 0.2056498844485717, "grad_norm": 0.1396484375, "learning_rate": 4.648550698554083e-05, "loss": 1.5600430965423584, "step": 2436 }, { "epoch": 0.2057343055834028, "grad_norm": 0.16796875, "learning_rate": 4.648217803222366e-05, "loss": 1.5785653591156006, "step": 2437 }, { "epoch": 0.2058187267182339, "grad_norm": 0.1455078125, "learning_rate": 4.647884762236319e-05, "loss": 1.4719270467758179, "step": 2438 }, { "epoch": 0.20590314785306502, "grad_norm": 0.13671875, "learning_rate": 4.647551575618523e-05, "loss": 1.504563570022583, "step": 2439 }, { "epoch": 0.2059875689878961, "grad_norm": 0.1513671875, "learning_rate": 4.6472182433915676e-05, "loss": 1.5397858619689941, "step": 2440 }, { "epoch": 0.20607199012272723, "grad_norm": 0.1455078125, "learning_rate": 4.646884765578054e-05, "loss": 1.5522780418395996, "step": 2441 }, { "epoch": 0.20615641125755832, "grad_norm": 0.1484375, "learning_rate": 4.6465511422005924e-05, "loss": 1.557563066482544, "step": 2442 }, { "epoch": 0.20624083239238944, "grad_norm": 0.1494140625, "learning_rate": 4.6462173732818045e-05, "loss": 1.5788042545318604, "step": 2443 }, { "epoch": 0.20632525352722053, "grad_norm": 0.13671875, "learning_rate": 4.64588345884432e-05, "loss": 1.5177439451217651, "step": 2444 }, { "epoch": 0.20640967466205165, "grad_norm": 0.138671875, "learning_rate": 4.645549398910778e-05, "loss": 1.5950896739959717, "step": 2445 }, { "epoch": 0.20649409579688274, "grad_norm": 0.126953125, "learning_rate": 4.64521519350383e-05, "loss": 1.4904080629348755, "step": 2446 }, { "epoch": 0.20657851693171386, "grad_norm": 0.1474609375, "learning_rate": 4.644880842646136e-05, "loss": 1.6726230382919312, "step": 2447 }, { "epoch": 0.20666293806654495, "grad_norm": 0.1630859375, "learning_rate": 4.644546346360364e-05, "loss": 1.5799078941345215, "step": 2448 }, { "epoch": 0.20674735920137607, "grad_norm": 0.162109375, "learning_rate": 4.6442117046691966e-05, "loss": 1.5205641984939575, "step": 2449 }, { "epoch": 0.20683178033620717, "grad_norm": 0.166015625, "learning_rate": 4.643876917595321e-05, "loss": 1.5259591341018677, "step": 2450 }, { "epoch": 0.20691620147103829, "grad_norm": 0.142578125, "learning_rate": 4.6435419851614363e-05, "loss": 1.546921730041504, "step": 2451 }, { "epoch": 0.20700062260586938, "grad_norm": 0.166015625, "learning_rate": 4.6432069073902534e-05, "loss": 1.5921525955200195, "step": 2452 }, { "epoch": 0.2070850437407005, "grad_norm": 0.1396484375, "learning_rate": 4.642871684304491e-05, "loss": 1.4425004720687866, "step": 2453 }, { "epoch": 0.2071694648755316, "grad_norm": 0.134765625, "learning_rate": 4.642536315926877e-05, "loss": 1.5799096822738647, "step": 2454 }, { "epoch": 0.20725388601036268, "grad_norm": 0.15234375, "learning_rate": 4.64220080228015e-05, "loss": 1.4814854860305786, "step": 2455 }, { "epoch": 0.2073383071451938, "grad_norm": 0.140625, "learning_rate": 4.641865143387061e-05, "loss": 1.6170902252197266, "step": 2456 }, { "epoch": 0.2074227282800249, "grad_norm": 0.1435546875, "learning_rate": 4.6415293392703655e-05, "loss": 1.569427490234375, "step": 2457 }, { "epoch": 0.207507149414856, "grad_norm": 0.16015625, "learning_rate": 4.6411933899528335e-05, "loss": 1.5759319067001343, "step": 2458 }, { "epoch": 0.2075915705496871, "grad_norm": 0.1416015625, "learning_rate": 4.640857295457244e-05, "loss": 1.556318998336792, "step": 2459 }, { "epoch": 0.20767599168451822, "grad_norm": 0.1337890625, "learning_rate": 4.640521055806383e-05, "loss": 1.5122416019439697, "step": 2460 }, { "epoch": 0.20776041281934932, "grad_norm": 0.1474609375, "learning_rate": 4.64018467102305e-05, "loss": 1.5854129791259766, "step": 2461 }, { "epoch": 0.20784483395418044, "grad_norm": 0.146484375, "learning_rate": 4.639848141130051e-05, "loss": 1.598819375038147, "step": 2462 }, { "epoch": 0.20792925508901153, "grad_norm": 0.142578125, "learning_rate": 4.639511466150205e-05, "loss": 1.5122277736663818, "step": 2463 }, { "epoch": 0.20801367622384265, "grad_norm": 0.138671875, "learning_rate": 4.639174646106339e-05, "loss": 1.5423375368118286, "step": 2464 }, { "epoch": 0.20809809735867374, "grad_norm": 0.1376953125, "learning_rate": 4.6388376810212905e-05, "loss": 1.5974887609481812, "step": 2465 }, { "epoch": 0.20818251849350486, "grad_norm": 0.1376953125, "learning_rate": 4.638500570917905e-05, "loss": 1.53981614112854, "step": 2466 }, { "epoch": 0.20826693962833595, "grad_norm": 0.1435546875, "learning_rate": 4.6381633158190417e-05, "loss": 1.5189930200576782, "step": 2467 }, { "epoch": 0.20835136076316707, "grad_norm": 0.1416015625, "learning_rate": 4.637825915747565e-05, "loss": 1.5885143280029297, "step": 2468 }, { "epoch": 0.20843578189799816, "grad_norm": 0.14453125, "learning_rate": 4.6374883707263535e-05, "loss": 1.508703351020813, "step": 2469 }, { "epoch": 0.20852020303282928, "grad_norm": 0.15625, "learning_rate": 4.637150680778292e-05, "loss": 1.5723552703857422, "step": 2470 }, { "epoch": 0.20860462416766037, "grad_norm": 0.154296875, "learning_rate": 4.636812845926278e-05, "loss": 1.5467106103897095, "step": 2471 }, { "epoch": 0.20868904530249147, "grad_norm": 0.1728515625, "learning_rate": 4.6364748661932163e-05, "loss": 1.4353325366973877, "step": 2472 }, { "epoch": 0.20877346643732259, "grad_norm": 0.1494140625, "learning_rate": 4.636136741602023e-05, "loss": 1.542061686515808, "step": 2473 }, { "epoch": 0.20885788757215368, "grad_norm": 0.1591796875, "learning_rate": 4.635798472175624e-05, "loss": 1.5634695291519165, "step": 2474 }, { "epoch": 0.2089423087069848, "grad_norm": 0.1533203125, "learning_rate": 4.635460057936956e-05, "loss": 1.602311134338379, "step": 2475 }, { "epoch": 0.2090267298418159, "grad_norm": 0.1611328125, "learning_rate": 4.635121498908962e-05, "loss": 1.6194188594818115, "step": 2476 }, { "epoch": 0.209111150976647, "grad_norm": 0.150390625, "learning_rate": 4.6347827951145986e-05, "loss": 1.5387647151947021, "step": 2477 }, { "epoch": 0.2091955721114781, "grad_norm": 0.1484375, "learning_rate": 4.63444394657683e-05, "loss": 1.5990054607391357, "step": 2478 }, { "epoch": 0.20927999324630922, "grad_norm": 0.14453125, "learning_rate": 4.634104953318632e-05, "loss": 1.5396181344985962, "step": 2479 }, { "epoch": 0.2093644143811403, "grad_norm": 0.201171875, "learning_rate": 4.6337658153629876e-05, "loss": 1.5817742347717285, "step": 2480 }, { "epoch": 0.20944883551597143, "grad_norm": 0.1435546875, "learning_rate": 4.633426532732893e-05, "loss": 1.5447707176208496, "step": 2481 }, { "epoch": 0.20953325665080252, "grad_norm": 0.146484375, "learning_rate": 4.6330871054513503e-05, "loss": 1.5771139860153198, "step": 2482 }, { "epoch": 0.20961767778563364, "grad_norm": 0.140625, "learning_rate": 4.632747533541375e-05, "loss": 1.5345653295516968, "step": 2483 }, { "epoch": 0.20970209892046474, "grad_norm": 0.1416015625, "learning_rate": 4.632407817025991e-05, "loss": 1.5617320537567139, "step": 2484 }, { "epoch": 0.20978652005529586, "grad_norm": 0.154296875, "learning_rate": 4.632067955928231e-05, "loss": 1.5741745233535767, "step": 2485 }, { "epoch": 0.20987094119012695, "grad_norm": 0.1591796875, "learning_rate": 4.6317279502711385e-05, "loss": 1.5549976825714111, "step": 2486 }, { "epoch": 0.20995536232495807, "grad_norm": 0.1494140625, "learning_rate": 4.631387800077767e-05, "loss": 1.554688811302185, "step": 2487 }, { "epoch": 0.21003978345978916, "grad_norm": 0.158203125, "learning_rate": 4.63104750537118e-05, "loss": 1.560652256011963, "step": 2488 }, { "epoch": 0.21012420459462025, "grad_norm": 0.1572265625, "learning_rate": 4.630707066174449e-05, "loss": 1.5919337272644043, "step": 2489 }, { "epoch": 0.21020862572945137, "grad_norm": 0.146484375, "learning_rate": 4.630366482510658e-05, "loss": 1.5534707307815552, "step": 2490 }, { "epoch": 0.21029304686428246, "grad_norm": 0.140625, "learning_rate": 4.6300257544028984e-05, "loss": 1.5988248586654663, "step": 2491 }, { "epoch": 0.21037746799911358, "grad_norm": 0.1376953125, "learning_rate": 4.6296848818742736e-05, "loss": 1.5242270231246948, "step": 2492 }, { "epoch": 0.21046188913394467, "grad_norm": 0.1435546875, "learning_rate": 4.6293438649478935e-05, "loss": 1.4427239894866943, "step": 2493 }, { "epoch": 0.2105463102687758, "grad_norm": 0.1513671875, "learning_rate": 4.629002703646882e-05, "loss": 1.4675744771957397, "step": 2494 }, { "epoch": 0.21063073140360689, "grad_norm": 0.142578125, "learning_rate": 4.6286613979943686e-05, "loss": 1.589379906654358, "step": 2495 }, { "epoch": 0.210715152538438, "grad_norm": 0.142578125, "learning_rate": 4.628319948013497e-05, "loss": 1.6099706888198853, "step": 2496 }, { "epoch": 0.2107995736732691, "grad_norm": 0.1494140625, "learning_rate": 4.627978353727417e-05, "loss": 1.5869879722595215, "step": 2497 }, { "epoch": 0.21088399480810022, "grad_norm": 0.140625, "learning_rate": 4.627636615159289e-05, "loss": 1.5031189918518066, "step": 2498 }, { "epoch": 0.2109684159429313, "grad_norm": 0.140625, "learning_rate": 4.627294732332285e-05, "loss": 1.5228790044784546, "step": 2499 }, { "epoch": 0.21105283707776243, "grad_norm": 0.1337890625, "learning_rate": 4.626952705269584e-05, "loss": 1.527387022972107, "step": 2500 }, { "epoch": 0.21113725821259352, "grad_norm": 0.14453125, "learning_rate": 4.626610533994378e-05, "loss": 1.5449631214141846, "step": 2501 }, { "epoch": 0.21122167934742464, "grad_norm": 0.1337890625, "learning_rate": 4.626268218529865e-05, "loss": 1.5362398624420166, "step": 2502 }, { "epoch": 0.21130610048225573, "grad_norm": 0.1474609375, "learning_rate": 4.625925758899257e-05, "loss": 1.6201088428497314, "step": 2503 }, { "epoch": 0.21139052161708682, "grad_norm": 0.1533203125, "learning_rate": 4.625583155125771e-05, "loss": 1.4889813661575317, "step": 2504 }, { "epoch": 0.21147494275191794, "grad_norm": 0.1435546875, "learning_rate": 4.62524040723264e-05, "loss": 1.5344892740249634, "step": 2505 }, { "epoch": 0.21155936388674904, "grad_norm": 0.1337890625, "learning_rate": 4.624897515243099e-05, "loss": 1.4947420358657837, "step": 2506 }, { "epoch": 0.21164378502158016, "grad_norm": 0.1416015625, "learning_rate": 4.6245544791804e-05, "loss": 1.5634745359420776, "step": 2507 }, { "epoch": 0.21172820615641125, "grad_norm": 0.13671875, "learning_rate": 4.6242112990678e-05, "loss": 1.5353899002075195, "step": 2508 }, { "epoch": 0.21181262729124237, "grad_norm": 0.14453125, "learning_rate": 4.623867974928569e-05, "loss": 1.644744873046875, "step": 2509 }, { "epoch": 0.21189704842607346, "grad_norm": 0.13671875, "learning_rate": 4.6235245067859825e-05, "loss": 1.5835380554199219, "step": 2510 }, { "epoch": 0.21198146956090458, "grad_norm": 0.14453125, "learning_rate": 4.623180894663332e-05, "loss": 1.5394878387451172, "step": 2511 }, { "epoch": 0.21206589069573567, "grad_norm": 0.14453125, "learning_rate": 4.622837138583912e-05, "loss": 1.4619042873382568, "step": 2512 }, { "epoch": 0.2121503118305668, "grad_norm": 0.140625, "learning_rate": 4.6224932385710316e-05, "loss": 1.5624232292175293, "step": 2513 }, { "epoch": 0.21223473296539788, "grad_norm": 0.1328125, "learning_rate": 4.622149194648008e-05, "loss": 1.4960458278656006, "step": 2514 }, { "epoch": 0.212319154100229, "grad_norm": 0.1494140625, "learning_rate": 4.621805006838168e-05, "loss": 1.5616682767868042, "step": 2515 }, { "epoch": 0.2124035752350601, "grad_norm": 0.13671875, "learning_rate": 4.6214606751648485e-05, "loss": 1.532882571220398, "step": 2516 }, { "epoch": 0.2124879963698912, "grad_norm": 0.1435546875, "learning_rate": 4.621116199651396e-05, "loss": 1.5261077880859375, "step": 2517 }, { "epoch": 0.2125724175047223, "grad_norm": 0.142578125, "learning_rate": 4.620771580321167e-05, "loss": 1.5894930362701416, "step": 2518 }, { "epoch": 0.21265683863955342, "grad_norm": 0.1435546875, "learning_rate": 4.620426817197526e-05, "loss": 1.5903822183609009, "step": 2519 }, { "epoch": 0.21274125977438452, "grad_norm": 0.1572265625, "learning_rate": 4.6200819103038514e-05, "loss": 1.506720781326294, "step": 2520 }, { "epoch": 0.2128256809092156, "grad_norm": 0.1328125, "learning_rate": 4.619736859663527e-05, "loss": 1.519622564315796, "step": 2521 }, { "epoch": 0.21291010204404673, "grad_norm": 0.1357421875, "learning_rate": 4.6193916652999467e-05, "loss": 1.54031240940094, "step": 2522 }, { "epoch": 0.21299452317887782, "grad_norm": 0.1533203125, "learning_rate": 4.619046327236519e-05, "loss": 1.489634394645691, "step": 2523 }, { "epoch": 0.21307894431370894, "grad_norm": 0.14453125, "learning_rate": 4.618700845496656e-05, "loss": 1.5036062002182007, "step": 2524 }, { "epoch": 0.21316336544854003, "grad_norm": 0.1435546875, "learning_rate": 4.618355220103784e-05, "loss": 1.5148918628692627, "step": 2525 }, { "epoch": 0.21324778658337115, "grad_norm": 0.1396484375, "learning_rate": 4.618009451081335e-05, "loss": 1.5358237028121948, "step": 2526 }, { "epoch": 0.21333220771820224, "grad_norm": 0.1416015625, "learning_rate": 4.6176635384527544e-05, "loss": 1.5408978462219238, "step": 2527 }, { "epoch": 0.21341662885303336, "grad_norm": 0.142578125, "learning_rate": 4.617317482241496e-05, "loss": 1.5651355981826782, "step": 2528 }, { "epoch": 0.21350104998786446, "grad_norm": 0.138671875, "learning_rate": 4.6169712824710226e-05, "loss": 1.5830373764038086, "step": 2529 }, { "epoch": 0.21358547112269557, "grad_norm": 0.142578125, "learning_rate": 4.616624939164808e-05, "loss": 1.5768994092941284, "step": 2530 }, { "epoch": 0.21366989225752667, "grad_norm": 0.1357421875, "learning_rate": 4.616278452346335e-05, "loss": 1.5550382137298584, "step": 2531 }, { "epoch": 0.2137543133923578, "grad_norm": 0.138671875, "learning_rate": 4.615931822039096e-05, "loss": 1.5412366390228271, "step": 2532 }, { "epoch": 0.21383873452718888, "grad_norm": 0.154296875, "learning_rate": 4.615585048266593e-05, "loss": 1.4869418144226074, "step": 2533 }, { "epoch": 0.21392315566202, "grad_norm": 0.1474609375, "learning_rate": 4.6152381310523387e-05, "loss": 1.5391485691070557, "step": 2534 }, { "epoch": 0.2140075767968511, "grad_norm": 0.1484375, "learning_rate": 4.614891070419855e-05, "loss": 1.64539635181427, "step": 2535 }, { "epoch": 0.2140919979316822, "grad_norm": 0.1328125, "learning_rate": 4.614543866392673e-05, "loss": 1.569258213043213, "step": 2536 }, { "epoch": 0.2141764190665133, "grad_norm": 0.140625, "learning_rate": 4.614196518994335e-05, "loss": 1.517230749130249, "step": 2537 }, { "epoch": 0.2142608402013444, "grad_norm": 0.1318359375, "learning_rate": 4.61384902824839e-05, "loss": 1.5687360763549805, "step": 2538 }, { "epoch": 0.2143452613361755, "grad_norm": 0.1357421875, "learning_rate": 4.6135013941784e-05, "loss": 1.482677936553955, "step": 2539 }, { "epoch": 0.2144296824710066, "grad_norm": 0.1396484375, "learning_rate": 4.613153616807935e-05, "loss": 1.520455241203308, "step": 2540 }, { "epoch": 0.21451410360583772, "grad_norm": 0.14453125, "learning_rate": 4.6128056961605764e-05, "loss": 1.4920873641967773, "step": 2541 }, { "epoch": 0.21459852474066882, "grad_norm": 0.134765625, "learning_rate": 4.612457632259912e-05, "loss": 1.5750365257263184, "step": 2542 }, { "epoch": 0.21468294587549994, "grad_norm": 0.1376953125, "learning_rate": 4.6121094251295436e-05, "loss": 1.5371496677398682, "step": 2543 }, { "epoch": 0.21476736701033103, "grad_norm": 0.14453125, "learning_rate": 4.61176107479308e-05, "loss": 1.5872434377670288, "step": 2544 }, { "epoch": 0.21485178814516215, "grad_norm": 0.1376953125, "learning_rate": 4.611412581274137e-05, "loss": 1.5827621221542358, "step": 2545 }, { "epoch": 0.21493620927999324, "grad_norm": 0.1474609375, "learning_rate": 4.6110639445963476e-05, "loss": 1.5618284940719604, "step": 2546 }, { "epoch": 0.21502063041482436, "grad_norm": 0.16015625, "learning_rate": 4.610715164783348e-05, "loss": 1.5683842897415161, "step": 2547 }, { "epoch": 0.21510505154965545, "grad_norm": 0.1416015625, "learning_rate": 4.6103662418587867e-05, "loss": 1.4405741691589355, "step": 2548 }, { "epoch": 0.21518947268448657, "grad_norm": 0.138671875, "learning_rate": 4.6100171758463215e-05, "loss": 1.530532717704773, "step": 2549 }, { "epoch": 0.21527389381931766, "grad_norm": 0.154296875, "learning_rate": 4.60966796676962e-05, "loss": 1.5332732200622559, "step": 2550 }, { "epoch": 0.21535831495414878, "grad_norm": 0.1416015625, "learning_rate": 4.609318614652359e-05, "loss": 1.4820117950439453, "step": 2551 }, { "epoch": 0.21544273608897987, "grad_norm": 0.1552734375, "learning_rate": 4.6089691195182265e-05, "loss": 1.5462971925735474, "step": 2552 }, { "epoch": 0.215527157223811, "grad_norm": 0.1533203125, "learning_rate": 4.6086194813909185e-05, "loss": 1.664762020111084, "step": 2553 }, { "epoch": 0.2156115783586421, "grad_norm": 0.14453125, "learning_rate": 4.608269700294141e-05, "loss": 1.6036925315856934, "step": 2554 }, { "epoch": 0.21569599949347318, "grad_norm": 0.134765625, "learning_rate": 4.6079197762516104e-05, "loss": 1.4787901639938354, "step": 2555 }, { "epoch": 0.2157804206283043, "grad_norm": 0.146484375, "learning_rate": 4.607569709287051e-05, "loss": 1.5138574838638306, "step": 2556 }, { "epoch": 0.2158648417631354, "grad_norm": 0.1376953125, "learning_rate": 4.6072194994242e-05, "loss": 1.5200246572494507, "step": 2557 }, { "epoch": 0.2159492628979665, "grad_norm": 0.1552734375, "learning_rate": 4.606869146686802e-05, "loss": 1.4948362112045288, "step": 2558 }, { "epoch": 0.2160336840327976, "grad_norm": 0.171875, "learning_rate": 4.6065186510986126e-05, "loss": 1.5835615396499634, "step": 2559 }, { "epoch": 0.21611810516762872, "grad_norm": 0.1689453125, "learning_rate": 4.606168012683394e-05, "loss": 1.614016056060791, "step": 2560 }, { "epoch": 0.2162025263024598, "grad_norm": 0.1669921875, "learning_rate": 4.6058172314649215e-05, "loss": 1.5693984031677246, "step": 2561 }, { "epoch": 0.21628694743729093, "grad_norm": 0.15625, "learning_rate": 4.605466307466979e-05, "loss": 1.5561596155166626, "step": 2562 }, { "epoch": 0.21637136857212202, "grad_norm": 0.2080078125, "learning_rate": 4.6051152407133616e-05, "loss": 1.509808897972107, "step": 2563 }, { "epoch": 0.21645578970695314, "grad_norm": 0.162109375, "learning_rate": 4.604764031227869e-05, "loss": 1.4973108768463135, "step": 2564 }, { "epoch": 0.21654021084178424, "grad_norm": 0.146484375, "learning_rate": 4.6044126790343166e-05, "loss": 1.519140601158142, "step": 2565 }, { "epoch": 0.21662463197661536, "grad_norm": 0.1396484375, "learning_rate": 4.604061184156526e-05, "loss": 1.555765986442566, "step": 2566 }, { "epoch": 0.21670905311144645, "grad_norm": 0.1640625, "learning_rate": 4.60370954661833e-05, "loss": 1.4770346879959106, "step": 2567 }, { "epoch": 0.21679347424627757, "grad_norm": 0.1669921875, "learning_rate": 4.60335776644357e-05, "loss": 1.5110646486282349, "step": 2568 }, { "epoch": 0.21687789538110866, "grad_norm": 0.1650390625, "learning_rate": 4.6030058436560974e-05, "loss": 1.44090735912323, "step": 2569 }, { "epoch": 0.21696231651593978, "grad_norm": 0.146484375, "learning_rate": 4.6026537782797735e-05, "loss": 1.5571222305297852, "step": 2570 }, { "epoch": 0.21704673765077087, "grad_norm": 0.1591796875, "learning_rate": 4.6023015703384695e-05, "loss": 1.5331401824951172, "step": 2571 }, { "epoch": 0.21713115878560196, "grad_norm": 0.16015625, "learning_rate": 4.601949219856066e-05, "loss": 1.6256548166275024, "step": 2572 }, { "epoch": 0.21721557992043308, "grad_norm": 0.1591796875, "learning_rate": 4.601596726856453e-05, "loss": 1.4478954076766968, "step": 2573 }, { "epoch": 0.21730000105526417, "grad_norm": 2.203125, "learning_rate": 4.601244091363529e-05, "loss": 1.5677152872085571, "step": 2574 }, { "epoch": 0.2173844221900953, "grad_norm": 0.138671875, "learning_rate": 4.6008913134012066e-05, "loss": 1.6217679977416992, "step": 2575 }, { "epoch": 0.2174688433249264, "grad_norm": 0.1455078125, "learning_rate": 4.6005383929934025e-05, "loss": 1.5631206035614014, "step": 2576 }, { "epoch": 0.2175532644597575, "grad_norm": 0.1455078125, "learning_rate": 4.600185330164047e-05, "loss": 1.5343576669692993, "step": 2577 }, { "epoch": 0.2176376855945886, "grad_norm": 0.1689453125, "learning_rate": 4.599832124937077e-05, "loss": 1.5592225790023804, "step": 2578 }, { "epoch": 0.21772210672941972, "grad_norm": 0.16015625, "learning_rate": 4.5994787773364425e-05, "loss": 1.58864164352417, "step": 2579 }, { "epoch": 0.2178065278642508, "grad_norm": 0.15234375, "learning_rate": 4.5991252873861e-05, "loss": 1.5630178451538086, "step": 2580 }, { "epoch": 0.21789094899908193, "grad_norm": 0.1640625, "learning_rate": 4.598771655110017e-05, "loss": 1.5068466663360596, "step": 2581 }, { "epoch": 0.21797537013391302, "grad_norm": 0.1669921875, "learning_rate": 4.598417880532171e-05, "loss": 1.5538742542266846, "step": 2582 }, { "epoch": 0.21805979126874414, "grad_norm": 0.158203125, "learning_rate": 4.598063963676549e-05, "loss": 1.5733683109283447, "step": 2583 }, { "epoch": 0.21814421240357523, "grad_norm": 0.1572265625, "learning_rate": 4.5977099045671476e-05, "loss": 1.5075790882110596, "step": 2584 }, { "epoch": 0.21822863353840635, "grad_norm": 0.1552734375, "learning_rate": 4.5973557032279726e-05, "loss": 1.6179583072662354, "step": 2585 }, { "epoch": 0.21831305467323744, "grad_norm": 0.1494140625, "learning_rate": 4.597001359683038e-05, "loss": 1.5965888500213623, "step": 2586 }, { "epoch": 0.21839747580806854, "grad_norm": 0.154296875, "learning_rate": 4.5966468739563725e-05, "loss": 1.5268125534057617, "step": 2587 }, { "epoch": 0.21848189694289966, "grad_norm": 0.1767578125, "learning_rate": 4.596292246072008e-05, "loss": 1.5661431550979614, "step": 2588 }, { "epoch": 0.21856631807773075, "grad_norm": 0.158203125, "learning_rate": 4.595937476053991e-05, "loss": 1.6003453731536865, "step": 2589 }, { "epoch": 0.21865073921256187, "grad_norm": 0.1533203125, "learning_rate": 4.595582563926375e-05, "loss": 1.5880389213562012, "step": 2590 }, { "epoch": 0.21873516034739296, "grad_norm": 0.142578125, "learning_rate": 4.5952275097132245e-05, "loss": 1.5396755933761597, "step": 2591 }, { "epoch": 0.21881958148222408, "grad_norm": 0.162109375, "learning_rate": 4.594872313438612e-05, "loss": 1.5930533409118652, "step": 2592 }, { "epoch": 0.21890400261705517, "grad_norm": 0.1572265625, "learning_rate": 4.594516975126621e-05, "loss": 1.5379685163497925, "step": 2593 }, { "epoch": 0.2189884237518863, "grad_norm": 0.162109375, "learning_rate": 4.5941614948013456e-05, "loss": 1.5246291160583496, "step": 2594 }, { "epoch": 0.21907284488671738, "grad_norm": 0.1455078125, "learning_rate": 4.593805872486886e-05, "loss": 1.532102346420288, "step": 2595 }, { "epoch": 0.2191572660215485, "grad_norm": 0.1591796875, "learning_rate": 4.5934501082073564e-05, "loss": 1.4192147254943848, "step": 2596 }, { "epoch": 0.2192416871563796, "grad_norm": 0.1513671875, "learning_rate": 4.593094201986877e-05, "loss": 1.5739811658859253, "step": 2597 }, { "epoch": 0.21932610829121071, "grad_norm": 0.16015625, "learning_rate": 4.5927381538495794e-05, "loss": 1.5553871393203735, "step": 2598 }, { "epoch": 0.2194105294260418, "grad_norm": 0.1455078125, "learning_rate": 4.592381963819605e-05, "loss": 1.635824203491211, "step": 2599 }, { "epoch": 0.21949495056087293, "grad_norm": 0.1484375, "learning_rate": 4.5920256319211035e-05, "loss": 1.5467655658721924, "step": 2600 }, { "epoch": 0.21957937169570402, "grad_norm": 0.150390625, "learning_rate": 4.591669158178235e-05, "loss": 1.5999982357025146, "step": 2601 }, { "epoch": 0.21966379283053514, "grad_norm": 0.150390625, "learning_rate": 4.5913125426151716e-05, "loss": 1.5192506313323975, "step": 2602 }, { "epoch": 0.21974821396536623, "grad_norm": 0.1494140625, "learning_rate": 4.59095578525609e-05, "loss": 1.574501872062683, "step": 2603 }, { "epoch": 0.21983263510019732, "grad_norm": 0.158203125, "learning_rate": 4.59059888612518e-05, "loss": 1.517639398574829, "step": 2604 }, { "epoch": 0.21991705623502844, "grad_norm": 0.1455078125, "learning_rate": 4.590241845246641e-05, "loss": 1.592824101448059, "step": 2605 }, { "epoch": 0.22000147736985953, "grad_norm": 0.1455078125, "learning_rate": 4.5898846626446805e-05, "loss": 1.5715789794921875, "step": 2606 }, { "epoch": 0.22008589850469065, "grad_norm": 0.1640625, "learning_rate": 4.5895273383435166e-05, "loss": 1.5337423086166382, "step": 2607 }, { "epoch": 0.22017031963952174, "grad_norm": 0.1474609375, "learning_rate": 4.589169872367376e-05, "loss": 1.570112943649292, "step": 2608 }, { "epoch": 0.22025474077435286, "grad_norm": 0.1416015625, "learning_rate": 4.5888122647404966e-05, "loss": 1.555795431137085, "step": 2609 }, { "epoch": 0.22033916190918396, "grad_norm": 0.1572265625, "learning_rate": 4.588454515487125e-05, "loss": 1.4824212789535522, "step": 2610 }, { "epoch": 0.22042358304401508, "grad_norm": 0.1513671875, "learning_rate": 4.588096624631517e-05, "loss": 1.570648431777954, "step": 2611 }, { "epoch": 0.22050800417884617, "grad_norm": 0.1494140625, "learning_rate": 4.5877385921979386e-05, "loss": 1.477197289466858, "step": 2612 }, { "epoch": 0.2205924253136773, "grad_norm": 0.1708984375, "learning_rate": 4.587380418210666e-05, "loss": 1.5237650871276855, "step": 2613 }, { "epoch": 0.22067684644850838, "grad_norm": 0.1533203125, "learning_rate": 4.587022102693983e-05, "loss": 1.5519777536392212, "step": 2614 }, { "epoch": 0.2207612675833395, "grad_norm": 0.1533203125, "learning_rate": 4.5866636456721857e-05, "loss": 1.5047094821929932, "step": 2615 }, { "epoch": 0.2208456887181706, "grad_norm": 0.1435546875, "learning_rate": 4.586305047169577e-05, "loss": 1.5610692501068115, "step": 2616 }, { "epoch": 0.2209301098530017, "grad_norm": 0.1396484375, "learning_rate": 4.585946307210471e-05, "loss": 1.4945124387741089, "step": 2617 }, { "epoch": 0.2210145309878328, "grad_norm": 0.1318359375, "learning_rate": 4.585587425819192e-05, "loss": 1.5294678211212158, "step": 2618 }, { "epoch": 0.22109895212266392, "grad_norm": 0.146484375, "learning_rate": 4.585228403020072e-05, "loss": 1.5749257802963257, "step": 2619 }, { "epoch": 0.22118337325749501, "grad_norm": 0.1513671875, "learning_rate": 4.5848692388374545e-05, "loss": 1.455872893333435, "step": 2620 }, { "epoch": 0.2212677943923261, "grad_norm": 0.1455078125, "learning_rate": 4.5845099332956905e-05, "loss": 1.4980067014694214, "step": 2621 }, { "epoch": 0.22135221552715723, "grad_norm": 0.16015625, "learning_rate": 4.584150486419143e-05, "loss": 1.5462788343429565, "step": 2622 }, { "epoch": 0.22143663666198832, "grad_norm": 0.1376953125, "learning_rate": 4.583790898232183e-05, "loss": 1.5732280015945435, "step": 2623 }, { "epoch": 0.22152105779681944, "grad_norm": 0.13671875, "learning_rate": 4.583431168759191e-05, "loss": 1.5169339179992676, "step": 2624 }, { "epoch": 0.22160547893165053, "grad_norm": 0.150390625, "learning_rate": 4.5830712980245576e-05, "loss": 1.5433387756347656, "step": 2625 }, { "epoch": 0.22168990006648165, "grad_norm": 0.1376953125, "learning_rate": 4.582711286052684e-05, "loss": 1.5492312908172607, "step": 2626 }, { "epoch": 0.22177432120131274, "grad_norm": 0.1396484375, "learning_rate": 4.582351132867978e-05, "loss": 1.5473778247833252, "step": 2627 }, { "epoch": 0.22185874233614386, "grad_norm": 0.13671875, "learning_rate": 4.5819908384948604e-05, "loss": 1.4989293813705444, "step": 2628 }, { "epoch": 0.22194316347097495, "grad_norm": 0.142578125, "learning_rate": 4.58163040295776e-05, "loss": 1.5102088451385498, "step": 2629 }, { "epoch": 0.22202758460580607, "grad_norm": 0.1533203125, "learning_rate": 4.5812698262811146e-05, "loss": 1.5869762897491455, "step": 2630 }, { "epoch": 0.22211200574063716, "grad_norm": 0.1513671875, "learning_rate": 4.580909108489372e-05, "loss": 1.6184906959533691, "step": 2631 }, { "epoch": 0.22219642687546828, "grad_norm": 0.162109375, "learning_rate": 4.58054824960699e-05, "loss": 1.5574557781219482, "step": 2632 }, { "epoch": 0.22228084801029938, "grad_norm": 0.142578125, "learning_rate": 4.580187249658435e-05, "loss": 1.6138005256652832, "step": 2633 }, { "epoch": 0.2223652691451305, "grad_norm": 0.1474609375, "learning_rate": 4.579826108668185e-05, "loss": 1.551316261291504, "step": 2634 }, { "epoch": 0.2224496902799616, "grad_norm": 0.1396484375, "learning_rate": 4.5794648266607254e-05, "loss": 1.5122675895690918, "step": 2635 }, { "epoch": 0.2225341114147927, "grad_norm": 0.1435546875, "learning_rate": 4.579103403660553e-05, "loss": 1.5617790222167969, "step": 2636 }, { "epoch": 0.2226185325496238, "grad_norm": 0.1494140625, "learning_rate": 4.578741839692171e-05, "loss": 1.6291545629501343, "step": 2637 }, { "epoch": 0.2227029536844549, "grad_norm": 0.142578125, "learning_rate": 4.578380134780097e-05, "loss": 1.5291410684585571, "step": 2638 }, { "epoch": 0.222787374819286, "grad_norm": 0.134765625, "learning_rate": 4.578018288948853e-05, "loss": 1.483228325843811, "step": 2639 }, { "epoch": 0.2228717959541171, "grad_norm": 0.146484375, "learning_rate": 4.5776563022229746e-05, "loss": 1.5667985677719116, "step": 2640 }, { "epoch": 0.22295621708894822, "grad_norm": 0.130859375, "learning_rate": 4.5772941746270046e-05, "loss": 1.4589160680770874, "step": 2641 }, { "epoch": 0.22304063822377931, "grad_norm": 0.1513671875, "learning_rate": 4.576931906185497e-05, "loss": 1.5241262912750244, "step": 2642 }, { "epoch": 0.22312505935861043, "grad_norm": 0.134765625, "learning_rate": 4.576569496923013e-05, "loss": 1.556489109992981, "step": 2643 }, { "epoch": 0.22320948049344153, "grad_norm": 0.1484375, "learning_rate": 4.576206946864127e-05, "loss": 1.5181094408035278, "step": 2644 }, { "epoch": 0.22329390162827265, "grad_norm": 0.1376953125, "learning_rate": 4.575844256033418e-05, "loss": 1.532322645187378, "step": 2645 }, { "epoch": 0.22337832276310374, "grad_norm": 0.1484375, "learning_rate": 4.5754814244554786e-05, "loss": 1.472534418106079, "step": 2646 }, { "epoch": 0.22346274389793486, "grad_norm": 0.15625, "learning_rate": 4.575118452154911e-05, "loss": 1.5613890886306763, "step": 2647 }, { "epoch": 0.22354716503276595, "grad_norm": 0.15234375, "learning_rate": 4.574755339156324e-05, "loss": 1.6187365055084229, "step": 2648 }, { "epoch": 0.22363158616759707, "grad_norm": 0.146484375, "learning_rate": 4.574392085484338e-05, "loss": 1.599360704421997, "step": 2649 }, { "epoch": 0.22371600730242816, "grad_norm": 0.138671875, "learning_rate": 4.5740286911635826e-05, "loss": 1.5310544967651367, "step": 2650 }, { "epoch": 0.22380042843725928, "grad_norm": 0.1376953125, "learning_rate": 4.5736651562186966e-05, "loss": 1.5272455215454102, "step": 2651 }, { "epoch": 0.22388484957209037, "grad_norm": 0.1376953125, "learning_rate": 4.573301480674328e-05, "loss": 1.5463523864746094, "step": 2652 }, { "epoch": 0.2239692707069215, "grad_norm": 0.1435546875, "learning_rate": 4.572937664555136e-05, "loss": 1.6056491136550903, "step": 2653 }, { "epoch": 0.22405369184175258, "grad_norm": 0.1513671875, "learning_rate": 4.5725737078857876e-05, "loss": 1.567875623703003, "step": 2654 }, { "epoch": 0.22413811297658368, "grad_norm": 0.1494140625, "learning_rate": 4.5722096106909595e-05, "loss": 1.4945659637451172, "step": 2655 }, { "epoch": 0.2242225341114148, "grad_norm": 0.1416015625, "learning_rate": 4.5718453729953394e-05, "loss": 1.4989802837371826, "step": 2656 }, { "epoch": 0.2243069552462459, "grad_norm": 0.1474609375, "learning_rate": 4.571480994823623e-05, "loss": 1.5132405757904053, "step": 2657 }, { "epoch": 0.224391376381077, "grad_norm": 0.1416015625, "learning_rate": 4.571116476200516e-05, "loss": 1.5584441423416138, "step": 2658 }, { "epoch": 0.2244757975159081, "grad_norm": 0.1318359375, "learning_rate": 4.570751817150734e-05, "loss": 1.5379695892333984, "step": 2659 }, { "epoch": 0.22456021865073922, "grad_norm": 0.142578125, "learning_rate": 4.570387017699e-05, "loss": 1.5989307165145874, "step": 2660 }, { "epoch": 0.2246446397855703, "grad_norm": 0.1376953125, "learning_rate": 4.5700220778700504e-05, "loss": 1.5421241521835327, "step": 2661 }, { "epoch": 0.22472906092040143, "grad_norm": 0.15234375, "learning_rate": 4.5696569976886284e-05, "loss": 1.6382865905761719, "step": 2662 }, { "epoch": 0.22481348205523252, "grad_norm": 0.134765625, "learning_rate": 4.569291777179487e-05, "loss": 1.5524755716323853, "step": 2663 }, { "epoch": 0.22489790319006364, "grad_norm": 0.158203125, "learning_rate": 4.568926416367389e-05, "loss": 1.5336220264434814, "step": 2664 }, { "epoch": 0.22498232432489473, "grad_norm": 0.1396484375, "learning_rate": 4.568560915277107e-05, "loss": 1.4749435186386108, "step": 2665 }, { "epoch": 0.22506674545972585, "grad_norm": 0.146484375, "learning_rate": 4.5681952739334235e-05, "loss": 1.5197625160217285, "step": 2666 }, { "epoch": 0.22515116659455695, "grad_norm": 0.1435546875, "learning_rate": 4.567829492361128e-05, "loss": 1.5047203302383423, "step": 2667 }, { "epoch": 0.22523558772938806, "grad_norm": 0.1455078125, "learning_rate": 4.5674635705850235e-05, "loss": 1.537000298500061, "step": 2668 }, { "epoch": 0.22532000886421916, "grad_norm": 0.1435546875, "learning_rate": 4.567097508629918e-05, "loss": 1.5411643981933594, "step": 2669 }, { "epoch": 0.22540442999905025, "grad_norm": 0.1474609375, "learning_rate": 4.566731306520634e-05, "loss": 1.5293954610824585, "step": 2670 }, { "epoch": 0.22548885113388137, "grad_norm": 0.1416015625, "learning_rate": 4.5663649642819994e-05, "loss": 1.6031074523925781, "step": 2671 }, { "epoch": 0.22557327226871246, "grad_norm": 0.1640625, "learning_rate": 4.565998481938853e-05, "loss": 1.5922755002975464, "step": 2672 }, { "epoch": 0.22565769340354358, "grad_norm": 0.1337890625, "learning_rate": 4.5656318595160444e-05, "loss": 1.5257439613342285, "step": 2673 }, { "epoch": 0.22574211453837467, "grad_norm": 0.13671875, "learning_rate": 4.565265097038429e-05, "loss": 1.5616118907928467, "step": 2674 }, { "epoch": 0.2258265356732058, "grad_norm": 0.146484375, "learning_rate": 4.564898194530878e-05, "loss": 1.5207557678222656, "step": 2675 }, { "epoch": 0.22591095680803688, "grad_norm": 0.166015625, "learning_rate": 4.564531152018264e-05, "loss": 1.630458116531372, "step": 2676 }, { "epoch": 0.225995377942868, "grad_norm": 0.1435546875, "learning_rate": 4.564163969525477e-05, "loss": 1.5150208473205566, "step": 2677 }, { "epoch": 0.2260797990776991, "grad_norm": 0.134765625, "learning_rate": 4.5637966470774095e-05, "loss": 1.540768027305603, "step": 2678 }, { "epoch": 0.22616422021253021, "grad_norm": 0.1396484375, "learning_rate": 4.5634291846989694e-05, "loss": 1.5968044996261597, "step": 2679 }, { "epoch": 0.2262486413473613, "grad_norm": 0.140625, "learning_rate": 4.5630615824150716e-05, "loss": 1.4842356443405151, "step": 2680 }, { "epoch": 0.22633306248219243, "grad_norm": 0.146484375, "learning_rate": 4.562693840250639e-05, "loss": 1.5221506357192993, "step": 2681 }, { "epoch": 0.22641748361702352, "grad_norm": 0.142578125, "learning_rate": 4.5623259582306056e-05, "loss": 1.6265898942947388, "step": 2682 }, { "epoch": 0.22650190475185464, "grad_norm": 0.146484375, "learning_rate": 4.5619579363799155e-05, "loss": 1.5927585363388062, "step": 2683 }, { "epoch": 0.22658632588668573, "grad_norm": 0.1591796875, "learning_rate": 4.561589774723521e-05, "loss": 1.54116952419281, "step": 2684 }, { "epoch": 0.22667074702151685, "grad_norm": 0.158203125, "learning_rate": 4.561221473286384e-05, "loss": 1.557170033454895, "step": 2685 }, { "epoch": 0.22675516815634794, "grad_norm": 0.1533203125, "learning_rate": 4.560853032093477e-05, "loss": 1.5015616416931152, "step": 2686 }, { "epoch": 0.22683958929117903, "grad_norm": 0.1416015625, "learning_rate": 4.560484451169781e-05, "loss": 1.5970721244812012, "step": 2687 }, { "epoch": 0.22692401042601015, "grad_norm": 0.1435546875, "learning_rate": 4.5601157305402854e-05, "loss": 1.443543553352356, "step": 2688 }, { "epoch": 0.22700843156084125, "grad_norm": 0.1650390625, "learning_rate": 4.5597468702299924e-05, "loss": 1.5977394580841064, "step": 2689 }, { "epoch": 0.22709285269567236, "grad_norm": 0.1337890625, "learning_rate": 4.55937787026391e-05, "loss": 1.4600883722305298, "step": 2690 }, { "epoch": 0.22717727383050346, "grad_norm": 0.1357421875, "learning_rate": 4.559008730667058e-05, "loss": 1.5290873050689697, "step": 2691 }, { "epoch": 0.22726169496533458, "grad_norm": 0.1513671875, "learning_rate": 4.5586394514644654e-05, "loss": 1.6085238456726074, "step": 2692 }, { "epoch": 0.22734611610016567, "grad_norm": 0.15234375, "learning_rate": 4.558270032681169e-05, "loss": 1.5391654968261719, "step": 2693 }, { "epoch": 0.2274305372349968, "grad_norm": 0.16796875, "learning_rate": 4.557900474342217e-05, "loss": 1.5266666412353516, "step": 2694 }, { "epoch": 0.22751495836982788, "grad_norm": 0.1416015625, "learning_rate": 4.557530776472667e-05, "loss": 1.5425282716751099, "step": 2695 }, { "epoch": 0.227599379504659, "grad_norm": 0.13671875, "learning_rate": 4.557160939097585e-05, "loss": 1.524420142173767, "step": 2696 }, { "epoch": 0.2276838006394901, "grad_norm": 0.146484375, "learning_rate": 4.556790962242045e-05, "loss": 1.5917925834655762, "step": 2697 }, { "epoch": 0.2277682217743212, "grad_norm": 0.1494140625, "learning_rate": 4.5564208459311356e-05, "loss": 1.5838687419891357, "step": 2698 }, { "epoch": 0.2278526429091523, "grad_norm": 0.1494140625, "learning_rate": 4.5560505901899485e-05, "loss": 1.575180172920227, "step": 2699 }, { "epoch": 0.22793706404398342, "grad_norm": 0.1474609375, "learning_rate": 4.55568019504359e-05, "loss": 1.5258417129516602, "step": 2700 }, { "epoch": 0.22802148517881451, "grad_norm": 0.140625, "learning_rate": 4.555309660517172e-05, "loss": 1.47622549533844, "step": 2701 }, { "epoch": 0.22810590631364563, "grad_norm": 0.1376953125, "learning_rate": 4.55493898663582e-05, "loss": 1.5005701780319214, "step": 2702 }, { "epoch": 0.22819032744847673, "grad_norm": 0.1328125, "learning_rate": 4.554568173424665e-05, "loss": 1.51368248462677, "step": 2703 }, { "epoch": 0.22827474858330782, "grad_norm": 0.1533203125, "learning_rate": 4.554197220908849e-05, "loss": 1.5786269903182983, "step": 2704 }, { "epoch": 0.22835916971813894, "grad_norm": 0.1357421875, "learning_rate": 4.5538261291135237e-05, "loss": 1.5348161458969116, "step": 2705 }, { "epoch": 0.22844359085297003, "grad_norm": 0.1357421875, "learning_rate": 4.5534548980638504e-05, "loss": 1.4792208671569824, "step": 2706 }, { "epoch": 0.22852801198780115, "grad_norm": 0.1357421875, "learning_rate": 4.553083527784999e-05, "loss": 1.5380760431289673, "step": 2707 }, { "epoch": 0.22861243312263224, "grad_norm": 0.1455078125, "learning_rate": 4.55271201830215e-05, "loss": 1.5648481845855713, "step": 2708 }, { "epoch": 0.22869685425746336, "grad_norm": 0.13671875, "learning_rate": 4.552340369640491e-05, "loss": 1.5203373432159424, "step": 2709 }, { "epoch": 0.22878127539229445, "grad_norm": 0.1435546875, "learning_rate": 4.551968581825222e-05, "loss": 1.505414605140686, "step": 2710 }, { "epoch": 0.22886569652712557, "grad_norm": 0.16015625, "learning_rate": 4.551596654881552e-05, "loss": 1.5532190799713135, "step": 2711 }, { "epoch": 0.22895011766195666, "grad_norm": 0.142578125, "learning_rate": 4.551224588834696e-05, "loss": 1.5686125755310059, "step": 2712 }, { "epoch": 0.22903453879678778, "grad_norm": 0.142578125, "learning_rate": 4.550852383709884e-05, "loss": 1.5687792301177979, "step": 2713 }, { "epoch": 0.22911895993161888, "grad_norm": 0.1435546875, "learning_rate": 4.5504800395323495e-05, "loss": 1.5596998929977417, "step": 2714 }, { "epoch": 0.22920338106645, "grad_norm": 0.1435546875, "learning_rate": 4.55010755632734e-05, "loss": 1.4886103868484497, "step": 2715 }, { "epoch": 0.2292878022012811, "grad_norm": 0.13671875, "learning_rate": 4.54973493412011e-05, "loss": 1.6163206100463867, "step": 2716 }, { "epoch": 0.2293722233361122, "grad_norm": 0.1552734375, "learning_rate": 4.5493621729359246e-05, "loss": 1.5546377897262573, "step": 2717 }, { "epoch": 0.2294566444709433, "grad_norm": 0.15234375, "learning_rate": 4.5489892728000584e-05, "loss": 1.538777470588684, "step": 2718 }, { "epoch": 0.22954106560577442, "grad_norm": 0.140625, "learning_rate": 4.548616233737794e-05, "loss": 1.5504001379013062, "step": 2719 }, { "epoch": 0.2296254867406055, "grad_norm": 0.138671875, "learning_rate": 4.548243055774425e-05, "loss": 1.5370904207229614, "step": 2720 }, { "epoch": 0.2297099078754366, "grad_norm": 0.1533203125, "learning_rate": 4.547869738935253e-05, "loss": 1.6116868257522583, "step": 2721 }, { "epoch": 0.22979432901026772, "grad_norm": 0.1337890625, "learning_rate": 4.547496283245591e-05, "loss": 1.4933233261108398, "step": 2722 }, { "epoch": 0.22987875014509881, "grad_norm": 0.140625, "learning_rate": 4.5471226887307586e-05, "loss": 1.6133463382720947, "step": 2723 }, { "epoch": 0.22996317127992993, "grad_norm": 0.138671875, "learning_rate": 4.546748955416088e-05, "loss": 1.5372508764266968, "step": 2724 }, { "epoch": 0.23004759241476103, "grad_norm": 0.140625, "learning_rate": 4.5463750833269184e-05, "loss": 1.5121521949768066, "step": 2725 }, { "epoch": 0.23013201354959215, "grad_norm": 0.142578125, "learning_rate": 4.546001072488599e-05, "loss": 1.518617033958435, "step": 2726 }, { "epoch": 0.23021643468442324, "grad_norm": 0.1328125, "learning_rate": 4.545626922926489e-05, "loss": 1.5161361694335938, "step": 2727 }, { "epoch": 0.23030085581925436, "grad_norm": 0.1533203125, "learning_rate": 4.545252634665956e-05, "loss": 1.4734803438186646, "step": 2728 }, { "epoch": 0.23038527695408545, "grad_norm": 0.1552734375, "learning_rate": 4.544878207732379e-05, "loss": 1.5951194763183594, "step": 2729 }, { "epoch": 0.23046969808891657, "grad_norm": 0.1474609375, "learning_rate": 4.5445036421511446e-05, "loss": 1.5392214059829712, "step": 2730 }, { "epoch": 0.23055411922374766, "grad_norm": 0.150390625, "learning_rate": 4.5441289379476484e-05, "loss": 1.6048164367675781, "step": 2731 }, { "epoch": 0.23063854035857878, "grad_norm": 0.1962890625, "learning_rate": 4.5437540951472966e-05, "loss": 1.5659548044204712, "step": 2732 }, { "epoch": 0.23072296149340987, "grad_norm": 0.1396484375, "learning_rate": 4.5433791137755056e-05, "loss": 1.5367846488952637, "step": 2733 }, { "epoch": 0.230807382628241, "grad_norm": 0.14453125, "learning_rate": 4.543003993857698e-05, "loss": 1.491944432258606, "step": 2734 }, { "epoch": 0.23089180376307208, "grad_norm": 0.1513671875, "learning_rate": 4.5426287354193095e-05, "loss": 1.5850335359573364, "step": 2735 }, { "epoch": 0.23097622489790318, "grad_norm": 0.1572265625, "learning_rate": 4.542253338485783e-05, "loss": 1.6093027591705322, "step": 2736 }, { "epoch": 0.2310606460327343, "grad_norm": 0.1455078125, "learning_rate": 4.54187780308257e-05, "loss": 1.496721863746643, "step": 2737 }, { "epoch": 0.2311450671675654, "grad_norm": 0.1552734375, "learning_rate": 4.5415021292351344e-05, "loss": 1.4760323762893677, "step": 2738 }, { "epoch": 0.2312294883023965, "grad_norm": 0.140625, "learning_rate": 4.541126316968948e-05, "loss": 1.4941680431365967, "step": 2739 }, { "epoch": 0.2313139094372276, "grad_norm": 0.138671875, "learning_rate": 4.540750366309491e-05, "loss": 1.5695915222167969, "step": 2740 }, { "epoch": 0.23139833057205872, "grad_norm": 0.1396484375, "learning_rate": 4.5403742772822536e-05, "loss": 1.4861128330230713, "step": 2741 }, { "epoch": 0.2314827517068898, "grad_norm": 0.1396484375, "learning_rate": 4.5399980499127355e-05, "loss": 1.4667850732803345, "step": 2742 }, { "epoch": 0.23156717284172093, "grad_norm": 0.1455078125, "learning_rate": 4.539621684226446e-05, "loss": 1.5258398056030273, "step": 2743 }, { "epoch": 0.23165159397655202, "grad_norm": 0.1376953125, "learning_rate": 4.5392451802489045e-05, "loss": 1.613565444946289, "step": 2744 }, { "epoch": 0.23173601511138314, "grad_norm": 0.142578125, "learning_rate": 4.538868538005637e-05, "loss": 1.5309559106826782, "step": 2745 }, { "epoch": 0.23182043624621423, "grad_norm": 0.142578125, "learning_rate": 4.538491757522183e-05, "loss": 1.5486176013946533, "step": 2746 }, { "epoch": 0.23190485738104535, "grad_norm": 0.142578125, "learning_rate": 4.5381148388240875e-05, "loss": 1.5818564891815186, "step": 2747 }, { "epoch": 0.23198927851587645, "grad_norm": 0.134765625, "learning_rate": 4.537737781936907e-05, "loss": 1.5284004211425781, "step": 2748 }, { "epoch": 0.23207369965070757, "grad_norm": 0.1455078125, "learning_rate": 4.5373605868862066e-05, "loss": 1.5902705192565918, "step": 2749 }, { "epoch": 0.23215812078553866, "grad_norm": 0.1533203125, "learning_rate": 4.536983253697561e-05, "loss": 1.5453637838363647, "step": 2750 }, { "epoch": 0.23224254192036978, "grad_norm": 0.1455078125, "learning_rate": 4.536605782396555e-05, "loss": 1.5574737787246704, "step": 2751 }, { "epoch": 0.23232696305520087, "grad_norm": 0.1396484375, "learning_rate": 4.536228173008782e-05, "loss": 1.617344856262207, "step": 2752 }, { "epoch": 0.23241138419003196, "grad_norm": 0.146484375, "learning_rate": 4.535850425559843e-05, "loss": 1.502151608467102, "step": 2753 }, { "epoch": 0.23249580532486308, "grad_norm": 0.140625, "learning_rate": 4.535472540075353e-05, "loss": 1.5825976133346558, "step": 2754 }, { "epoch": 0.23258022645969417, "grad_norm": 0.130859375, "learning_rate": 4.535094516580932e-05, "loss": 1.599045991897583, "step": 2755 }, { "epoch": 0.2326646475945253, "grad_norm": 0.138671875, "learning_rate": 4.53471635510221e-05, "loss": 1.5226430892944336, "step": 2756 }, { "epoch": 0.23274906872935638, "grad_norm": 0.1298828125, "learning_rate": 4.5343380556648297e-05, "loss": 1.574120044708252, "step": 2757 }, { "epoch": 0.2328334898641875, "grad_norm": 0.1318359375, "learning_rate": 4.533959618294438e-05, "loss": 1.4983936548233032, "step": 2758 }, { "epoch": 0.2329179109990186, "grad_norm": 0.158203125, "learning_rate": 4.533581043016696e-05, "loss": 1.5507164001464844, "step": 2759 }, { "epoch": 0.23300233213384972, "grad_norm": 0.140625, "learning_rate": 4.533202329857271e-05, "loss": 1.5472466945648193, "step": 2760 }, { "epoch": 0.2330867532686808, "grad_norm": 0.1337890625, "learning_rate": 4.5328234788418413e-05, "loss": 1.5234897136688232, "step": 2761 }, { "epoch": 0.23317117440351193, "grad_norm": 0.150390625, "learning_rate": 4.532444489996093e-05, "loss": 1.5202388763427734, "step": 2762 }, { "epoch": 0.23325559553834302, "grad_norm": 0.13671875, "learning_rate": 4.532065363345723e-05, "loss": 1.5938372611999512, "step": 2763 }, { "epoch": 0.23334001667317414, "grad_norm": 0.1416015625, "learning_rate": 4.531686098916437e-05, "loss": 1.52312433719635, "step": 2764 }, { "epoch": 0.23342443780800523, "grad_norm": 0.1357421875, "learning_rate": 4.531306696733949e-05, "loss": 1.502943754196167, "step": 2765 }, { "epoch": 0.23350885894283635, "grad_norm": 0.146484375, "learning_rate": 4.530927156823985e-05, "loss": 1.603611946105957, "step": 2766 }, { "epoch": 0.23359328007766744, "grad_norm": 0.138671875, "learning_rate": 4.5305474792122794e-05, "loss": 1.5624431371688843, "step": 2767 }, { "epoch": 0.23367770121249856, "grad_norm": 0.1279296875, "learning_rate": 4.5301676639245724e-05, "loss": 1.474685549736023, "step": 2768 }, { "epoch": 0.23376212234732965, "grad_norm": 0.1357421875, "learning_rate": 4.529787710986618e-05, "loss": 1.534228801727295, "step": 2769 }, { "epoch": 0.23384654348216075, "grad_norm": 0.126953125, "learning_rate": 4.529407620424178e-05, "loss": 1.4770699739456177, "step": 2770 }, { "epoch": 0.23393096461699187, "grad_norm": 0.1591796875, "learning_rate": 4.529027392263023e-05, "loss": 1.5395339727401733, "step": 2771 }, { "epoch": 0.23401538575182296, "grad_norm": 0.1357421875, "learning_rate": 4.528647026528935e-05, "loss": 1.4520504474639893, "step": 2772 }, { "epoch": 0.23409980688665408, "grad_norm": 0.1767578125, "learning_rate": 4.528266523247701e-05, "loss": 1.5049450397491455, "step": 2773 }, { "epoch": 0.23418422802148517, "grad_norm": 0.138671875, "learning_rate": 4.527885882445122e-05, "loss": 1.5022006034851074, "step": 2774 }, { "epoch": 0.2342686491563163, "grad_norm": 0.1455078125, "learning_rate": 4.527505104147006e-05, "loss": 1.5495988130569458, "step": 2775 }, { "epoch": 0.23435307029114738, "grad_norm": 0.1416015625, "learning_rate": 4.52712418837917e-05, "loss": 1.587151288986206, "step": 2776 }, { "epoch": 0.2344374914259785, "grad_norm": 0.1396484375, "learning_rate": 4.526743135167441e-05, "loss": 1.5895789861679077, "step": 2777 }, { "epoch": 0.2345219125608096, "grad_norm": 0.1318359375, "learning_rate": 4.526361944537657e-05, "loss": 1.5512733459472656, "step": 2778 }, { "epoch": 0.2346063336956407, "grad_norm": 0.15625, "learning_rate": 4.525980616515662e-05, "loss": 1.5177028179168701, "step": 2779 }, { "epoch": 0.2346907548304718, "grad_norm": 0.1396484375, "learning_rate": 4.52559915112731e-05, "loss": 1.5496708154678345, "step": 2780 }, { "epoch": 0.23477517596530292, "grad_norm": 0.1455078125, "learning_rate": 4.5252175483984684e-05, "loss": 1.5964192152023315, "step": 2781 }, { "epoch": 0.23485959710013402, "grad_norm": 0.1552734375, "learning_rate": 4.524835808355008e-05, "loss": 1.579667568206787, "step": 2782 }, { "epoch": 0.23494401823496514, "grad_norm": 0.1455078125, "learning_rate": 4.524453931022813e-05, "loss": 1.5378667116165161, "step": 2783 }, { "epoch": 0.23502843936979623, "grad_norm": 0.140625, "learning_rate": 4.524071916427776e-05, "loss": 1.4730250835418701, "step": 2784 }, { "epoch": 0.23511286050462735, "grad_norm": 0.138671875, "learning_rate": 4.523689764595797e-05, "loss": 1.5868921279907227, "step": 2785 }, { "epoch": 0.23519728163945844, "grad_norm": 0.1416015625, "learning_rate": 4.5233074755527884e-05, "loss": 1.5824310779571533, "step": 2786 }, { "epoch": 0.23528170277428953, "grad_norm": 0.1533203125, "learning_rate": 4.5229250493246686e-05, "loss": 1.5983896255493164, "step": 2787 }, { "epoch": 0.23536612390912065, "grad_norm": 1.8203125, "learning_rate": 4.522542485937369e-05, "loss": 1.6011332273483276, "step": 2788 }, { "epoch": 0.23545054504395174, "grad_norm": 0.1611328125, "learning_rate": 4.5221597854168264e-05, "loss": 1.632456660270691, "step": 2789 }, { "epoch": 0.23553496617878286, "grad_norm": 0.1474609375, "learning_rate": 4.5217769477889905e-05, "loss": 1.481457233428955, "step": 2790 }, { "epoch": 0.23561938731361395, "grad_norm": 0.142578125, "learning_rate": 4.521393973079817e-05, "loss": 1.5792434215545654, "step": 2791 }, { "epoch": 0.23570380844844507, "grad_norm": 0.14453125, "learning_rate": 4.521010861315275e-05, "loss": 1.563545823097229, "step": 2792 }, { "epoch": 0.23578822958327617, "grad_norm": 0.150390625, "learning_rate": 4.5206276125213366e-05, "loss": 1.6496338844299316, "step": 2793 }, { "epoch": 0.23587265071810729, "grad_norm": 0.1396484375, "learning_rate": 4.5202442267239906e-05, "loss": 1.5851142406463623, "step": 2794 }, { "epoch": 0.23595707185293838, "grad_norm": 0.1474609375, "learning_rate": 4.519860703949229e-05, "loss": 1.6360245943069458, "step": 2795 }, { "epoch": 0.2360414929877695, "grad_norm": 0.1552734375, "learning_rate": 4.519477044223057e-05, "loss": 1.6036860942840576, "step": 2796 }, { "epoch": 0.2361259141226006, "grad_norm": 0.140625, "learning_rate": 4.5190932475714874e-05, "loss": 1.509798288345337, "step": 2797 }, { "epoch": 0.2362103352574317, "grad_norm": 0.1416015625, "learning_rate": 4.518709314020542e-05, "loss": 1.478151559829712, "step": 2798 }, { "epoch": 0.2362947563922628, "grad_norm": 0.150390625, "learning_rate": 4.518325243596253e-05, "loss": 1.5519187450408936, "step": 2799 }, { "epoch": 0.23637917752709392, "grad_norm": 0.1484375, "learning_rate": 4.517941036324661e-05, "loss": 1.6106548309326172, "step": 2800 }, { "epoch": 0.236463598661925, "grad_norm": 0.1552734375, "learning_rate": 4.5175566922318166e-05, "loss": 1.5101830959320068, "step": 2801 }, { "epoch": 0.23654801979675613, "grad_norm": 0.1396484375, "learning_rate": 4.517172211343779e-05, "loss": 1.5453420877456665, "step": 2802 }, { "epoch": 0.23663244093158722, "grad_norm": 0.14453125, "learning_rate": 4.5167875936866155e-05, "loss": 1.48526132106781, "step": 2803 }, { "epoch": 0.23671686206641832, "grad_norm": 0.1494140625, "learning_rate": 4.5164028392864065e-05, "loss": 1.5563520193099976, "step": 2804 }, { "epoch": 0.23680128320124944, "grad_norm": 0.1474609375, "learning_rate": 4.516017948169238e-05, "loss": 1.6251996755599976, "step": 2805 }, { "epoch": 0.23688570433608053, "grad_norm": 0.1796875, "learning_rate": 4.515632920361207e-05, "loss": 1.579056978225708, "step": 2806 }, { "epoch": 0.23697012547091165, "grad_norm": 0.146484375, "learning_rate": 4.5152477558884186e-05, "loss": 1.600786805152893, "step": 2807 }, { "epoch": 0.23705454660574274, "grad_norm": 0.142578125, "learning_rate": 4.514862454776989e-05, "loss": 1.5893117189407349, "step": 2808 }, { "epoch": 0.23713896774057386, "grad_norm": 0.1484375, "learning_rate": 4.514477017053041e-05, "loss": 1.5894018411636353, "step": 2809 }, { "epoch": 0.23722338887540495, "grad_norm": 0.1474609375, "learning_rate": 4.5140914427427094e-05, "loss": 1.570258378982544, "step": 2810 }, { "epoch": 0.23730781001023607, "grad_norm": 0.1513671875, "learning_rate": 4.5137057318721375e-05, "loss": 1.5021098852157593, "step": 2811 }, { "epoch": 0.23739223114506716, "grad_norm": 0.1494140625, "learning_rate": 4.513319884467476e-05, "loss": 1.5531977415084839, "step": 2812 }, { "epoch": 0.23747665227989828, "grad_norm": 0.1376953125, "learning_rate": 4.512933900554887e-05, "loss": 1.5328201055526733, "step": 2813 }, { "epoch": 0.23756107341472937, "grad_norm": 0.1396484375, "learning_rate": 4.512547780160541e-05, "loss": 1.5569621324539185, "step": 2814 }, { "epoch": 0.2376454945495605, "grad_norm": 0.140625, "learning_rate": 4.512161523310618e-05, "loss": 1.512877106666565, "step": 2815 }, { "epoch": 0.23772991568439159, "grad_norm": 0.154296875, "learning_rate": 4.5117751300313075e-05, "loss": 1.51918363571167, "step": 2816 }, { "epoch": 0.2378143368192227, "grad_norm": 0.1435546875, "learning_rate": 4.511388600348807e-05, "loss": 1.5669543743133545, "step": 2817 }, { "epoch": 0.2378987579540538, "grad_norm": 0.1455078125, "learning_rate": 4.511001934289325e-05, "loss": 1.512717604637146, "step": 2818 }, { "epoch": 0.2379831790888849, "grad_norm": 0.150390625, "learning_rate": 4.5106151318790775e-05, "loss": 1.5140949487686157, "step": 2819 }, { "epoch": 0.238067600223716, "grad_norm": 0.1357421875, "learning_rate": 4.5102281931442916e-05, "loss": 1.625216007232666, "step": 2820 }, { "epoch": 0.2381520213585471, "grad_norm": 0.13671875, "learning_rate": 4.509841118111202e-05, "loss": 1.5435773134231567, "step": 2821 }, { "epoch": 0.23823644249337822, "grad_norm": 0.1376953125, "learning_rate": 4.509453906806054e-05, "loss": 1.5194810628890991, "step": 2822 }, { "epoch": 0.2383208636282093, "grad_norm": 0.1328125, "learning_rate": 4.509066559255101e-05, "loss": 1.6157913208007812, "step": 2823 }, { "epoch": 0.23840528476304043, "grad_norm": 0.130859375, "learning_rate": 4.508679075484605e-05, "loss": 1.4931309223175049, "step": 2824 }, { "epoch": 0.23848970589787152, "grad_norm": 0.1416015625, "learning_rate": 4.508291455520841e-05, "loss": 1.5108555555343628, "step": 2825 }, { "epoch": 0.23857412703270264, "grad_norm": 0.15625, "learning_rate": 4.507903699390088e-05, "loss": 1.614516258239746, "step": 2826 }, { "epoch": 0.23865854816753374, "grad_norm": 0.1376953125, "learning_rate": 4.507515807118639e-05, "loss": 1.512903094291687, "step": 2827 }, { "epoch": 0.23874296930236485, "grad_norm": 0.150390625, "learning_rate": 4.507127778732791e-05, "loss": 1.5034388303756714, "step": 2828 }, { "epoch": 0.23882739043719595, "grad_norm": 0.146484375, "learning_rate": 4.506739614258857e-05, "loss": 1.4952982664108276, "step": 2829 }, { "epoch": 0.23891181157202707, "grad_norm": 0.1455078125, "learning_rate": 4.506351313723153e-05, "loss": 1.5405538082122803, "step": 2830 }, { "epoch": 0.23899623270685816, "grad_norm": 0.146484375, "learning_rate": 4.505962877152007e-05, "loss": 1.6380301713943481, "step": 2831 }, { "epoch": 0.23908065384168928, "grad_norm": 0.1396484375, "learning_rate": 4.505574304571756e-05, "loss": 1.5905380249023438, "step": 2832 }, { "epoch": 0.23916507497652037, "grad_norm": 0.134765625, "learning_rate": 4.505185596008746e-05, "loss": 1.5374517440795898, "step": 2833 }, { "epoch": 0.2392494961113515, "grad_norm": 0.140625, "learning_rate": 4.504796751489334e-05, "loss": 1.5961549282073975, "step": 2834 }, { "epoch": 0.23933391724618258, "grad_norm": 0.134765625, "learning_rate": 4.504407771039883e-05, "loss": 1.5309557914733887, "step": 2835 }, { "epoch": 0.23941833838101367, "grad_norm": 0.14453125, "learning_rate": 4.504018654686767e-05, "loss": 1.5320147275924683, "step": 2836 }, { "epoch": 0.2395027595158448, "grad_norm": 0.146484375, "learning_rate": 4.503629402456368e-05, "loss": 1.514051914215088, "step": 2837 }, { "epoch": 0.23958718065067588, "grad_norm": 0.1591796875, "learning_rate": 4.5032400143750815e-05, "loss": 1.515143632888794, "step": 2838 }, { "epoch": 0.239671601785507, "grad_norm": 0.1435546875, "learning_rate": 4.502850490469306e-05, "loss": 1.6068429946899414, "step": 2839 }, { "epoch": 0.2397560229203381, "grad_norm": 0.142578125, "learning_rate": 4.502460830765453e-05, "loss": 1.5780634880065918, "step": 2840 }, { "epoch": 0.23984044405516922, "grad_norm": 0.1357421875, "learning_rate": 4.502071035289942e-05, "loss": 1.5058059692382812, "step": 2841 }, { "epoch": 0.2399248651900003, "grad_norm": 0.15234375, "learning_rate": 4.501681104069203e-05, "loss": 1.5051969289779663, "step": 2842 }, { "epoch": 0.24000928632483143, "grad_norm": 0.14453125, "learning_rate": 4.5012910371296735e-05, "loss": 1.4888826608657837, "step": 2843 }, { "epoch": 0.24009370745966252, "grad_norm": 0.1376953125, "learning_rate": 4.500900834497801e-05, "loss": 1.5343167781829834, "step": 2844 }, { "epoch": 0.24017812859449364, "grad_norm": 0.15234375, "learning_rate": 4.5005104962000436e-05, "loss": 1.6238172054290771, "step": 2845 }, { "epoch": 0.24026254972932473, "grad_norm": 0.1357421875, "learning_rate": 4.500120022262864e-05, "loss": 1.559699296951294, "step": 2846 }, { "epoch": 0.24034697086415585, "grad_norm": 0.1455078125, "learning_rate": 4.499729412712741e-05, "loss": 1.5645644664764404, "step": 2847 }, { "epoch": 0.24043139199898694, "grad_norm": 0.1337890625, "learning_rate": 4.499338667576156e-05, "loss": 1.5586308240890503, "step": 2848 }, { "epoch": 0.24051581313381806, "grad_norm": 0.1474609375, "learning_rate": 4.498947786879604e-05, "loss": 1.5244332551956177, "step": 2849 }, { "epoch": 0.24060023426864915, "grad_norm": 0.1396484375, "learning_rate": 4.498556770649587e-05, "loss": 1.5819425582885742, "step": 2850 }, { "epoch": 0.24068465540348027, "grad_norm": 0.1337890625, "learning_rate": 4.498165618912617e-05, "loss": 1.4979883432388306, "step": 2851 }, { "epoch": 0.24076907653831137, "grad_norm": 0.140625, "learning_rate": 4.497774331695215e-05, "loss": 1.5454455614089966, "step": 2852 }, { "epoch": 0.24085349767314246, "grad_norm": 0.1376953125, "learning_rate": 4.4973829090239115e-05, "loss": 1.584587812423706, "step": 2853 }, { "epoch": 0.24093791880797358, "grad_norm": 0.142578125, "learning_rate": 4.496991350925246e-05, "loss": 1.5789577960968018, "step": 2854 }, { "epoch": 0.24102233994280467, "grad_norm": 0.1435546875, "learning_rate": 4.496599657425766e-05, "loss": 1.4985443353652954, "step": 2855 }, { "epoch": 0.2411067610776358, "grad_norm": 0.140625, "learning_rate": 4.4962078285520306e-05, "loss": 1.5429413318634033, "step": 2856 }, { "epoch": 0.24119118221246688, "grad_norm": 0.138671875, "learning_rate": 4.495815864330607e-05, "loss": 1.5240068435668945, "step": 2857 }, { "epoch": 0.241275603347298, "grad_norm": 0.1416015625, "learning_rate": 4.4954237647880694e-05, "loss": 1.526476502418518, "step": 2858 }, { "epoch": 0.2413600244821291, "grad_norm": 0.1474609375, "learning_rate": 4.495031529951004e-05, "loss": 1.634973406791687, "step": 2859 }, { "epoch": 0.2414444456169602, "grad_norm": 0.1689453125, "learning_rate": 4.494639159846006e-05, "loss": 1.5143646001815796, "step": 2860 }, { "epoch": 0.2415288667517913, "grad_norm": 0.134765625, "learning_rate": 4.494246654499678e-05, "loss": 1.5650051832199097, "step": 2861 }, { "epoch": 0.24161328788662242, "grad_norm": 0.1455078125, "learning_rate": 4.493854013938634e-05, "loss": 1.6022329330444336, "step": 2862 }, { "epoch": 0.24169770902145352, "grad_norm": 0.1494140625, "learning_rate": 4.493461238189495e-05, "loss": 1.488468885421753, "step": 2863 }, { "epoch": 0.24178213015628464, "grad_norm": 0.130859375, "learning_rate": 4.493068327278892e-05, "loss": 1.4563285112380981, "step": 2864 }, { "epoch": 0.24186655129111573, "grad_norm": 0.1455078125, "learning_rate": 4.492675281233466e-05, "loss": 1.5459274053573608, "step": 2865 }, { "epoch": 0.24195097242594685, "grad_norm": 0.158203125, "learning_rate": 4.492282100079866e-05, "loss": 1.5874090194702148, "step": 2866 }, { "epoch": 0.24203539356077794, "grad_norm": 0.1513671875, "learning_rate": 4.491888783844751e-05, "loss": 1.5859181880950928, "step": 2867 }, { "epoch": 0.24211981469560906, "grad_norm": 0.1328125, "learning_rate": 4.491495332554788e-05, "loss": 1.5672787427902222, "step": 2868 }, { "epoch": 0.24220423583044015, "grad_norm": 0.1259765625, "learning_rate": 4.491101746236656e-05, "loss": 1.5120879411697388, "step": 2869 }, { "epoch": 0.24228865696527124, "grad_norm": 0.1455078125, "learning_rate": 4.490708024917039e-05, "loss": 1.6198405027389526, "step": 2870 }, { "epoch": 0.24237307810010236, "grad_norm": 0.138671875, "learning_rate": 4.4903141686226316e-05, "loss": 1.5248008966445923, "step": 2871 }, { "epoch": 0.24245749923493345, "grad_norm": 0.1337890625, "learning_rate": 4.48992017738014e-05, "loss": 1.4732407331466675, "step": 2872 }, { "epoch": 0.24254192036976457, "grad_norm": 0.13671875, "learning_rate": 4.489526051216278e-05, "loss": 1.4884049892425537, "step": 2873 }, { "epoch": 0.24262634150459567, "grad_norm": 0.1416015625, "learning_rate": 4.4891317901577676e-05, "loss": 1.5160598754882812, "step": 2874 }, { "epoch": 0.24271076263942679, "grad_norm": 0.1376953125, "learning_rate": 4.48873739423134e-05, "loss": 1.503913164138794, "step": 2875 }, { "epoch": 0.24279518377425788, "grad_norm": 0.138671875, "learning_rate": 4.488342863463737e-05, "loss": 1.5039985179901123, "step": 2876 }, { "epoch": 0.242879604909089, "grad_norm": 0.1298828125, "learning_rate": 4.487948197881708e-05, "loss": 1.5060417652130127, "step": 2877 }, { "epoch": 0.2429640260439201, "grad_norm": 0.13671875, "learning_rate": 4.4875533975120136e-05, "loss": 1.491256594657898, "step": 2878 }, { "epoch": 0.2430484471787512, "grad_norm": 0.1337890625, "learning_rate": 4.4871584623814214e-05, "loss": 1.5740751028060913, "step": 2879 }, { "epoch": 0.2431328683135823, "grad_norm": 0.1376953125, "learning_rate": 4.486763392516708e-05, "loss": 1.5124117136001587, "step": 2880 }, { "epoch": 0.24321728944841342, "grad_norm": 0.1318359375, "learning_rate": 4.486368187944662e-05, "loss": 1.5020575523376465, "step": 2881 }, { "epoch": 0.2433017105832445, "grad_norm": 0.1455078125, "learning_rate": 4.4859728486920776e-05, "loss": 1.564115285873413, "step": 2882 }, { "epoch": 0.24338613171807563, "grad_norm": 0.14453125, "learning_rate": 4.485577374785761e-05, "loss": 1.537955641746521, "step": 2883 }, { "epoch": 0.24347055285290672, "grad_norm": 0.1513671875, "learning_rate": 4.4851817662525254e-05, "loss": 1.5316166877746582, "step": 2884 }, { "epoch": 0.24355497398773784, "grad_norm": 0.1455078125, "learning_rate": 4.484786023119194e-05, "loss": 1.6396516561508179, "step": 2885 }, { "epoch": 0.24363939512256894, "grad_norm": 0.1455078125, "learning_rate": 4.4843901454126004e-05, "loss": 1.6227295398712158, "step": 2886 }, { "epoch": 0.24372381625740003, "grad_norm": 0.1572265625, "learning_rate": 4.483994133159584e-05, "loss": 1.5172810554504395, "step": 2887 }, { "epoch": 0.24380823739223115, "grad_norm": 0.1396484375, "learning_rate": 4.483597986386997e-05, "loss": 1.5224759578704834, "step": 2888 }, { "epoch": 0.24389265852706224, "grad_norm": 0.1474609375, "learning_rate": 4.4832017051216986e-05, "loss": 1.5017386674880981, "step": 2889 }, { "epoch": 0.24397707966189336, "grad_norm": 0.142578125, "learning_rate": 4.482805289390557e-05, "loss": 1.5017311573028564, "step": 2890 }, { "epoch": 0.24406150079672445, "grad_norm": 0.1435546875, "learning_rate": 4.482408739220452e-05, "loss": 1.5611481666564941, "step": 2891 }, { "epoch": 0.24414592193155557, "grad_norm": 0.1318359375, "learning_rate": 4.4820120546382685e-05, "loss": 1.516399621963501, "step": 2892 }, { "epoch": 0.24423034306638666, "grad_norm": 0.13671875, "learning_rate": 4.481615235670903e-05, "loss": 1.4889165163040161, "step": 2893 }, { "epoch": 0.24431476420121778, "grad_norm": 0.1474609375, "learning_rate": 4.481218282345262e-05, "loss": 1.5628968477249146, "step": 2894 }, { "epoch": 0.24439918533604887, "grad_norm": 0.140625, "learning_rate": 4.480821194688259e-05, "loss": 1.5792975425720215, "step": 2895 }, { "epoch": 0.24448360647088, "grad_norm": 0.13671875, "learning_rate": 4.480423972726818e-05, "loss": 1.526820182800293, "step": 2896 }, { "epoch": 0.24456802760571109, "grad_norm": 0.134765625, "learning_rate": 4.4800266164878716e-05, "loss": 1.5460140705108643, "step": 2897 }, { "epoch": 0.2446524487405422, "grad_norm": 0.142578125, "learning_rate": 4.4796291259983616e-05, "loss": 1.6225513219833374, "step": 2898 }, { "epoch": 0.2447368698753733, "grad_norm": 0.1376953125, "learning_rate": 4.479231501285238e-05, "loss": 1.5496857166290283, "step": 2899 }, { "epoch": 0.24482129101020442, "grad_norm": 0.146484375, "learning_rate": 4.4788337423754606e-05, "loss": 1.5542892217636108, "step": 2900 }, { "epoch": 0.2449057121450355, "grad_norm": 0.140625, "learning_rate": 4.478435849295999e-05, "loss": 1.5000548362731934, "step": 2901 }, { "epoch": 0.2449901332798666, "grad_norm": 0.1513671875, "learning_rate": 4.478037822073832e-05, "loss": 1.549593448638916, "step": 2902 }, { "epoch": 0.24507455441469772, "grad_norm": 0.1630859375, "learning_rate": 4.477639660735946e-05, "loss": 1.641503095626831, "step": 2903 }, { "epoch": 0.2451589755495288, "grad_norm": 0.1591796875, "learning_rate": 4.477241365309337e-05, "loss": 1.5738587379455566, "step": 2904 }, { "epoch": 0.24524339668435993, "grad_norm": 0.140625, "learning_rate": 4.476842935821011e-05, "loss": 1.5366235971450806, "step": 2905 }, { "epoch": 0.24532781781919102, "grad_norm": 0.1474609375, "learning_rate": 4.476444372297982e-05, "loss": 1.5112464427947998, "step": 2906 }, { "epoch": 0.24541223895402214, "grad_norm": 0.166015625, "learning_rate": 4.476045674767274e-05, "loss": 1.5197086334228516, "step": 2907 }, { "epoch": 0.24549666008885324, "grad_norm": 0.1728515625, "learning_rate": 4.47564684325592e-05, "loss": 1.523735761642456, "step": 2908 }, { "epoch": 0.24558108122368436, "grad_norm": 0.1630859375, "learning_rate": 4.47524787779096e-05, "loss": 1.4941048622131348, "step": 2909 }, { "epoch": 0.24566550235851545, "grad_norm": 0.142578125, "learning_rate": 4.474848778399446e-05, "loss": 1.4766111373901367, "step": 2910 }, { "epoch": 0.24574992349334657, "grad_norm": 0.142578125, "learning_rate": 4.474449545108439e-05, "loss": 1.5683767795562744, "step": 2911 }, { "epoch": 0.24583434462817766, "grad_norm": 0.1572265625, "learning_rate": 4.4740501779450064e-05, "loss": 1.6130894422531128, "step": 2912 }, { "epoch": 0.24591876576300878, "grad_norm": 0.142578125, "learning_rate": 4.473650676936227e-05, "loss": 1.4286149740219116, "step": 2913 }, { "epoch": 0.24600318689783987, "grad_norm": 0.2001953125, "learning_rate": 4.473251042109188e-05, "loss": 1.629665493965149, "step": 2914 }, { "epoch": 0.246087608032671, "grad_norm": 0.1357421875, "learning_rate": 4.4728512734909844e-05, "loss": 1.5257972478866577, "step": 2915 }, { "epoch": 0.24617202916750208, "grad_norm": 0.1416015625, "learning_rate": 4.4724513711087226e-05, "loss": 1.5987324714660645, "step": 2916 }, { "epoch": 0.2462564503023332, "grad_norm": 0.171875, "learning_rate": 4.4720513349895164e-05, "loss": 1.5906068086624146, "step": 2917 }, { "epoch": 0.2463408714371643, "grad_norm": 0.1669921875, "learning_rate": 4.4716511651604904e-05, "loss": 1.4611468315124512, "step": 2918 }, { "epoch": 0.24642529257199539, "grad_norm": 0.15234375, "learning_rate": 4.471250861648776e-05, "loss": 1.5439836978912354, "step": 2919 }, { "epoch": 0.2465097137068265, "grad_norm": 0.1669921875, "learning_rate": 4.470850424481514e-05, "loss": 1.5908854007720947, "step": 2920 }, { "epoch": 0.2465941348416576, "grad_norm": 0.14453125, "learning_rate": 4.470449853685856e-05, "loss": 1.6355448961257935, "step": 2921 }, { "epoch": 0.24667855597648872, "grad_norm": 0.158203125, "learning_rate": 4.470049149288962e-05, "loss": 1.5273919105529785, "step": 2922 }, { "epoch": 0.2467629771113198, "grad_norm": 0.146484375, "learning_rate": 4.469648311318001e-05, "loss": 1.4750471115112305, "step": 2923 }, { "epoch": 0.24684739824615093, "grad_norm": 0.1435546875, "learning_rate": 4.4692473398001496e-05, "loss": 1.515262484550476, "step": 2924 }, { "epoch": 0.24693181938098202, "grad_norm": 0.1455078125, "learning_rate": 4.468846234762595e-05, "loss": 1.6833069324493408, "step": 2925 }, { "epoch": 0.24701624051581314, "grad_norm": 0.146484375, "learning_rate": 4.468444996232533e-05, "loss": 1.515828251838684, "step": 2926 }, { "epoch": 0.24710066165064423, "grad_norm": 0.1357421875, "learning_rate": 4.4680436242371686e-05, "loss": 1.5366283655166626, "step": 2927 }, { "epoch": 0.24718508278547535, "grad_norm": 0.15234375, "learning_rate": 4.467642118803716e-05, "loss": 1.5829052925109863, "step": 2928 }, { "epoch": 0.24726950392030644, "grad_norm": 0.1455078125, "learning_rate": 4.467240479959399e-05, "loss": 1.5299217700958252, "step": 2929 }, { "epoch": 0.24735392505513756, "grad_norm": 0.1435546875, "learning_rate": 4.4668387077314476e-05, "loss": 1.4684587717056274, "step": 2930 }, { "epoch": 0.24743834618996866, "grad_norm": 0.1513671875, "learning_rate": 4.466436802147106e-05, "loss": 1.5547478199005127, "step": 2931 }, { "epoch": 0.24752276732479978, "grad_norm": 0.1416015625, "learning_rate": 4.466034763233621e-05, "loss": 1.5853313207626343, "step": 2932 }, { "epoch": 0.24760718845963087, "grad_norm": 0.1474609375, "learning_rate": 4.465632591018253e-05, "loss": 1.5776417255401611, "step": 2933 }, { "epoch": 0.247691609594462, "grad_norm": 0.1416015625, "learning_rate": 4.4652302855282714e-05, "loss": 1.5264577865600586, "step": 2934 }, { "epoch": 0.24777603072929308, "grad_norm": 0.13671875, "learning_rate": 4.464827846790952e-05, "loss": 1.5195339918136597, "step": 2935 }, { "epoch": 0.24786045186412417, "grad_norm": 0.1328125, "learning_rate": 4.4644252748335825e-05, "loss": 1.4665708541870117, "step": 2936 }, { "epoch": 0.2479448729989553, "grad_norm": 0.1396484375, "learning_rate": 4.464022569683457e-05, "loss": 1.531604290008545, "step": 2937 }, { "epoch": 0.24802929413378638, "grad_norm": 0.162109375, "learning_rate": 4.463619731367881e-05, "loss": 1.6316922903060913, "step": 2938 }, { "epoch": 0.2481137152686175, "grad_norm": 0.1513671875, "learning_rate": 4.463216759914167e-05, "loss": 1.5223711729049683, "step": 2939 }, { "epoch": 0.2481981364034486, "grad_norm": 0.169921875, "learning_rate": 4.4628136553496375e-05, "loss": 1.519074559211731, "step": 2940 }, { "epoch": 0.2482825575382797, "grad_norm": 0.1337890625, "learning_rate": 4.462410417701625e-05, "loss": 1.5195482969284058, "step": 2941 }, { "epoch": 0.2483669786731108, "grad_norm": 0.1416015625, "learning_rate": 4.462007046997468e-05, "loss": 1.538722276687622, "step": 2942 }, { "epoch": 0.24845139980794193, "grad_norm": 0.1416015625, "learning_rate": 4.4616035432645175e-05, "loss": 1.5838724374771118, "step": 2943 }, { "epoch": 0.24853582094277302, "grad_norm": 0.1533203125, "learning_rate": 4.461199906530132e-05, "loss": 1.5826259851455688, "step": 2944 }, { "epoch": 0.24862024207760414, "grad_norm": 0.1416015625, "learning_rate": 4.4607961368216786e-05, "loss": 1.5872690677642822, "step": 2945 }, { "epoch": 0.24870466321243523, "grad_norm": 0.14453125, "learning_rate": 4.460392234166534e-05, "loss": 1.5198367834091187, "step": 2946 }, { "epoch": 0.24878908434726635, "grad_norm": 0.1474609375, "learning_rate": 4.459988198592083e-05, "loss": 1.5165635347366333, "step": 2947 }, { "epoch": 0.24887350548209744, "grad_norm": 0.1455078125, "learning_rate": 4.459584030125722e-05, "loss": 1.5353940725326538, "step": 2948 }, { "epoch": 0.24895792661692856, "grad_norm": 0.138671875, "learning_rate": 4.459179728794853e-05, "loss": 1.4940720796585083, "step": 2949 }, { "epoch": 0.24904234775175965, "grad_norm": 0.1416015625, "learning_rate": 4.45877529462689e-05, "loss": 1.5162655115127563, "step": 2950 }, { "epoch": 0.24912676888659077, "grad_norm": 0.13671875, "learning_rate": 4.4583707276492524e-05, "loss": 1.625322937965393, "step": 2951 }, { "epoch": 0.24921119002142186, "grad_norm": 0.13671875, "learning_rate": 4.457966027889373e-05, "loss": 1.513053059577942, "step": 2952 }, { "epoch": 0.24929561115625296, "grad_norm": 0.1396484375, "learning_rate": 4.457561195374691e-05, "loss": 1.551842451095581, "step": 2953 }, { "epoch": 0.24938003229108407, "grad_norm": 0.146484375, "learning_rate": 4.457156230132654e-05, "loss": 1.637073040008545, "step": 2954 }, { "epoch": 0.24946445342591517, "grad_norm": 0.1513671875, "learning_rate": 4.4567511321907194e-05, "loss": 1.523378849029541, "step": 2955 }, { "epoch": 0.2495488745607463, "grad_norm": 0.146484375, "learning_rate": 4.4563459015763557e-05, "loss": 1.5065183639526367, "step": 2956 }, { "epoch": 0.24963329569557738, "grad_norm": 0.1328125, "learning_rate": 4.455940538317037e-05, "loss": 1.5092977285385132, "step": 2957 }, { "epoch": 0.2497177168304085, "grad_norm": 0.140625, "learning_rate": 4.4555350424402484e-05, "loss": 1.5073587894439697, "step": 2958 }, { "epoch": 0.2498021379652396, "grad_norm": 0.140625, "learning_rate": 4.455129413973485e-05, "loss": 1.5890779495239258, "step": 2959 }, { "epoch": 0.2498865591000707, "grad_norm": 0.140625, "learning_rate": 4.454723652944246e-05, "loss": 1.5354396104812622, "step": 2960 }, { "epoch": 0.2499709802349018, "grad_norm": 0.1416015625, "learning_rate": 4.454317759380045e-05, "loss": 1.4770289659500122, "step": 2961 }, { "epoch": 0.2500554013697329, "grad_norm": 0.150390625, "learning_rate": 4.4539117333084026e-05, "loss": 1.4769326448440552, "step": 2962 }, { "epoch": 0.250139822504564, "grad_norm": 0.1591796875, "learning_rate": 4.4535055747568474e-05, "loss": 1.676053524017334, "step": 2963 }, { "epoch": 0.2502242436393951, "grad_norm": 0.1484375, "learning_rate": 4.453099283752919e-05, "loss": 1.5827044248580933, "step": 2964 }, { "epoch": 0.25030866477422625, "grad_norm": 0.1630859375, "learning_rate": 4.452692860324166e-05, "loss": 1.5816679000854492, "step": 2965 }, { "epoch": 0.25039308590905734, "grad_norm": 0.1328125, "learning_rate": 4.452286304498142e-05, "loss": 1.5391442775726318, "step": 2966 }, { "epoch": 0.25047750704388844, "grad_norm": 0.138671875, "learning_rate": 4.4518796163024136e-05, "loss": 1.4886586666107178, "step": 2967 }, { "epoch": 0.25056192817871953, "grad_norm": 0.15234375, "learning_rate": 4.451472795764557e-05, "loss": 1.6258240938186646, "step": 2968 }, { "epoch": 0.2506463493135506, "grad_norm": 0.134765625, "learning_rate": 4.451065842912152e-05, "loss": 1.5332189798355103, "step": 2969 }, { "epoch": 0.25073077044838177, "grad_norm": 0.1416015625, "learning_rate": 4.4506587577727945e-05, "loss": 1.5341681241989136, "step": 2970 }, { "epoch": 0.25081519158321286, "grad_norm": 0.1416015625, "learning_rate": 4.450251540374084e-05, "loss": 1.5555287599563599, "step": 2971 }, { "epoch": 0.25089961271804395, "grad_norm": 0.1376953125, "learning_rate": 4.4498441907436316e-05, "loss": 1.5084978342056274, "step": 2972 }, { "epoch": 0.25098403385287504, "grad_norm": 0.1435546875, "learning_rate": 4.449436708909056e-05, "loss": 1.6080126762390137, "step": 2973 }, { "epoch": 0.2510684549877062, "grad_norm": 0.1474609375, "learning_rate": 4.4490290948979863e-05, "loss": 1.4909805059432983, "step": 2974 }, { "epoch": 0.2511528761225373, "grad_norm": 0.1552734375, "learning_rate": 4.4486213487380586e-05, "loss": 1.5613503456115723, "step": 2975 }, { "epoch": 0.2512372972573684, "grad_norm": 0.1552734375, "learning_rate": 4.4482134704569194e-05, "loss": 1.5399154424667358, "step": 2976 }, { "epoch": 0.25132171839219947, "grad_norm": 0.1396484375, "learning_rate": 4.4478054600822246e-05, "loss": 1.5480237007141113, "step": 2977 }, { "epoch": 0.2514061395270306, "grad_norm": 0.146484375, "learning_rate": 4.447397317641637e-05, "loss": 1.50503408908844, "step": 2978 }, { "epoch": 0.2514905606618617, "grad_norm": 0.140625, "learning_rate": 4.4469890431628303e-05, "loss": 1.5490577220916748, "step": 2979 }, { "epoch": 0.2515749817966928, "grad_norm": 0.1630859375, "learning_rate": 4.4465806366734875e-05, "loss": 1.5351877212524414, "step": 2980 }, { "epoch": 0.2516594029315239, "grad_norm": 0.142578125, "learning_rate": 4.4461720982012977e-05, "loss": 1.4781955480575562, "step": 2981 }, { "epoch": 0.25174382406635504, "grad_norm": 0.1396484375, "learning_rate": 4.445763427773962e-05, "loss": 1.4646040201187134, "step": 2982 }, { "epoch": 0.25182824520118613, "grad_norm": 0.1533203125, "learning_rate": 4.4453546254191894e-05, "loss": 1.5627672672271729, "step": 2983 }, { "epoch": 0.2519126663360172, "grad_norm": 0.1513671875, "learning_rate": 4.444945691164696e-05, "loss": 1.5410178899765015, "step": 2984 }, { "epoch": 0.2519970874708483, "grad_norm": 0.1435546875, "learning_rate": 4.4445366250382106e-05, "loss": 1.5204015970230103, "step": 2985 }, { "epoch": 0.2520815086056794, "grad_norm": 0.1533203125, "learning_rate": 4.444127427067468e-05, "loss": 1.5568822622299194, "step": 2986 }, { "epoch": 0.25216592974051055, "grad_norm": 0.1455078125, "learning_rate": 4.4437180972802114e-05, "loss": 1.5978312492370605, "step": 2987 }, { "epoch": 0.25225035087534164, "grad_norm": 0.1396484375, "learning_rate": 4.443308635704197e-05, "loss": 1.489148736000061, "step": 2988 }, { "epoch": 0.25233477201017274, "grad_norm": 0.1357421875, "learning_rate": 4.4428990423671864e-05, "loss": 1.5217565298080444, "step": 2989 }, { "epoch": 0.25241919314500383, "grad_norm": 0.142578125, "learning_rate": 4.44248931729695e-05, "loss": 1.6103894710540771, "step": 2990 }, { "epoch": 0.252503614279835, "grad_norm": 0.154296875, "learning_rate": 4.442079460521269e-05, "loss": 1.472346544265747, "step": 2991 }, { "epoch": 0.25258803541466607, "grad_norm": 0.1318359375, "learning_rate": 4.4416694720679316e-05, "loss": 1.496686577796936, "step": 2992 }, { "epoch": 0.25267245654949716, "grad_norm": 0.1337890625, "learning_rate": 4.441259351964738e-05, "loss": 1.522696852684021, "step": 2993 }, { "epoch": 0.25275687768432825, "grad_norm": 0.146484375, "learning_rate": 4.440849100239493e-05, "loss": 1.5091480016708374, "step": 2994 }, { "epoch": 0.2528412988191594, "grad_norm": 0.1396484375, "learning_rate": 4.4404387169200146e-05, "loss": 1.5010427236557007, "step": 2995 }, { "epoch": 0.2529257199539905, "grad_norm": 0.1298828125, "learning_rate": 4.4400282020341266e-05, "loss": 1.4915771484375, "step": 2996 }, { "epoch": 0.2530101410888216, "grad_norm": 0.1396484375, "learning_rate": 4.439617555609664e-05, "loss": 1.5182535648345947, "step": 2997 }, { "epoch": 0.2530945622236527, "grad_norm": 0.13671875, "learning_rate": 4.4392067776744684e-05, "loss": 1.5162526369094849, "step": 2998 }, { "epoch": 0.2531789833584838, "grad_norm": 0.140625, "learning_rate": 4.438795868256392e-05, "loss": 1.5845050811767578, "step": 2999 }, { "epoch": 0.2532634044933149, "grad_norm": 0.1474609375, "learning_rate": 4.438384827383295e-05, "loss": 1.5434470176696777, "step": 3000 }, { "epoch": 0.253347825628146, "grad_norm": 0.1513671875, "learning_rate": 4.437973655083049e-05, "loss": 1.5015153884887695, "step": 3001 }, { "epoch": 0.2534322467629771, "grad_norm": 0.1513671875, "learning_rate": 4.43756235138353e-05, "loss": 1.5814660787582397, "step": 3002 }, { "epoch": 0.2535166678978082, "grad_norm": 0.13671875, "learning_rate": 4.437150916312626e-05, "loss": 1.5530688762664795, "step": 3003 }, { "epoch": 0.25360108903263934, "grad_norm": 0.154296875, "learning_rate": 4.436739349898233e-05, "loss": 1.5285940170288086, "step": 3004 }, { "epoch": 0.25368551016747043, "grad_norm": 0.138671875, "learning_rate": 4.4363276521682575e-05, "loss": 1.5289404392242432, "step": 3005 }, { "epoch": 0.2537699313023015, "grad_norm": 0.140625, "learning_rate": 4.4359158231506124e-05, "loss": 1.4832535982131958, "step": 3006 }, { "epoch": 0.2538543524371326, "grad_norm": 0.146484375, "learning_rate": 4.435503862873222e-05, "loss": 1.637016773223877, "step": 3007 }, { "epoch": 0.25393877357196376, "grad_norm": 0.1416015625, "learning_rate": 4.4350917713640175e-05, "loss": 1.5513352155685425, "step": 3008 }, { "epoch": 0.25402319470679485, "grad_norm": 0.1435546875, "learning_rate": 4.4346795486509386e-05, "loss": 1.5900315046310425, "step": 3009 }, { "epoch": 0.25410761584162594, "grad_norm": 0.1484375, "learning_rate": 4.434267194761936e-05, "loss": 1.5140234231948853, "step": 3010 }, { "epoch": 0.25419203697645704, "grad_norm": 0.15234375, "learning_rate": 4.4338547097249693e-05, "loss": 1.5797555446624756, "step": 3011 }, { "epoch": 0.2542764581112882, "grad_norm": 0.1318359375, "learning_rate": 4.4334420935680036e-05, "loss": 1.4733966588974, "step": 3012 }, { "epoch": 0.2543608792461193, "grad_norm": 0.140625, "learning_rate": 4.4330293463190174e-05, "loss": 1.4732847213745117, "step": 3013 }, { "epoch": 0.25444530038095037, "grad_norm": 0.1396484375, "learning_rate": 4.432616468005995e-05, "loss": 1.5821950435638428, "step": 3014 }, { "epoch": 0.25452972151578146, "grad_norm": 0.1357421875, "learning_rate": 4.4322034586569306e-05, "loss": 1.5000652074813843, "step": 3015 }, { "epoch": 0.2546141426506126, "grad_norm": 0.1572265625, "learning_rate": 4.431790318299827e-05, "loss": 1.6521297693252563, "step": 3016 }, { "epoch": 0.2546985637854437, "grad_norm": 0.1533203125, "learning_rate": 4.431377046962697e-05, "loss": 1.4474904537200928, "step": 3017 }, { "epoch": 0.2547829849202748, "grad_norm": 0.142578125, "learning_rate": 4.4309636446735604e-05, "loss": 1.5276896953582764, "step": 3018 }, { "epoch": 0.2548674060551059, "grad_norm": 0.14453125, "learning_rate": 4.430550111460447e-05, "loss": 1.4939745664596558, "step": 3019 }, { "epoch": 0.254951827189937, "grad_norm": 0.1435546875, "learning_rate": 4.430136447351396e-05, "loss": 1.5703859329223633, "step": 3020 }, { "epoch": 0.2550362483247681, "grad_norm": 0.138671875, "learning_rate": 4.429722652374455e-05, "loss": 1.6005146503448486, "step": 3021 }, { "epoch": 0.2551206694595992, "grad_norm": 0.146484375, "learning_rate": 4.429308726557679e-05, "loss": 1.5583841800689697, "step": 3022 }, { "epoch": 0.2552050905944303, "grad_norm": 0.142578125, "learning_rate": 4.428894669929134e-05, "loss": 1.648425579071045, "step": 3023 }, { "epoch": 0.2552895117292614, "grad_norm": 0.1484375, "learning_rate": 4.4284804825168944e-05, "loss": 1.5352987051010132, "step": 3024 }, { "epoch": 0.25537393286409255, "grad_norm": 0.140625, "learning_rate": 4.428066164349042e-05, "loss": 1.4606478214263916, "step": 3025 }, { "epoch": 0.25545835399892364, "grad_norm": 0.1484375, "learning_rate": 4.427651715453669e-05, "loss": 1.5870914459228516, "step": 3026 }, { "epoch": 0.25554277513375473, "grad_norm": 0.1318359375, "learning_rate": 4.427237135858876e-05, "loss": 1.534138560295105, "step": 3027 }, { "epoch": 0.2556271962685858, "grad_norm": 0.1474609375, "learning_rate": 4.4268224255927735e-05, "loss": 1.5118683576583862, "step": 3028 }, { "epoch": 0.25571161740341697, "grad_norm": 0.1318359375, "learning_rate": 4.4264075846834796e-05, "loss": 1.4817787408828735, "step": 3029 }, { "epoch": 0.25579603853824806, "grad_norm": 0.1484375, "learning_rate": 4.42599261315912e-05, "loss": 1.5973149538040161, "step": 3030 }, { "epoch": 0.25588045967307915, "grad_norm": 0.1376953125, "learning_rate": 4.425577511047832e-05, "loss": 1.5548697710037231, "step": 3031 }, { "epoch": 0.25596488080791024, "grad_norm": 0.1455078125, "learning_rate": 4.42516227837776e-05, "loss": 1.6361396312713623, "step": 3032 }, { "epoch": 0.2560493019427414, "grad_norm": 0.138671875, "learning_rate": 4.4247469151770586e-05, "loss": 1.547802209854126, "step": 3033 }, { "epoch": 0.2561337230775725, "grad_norm": 0.15625, "learning_rate": 4.4243314214738894e-05, "loss": 1.4996528625488281, "step": 3034 }, { "epoch": 0.2562181442124036, "grad_norm": 0.146484375, "learning_rate": 4.423915797296425e-05, "loss": 1.5877224206924438, "step": 3035 }, { "epoch": 0.25630256534723467, "grad_norm": 0.1396484375, "learning_rate": 4.423500042672845e-05, "loss": 1.5444319248199463, "step": 3036 }, { "epoch": 0.25638698648206576, "grad_norm": 0.1474609375, "learning_rate": 4.423084157631337e-05, "loss": 1.567773699760437, "step": 3037 }, { "epoch": 0.2564714076168969, "grad_norm": 0.1435546875, "learning_rate": 4.4226681422001026e-05, "loss": 1.5606650114059448, "step": 3038 }, { "epoch": 0.256555828751728, "grad_norm": 0.1328125, "learning_rate": 4.4222519964073464e-05, "loss": 1.5899502038955688, "step": 3039 }, { "epoch": 0.2566402498865591, "grad_norm": 0.14453125, "learning_rate": 4.421835720281283e-05, "loss": 1.4710230827331543, "step": 3040 }, { "epoch": 0.2567246710213902, "grad_norm": 0.1455078125, "learning_rate": 4.4214193138501395e-05, "loss": 1.5149198770523071, "step": 3041 }, { "epoch": 0.25680909215622133, "grad_norm": 0.1484375, "learning_rate": 4.421002777142148e-05, "loss": 1.5208133459091187, "step": 3042 }, { "epoch": 0.2568935132910524, "grad_norm": 0.1376953125, "learning_rate": 4.4205861101855505e-05, "loss": 1.5354764461517334, "step": 3043 }, { "epoch": 0.2569779344258835, "grad_norm": 0.138671875, "learning_rate": 4.420169313008598e-05, "loss": 1.5975621938705444, "step": 3044 }, { "epoch": 0.2570623555607146, "grad_norm": 0.1357421875, "learning_rate": 4.419752385639551e-05, "loss": 1.5311359167099, "step": 3045 }, { "epoch": 0.25714677669554575, "grad_norm": 0.1357421875, "learning_rate": 4.4193353281066776e-05, "loss": 1.4394351243972778, "step": 3046 }, { "epoch": 0.25723119783037685, "grad_norm": 0.138671875, "learning_rate": 4.418918140438255e-05, "loss": 1.4929965734481812, "step": 3047 }, { "epoch": 0.25731561896520794, "grad_norm": 0.134765625, "learning_rate": 4.4185008226625705e-05, "loss": 1.515657901763916, "step": 3048 }, { "epoch": 0.25740004010003903, "grad_norm": 0.142578125, "learning_rate": 4.418083374807919e-05, "loss": 1.542114019393921, "step": 3049 }, { "epoch": 0.2574844612348702, "grad_norm": 0.1650390625, "learning_rate": 4.4176657969026036e-05, "loss": 1.5938843488693237, "step": 3050 }, { "epoch": 0.25756888236970127, "grad_norm": 0.1591796875, "learning_rate": 4.417248088974938e-05, "loss": 1.4758713245391846, "step": 3051 }, { "epoch": 0.25765330350453236, "grad_norm": 0.150390625, "learning_rate": 4.416830251053243e-05, "loss": 1.507351279258728, "step": 3052 }, { "epoch": 0.25773772463936345, "grad_norm": 0.1494140625, "learning_rate": 4.4164122831658506e-05, "loss": 1.5728883743286133, "step": 3053 }, { "epoch": 0.25782214577419454, "grad_norm": 0.15625, "learning_rate": 4.4159941853410986e-05, "loss": 1.592926025390625, "step": 3054 }, { "epoch": 0.2579065669090257, "grad_norm": 0.1484375, "learning_rate": 4.415575957607335e-05, "loss": 1.586340069770813, "step": 3055 }, { "epoch": 0.2579909880438568, "grad_norm": 0.14453125, "learning_rate": 4.4151575999929175e-05, "loss": 1.4990779161453247, "step": 3056 }, { "epoch": 0.2580754091786879, "grad_norm": 0.1484375, "learning_rate": 4.4147391125262104e-05, "loss": 1.574190616607666, "step": 3057 }, { "epoch": 0.25815983031351897, "grad_norm": 0.1533203125, "learning_rate": 4.4143204952355896e-05, "loss": 1.5729633569717407, "step": 3058 }, { "epoch": 0.2582442514483501, "grad_norm": 0.1455078125, "learning_rate": 4.413901748149438e-05, "loss": 1.542130470275879, "step": 3059 }, { "epoch": 0.2583286725831812, "grad_norm": 0.1435546875, "learning_rate": 4.413482871296148e-05, "loss": 1.568253755569458, "step": 3060 }, { "epoch": 0.2584130937180123, "grad_norm": 0.1396484375, "learning_rate": 4.413063864704119e-05, "loss": 1.5714493989944458, "step": 3061 }, { "epoch": 0.2584975148528434, "grad_norm": 0.1484375, "learning_rate": 4.412644728401762e-05, "loss": 1.6709858179092407, "step": 3062 }, { "epoch": 0.25858193598767454, "grad_norm": 0.1572265625, "learning_rate": 4.4122254624174944e-05, "loss": 1.5949231386184692, "step": 3063 }, { "epoch": 0.25866635712250563, "grad_norm": 0.138671875, "learning_rate": 4.4118060667797446e-05, "loss": 1.4627571105957031, "step": 3064 }, { "epoch": 0.2587507782573367, "grad_norm": 0.13671875, "learning_rate": 4.411386541516948e-05, "loss": 1.5153329372406006, "step": 3065 }, { "epoch": 0.2588351993921678, "grad_norm": 0.1357421875, "learning_rate": 4.4109668866575496e-05, "loss": 1.5527722835540771, "step": 3066 }, { "epoch": 0.25891962052699896, "grad_norm": 0.1435546875, "learning_rate": 4.4105471022300033e-05, "loss": 1.5567631721496582, "step": 3067 }, { "epoch": 0.25900404166183005, "grad_norm": 0.1376953125, "learning_rate": 4.41012718826277e-05, "loss": 1.5454623699188232, "step": 3068 }, { "epoch": 0.25908846279666115, "grad_norm": 0.134765625, "learning_rate": 4.409707144784323e-05, "loss": 1.5194368362426758, "step": 3069 }, { "epoch": 0.25917288393149224, "grad_norm": 0.134765625, "learning_rate": 4.409286971823141e-05, "loss": 1.5097973346710205, "step": 3070 }, { "epoch": 0.25925730506632333, "grad_norm": 0.1494140625, "learning_rate": 4.408866669407713e-05, "loss": 1.544698715209961, "step": 3071 }, { "epoch": 0.2593417262011545, "grad_norm": 0.13671875, "learning_rate": 4.4084462375665364e-05, "loss": 1.56687593460083, "step": 3072 }, { "epoch": 0.25942614733598557, "grad_norm": 0.15234375, "learning_rate": 4.408025676328118e-05, "loss": 1.55316162109375, "step": 3073 }, { "epoch": 0.25951056847081666, "grad_norm": 0.1376953125, "learning_rate": 4.407604985720972e-05, "loss": 1.561450719833374, "step": 3074 }, { "epoch": 0.25959498960564775, "grad_norm": 0.142578125, "learning_rate": 4.407184165773622e-05, "loss": 1.574828863143921, "step": 3075 }, { "epoch": 0.2596794107404789, "grad_norm": 0.138671875, "learning_rate": 4.406763216514602e-05, "loss": 1.6431642770767212, "step": 3076 }, { "epoch": 0.25976383187531, "grad_norm": 0.1455078125, "learning_rate": 4.406342137972453e-05, "loss": 1.5805743932724, "step": 3077 }, { "epoch": 0.2598482530101411, "grad_norm": 0.146484375, "learning_rate": 4.405920930175725e-05, "loss": 1.5937111377716064, "step": 3078 }, { "epoch": 0.2599326741449722, "grad_norm": 0.1611328125, "learning_rate": 4.405499593152976e-05, "loss": 1.4704318046569824, "step": 3079 }, { "epoch": 0.2600170952798033, "grad_norm": 0.146484375, "learning_rate": 4.405078126932774e-05, "loss": 1.598439335823059, "step": 3080 }, { "epoch": 0.2601015164146344, "grad_norm": 0.138671875, "learning_rate": 4.4046565315436964e-05, "loss": 1.5945656299591064, "step": 3081 }, { "epoch": 0.2601859375494655, "grad_norm": 0.138671875, "learning_rate": 4.404234807014328e-05, "loss": 1.5561026334762573, "step": 3082 }, { "epoch": 0.2602703586842966, "grad_norm": 0.1474609375, "learning_rate": 4.403812953373262e-05, "loss": 1.6235796213150024, "step": 3083 }, { "epoch": 0.26035477981912775, "grad_norm": 0.1513671875, "learning_rate": 4.403390970649102e-05, "loss": 1.6113736629486084, "step": 3084 }, { "epoch": 0.26043920095395884, "grad_norm": 0.1396484375, "learning_rate": 4.402968858870459e-05, "loss": 1.5523937940597534, "step": 3085 }, { "epoch": 0.26052362208878993, "grad_norm": 0.134765625, "learning_rate": 4.402546618065954e-05, "loss": 1.5148285627365112, "step": 3086 }, { "epoch": 0.260608043223621, "grad_norm": 0.150390625, "learning_rate": 4.402124248264213e-05, "loss": 1.5090147256851196, "step": 3087 }, { "epoch": 0.2606924643584521, "grad_norm": 0.15234375, "learning_rate": 4.4017017494938775e-05, "loss": 1.6226763725280762, "step": 3088 }, { "epoch": 0.26077688549328326, "grad_norm": 0.138671875, "learning_rate": 4.4012791217835924e-05, "loss": 1.4838030338287354, "step": 3089 }, { "epoch": 0.26086130662811435, "grad_norm": 0.1396484375, "learning_rate": 4.400856365162012e-05, "loss": 1.5906047821044922, "step": 3090 }, { "epoch": 0.26094572776294545, "grad_norm": 0.1533203125, "learning_rate": 4.4004334796578015e-05, "loss": 1.481911301612854, "step": 3091 }, { "epoch": 0.26103014889777654, "grad_norm": 0.1474609375, "learning_rate": 4.4000104652996324e-05, "loss": 1.544538974761963, "step": 3092 }, { "epoch": 0.2611145700326077, "grad_norm": 0.134765625, "learning_rate": 4.399587322116188e-05, "loss": 1.4615577459335327, "step": 3093 }, { "epoch": 0.2611989911674388, "grad_norm": 0.1494140625, "learning_rate": 4.3991640501361556e-05, "loss": 1.5733224153518677, "step": 3094 }, { "epoch": 0.26128341230226987, "grad_norm": 0.140625, "learning_rate": 4.398740649388237e-05, "loss": 1.4544768333435059, "step": 3095 }, { "epoch": 0.26136783343710096, "grad_norm": 0.1513671875, "learning_rate": 4.398317119901138e-05, "loss": 1.4867935180664062, "step": 3096 }, { "epoch": 0.2614522545719321, "grad_norm": 0.1435546875, "learning_rate": 4.3978934617035746e-05, "loss": 1.5396995544433594, "step": 3097 }, { "epoch": 0.2615366757067632, "grad_norm": 0.13671875, "learning_rate": 4.397469674824273e-05, "loss": 1.568376898765564, "step": 3098 }, { "epoch": 0.2616210968415943, "grad_norm": 0.1279296875, "learning_rate": 4.397045759291966e-05, "loss": 1.5317209959030151, "step": 3099 }, { "epoch": 0.2617055179764254, "grad_norm": 0.1357421875, "learning_rate": 4.396621715135397e-05, "loss": 1.5570074319839478, "step": 3100 }, { "epoch": 0.2617899391112565, "grad_norm": 0.1376953125, "learning_rate": 4.396197542383317e-05, "loss": 1.5476094484329224, "step": 3101 }, { "epoch": 0.2618743602460876, "grad_norm": 0.1435546875, "learning_rate": 4.395773241064486e-05, "loss": 1.580899715423584, "step": 3102 }, { "epoch": 0.2619587813809187, "grad_norm": 0.1337890625, "learning_rate": 4.395348811207672e-05, "loss": 1.4401071071624756, "step": 3103 }, { "epoch": 0.2620432025157498, "grad_norm": 0.140625, "learning_rate": 4.3949242528416535e-05, "loss": 1.6010481119155884, "step": 3104 }, { "epoch": 0.2621276236505809, "grad_norm": 0.13671875, "learning_rate": 4.394499565995215e-05, "loss": 1.5179283618927002, "step": 3105 }, { "epoch": 0.26221204478541205, "grad_norm": 0.1328125, "learning_rate": 4.3940747506971526e-05, "loss": 1.5222206115722656, "step": 3106 }, { "epoch": 0.26229646592024314, "grad_norm": 0.1513671875, "learning_rate": 4.3936498069762694e-05, "loss": 1.5476911067962646, "step": 3107 }, { "epoch": 0.26238088705507423, "grad_norm": 0.140625, "learning_rate": 4.393224734861378e-05, "loss": 1.5746346712112427, "step": 3108 }, { "epoch": 0.2624653081899053, "grad_norm": 0.171875, "learning_rate": 4.392799534381298e-05, "loss": 1.578749656677246, "step": 3109 }, { "epoch": 0.26254972932473647, "grad_norm": 0.14453125, "learning_rate": 4.39237420556486e-05, "loss": 1.552098274230957, "step": 3110 }, { "epoch": 0.26263415045956756, "grad_norm": 0.1494140625, "learning_rate": 4.391948748440902e-05, "loss": 1.5657362937927246, "step": 3111 }, { "epoch": 0.26271857159439865, "grad_norm": 0.1416015625, "learning_rate": 4.3915231630382716e-05, "loss": 1.5774173736572266, "step": 3112 }, { "epoch": 0.26280299272922975, "grad_norm": 0.1474609375, "learning_rate": 4.391097449385824e-05, "loss": 1.4613804817199707, "step": 3113 }, { "epoch": 0.2628874138640609, "grad_norm": 0.150390625, "learning_rate": 4.390671607512424e-05, "loss": 1.525582194328308, "step": 3114 }, { "epoch": 0.262971834998892, "grad_norm": 0.13671875, "learning_rate": 4.390245637446944e-05, "loss": 1.5914453268051147, "step": 3115 }, { "epoch": 0.2630562561337231, "grad_norm": 0.13671875, "learning_rate": 4.3898195392182664e-05, "loss": 1.4883939027786255, "step": 3116 }, { "epoch": 0.26314067726855417, "grad_norm": 0.1416015625, "learning_rate": 4.389393312855281e-05, "loss": 1.5131988525390625, "step": 3117 }, { "epoch": 0.26322509840338526, "grad_norm": 0.1357421875, "learning_rate": 4.388966958386889e-05, "loss": 1.487744927406311, "step": 3118 }, { "epoch": 0.2633095195382164, "grad_norm": 0.1328125, "learning_rate": 4.3885404758419954e-05, "loss": 1.573581576347351, "step": 3119 }, { "epoch": 0.2633939406730475, "grad_norm": 0.1533203125, "learning_rate": 4.388113865249519e-05, "loss": 1.5616201162338257, "step": 3120 }, { "epoch": 0.2634783618078786, "grad_norm": 0.1318359375, "learning_rate": 4.3876871266383826e-05, "loss": 1.5162285566329956, "step": 3121 }, { "epoch": 0.2635627829427097, "grad_norm": 0.138671875, "learning_rate": 4.387260260037523e-05, "loss": 1.5674731731414795, "step": 3122 }, { "epoch": 0.26364720407754083, "grad_norm": 0.1591796875, "learning_rate": 4.386833265475881e-05, "loss": 1.5745676755905151, "step": 3123 }, { "epoch": 0.2637316252123719, "grad_norm": 0.15234375, "learning_rate": 4.386406142982408e-05, "loss": 1.5880616903305054, "step": 3124 }, { "epoch": 0.263816046347203, "grad_norm": 0.134765625, "learning_rate": 4.385978892586064e-05, "loss": 1.5881510972976685, "step": 3125 }, { "epoch": 0.2639004674820341, "grad_norm": 0.142578125, "learning_rate": 4.3855515143158185e-05, "loss": 1.612423062324524, "step": 3126 }, { "epoch": 0.26398488861686525, "grad_norm": 0.154296875, "learning_rate": 4.3851240082006485e-05, "loss": 1.527675747871399, "step": 3127 }, { "epoch": 0.26406930975169635, "grad_norm": 0.134765625, "learning_rate": 4.384696374269538e-05, "loss": 1.4862849712371826, "step": 3128 }, { "epoch": 0.26415373088652744, "grad_norm": 0.138671875, "learning_rate": 4.384268612551484e-05, "loss": 1.647922396659851, "step": 3129 }, { "epoch": 0.26423815202135853, "grad_norm": 0.14453125, "learning_rate": 4.3838407230754885e-05, "loss": 1.534241795539856, "step": 3130 }, { "epoch": 0.2643225731561897, "grad_norm": 0.1435546875, "learning_rate": 4.3834127058705646e-05, "loss": 1.5670623779296875, "step": 3131 }, { "epoch": 0.26440699429102077, "grad_norm": 0.1396484375, "learning_rate": 4.382984560965732e-05, "loss": 1.5863524675369263, "step": 3132 }, { "epoch": 0.26449141542585186, "grad_norm": 0.134765625, "learning_rate": 4.38255628839002e-05, "loss": 1.5043619871139526, "step": 3133 }, { "epoch": 0.26457583656068295, "grad_norm": 0.1396484375, "learning_rate": 4.382127888172465e-05, "loss": 1.504685640335083, "step": 3134 }, { "epoch": 0.26466025769551405, "grad_norm": 0.1376953125, "learning_rate": 4.381699360342116e-05, "loss": 1.5319490432739258, "step": 3135 }, { "epoch": 0.2647446788303452, "grad_norm": 0.1484375, "learning_rate": 4.381270704928029e-05, "loss": 1.5687130689620972, "step": 3136 }, { "epoch": 0.2648290999651763, "grad_norm": 0.13671875, "learning_rate": 4.3808419219592645e-05, "loss": 1.5686450004577637, "step": 3137 }, { "epoch": 0.2649135211000074, "grad_norm": 0.1435546875, "learning_rate": 4.380413011464897e-05, "loss": 1.5153987407684326, "step": 3138 }, { "epoch": 0.26499794223483847, "grad_norm": 0.1494140625, "learning_rate": 4.3799839734740075e-05, "loss": 1.5013879537582397, "step": 3139 }, { "epoch": 0.2650823633696696, "grad_norm": 0.146484375, "learning_rate": 4.3795548080156865e-05, "loss": 1.6081719398498535, "step": 3140 }, { "epoch": 0.2651667845045007, "grad_norm": 0.13671875, "learning_rate": 4.3791255151190305e-05, "loss": 1.6058018207550049, "step": 3141 }, { "epoch": 0.2652512056393318, "grad_norm": 0.1484375, "learning_rate": 4.378696094813148e-05, "loss": 1.6187266111373901, "step": 3142 }, { "epoch": 0.2653356267741629, "grad_norm": 0.1494140625, "learning_rate": 4.3782665471271555e-05, "loss": 1.539136290550232, "step": 3143 }, { "epoch": 0.26542004790899404, "grad_norm": 0.140625, "learning_rate": 4.377836872090175e-05, "loss": 1.5573350191116333, "step": 3144 }, { "epoch": 0.26550446904382513, "grad_norm": 0.1455078125, "learning_rate": 4.377407069731342e-05, "loss": 1.5102510452270508, "step": 3145 }, { "epoch": 0.2655888901786562, "grad_norm": 0.134765625, "learning_rate": 4.376977140079796e-05, "loss": 1.5431033372879028, "step": 3146 }, { "epoch": 0.2656733113134873, "grad_norm": 0.1357421875, "learning_rate": 4.376547083164688e-05, "loss": 1.4437298774719238, "step": 3147 }, { "epoch": 0.26575773244831846, "grad_norm": 0.1396484375, "learning_rate": 4.376116899015178e-05, "loss": 1.5676177740097046, "step": 3148 }, { "epoch": 0.26584215358314955, "grad_norm": 0.14453125, "learning_rate": 4.375686587660432e-05, "loss": 1.5518412590026855, "step": 3149 }, { "epoch": 0.26592657471798065, "grad_norm": 0.1318359375, "learning_rate": 4.375256149129628e-05, "loss": 1.5373038053512573, "step": 3150 }, { "epoch": 0.26601099585281174, "grad_norm": 0.1318359375, "learning_rate": 4.374825583451949e-05, "loss": 1.510561466217041, "step": 3151 }, { "epoch": 0.26609541698764283, "grad_norm": 0.1328125, "learning_rate": 4.374394890656588e-05, "loss": 1.5250976085662842, "step": 3152 }, { "epoch": 0.266179838122474, "grad_norm": 0.1376953125, "learning_rate": 4.373964070772749e-05, "loss": 1.5433236360549927, "step": 3153 }, { "epoch": 0.26626425925730507, "grad_norm": 0.142578125, "learning_rate": 4.3735331238296415e-05, "loss": 1.5544815063476562, "step": 3154 }, { "epoch": 0.26634868039213616, "grad_norm": 0.154296875, "learning_rate": 4.3731020498564846e-05, "loss": 1.4997767210006714, "step": 3155 }, { "epoch": 0.26643310152696725, "grad_norm": 0.1337890625, "learning_rate": 4.372670848882506e-05, "loss": 1.5021405220031738, "step": 3156 }, { "epoch": 0.2665175226617984, "grad_norm": 0.146484375, "learning_rate": 4.3722395209369434e-05, "loss": 1.6072989702224731, "step": 3157 }, { "epoch": 0.2666019437966295, "grad_norm": 0.140625, "learning_rate": 4.37180806604904e-05, "loss": 1.551859736442566, "step": 3158 }, { "epoch": 0.2666863649314606, "grad_norm": 0.140625, "learning_rate": 4.3713764842480514e-05, "loss": 1.5871456861495972, "step": 3159 }, { "epoch": 0.2667707860662917, "grad_norm": 0.1533203125, "learning_rate": 4.370944775563239e-05, "loss": 1.5102545022964478, "step": 3160 }, { "epoch": 0.2668552072011228, "grad_norm": 0.140625, "learning_rate": 4.370512940023873e-05, "loss": 1.590701937675476, "step": 3161 }, { "epoch": 0.2669396283359539, "grad_norm": 0.134765625, "learning_rate": 4.370080977659234e-05, "loss": 1.5448678731918335, "step": 3162 }, { "epoch": 0.267024049470785, "grad_norm": 0.138671875, "learning_rate": 4.369648888498609e-05, "loss": 1.5500240325927734, "step": 3163 }, { "epoch": 0.2671084706056161, "grad_norm": 0.1357421875, "learning_rate": 4.3692166725712955e-05, "loss": 1.5380444526672363, "step": 3164 }, { "epoch": 0.26719289174044725, "grad_norm": 0.1767578125, "learning_rate": 4.368784329906599e-05, "loss": 1.501344084739685, "step": 3165 }, { "epoch": 0.26727731287527834, "grad_norm": 0.142578125, "learning_rate": 4.368351860533833e-05, "loss": 1.5418946743011475, "step": 3166 }, { "epoch": 0.26736173401010943, "grad_norm": 0.1416015625, "learning_rate": 4.3679192644823196e-05, "loss": 1.5765101909637451, "step": 3167 }, { "epoch": 0.2674461551449405, "grad_norm": 0.142578125, "learning_rate": 4.3674865417813904e-05, "loss": 1.5890403985977173, "step": 3168 }, { "epoch": 0.2675305762797716, "grad_norm": 0.138671875, "learning_rate": 4.367053692460385e-05, "loss": 1.5869803428649902, "step": 3169 }, { "epoch": 0.26761499741460276, "grad_norm": 0.1455078125, "learning_rate": 4.366620716548651e-05, "loss": 1.513274908065796, "step": 3170 }, { "epoch": 0.26769941854943385, "grad_norm": 0.1513671875, "learning_rate": 4.366187614075546e-05, "loss": 1.579408049583435, "step": 3171 }, { "epoch": 0.26778383968426495, "grad_norm": 0.1806640625, "learning_rate": 4.365754385070435e-05, "loss": 1.6823519468307495, "step": 3172 }, { "epoch": 0.26786826081909604, "grad_norm": 0.1337890625, "learning_rate": 4.365321029562692e-05, "loss": 1.5001224279403687, "step": 3173 }, { "epoch": 0.2679526819539272, "grad_norm": 0.1416015625, "learning_rate": 4.364887547581699e-05, "loss": 1.5556676387786865, "step": 3174 }, { "epoch": 0.2680371030887583, "grad_norm": 0.150390625, "learning_rate": 4.364453939156848e-05, "loss": 1.5672390460968018, "step": 3175 }, { "epoch": 0.26812152422358937, "grad_norm": 0.1591796875, "learning_rate": 4.3640202043175385e-05, "loss": 1.4455089569091797, "step": 3176 }, { "epoch": 0.26820594535842046, "grad_norm": 0.1416015625, "learning_rate": 4.363586343093179e-05, "loss": 1.5376383066177368, "step": 3177 }, { "epoch": 0.2682903664932516, "grad_norm": 0.158203125, "learning_rate": 4.3631523555131855e-05, "loss": 1.5951008796691895, "step": 3178 }, { "epoch": 0.2683747876280827, "grad_norm": 0.158203125, "learning_rate": 4.362718241606983e-05, "loss": 1.6045126914978027, "step": 3179 }, { "epoch": 0.2684592087629138, "grad_norm": 0.142578125, "learning_rate": 4.362284001404008e-05, "loss": 1.5708165168762207, "step": 3180 }, { "epoch": 0.2685436298977449, "grad_norm": 0.150390625, "learning_rate": 4.3618496349337006e-05, "loss": 1.595387578010559, "step": 3181 }, { "epoch": 0.26862805103257603, "grad_norm": 0.1494140625, "learning_rate": 4.3614151422255126e-05, "loss": 1.479487419128418, "step": 3182 }, { "epoch": 0.2687124721674071, "grad_norm": 0.146484375, "learning_rate": 4.360980523308904e-05, "loss": 1.4965882301330566, "step": 3183 }, { "epoch": 0.2687968933022382, "grad_norm": 0.140625, "learning_rate": 4.360545778213343e-05, "loss": 1.526114583015442, "step": 3184 }, { "epoch": 0.2688813144370693, "grad_norm": 0.138671875, "learning_rate": 4.360110906968305e-05, "loss": 1.5139269828796387, "step": 3185 }, { "epoch": 0.2689657355719004, "grad_norm": 0.15234375, "learning_rate": 4.359675909603277e-05, "loss": 1.5594452619552612, "step": 3186 }, { "epoch": 0.26905015670673155, "grad_norm": 0.150390625, "learning_rate": 4.359240786147753e-05, "loss": 1.5846797227859497, "step": 3187 }, { "epoch": 0.26913457784156264, "grad_norm": 0.1572265625, "learning_rate": 4.358805536631233e-05, "loss": 1.4820220470428467, "step": 3188 }, { "epoch": 0.26921899897639373, "grad_norm": 0.1484375, "learning_rate": 4.3583701610832304e-05, "loss": 1.541252851486206, "step": 3189 }, { "epoch": 0.2693034201112248, "grad_norm": 0.140625, "learning_rate": 4.3579346595332645e-05, "loss": 1.5389989614486694, "step": 3190 }, { "epoch": 0.26938784124605597, "grad_norm": 0.1328125, "learning_rate": 4.357499032010862e-05, "loss": 1.5238523483276367, "step": 3191 }, { "epoch": 0.26947226238088706, "grad_norm": 0.1435546875, "learning_rate": 4.357063278545561e-05, "loss": 1.4950926303863525, "step": 3192 }, { "epoch": 0.26955668351571815, "grad_norm": 0.1455078125, "learning_rate": 4.356627399166906e-05, "loss": 1.5491645336151123, "step": 3193 }, { "epoch": 0.26964110465054925, "grad_norm": 0.1337890625, "learning_rate": 4.35619139390445e-05, "loss": 1.5143702030181885, "step": 3194 }, { "epoch": 0.2697255257853804, "grad_norm": 0.1474609375, "learning_rate": 4.3557552627877565e-05, "loss": 1.5164361000061035, "step": 3195 }, { "epoch": 0.2698099469202115, "grad_norm": 0.1416015625, "learning_rate": 4.355319005846394e-05, "loss": 1.5351718664169312, "step": 3196 }, { "epoch": 0.2698943680550426, "grad_norm": 0.158203125, "learning_rate": 4.354882623109945e-05, "loss": 1.5843499898910522, "step": 3197 }, { "epoch": 0.26997878918987367, "grad_norm": 0.1396484375, "learning_rate": 4.354446114607995e-05, "loss": 1.5150223970413208, "step": 3198 }, { "epoch": 0.2700632103247048, "grad_norm": 0.13671875, "learning_rate": 4.35400948037014e-05, "loss": 1.554570198059082, "step": 3199 }, { "epoch": 0.2701476314595359, "grad_norm": 0.1455078125, "learning_rate": 4.3535727204259865e-05, "loss": 1.5473562479019165, "step": 3200 }, { "epoch": 0.270232052594367, "grad_norm": 0.1513671875, "learning_rate": 4.353135834805148e-05, "loss": 1.5343297719955444, "step": 3201 }, { "epoch": 0.2703164737291981, "grad_norm": 0.142578125, "learning_rate": 4.3526988235372444e-05, "loss": 1.473273754119873, "step": 3202 }, { "epoch": 0.2704008948640292, "grad_norm": 0.140625, "learning_rate": 4.352261686651908e-05, "loss": 1.45210599899292, "step": 3203 }, { "epoch": 0.27048531599886033, "grad_norm": 0.1435546875, "learning_rate": 4.351824424178777e-05, "loss": 1.5633243322372437, "step": 3204 }, { "epoch": 0.2705697371336914, "grad_norm": 0.142578125, "learning_rate": 4.3513870361474985e-05, "loss": 1.5837273597717285, "step": 3205 }, { "epoch": 0.2706541582685225, "grad_norm": 0.14453125, "learning_rate": 4.350949522587728e-05, "loss": 1.619390606880188, "step": 3206 }, { "epoch": 0.2707385794033536, "grad_norm": 0.1396484375, "learning_rate": 4.350511883529132e-05, "loss": 1.500652551651001, "step": 3207 }, { "epoch": 0.27082300053818475, "grad_norm": 0.138671875, "learning_rate": 4.3500741190013824e-05, "loss": 1.5170310735702515, "step": 3208 }, { "epoch": 0.27090742167301585, "grad_norm": 0.1337890625, "learning_rate": 4.34963622903416e-05, "loss": 1.5310025215148926, "step": 3209 }, { "epoch": 0.27099184280784694, "grad_norm": 0.1494140625, "learning_rate": 4.3491982136571554e-05, "loss": 1.4985790252685547, "step": 3210 }, { "epoch": 0.27107626394267803, "grad_norm": 0.1474609375, "learning_rate": 4.348760072900067e-05, "loss": 1.5543742179870605, "step": 3211 }, { "epoch": 0.2711606850775092, "grad_norm": 0.146484375, "learning_rate": 4.348321806792601e-05, "loss": 1.5350184440612793, "step": 3212 }, { "epoch": 0.27124510621234027, "grad_norm": 0.142578125, "learning_rate": 4.347883415364475e-05, "loss": 1.5500046014785767, "step": 3213 }, { "epoch": 0.27132952734717136, "grad_norm": 0.1357421875, "learning_rate": 4.347444898645411e-05, "loss": 1.506032943725586, "step": 3214 }, { "epoch": 0.27141394848200245, "grad_norm": 0.14453125, "learning_rate": 4.347006256665143e-05, "loss": 1.6214585304260254, "step": 3215 }, { "epoch": 0.2714983696168336, "grad_norm": 0.1357421875, "learning_rate": 4.34656748945341e-05, "loss": 1.5425221920013428, "step": 3216 }, { "epoch": 0.2715827907516647, "grad_norm": 0.1318359375, "learning_rate": 4.346128597039963e-05, "loss": 1.5477957725524902, "step": 3217 }, { "epoch": 0.2716672118864958, "grad_norm": 0.140625, "learning_rate": 4.34568957945456e-05, "loss": 1.512354850769043, "step": 3218 }, { "epoch": 0.2717516330213269, "grad_norm": 0.1416015625, "learning_rate": 4.345250436726967e-05, "loss": 1.503678798675537, "step": 3219 }, { "epoch": 0.27183605415615797, "grad_norm": 0.140625, "learning_rate": 4.3448111688869594e-05, "loss": 1.5686824321746826, "step": 3220 }, { "epoch": 0.2719204752909891, "grad_norm": 0.1513671875, "learning_rate": 4.34437177596432e-05, "loss": 1.522133708000183, "step": 3221 }, { "epoch": 0.2720048964258202, "grad_norm": 0.16796875, "learning_rate": 4.3439322579888394e-05, "loss": 1.6216323375701904, "step": 3222 }, { "epoch": 0.2720893175606513, "grad_norm": 0.150390625, "learning_rate": 4.343492614990321e-05, "loss": 1.4895859956741333, "step": 3223 }, { "epoch": 0.2721737386954824, "grad_norm": 0.1435546875, "learning_rate": 4.343052846998572e-05, "loss": 1.5013456344604492, "step": 3224 }, { "epoch": 0.27225815983031354, "grad_norm": 0.1484375, "learning_rate": 4.34261295404341e-05, "loss": 1.5182287693023682, "step": 3225 }, { "epoch": 0.27234258096514463, "grad_norm": 0.1337890625, "learning_rate": 4.3421729361546605e-05, "loss": 1.5263035297393799, "step": 3226 }, { "epoch": 0.2724270020999757, "grad_norm": 0.1396484375, "learning_rate": 4.341732793362158e-05, "loss": 1.5129978656768799, "step": 3227 }, { "epoch": 0.2725114232348068, "grad_norm": 0.15234375, "learning_rate": 4.341292525695745e-05, "loss": 1.5553306341171265, "step": 3228 }, { "epoch": 0.27259584436963796, "grad_norm": 0.1455078125, "learning_rate": 4.340852133185272e-05, "loss": 1.601157784461975, "step": 3229 }, { "epoch": 0.27268026550446905, "grad_norm": 0.1416015625, "learning_rate": 4.340411615860601e-05, "loss": 1.5206400156021118, "step": 3230 }, { "epoch": 0.27276468663930015, "grad_norm": 0.1552734375, "learning_rate": 4.339970973751597e-05, "loss": 1.598846673965454, "step": 3231 }, { "epoch": 0.27284910777413124, "grad_norm": 0.142578125, "learning_rate": 4.33953020688814e-05, "loss": 1.5478969812393188, "step": 3232 }, { "epoch": 0.2729335289089624, "grad_norm": 0.13671875, "learning_rate": 4.339089315300112e-05, "loss": 1.5583069324493408, "step": 3233 }, { "epoch": 0.2730179500437935, "grad_norm": 0.146484375, "learning_rate": 4.3386482990174095e-05, "loss": 1.6008522510528564, "step": 3234 }, { "epoch": 0.27310237117862457, "grad_norm": 0.134765625, "learning_rate": 4.3382071580699314e-05, "loss": 1.4806853532791138, "step": 3235 }, { "epoch": 0.27318679231345566, "grad_norm": 0.1416015625, "learning_rate": 4.33776589248759e-05, "loss": 1.527299165725708, "step": 3236 }, { "epoch": 0.27327121344828675, "grad_norm": 0.142578125, "learning_rate": 4.337324502300303e-05, "loss": 1.5614091157913208, "step": 3237 }, { "epoch": 0.2733556345831179, "grad_norm": 0.138671875, "learning_rate": 4.336882987537999e-05, "loss": 1.5018413066864014, "step": 3238 }, { "epoch": 0.273440055717949, "grad_norm": 0.1396484375, "learning_rate": 4.3364413482306134e-05, "loss": 1.609758734703064, "step": 3239 }, { "epoch": 0.2735244768527801, "grad_norm": 0.138671875, "learning_rate": 4.33599958440809e-05, "loss": 1.4912688732147217, "step": 3240 }, { "epoch": 0.2736088979876112, "grad_norm": 0.1376953125, "learning_rate": 4.3355576961003815e-05, "loss": 1.5298938751220703, "step": 3241 }, { "epoch": 0.2736933191224423, "grad_norm": 0.150390625, "learning_rate": 4.335115683337449e-05, "loss": 1.6233971118927002, "step": 3242 }, { "epoch": 0.2737777402572734, "grad_norm": 0.14453125, "learning_rate": 4.334673546149262e-05, "loss": 1.5150525569915771, "step": 3243 }, { "epoch": 0.2738621613921045, "grad_norm": 0.150390625, "learning_rate": 4.334231284565799e-05, "loss": 1.4609044790267944, "step": 3244 }, { "epoch": 0.2739465825269356, "grad_norm": 0.1328125, "learning_rate": 4.333788898617046e-05, "loss": 1.471204400062561, "step": 3245 }, { "epoch": 0.27403100366176675, "grad_norm": 0.138671875, "learning_rate": 4.333346388332997e-05, "loss": 1.5272860527038574, "step": 3246 }, { "epoch": 0.27411542479659784, "grad_norm": 0.14453125, "learning_rate": 4.332903753743657e-05, "loss": 1.5440024137496948, "step": 3247 }, { "epoch": 0.27419984593142893, "grad_norm": 0.134765625, "learning_rate": 4.332460994879037e-05, "loss": 1.5907281637191772, "step": 3248 }, { "epoch": 0.27428426706626, "grad_norm": 0.15234375, "learning_rate": 4.332018111769156e-05, "loss": 1.6652889251708984, "step": 3249 }, { "epoch": 0.2743686882010911, "grad_norm": 0.150390625, "learning_rate": 4.3315751044440446e-05, "loss": 1.4951099157333374, "step": 3250 }, { "epoch": 0.27445310933592226, "grad_norm": 0.1357421875, "learning_rate": 4.331131972933737e-05, "loss": 1.4990131855010986, "step": 3251 }, { "epoch": 0.27453753047075335, "grad_norm": 0.138671875, "learning_rate": 4.330688717268281e-05, "loss": 1.5989800691604614, "step": 3252 }, { "epoch": 0.27462195160558445, "grad_norm": 0.134765625, "learning_rate": 4.3302453374777296e-05, "loss": 1.553876519203186, "step": 3253 }, { "epoch": 0.27470637274041554, "grad_norm": 0.1376953125, "learning_rate": 4.3298018335921456e-05, "loss": 1.5381405353546143, "step": 3254 }, { "epoch": 0.2747907938752467, "grad_norm": 0.14453125, "learning_rate": 4.3293582056415985e-05, "loss": 1.5521844625473022, "step": 3255 }, { "epoch": 0.2748752150100778, "grad_norm": 0.15234375, "learning_rate": 4.328914453656167e-05, "loss": 1.516120195388794, "step": 3256 }, { "epoch": 0.27495963614490887, "grad_norm": 0.130859375, "learning_rate": 4.3284705776659406e-05, "loss": 1.520018458366394, "step": 3257 }, { "epoch": 0.27504405727973996, "grad_norm": 0.130859375, "learning_rate": 4.328026577701013e-05, "loss": 1.4978630542755127, "step": 3258 }, { "epoch": 0.2751284784145711, "grad_norm": 0.138671875, "learning_rate": 4.32758245379149e-05, "loss": 1.5219719409942627, "step": 3259 }, { "epoch": 0.2752128995494022, "grad_norm": 0.1318359375, "learning_rate": 4.327138205967484e-05, "loss": 1.543952226638794, "step": 3260 }, { "epoch": 0.2752973206842333, "grad_norm": 0.1318359375, "learning_rate": 4.326693834259116e-05, "loss": 1.5052112340927124, "step": 3261 }, { "epoch": 0.2753817418190644, "grad_norm": 0.1455078125, "learning_rate": 4.326249338696514e-05, "loss": 1.4713749885559082, "step": 3262 }, { "epoch": 0.27546616295389553, "grad_norm": 0.140625, "learning_rate": 4.3258047193098176e-05, "loss": 1.5631266832351685, "step": 3263 }, { "epoch": 0.2755505840887266, "grad_norm": 0.1591796875, "learning_rate": 4.325359976129173e-05, "loss": 1.571903109550476, "step": 3264 }, { "epoch": 0.2756350052235577, "grad_norm": 0.142578125, "learning_rate": 4.324915109184734e-05, "loss": 1.4774366617202759, "step": 3265 }, { "epoch": 0.2757194263583888, "grad_norm": 0.171875, "learning_rate": 4.324470118506664e-05, "loss": 1.4905574321746826, "step": 3266 }, { "epoch": 0.2758038474932199, "grad_norm": 0.1455078125, "learning_rate": 4.324025004125135e-05, "loss": 1.528394103050232, "step": 3267 }, { "epoch": 0.27588826862805105, "grad_norm": 0.1357421875, "learning_rate": 4.3235797660703265e-05, "loss": 1.5195467472076416, "step": 3268 }, { "epoch": 0.27597268976288214, "grad_norm": 0.154296875, "learning_rate": 4.323134404372426e-05, "loss": 1.5801026821136475, "step": 3269 }, { "epoch": 0.27605711089771323, "grad_norm": 0.1396484375, "learning_rate": 4.322688919061631e-05, "loss": 1.5294899940490723, "step": 3270 }, { "epoch": 0.2761415320325443, "grad_norm": 0.140625, "learning_rate": 4.322243310168146e-05, "loss": 1.583315134048462, "step": 3271 }, { "epoch": 0.27622595316737547, "grad_norm": 0.138671875, "learning_rate": 4.3217975777221844e-05, "loss": 1.502877116203308, "step": 3272 }, { "epoch": 0.27631037430220656, "grad_norm": 0.15234375, "learning_rate": 4.321351721753968e-05, "loss": 1.5732223987579346, "step": 3273 }, { "epoch": 0.27639479543703765, "grad_norm": 0.1435546875, "learning_rate": 4.3209057422937274e-05, "loss": 1.4963270425796509, "step": 3274 }, { "epoch": 0.27647921657186875, "grad_norm": 0.146484375, "learning_rate": 4.320459639371699e-05, "loss": 1.6077682971954346, "step": 3275 }, { "epoch": 0.2765636377066999, "grad_norm": 0.1669921875, "learning_rate": 4.320013413018133e-05, "loss": 1.5833985805511475, "step": 3276 }, { "epoch": 0.276648058841531, "grad_norm": 0.1396484375, "learning_rate": 4.319567063263282e-05, "loss": 1.5472021102905273, "step": 3277 }, { "epoch": 0.2767324799763621, "grad_norm": 0.1435546875, "learning_rate": 4.319120590137411e-05, "loss": 1.528731346130371, "step": 3278 }, { "epoch": 0.27681690111119317, "grad_norm": 0.1328125, "learning_rate": 4.318673993670791e-05, "loss": 1.514371395111084, "step": 3279 }, { "epoch": 0.2769013222460243, "grad_norm": 0.1513671875, "learning_rate": 4.318227273893703e-05, "loss": 1.495383381843567, "step": 3280 }, { "epoch": 0.2769857433808554, "grad_norm": 0.1416015625, "learning_rate": 4.3177804308364346e-05, "loss": 1.502923607826233, "step": 3281 }, { "epoch": 0.2770701645156865, "grad_norm": 0.1435546875, "learning_rate": 4.317333464529284e-05, "loss": 1.506026029586792, "step": 3282 }, { "epoch": 0.2771545856505176, "grad_norm": 0.1513671875, "learning_rate": 4.316886375002557e-05, "loss": 1.5747185945510864, "step": 3283 }, { "epoch": 0.2772390067853487, "grad_norm": 0.1474609375, "learning_rate": 4.316439162286565e-05, "loss": 1.5820660591125488, "step": 3284 }, { "epoch": 0.27732342792017983, "grad_norm": 0.146484375, "learning_rate": 4.3159918264116334e-05, "loss": 1.5396957397460938, "step": 3285 }, { "epoch": 0.2774078490550109, "grad_norm": 0.1455078125, "learning_rate": 4.3155443674080896e-05, "loss": 1.5558637380599976, "step": 3286 }, { "epoch": 0.277492270189842, "grad_norm": 0.140625, "learning_rate": 4.315096785306275e-05, "loss": 1.549727201461792, "step": 3287 }, { "epoch": 0.2775766913246731, "grad_norm": 0.1484375, "learning_rate": 4.3146490801365346e-05, "loss": 1.4946272373199463, "step": 3288 }, { "epoch": 0.27766111245950426, "grad_norm": 0.138671875, "learning_rate": 4.314201251929224e-05, "loss": 1.5175848007202148, "step": 3289 }, { "epoch": 0.27774553359433535, "grad_norm": 0.13671875, "learning_rate": 4.313753300714709e-05, "loss": 1.4845550060272217, "step": 3290 }, { "epoch": 0.27782995472916644, "grad_norm": 0.138671875, "learning_rate": 4.31330522652336e-05, "loss": 1.4887820482254028, "step": 3291 }, { "epoch": 0.27791437586399753, "grad_norm": 0.1357421875, "learning_rate": 4.312857029385559e-05, "loss": 1.4985685348510742, "step": 3292 }, { "epoch": 0.2779987969988287, "grad_norm": 0.14453125, "learning_rate": 4.312408709331692e-05, "loss": 1.4407670497894287, "step": 3293 }, { "epoch": 0.27808321813365977, "grad_norm": 0.1484375, "learning_rate": 4.311960266392159e-05, "loss": 1.5931235551834106, "step": 3294 }, { "epoch": 0.27816763926849086, "grad_norm": 0.15234375, "learning_rate": 4.3115117005973645e-05, "loss": 1.5218621492385864, "step": 3295 }, { "epoch": 0.27825206040332195, "grad_norm": 0.1396484375, "learning_rate": 4.311063011977723e-05, "loss": 1.5397180318832397, "step": 3296 }, { "epoch": 0.2783364815381531, "grad_norm": 0.140625, "learning_rate": 4.310614200563655e-05, "loss": 1.5486977100372314, "step": 3297 }, { "epoch": 0.2784209026729842, "grad_norm": 0.1513671875, "learning_rate": 4.310165266385593e-05, "loss": 1.544451117515564, "step": 3298 }, { "epoch": 0.2785053238078153, "grad_norm": 0.1337890625, "learning_rate": 4.309716209473974e-05, "loss": 1.5328631401062012, "step": 3299 }, { "epoch": 0.2785897449426464, "grad_norm": 0.1640625, "learning_rate": 4.309267029859246e-05, "loss": 1.6095600128173828, "step": 3300 }, { "epoch": 0.27867416607747747, "grad_norm": 0.255859375, "learning_rate": 4.308817727571865e-05, "loss": 1.5158663988113403, "step": 3301 }, { "epoch": 0.2787585872123086, "grad_norm": 0.146484375, "learning_rate": 4.308368302642295e-05, "loss": 1.5093660354614258, "step": 3302 }, { "epoch": 0.2788430083471397, "grad_norm": 0.1259765625, "learning_rate": 4.307918755101007e-05, "loss": 1.4821027517318726, "step": 3303 }, { "epoch": 0.2789274294819708, "grad_norm": 0.146484375, "learning_rate": 4.3074690849784804e-05, "loss": 1.463047742843628, "step": 3304 }, { "epoch": 0.2790118506168019, "grad_norm": 0.1376953125, "learning_rate": 4.3070192923052065e-05, "loss": 1.4990928173065186, "step": 3305 }, { "epoch": 0.27909627175163304, "grad_norm": 0.146484375, "learning_rate": 4.3065693771116804e-05, "loss": 1.572582721710205, "step": 3306 }, { "epoch": 0.27918069288646413, "grad_norm": 0.146484375, "learning_rate": 4.306119339428408e-05, "loss": 1.5904561281204224, "step": 3307 }, { "epoch": 0.2792651140212952, "grad_norm": 0.14453125, "learning_rate": 4.305669179285904e-05, "loss": 1.5261529684066772, "step": 3308 }, { "epoch": 0.2793495351561263, "grad_norm": 0.1396484375, "learning_rate": 4.305218896714689e-05, "loss": 1.4659738540649414, "step": 3309 }, { "epoch": 0.27943395629095746, "grad_norm": 0.13671875, "learning_rate": 4.3047684917452936e-05, "loss": 1.5713589191436768, "step": 3310 }, { "epoch": 0.27951837742578856, "grad_norm": 0.1396484375, "learning_rate": 4.304317964408256e-05, "loss": 1.5080450773239136, "step": 3311 }, { "epoch": 0.27960279856061965, "grad_norm": 0.140625, "learning_rate": 4.303867314734124e-05, "loss": 1.5759508609771729, "step": 3312 }, { "epoch": 0.27968721969545074, "grad_norm": 0.158203125, "learning_rate": 4.303416542753451e-05, "loss": 1.5302314758300781, "step": 3313 }, { "epoch": 0.2797716408302819, "grad_norm": 0.1494140625, "learning_rate": 4.302965648496803e-05, "loss": 1.5619739294052124, "step": 3314 }, { "epoch": 0.279856061965113, "grad_norm": 0.1396484375, "learning_rate": 4.3025146319947494e-05, "loss": 1.5286307334899902, "step": 3315 }, { "epoch": 0.27994048309994407, "grad_norm": 0.1357421875, "learning_rate": 4.3020634932778715e-05, "loss": 1.514813780784607, "step": 3316 }, { "epoch": 0.28002490423477516, "grad_norm": 0.13671875, "learning_rate": 4.3016122323767566e-05, "loss": 1.5202492475509644, "step": 3317 }, { "epoch": 0.28010932536960625, "grad_norm": 0.1669921875, "learning_rate": 4.301160849322002e-05, "loss": 1.5861619710922241, "step": 3318 }, { "epoch": 0.2801937465044374, "grad_norm": 0.150390625, "learning_rate": 4.300709344144213e-05, "loss": 1.6221058368682861, "step": 3319 }, { "epoch": 0.2802781676392685, "grad_norm": 0.1376953125, "learning_rate": 4.300257716874001e-05, "loss": 1.472442865371704, "step": 3320 }, { "epoch": 0.2803625887740996, "grad_norm": 0.142578125, "learning_rate": 4.29980596754199e-05, "loss": 1.5481148958206177, "step": 3321 }, { "epoch": 0.2804470099089307, "grad_norm": 0.1513671875, "learning_rate": 4.2993540961788073e-05, "loss": 1.5906766653060913, "step": 3322 }, { "epoch": 0.2805314310437618, "grad_norm": 0.134765625, "learning_rate": 4.2989021028150925e-05, "loss": 1.472304105758667, "step": 3323 }, { "epoch": 0.2806158521785929, "grad_norm": 0.140625, "learning_rate": 4.29844998748149e-05, "loss": 1.5549029111862183, "step": 3324 }, { "epoch": 0.280700273313424, "grad_norm": 0.171875, "learning_rate": 4.297997750208656e-05, "loss": 1.5117546319961548, "step": 3325 }, { "epoch": 0.2807846944482551, "grad_norm": 0.138671875, "learning_rate": 4.2975453910272536e-05, "loss": 1.5487724542617798, "step": 3326 }, { "epoch": 0.28086911558308625, "grad_norm": 0.16015625, "learning_rate": 4.297092909967951e-05, "loss": 1.5475046634674072, "step": 3327 }, { "epoch": 0.28095353671791734, "grad_norm": 0.1318359375, "learning_rate": 4.2966403070614315e-05, "loss": 1.5691739320755005, "step": 3328 }, { "epoch": 0.28103795785274843, "grad_norm": 0.158203125, "learning_rate": 4.296187582338379e-05, "loss": 1.541808843612671, "step": 3329 }, { "epoch": 0.2811223789875795, "grad_norm": 0.15234375, "learning_rate": 4.295734735829492e-05, "loss": 1.4738667011260986, "step": 3330 }, { "epoch": 0.28120680012241067, "grad_norm": 0.140625, "learning_rate": 4.2952817675654736e-05, "loss": 1.5370821952819824, "step": 3331 }, { "epoch": 0.28129122125724176, "grad_norm": 0.1357421875, "learning_rate": 4.294828677577035e-05, "loss": 1.490538239479065, "step": 3332 }, { "epoch": 0.28137564239207286, "grad_norm": 0.1552734375, "learning_rate": 4.2943754658948984e-05, "loss": 1.586043119430542, "step": 3333 }, { "epoch": 0.28146006352690395, "grad_norm": 0.1416015625, "learning_rate": 4.2939221325497924e-05, "loss": 1.4962332248687744, "step": 3334 }, { "epoch": 0.28154448466173504, "grad_norm": 0.1435546875, "learning_rate": 4.293468677572454e-05, "loss": 1.5169419050216675, "step": 3335 }, { "epoch": 0.2816289057965662, "grad_norm": 0.13671875, "learning_rate": 4.293015100993628e-05, "loss": 1.5671513080596924, "step": 3336 }, { "epoch": 0.2817133269313973, "grad_norm": 0.1474609375, "learning_rate": 4.292561402844069e-05, "loss": 1.5330133438110352, "step": 3337 }, { "epoch": 0.28179774806622837, "grad_norm": 0.13671875, "learning_rate": 4.2921075831545366e-05, "loss": 1.5571460723876953, "step": 3338 }, { "epoch": 0.28188216920105946, "grad_norm": 0.1494140625, "learning_rate": 4.291653641955803e-05, "loss": 1.5912076234817505, "step": 3339 }, { "epoch": 0.2819665903358906, "grad_norm": 0.14453125, "learning_rate": 4.291199579278646e-05, "loss": 1.6318542957305908, "step": 3340 }, { "epoch": 0.2820510114707217, "grad_norm": 0.1318359375, "learning_rate": 4.290745395153853e-05, "loss": 1.483595609664917, "step": 3341 }, { "epoch": 0.2821354326055528, "grad_norm": 0.134765625, "learning_rate": 4.2902910896122165e-05, "loss": 1.5586549043655396, "step": 3342 }, { "epoch": 0.2822198537403839, "grad_norm": 0.1455078125, "learning_rate": 4.2898366626845414e-05, "loss": 1.557803988456726, "step": 3343 }, { "epoch": 0.28230427487521503, "grad_norm": 0.142578125, "learning_rate": 4.289382114401639e-05, "loss": 1.5162532329559326, "step": 3344 }, { "epoch": 0.2823886960100461, "grad_norm": 0.138671875, "learning_rate": 4.2889274447943276e-05, "loss": 1.5267882347106934, "step": 3345 }, { "epoch": 0.2824731171448772, "grad_norm": 0.1357421875, "learning_rate": 4.288472653893435e-05, "loss": 1.4818129539489746, "step": 3346 }, { "epoch": 0.2825575382797083, "grad_norm": 0.146484375, "learning_rate": 4.288017741729797e-05, "loss": 1.5769331455230713, "step": 3347 }, { "epoch": 0.28264195941453946, "grad_norm": 0.14453125, "learning_rate": 4.2875627083342594e-05, "loss": 1.5425103902816772, "step": 3348 }, { "epoch": 0.28272638054937055, "grad_norm": 0.138671875, "learning_rate": 4.287107553737673e-05, "loss": 1.5589336156845093, "step": 3349 }, { "epoch": 0.28281080168420164, "grad_norm": 0.1591796875, "learning_rate": 4.2866522779708994e-05, "loss": 1.5063306093215942, "step": 3350 }, { "epoch": 0.28289522281903273, "grad_norm": 0.1533203125, "learning_rate": 4.286196881064807e-05, "loss": 1.5160033702850342, "step": 3351 }, { "epoch": 0.2829796439538638, "grad_norm": 0.140625, "learning_rate": 4.285741363050271e-05, "loss": 1.55186927318573, "step": 3352 }, { "epoch": 0.28306406508869497, "grad_norm": 0.14453125, "learning_rate": 4.285285723958179e-05, "loss": 1.584434986114502, "step": 3353 }, { "epoch": 0.28314848622352606, "grad_norm": 0.1416015625, "learning_rate": 4.284829963819424e-05, "loss": 1.5405813455581665, "step": 3354 }, { "epoch": 0.28323290735835716, "grad_norm": 0.1376953125, "learning_rate": 4.284374082664907e-05, "loss": 1.5493417978286743, "step": 3355 }, { "epoch": 0.28331732849318825, "grad_norm": 0.138671875, "learning_rate": 4.2839180805255385e-05, "loss": 1.5507501363754272, "step": 3356 }, { "epoch": 0.2834017496280194, "grad_norm": 0.1416015625, "learning_rate": 4.2834619574322365e-05, "loss": 1.5542045831680298, "step": 3357 }, { "epoch": 0.2834861707628505, "grad_norm": 0.1396484375, "learning_rate": 4.283005713415926e-05, "loss": 1.5540025234222412, "step": 3358 }, { "epoch": 0.2835705918976816, "grad_norm": 0.134765625, "learning_rate": 4.282549348507543e-05, "loss": 1.507716178894043, "step": 3359 }, { "epoch": 0.28365501303251267, "grad_norm": 0.1318359375, "learning_rate": 4.282092862738029e-05, "loss": 1.46546471118927, "step": 3360 }, { "epoch": 0.2837394341673438, "grad_norm": 0.1494140625, "learning_rate": 4.281636256138335e-05, "loss": 1.4757541418075562, "step": 3361 }, { "epoch": 0.2838238553021749, "grad_norm": 0.1455078125, "learning_rate": 4.2811795287394215e-05, "loss": 1.501790165901184, "step": 3362 }, { "epoch": 0.283908276437006, "grad_norm": 0.15234375, "learning_rate": 4.280722680572253e-05, "loss": 1.5581777095794678, "step": 3363 }, { "epoch": 0.2839926975718371, "grad_norm": 0.15625, "learning_rate": 4.280265711667808e-05, "loss": 1.5398118495941162, "step": 3364 }, { "epoch": 0.28407711870666824, "grad_norm": 0.1337890625, "learning_rate": 4.2798086220570674e-05, "loss": 1.5132874250411987, "step": 3365 }, { "epoch": 0.28416153984149933, "grad_norm": 0.13671875, "learning_rate": 4.279351411771025e-05, "loss": 1.5275940895080566, "step": 3366 }, { "epoch": 0.2842459609763304, "grad_norm": 0.1396484375, "learning_rate": 4.27889408084068e-05, "loss": 1.5078964233398438, "step": 3367 }, { "epoch": 0.2843303821111615, "grad_norm": 0.1484375, "learning_rate": 4.27843662929704e-05, "loss": 1.525527834892273, "step": 3368 }, { "epoch": 0.2844148032459926, "grad_norm": 0.1533203125, "learning_rate": 4.2779790571711216e-05, "loss": 1.5520200729370117, "step": 3369 }, { "epoch": 0.28449922438082376, "grad_norm": 0.1513671875, "learning_rate": 4.277521364493949e-05, "loss": 1.5119574069976807, "step": 3370 }, { "epoch": 0.28458364551565485, "grad_norm": 0.1435546875, "learning_rate": 4.277063551296556e-05, "loss": 1.527243971824646, "step": 3371 }, { "epoch": 0.28466806665048594, "grad_norm": 0.154296875, "learning_rate": 4.276605617609983e-05, "loss": 1.6341590881347656, "step": 3372 }, { "epoch": 0.28475248778531703, "grad_norm": 0.14453125, "learning_rate": 4.2761475634652784e-05, "loss": 1.5342506170272827, "step": 3373 }, { "epoch": 0.2848369089201482, "grad_norm": 0.1357421875, "learning_rate": 4.275689388893499e-05, "loss": 1.5970215797424316, "step": 3374 }, { "epoch": 0.28492133005497927, "grad_norm": 0.15234375, "learning_rate": 4.275231093925711e-05, "loss": 1.461211085319519, "step": 3375 }, { "epoch": 0.28500575118981036, "grad_norm": 0.1357421875, "learning_rate": 4.274772678592989e-05, "loss": 1.557026982307434, "step": 3376 }, { "epoch": 0.28509017232464146, "grad_norm": 0.146484375, "learning_rate": 4.274314142926412e-05, "loss": 1.4089616537094116, "step": 3377 }, { "epoch": 0.2851745934594726, "grad_norm": 0.1357421875, "learning_rate": 4.273855486957072e-05, "loss": 1.506041407585144, "step": 3378 }, { "epoch": 0.2852590145943037, "grad_norm": 0.1572265625, "learning_rate": 4.2733967107160656e-05, "loss": 1.5410685539245605, "step": 3379 }, { "epoch": 0.2853434357291348, "grad_norm": 0.1533203125, "learning_rate": 4.2729378142345e-05, "loss": 1.512073278427124, "step": 3380 }, { "epoch": 0.2854278568639659, "grad_norm": 0.1357421875, "learning_rate": 4.272478797543489e-05, "loss": 1.5405133962631226, "step": 3381 }, { "epoch": 0.285512277998797, "grad_norm": 0.1484375, "learning_rate": 4.2720196606741545e-05, "loss": 1.5580034255981445, "step": 3382 }, { "epoch": 0.2855966991336281, "grad_norm": 0.138671875, "learning_rate": 4.2715604036576284e-05, "loss": 1.4991703033447266, "step": 3383 }, { "epoch": 0.2856811202684592, "grad_norm": 0.138671875, "learning_rate": 4.271101026525049e-05, "loss": 1.5705655813217163, "step": 3384 }, { "epoch": 0.2857655414032903, "grad_norm": 0.14453125, "learning_rate": 4.270641529307562e-05, "loss": 1.5700867176055908, "step": 3385 }, { "epoch": 0.2858499625381214, "grad_norm": 0.1455078125, "learning_rate": 4.270181912036323e-05, "loss": 1.5393168926239014, "step": 3386 }, { "epoch": 0.28593438367295254, "grad_norm": 0.1357421875, "learning_rate": 4.269722174742496e-05, "loss": 1.5042243003845215, "step": 3387 }, { "epoch": 0.28601880480778363, "grad_norm": 0.1484375, "learning_rate": 4.2692623174572516e-05, "loss": 1.5056179761886597, "step": 3388 }, { "epoch": 0.2861032259426147, "grad_norm": 0.146484375, "learning_rate": 4.2688023402117695e-05, "loss": 1.5399218797683716, "step": 3389 }, { "epoch": 0.2861876470774458, "grad_norm": 0.142578125, "learning_rate": 4.2683422430372364e-05, "loss": 1.539203405380249, "step": 3390 }, { "epoch": 0.28627206821227696, "grad_norm": 0.140625, "learning_rate": 4.267882025964849e-05, "loss": 1.4696019887924194, "step": 3391 }, { "epoch": 0.28635648934710806, "grad_norm": 0.1396484375, "learning_rate": 4.267421689025811e-05, "loss": 1.5498729944229126, "step": 3392 }, { "epoch": 0.28644091048193915, "grad_norm": 0.138671875, "learning_rate": 4.266961232251334e-05, "loss": 1.5174181461334229, "step": 3393 }, { "epoch": 0.28652533161677024, "grad_norm": 0.1337890625, "learning_rate": 4.2665006556726386e-05, "loss": 1.5041396617889404, "step": 3394 }, { "epoch": 0.2866097527516014, "grad_norm": 0.140625, "learning_rate": 4.266039959320952e-05, "loss": 1.5117249488830566, "step": 3395 }, { "epoch": 0.2866941738864325, "grad_norm": 0.1279296875, "learning_rate": 4.2655791432275114e-05, "loss": 1.5511616468429565, "step": 3396 }, { "epoch": 0.28677859502126357, "grad_norm": 0.1337890625, "learning_rate": 4.265118207423562e-05, "loss": 1.533453106880188, "step": 3397 }, { "epoch": 0.28686301615609466, "grad_norm": 0.1552734375, "learning_rate": 4.2646571519403544e-05, "loss": 1.5144436359405518, "step": 3398 }, { "epoch": 0.2869474372909258, "grad_norm": 0.1337890625, "learning_rate": 4.26419597680915e-05, "loss": 1.5016541481018066, "step": 3399 }, { "epoch": 0.2870318584257569, "grad_norm": 0.1337890625, "learning_rate": 4.263734682061218e-05, "loss": 1.4261800050735474, "step": 3400 }, { "epoch": 0.287116279560588, "grad_norm": 0.1337890625, "learning_rate": 4.263273267727835e-05, "loss": 1.552312970161438, "step": 3401 }, { "epoch": 0.2872007006954191, "grad_norm": 0.130859375, "learning_rate": 4.262811733840286e-05, "loss": 1.5345522165298462, "step": 3402 }, { "epoch": 0.2872851218302502, "grad_norm": 0.140625, "learning_rate": 4.2623500804298654e-05, "loss": 1.5858620405197144, "step": 3403 }, { "epoch": 0.2873695429650813, "grad_norm": 0.15625, "learning_rate": 4.261888307527872e-05, "loss": 1.5044236183166504, "step": 3404 }, { "epoch": 0.2874539640999124, "grad_norm": 0.1435546875, "learning_rate": 4.261426415165617e-05, "loss": 1.5515038967132568, "step": 3405 }, { "epoch": 0.2875383852347435, "grad_norm": 0.1396484375, "learning_rate": 4.2609644033744166e-05, "loss": 1.5182665586471558, "step": 3406 }, { "epoch": 0.2876228063695746, "grad_norm": 0.1279296875, "learning_rate": 4.260502272185597e-05, "loss": 1.5636858940124512, "step": 3407 }, { "epoch": 0.28770722750440575, "grad_norm": 0.154296875, "learning_rate": 4.260040021630491e-05, "loss": 1.4067851305007935, "step": 3408 }, { "epoch": 0.28779164863923684, "grad_norm": 0.140625, "learning_rate": 4.2595776517404415e-05, "loss": 1.6378620862960815, "step": 3409 }, { "epoch": 0.28787606977406793, "grad_norm": 0.15234375, "learning_rate": 4.2591151625467986e-05, "loss": 1.5915995836257935, "step": 3410 }, { "epoch": 0.287960490908899, "grad_norm": 0.1435546875, "learning_rate": 4.258652554080918e-05, "loss": 1.5813432931900024, "step": 3411 }, { "epoch": 0.2880449120437302, "grad_norm": 0.142578125, "learning_rate": 4.258189826374168e-05, "loss": 1.4479116201400757, "step": 3412 }, { "epoch": 0.28812933317856126, "grad_norm": 0.140625, "learning_rate": 4.257726979457922e-05, "loss": 1.5953264236450195, "step": 3413 }, { "epoch": 0.28821375431339236, "grad_norm": 0.1484375, "learning_rate": 4.2572640133635604e-05, "loss": 1.494275689125061, "step": 3414 }, { "epoch": 0.28829817544822345, "grad_norm": 0.142578125, "learning_rate": 4.256800928122475e-05, "loss": 1.6149420738220215, "step": 3415 }, { "epoch": 0.28838259658305454, "grad_norm": 0.150390625, "learning_rate": 4.256337723766065e-05, "loss": 1.5807746648788452, "step": 3416 }, { "epoch": 0.2884670177178857, "grad_norm": 0.1376953125, "learning_rate": 4.2558744003257347e-05, "loss": 1.617737889289856, "step": 3417 }, { "epoch": 0.2885514388527168, "grad_norm": 0.134765625, "learning_rate": 4.2554109578329e-05, "loss": 1.4643285274505615, "step": 3418 }, { "epoch": 0.28863585998754787, "grad_norm": 0.134765625, "learning_rate": 4.2549473963189824e-05, "loss": 1.4899588823318481, "step": 3419 }, { "epoch": 0.28872028112237896, "grad_norm": 0.140625, "learning_rate": 4.254483715815413e-05, "loss": 1.6055889129638672, "step": 3420 }, { "epoch": 0.2888047022572101, "grad_norm": 0.1533203125, "learning_rate": 4.254019916353631e-05, "loss": 1.5595195293426514, "step": 3421 }, { "epoch": 0.2888891233920412, "grad_norm": 0.1494140625, "learning_rate": 4.2535559979650816e-05, "loss": 1.6099951267242432, "step": 3422 }, { "epoch": 0.2889735445268723, "grad_norm": 0.1533203125, "learning_rate": 4.2530919606812216e-05, "loss": 1.5480765104293823, "step": 3423 }, { "epoch": 0.2890579656617034, "grad_norm": 0.146484375, "learning_rate": 4.252627804533513e-05, "loss": 1.5463451147079468, "step": 3424 }, { "epoch": 0.28914238679653453, "grad_norm": 0.1279296875, "learning_rate": 4.252163529553426e-05, "loss": 1.5237605571746826, "step": 3425 }, { "epoch": 0.2892268079313656, "grad_norm": 0.142578125, "learning_rate": 4.251699135772439e-05, "loss": 1.4505901336669922, "step": 3426 }, { "epoch": 0.2893112290661967, "grad_norm": 0.1376953125, "learning_rate": 4.2512346232220414e-05, "loss": 1.510286808013916, "step": 3427 }, { "epoch": 0.2893956502010278, "grad_norm": 0.1357421875, "learning_rate": 4.250769991933726e-05, "loss": 1.477885365486145, "step": 3428 }, { "epoch": 0.28948007133585896, "grad_norm": 0.1376953125, "learning_rate": 4.250305241938998e-05, "loss": 1.6037484407424927, "step": 3429 }, { "epoch": 0.28956449247069005, "grad_norm": 0.1455078125, "learning_rate": 4.249840373269367e-05, "loss": 1.5688345432281494, "step": 3430 }, { "epoch": 0.28964891360552114, "grad_norm": 0.142578125, "learning_rate": 4.249375385956352e-05, "loss": 1.502158522605896, "step": 3431 }, { "epoch": 0.28973333474035223, "grad_norm": 0.142578125, "learning_rate": 4.248910280031481e-05, "loss": 1.5424624681472778, "step": 3432 }, { "epoch": 0.2898177558751833, "grad_norm": 0.1435546875, "learning_rate": 4.24844505552629e-05, "loss": 1.6348061561584473, "step": 3433 }, { "epoch": 0.2899021770100145, "grad_norm": 0.13671875, "learning_rate": 4.247979712472321e-05, "loss": 1.5801984071731567, "step": 3434 }, { "epoch": 0.28998659814484556, "grad_norm": 0.16015625, "learning_rate": 4.2475142509011254e-05, "loss": 1.6011847257614136, "step": 3435 }, { "epoch": 0.29007101927967666, "grad_norm": 0.1357421875, "learning_rate": 4.247048670844264e-05, "loss": 1.492274284362793, "step": 3436 }, { "epoch": 0.29015544041450775, "grad_norm": 0.1396484375, "learning_rate": 4.246582972333303e-05, "loss": 1.476335048675537, "step": 3437 }, { "epoch": 0.2902398615493389, "grad_norm": 0.1435546875, "learning_rate": 4.246117155399818e-05, "loss": 1.5584319829940796, "step": 3438 }, { "epoch": 0.29032428268417, "grad_norm": 0.13671875, "learning_rate": 4.2456512200753926e-05, "loss": 1.535527229309082, "step": 3439 }, { "epoch": 0.2904087038190011, "grad_norm": 0.1416015625, "learning_rate": 4.245185166391619e-05, "loss": 1.5338695049285889, "step": 3440 }, { "epoch": 0.29049312495383217, "grad_norm": 0.1357421875, "learning_rate": 4.2447189943800965e-05, "loss": 1.5457967519760132, "step": 3441 }, { "epoch": 0.2905775460886633, "grad_norm": 0.1357421875, "learning_rate": 4.244252704072432e-05, "loss": 1.571255087852478, "step": 3442 }, { "epoch": 0.2906619672234944, "grad_norm": 0.146484375, "learning_rate": 4.243786295500242e-05, "loss": 1.5052671432495117, "step": 3443 }, { "epoch": 0.2907463883583255, "grad_norm": 0.1337890625, "learning_rate": 4.243319768695149e-05, "loss": 1.5362120866775513, "step": 3444 }, { "epoch": 0.2908308094931566, "grad_norm": 0.1455078125, "learning_rate": 4.2428531236887855e-05, "loss": 1.6049597263336182, "step": 3445 }, { "epoch": 0.29091523062798774, "grad_norm": 0.16796875, "learning_rate": 4.242386360512791e-05, "loss": 1.5355783700942993, "step": 3446 }, { "epoch": 0.29099965176281883, "grad_norm": 0.1572265625, "learning_rate": 4.2419194791988124e-05, "loss": 1.531184196472168, "step": 3447 }, { "epoch": 0.2910840728976499, "grad_norm": 0.1416015625, "learning_rate": 4.2414524797785074e-05, "loss": 1.5132986307144165, "step": 3448 }, { "epoch": 0.291168494032481, "grad_norm": 0.13671875, "learning_rate": 4.2409853622835374e-05, "loss": 1.5924986600875854, "step": 3449 }, { "epoch": 0.2912529151673121, "grad_norm": 0.140625, "learning_rate": 4.240518126745575e-05, "loss": 1.488810420036316, "step": 3450 }, { "epoch": 0.29133733630214326, "grad_norm": 0.15625, "learning_rate": 4.2400507731963014e-05, "loss": 1.5149767398834229, "step": 3451 }, { "epoch": 0.29142175743697435, "grad_norm": 0.146484375, "learning_rate": 4.2395833016674015e-05, "loss": 1.5404547452926636, "step": 3452 }, { "epoch": 0.29150617857180544, "grad_norm": 0.1376953125, "learning_rate": 4.2391157121905724e-05, "loss": 1.4947843551635742, "step": 3453 }, { "epoch": 0.29159059970663653, "grad_norm": 0.1376953125, "learning_rate": 4.238648004797518e-05, "loss": 1.4593782424926758, "step": 3454 }, { "epoch": 0.2916750208414677, "grad_norm": 0.1357421875, "learning_rate": 4.23818017951995e-05, "loss": 1.5195382833480835, "step": 3455 }, { "epoch": 0.2917594419762988, "grad_norm": 0.154296875, "learning_rate": 4.237712236389587e-05, "loss": 1.5246224403381348, "step": 3456 }, { "epoch": 0.29184386311112986, "grad_norm": 0.1357421875, "learning_rate": 4.237244175438159e-05, "loss": 1.5448154211044312, "step": 3457 }, { "epoch": 0.29192828424596096, "grad_norm": 0.1396484375, "learning_rate": 4.236775996697398e-05, "loss": 1.5607408285140991, "step": 3458 }, { "epoch": 0.2920127053807921, "grad_norm": 0.134765625, "learning_rate": 4.236307700199051e-05, "loss": 1.4864838123321533, "step": 3459 }, { "epoch": 0.2920971265156232, "grad_norm": 0.1435546875, "learning_rate": 4.235839285974868e-05, "loss": 1.529130220413208, "step": 3460 }, { "epoch": 0.2921815476504543, "grad_norm": 0.1484375, "learning_rate": 4.235370754056609e-05, "loss": 1.5766805410385132, "step": 3461 }, { "epoch": 0.2922659687852854, "grad_norm": 0.140625, "learning_rate": 4.234902104476042e-05, "loss": 1.5381395816802979, "step": 3462 }, { "epoch": 0.2923503899201165, "grad_norm": 0.1494140625, "learning_rate": 4.2344333372649425e-05, "loss": 1.5332790613174438, "step": 3463 }, { "epoch": 0.2924348110549476, "grad_norm": 0.1416015625, "learning_rate": 4.233964452455093e-05, "loss": 1.511338233947754, "step": 3464 }, { "epoch": 0.2925192321897787, "grad_norm": 0.1474609375, "learning_rate": 4.233495450078286e-05, "loss": 1.6087217330932617, "step": 3465 }, { "epoch": 0.2926036533246098, "grad_norm": 0.1728515625, "learning_rate": 4.233026330166321e-05, "loss": 1.5684725046157837, "step": 3466 }, { "epoch": 0.2926880744594409, "grad_norm": 0.1318359375, "learning_rate": 4.232557092751004e-05, "loss": 1.5494807958602905, "step": 3467 }, { "epoch": 0.29277249559427204, "grad_norm": 0.1318359375, "learning_rate": 4.232087737864152e-05, "loss": 1.5287258625030518, "step": 3468 }, { "epoch": 0.29285691672910313, "grad_norm": 0.1435546875, "learning_rate": 4.231618265537589e-05, "loss": 1.5082420110702515, "step": 3469 }, { "epoch": 0.2929413378639342, "grad_norm": 0.1494140625, "learning_rate": 4.2311486758031446e-05, "loss": 1.5451112985610962, "step": 3470 }, { "epoch": 0.2930257589987653, "grad_norm": 0.1416015625, "learning_rate": 4.2306789686926586e-05, "loss": 1.5294427871704102, "step": 3471 }, { "epoch": 0.29311018013359647, "grad_norm": 0.1455078125, "learning_rate": 4.2302091442379794e-05, "loss": 1.584989309310913, "step": 3472 }, { "epoch": 0.29319460126842756, "grad_norm": 0.142578125, "learning_rate": 4.22973920247096e-05, "loss": 1.5451240539550781, "step": 3473 }, { "epoch": 0.29327902240325865, "grad_norm": 0.142578125, "learning_rate": 4.2292691434234664e-05, "loss": 1.593315839767456, "step": 3474 }, { "epoch": 0.29336344353808974, "grad_norm": 0.1435546875, "learning_rate": 4.2287989671273674e-05, "loss": 1.555517315864563, "step": 3475 }, { "epoch": 0.2934478646729209, "grad_norm": 0.138671875, "learning_rate": 4.2283286736145435e-05, "loss": 1.4524130821228027, "step": 3476 }, { "epoch": 0.293532285807752, "grad_norm": 0.15625, "learning_rate": 4.2278582629168805e-05, "loss": 1.654733419418335, "step": 3477 }, { "epoch": 0.29361670694258307, "grad_norm": 0.140625, "learning_rate": 4.227387735066274e-05, "loss": 1.5044177770614624, "step": 3478 }, { "epoch": 0.29370112807741416, "grad_norm": 0.140625, "learning_rate": 4.226917090094627e-05, "loss": 1.5077428817749023, "step": 3479 }, { "epoch": 0.2937855492122453, "grad_norm": 0.1357421875, "learning_rate": 4.226446328033851e-05, "loss": 1.4823237657546997, "step": 3480 }, { "epoch": 0.2938699703470764, "grad_norm": 0.1357421875, "learning_rate": 4.2259754489158646e-05, "loss": 1.5848968029022217, "step": 3481 }, { "epoch": 0.2939543914819075, "grad_norm": 0.142578125, "learning_rate": 4.225504452772593e-05, "loss": 1.5657591819763184, "step": 3482 }, { "epoch": 0.2940388126167386, "grad_norm": 0.1611328125, "learning_rate": 4.225033339635972e-05, "loss": 1.6075177192687988, "step": 3483 }, { "epoch": 0.2941232337515697, "grad_norm": 0.1572265625, "learning_rate": 4.224562109537944e-05, "loss": 1.5537824630737305, "step": 3484 }, { "epoch": 0.2942076548864008, "grad_norm": 0.140625, "learning_rate": 4.2240907625104606e-05, "loss": 1.5591217279434204, "step": 3485 }, { "epoch": 0.2942920760212319, "grad_norm": 0.1396484375, "learning_rate": 4.223619298585478e-05, "loss": 1.5044455528259277, "step": 3486 }, { "epoch": 0.294376497156063, "grad_norm": 0.1318359375, "learning_rate": 4.223147717794965e-05, "loss": 1.4831877946853638, "step": 3487 }, { "epoch": 0.2944609182908941, "grad_norm": 0.1435546875, "learning_rate": 4.222676020170895e-05, "loss": 1.4699987173080444, "step": 3488 }, { "epoch": 0.29454533942572525, "grad_norm": 0.1328125, "learning_rate": 4.222204205745249e-05, "loss": 1.5531227588653564, "step": 3489 }, { "epoch": 0.29462976056055634, "grad_norm": 0.130859375, "learning_rate": 4.2217322745500185e-05, "loss": 1.5044989585876465, "step": 3490 }, { "epoch": 0.29471418169538743, "grad_norm": 0.14453125, "learning_rate": 4.221260226617202e-05, "loss": 1.5618348121643066, "step": 3491 }, { "epoch": 0.2947986028302185, "grad_norm": 0.154296875, "learning_rate": 4.2207880619788046e-05, "loss": 1.5271202325820923, "step": 3492 }, { "epoch": 0.2948830239650497, "grad_norm": 0.1435546875, "learning_rate": 4.220315780666839e-05, "loss": 1.5514723062515259, "step": 3493 }, { "epoch": 0.29496744509988077, "grad_norm": 0.1484375, "learning_rate": 4.21984338271333e-05, "loss": 1.6244328022003174, "step": 3494 }, { "epoch": 0.29505186623471186, "grad_norm": 0.134765625, "learning_rate": 4.2193708681503056e-05, "loss": 1.5949116945266724, "step": 3495 }, { "epoch": 0.29513628736954295, "grad_norm": 0.1474609375, "learning_rate": 4.218898237009803e-05, "loss": 1.5301752090454102, "step": 3496 }, { "epoch": 0.2952207085043741, "grad_norm": 0.1484375, "learning_rate": 4.2184254893238685e-05, "loss": 1.5052320957183838, "step": 3497 }, { "epoch": 0.2953051296392052, "grad_norm": 0.1435546875, "learning_rate": 4.217952625124555e-05, "loss": 1.6129292249679565, "step": 3498 }, { "epoch": 0.2953895507740363, "grad_norm": 0.1376953125, "learning_rate": 4.2174796444439235e-05, "loss": 1.4962522983551025, "step": 3499 }, { "epoch": 0.29547397190886737, "grad_norm": 0.1435546875, "learning_rate": 4.217006547314045e-05, "loss": 1.547381043434143, "step": 3500 }, { "epoch": 0.29555839304369846, "grad_norm": 0.1484375, "learning_rate": 4.2165333337669947e-05, "loss": 1.5497004985809326, "step": 3501 }, { "epoch": 0.2956428141785296, "grad_norm": 0.1533203125, "learning_rate": 4.216060003834859e-05, "loss": 1.5566096305847168, "step": 3502 }, { "epoch": 0.2957272353133607, "grad_norm": 0.134765625, "learning_rate": 4.2155865575497296e-05, "loss": 1.5458340644836426, "step": 3503 }, { "epoch": 0.2958116564481918, "grad_norm": 0.146484375, "learning_rate": 4.215112994943708e-05, "loss": 1.5413999557495117, "step": 3504 }, { "epoch": 0.2958960775830229, "grad_norm": 0.142578125, "learning_rate": 4.214639316048903e-05, "loss": 1.5647056102752686, "step": 3505 }, { "epoch": 0.29598049871785403, "grad_norm": 0.1416015625, "learning_rate": 4.2141655208974304e-05, "loss": 1.5009089708328247, "step": 3506 }, { "epoch": 0.2960649198526851, "grad_norm": 0.1650390625, "learning_rate": 4.213691609521415e-05, "loss": 1.593458890914917, "step": 3507 }, { "epoch": 0.2961493409875162, "grad_norm": 0.1328125, "learning_rate": 4.2132175819529904e-05, "loss": 1.5484892129898071, "step": 3508 }, { "epoch": 0.2962337621223473, "grad_norm": 0.1328125, "learning_rate": 4.2127434382242956e-05, "loss": 1.4946471452713013, "step": 3509 }, { "epoch": 0.29631818325717846, "grad_norm": 0.14453125, "learning_rate": 4.2122691783674786e-05, "loss": 1.6034072637557983, "step": 3510 }, { "epoch": 0.29640260439200955, "grad_norm": 0.1396484375, "learning_rate": 4.211794802414695e-05, "loss": 1.4987081289291382, "step": 3511 }, { "epoch": 0.29648702552684064, "grad_norm": 0.134765625, "learning_rate": 4.211320310398109e-05, "loss": 1.5320595502853394, "step": 3512 }, { "epoch": 0.29657144666167173, "grad_norm": 0.138671875, "learning_rate": 4.210845702349893e-05, "loss": 1.5901312828063965, "step": 3513 }, { "epoch": 0.2966558677965029, "grad_norm": 0.15625, "learning_rate": 4.210370978302226e-05, "loss": 1.4512712955474854, "step": 3514 }, { "epoch": 0.296740288931334, "grad_norm": 0.138671875, "learning_rate": 4.209896138287296e-05, "loss": 1.5341485738754272, "step": 3515 }, { "epoch": 0.29682471006616507, "grad_norm": 0.12890625, "learning_rate": 4.209421182337296e-05, "loss": 1.4737058877944946, "step": 3516 }, { "epoch": 0.29690913120099616, "grad_norm": 0.142578125, "learning_rate": 4.208946110484433e-05, "loss": 1.5233832597732544, "step": 3517 }, { "epoch": 0.29699355233582725, "grad_norm": 0.1513671875, "learning_rate": 4.2084709227609156e-05, "loss": 1.5837512016296387, "step": 3518 }, { "epoch": 0.2970779734706584, "grad_norm": 0.1435546875, "learning_rate": 4.207995619198962e-05, "loss": 1.516871690750122, "step": 3519 }, { "epoch": 0.2971623946054895, "grad_norm": 0.1396484375, "learning_rate": 4.2075201998308006e-05, "loss": 1.5695346593856812, "step": 3520 }, { "epoch": 0.2972468157403206, "grad_norm": 0.134765625, "learning_rate": 4.207044664688665e-05, "loss": 1.5148061513900757, "step": 3521 }, { "epoch": 0.29733123687515167, "grad_norm": 0.1484375, "learning_rate": 4.2065690138047985e-05, "loss": 1.6197630167007446, "step": 3522 }, { "epoch": 0.2974156580099828, "grad_norm": 0.1513671875, "learning_rate": 4.20609324721145e-05, "loss": 1.5459208488464355, "step": 3523 }, { "epoch": 0.2975000791448139, "grad_norm": 0.13671875, "learning_rate": 4.2056173649408795e-05, "loss": 1.5300414562225342, "step": 3524 }, { "epoch": 0.297584500279645, "grad_norm": 0.142578125, "learning_rate": 4.205141367025351e-05, "loss": 1.497201919555664, "step": 3525 }, { "epoch": 0.2976689214144761, "grad_norm": 0.140625, "learning_rate": 4.20466525349714e-05, "loss": 1.5549209117889404, "step": 3526 }, { "epoch": 0.29775334254930724, "grad_norm": 0.1337890625, "learning_rate": 4.204189024388526e-05, "loss": 1.5179122686386108, "step": 3527 }, { "epoch": 0.29783776368413833, "grad_norm": 0.1396484375, "learning_rate": 4.2037126797318004e-05, "loss": 1.521048665046692, "step": 3528 }, { "epoch": 0.2979221848189694, "grad_norm": 0.1396484375, "learning_rate": 4.20323621955926e-05, "loss": 1.5883095264434814, "step": 3529 }, { "epoch": 0.2980066059538005, "grad_norm": 0.1513671875, "learning_rate": 4.2027596439032104e-05, "loss": 1.5038254261016846, "step": 3530 }, { "epoch": 0.29809102708863167, "grad_norm": 0.1435546875, "learning_rate": 4.202282952795964e-05, "loss": 1.5769246816635132, "step": 3531 }, { "epoch": 0.29817544822346276, "grad_norm": 0.1396484375, "learning_rate": 4.201806146269841e-05, "loss": 1.5387706756591797, "step": 3532 }, { "epoch": 0.29825986935829385, "grad_norm": 0.1396484375, "learning_rate": 4.2013292243571715e-05, "loss": 1.5563063621520996, "step": 3533 }, { "epoch": 0.29834429049312494, "grad_norm": 0.1494140625, "learning_rate": 4.20085218709029e-05, "loss": 1.5490984916687012, "step": 3534 }, { "epoch": 0.29842871162795603, "grad_norm": 0.1376953125, "learning_rate": 4.200375034501543e-05, "loss": 1.6101757287979126, "step": 3535 }, { "epoch": 0.2985131327627872, "grad_norm": 0.146484375, "learning_rate": 4.199897766623281e-05, "loss": 1.5226861238479614, "step": 3536 }, { "epoch": 0.2985975538976183, "grad_norm": 0.154296875, "learning_rate": 4.199420383487864e-05, "loss": 1.5416089296340942, "step": 3537 }, { "epoch": 0.29868197503244936, "grad_norm": 0.1474609375, "learning_rate": 4.198942885127661e-05, "loss": 1.5866180658340454, "step": 3538 }, { "epoch": 0.29876639616728046, "grad_norm": 0.1435546875, "learning_rate": 4.1984652715750464e-05, "loss": 1.5777603387832642, "step": 3539 }, { "epoch": 0.2988508173021116, "grad_norm": 0.142578125, "learning_rate": 4.1979875428624034e-05, "loss": 1.5747870206832886, "step": 3540 }, { "epoch": 0.2989352384369427, "grad_norm": 0.1328125, "learning_rate": 4.1975096990221244e-05, "loss": 1.495003581047058, "step": 3541 }, { "epoch": 0.2990196595717738, "grad_norm": 0.14453125, "learning_rate": 4.197031740086607e-05, "loss": 1.456132411956787, "step": 3542 }, { "epoch": 0.2991040807066049, "grad_norm": 0.1494140625, "learning_rate": 4.196553666088258e-05, "loss": 1.4988727569580078, "step": 3543 }, { "epoch": 0.299188501841436, "grad_norm": 0.1337890625, "learning_rate": 4.1960754770594926e-05, "loss": 1.4766954183578491, "step": 3544 }, { "epoch": 0.2992729229762671, "grad_norm": 0.1474609375, "learning_rate": 4.1955971730327335e-05, "loss": 1.5269625186920166, "step": 3545 }, { "epoch": 0.2993573441110982, "grad_norm": 0.1396484375, "learning_rate": 4.19511875404041e-05, "loss": 1.4546891450881958, "step": 3546 }, { "epoch": 0.2994417652459293, "grad_norm": 0.1484375, "learning_rate": 4.1946402201149604e-05, "loss": 1.5451070070266724, "step": 3547 }, { "epoch": 0.29952618638076045, "grad_norm": 0.1455078125, "learning_rate": 4.194161571288831e-05, "loss": 1.5607249736785889, "step": 3548 }, { "epoch": 0.29961060751559154, "grad_norm": 0.1328125, "learning_rate": 4.193682807594475e-05, "loss": 1.5106066465377808, "step": 3549 }, { "epoch": 0.29969502865042263, "grad_norm": 0.1357421875, "learning_rate": 4.193203929064353e-05, "loss": 1.5501583814620972, "step": 3550 }, { "epoch": 0.2997794497852537, "grad_norm": 0.138671875, "learning_rate": 4.192724935730935e-05, "loss": 1.5663018226623535, "step": 3551 }, { "epoch": 0.2998638709200848, "grad_norm": 0.1396484375, "learning_rate": 4.1922458276266974e-05, "loss": 1.5897060632705688, "step": 3552 }, { "epoch": 0.29994829205491597, "grad_norm": 0.1416015625, "learning_rate": 4.1917666047841255e-05, "loss": 1.6340515613555908, "step": 3553 }, { "epoch": 0.30003271318974706, "grad_norm": 0.1337890625, "learning_rate": 4.191287267235711e-05, "loss": 1.4798450469970703, "step": 3554 }, { "epoch": 0.30011713432457815, "grad_norm": 0.1396484375, "learning_rate": 4.1908078150139544e-05, "loss": 1.6084603071212769, "step": 3555 }, { "epoch": 0.30020155545940924, "grad_norm": 0.1396484375, "learning_rate": 4.1903282481513626e-05, "loss": 1.597575068473816, "step": 3556 }, { "epoch": 0.3002859765942404, "grad_norm": 0.14453125, "learning_rate": 4.189848566680454e-05, "loss": 1.640531063079834, "step": 3557 }, { "epoch": 0.3003703977290715, "grad_norm": 0.1435546875, "learning_rate": 4.18936877063375e-05, "loss": 1.5565260648727417, "step": 3558 }, { "epoch": 0.3004548188639026, "grad_norm": 0.1376953125, "learning_rate": 4.1888888600437836e-05, "loss": 1.4974629878997803, "step": 3559 }, { "epoch": 0.30053923999873366, "grad_norm": 0.146484375, "learning_rate": 4.188408834943093e-05, "loss": 1.5697975158691406, "step": 3560 }, { "epoch": 0.3006236611335648, "grad_norm": 0.1435546875, "learning_rate": 4.187928695364224e-05, "loss": 1.656376600265503, "step": 3561 }, { "epoch": 0.3007080822683959, "grad_norm": 0.13671875, "learning_rate": 4.1874484413397333e-05, "loss": 1.6130492687225342, "step": 3562 }, { "epoch": 0.300792503403227, "grad_norm": 0.1484375, "learning_rate": 4.186968072902181e-05, "loss": 1.5529136657714844, "step": 3563 }, { "epoch": 0.3008769245380581, "grad_norm": 0.1474609375, "learning_rate": 4.186487590084139e-05, "loss": 1.599708914756775, "step": 3564 }, { "epoch": 0.30096134567288924, "grad_norm": 0.1455078125, "learning_rate": 4.1860069929181846e-05, "loss": 1.6120455265045166, "step": 3565 }, { "epoch": 0.3010457668077203, "grad_norm": 0.138671875, "learning_rate": 4.1855262814369034e-05, "loss": 1.5535757541656494, "step": 3566 }, { "epoch": 0.3011301879425514, "grad_norm": 0.150390625, "learning_rate": 4.185045455672889e-05, "loss": 1.4991804361343384, "step": 3567 }, { "epoch": 0.3012146090773825, "grad_norm": 0.1435546875, "learning_rate": 4.184564515658742e-05, "loss": 1.5252643823623657, "step": 3568 }, { "epoch": 0.3012990302122136, "grad_norm": 0.1337890625, "learning_rate": 4.184083461427072e-05, "loss": 1.539621353149414, "step": 3569 }, { "epoch": 0.30138345134704475, "grad_norm": 0.146484375, "learning_rate": 4.183602293010495e-05, "loss": 1.5247522592544556, "step": 3570 }, { "epoch": 0.30146787248187584, "grad_norm": 0.138671875, "learning_rate": 4.1831210104416354e-05, "loss": 1.5358757972717285, "step": 3571 }, { "epoch": 0.30155229361670693, "grad_norm": 0.1513671875, "learning_rate": 4.182639613753127e-05, "loss": 1.5996562242507935, "step": 3572 }, { "epoch": 0.301636714751538, "grad_norm": 0.142578125, "learning_rate": 4.182158102977607e-05, "loss": 1.5530697107315063, "step": 3573 }, { "epoch": 0.3017211358863692, "grad_norm": 0.1376953125, "learning_rate": 4.181676478147725e-05, "loss": 1.519075870513916, "step": 3574 }, { "epoch": 0.30180555702120027, "grad_norm": 0.1474609375, "learning_rate": 4.1811947392961346e-05, "loss": 1.5386121273040771, "step": 3575 }, { "epoch": 0.30188997815603136, "grad_norm": 0.140625, "learning_rate": 4.1807128864555e-05, "loss": 1.5363507270812988, "step": 3576 }, { "epoch": 0.30197439929086245, "grad_norm": 0.1396484375, "learning_rate": 4.1802309196584925e-05, "loss": 1.4948744773864746, "step": 3577 }, { "epoch": 0.3020588204256936, "grad_norm": 0.1484375, "learning_rate": 4.179748838937789e-05, "loss": 1.5771673917770386, "step": 3578 }, { "epoch": 0.3021432415605247, "grad_norm": 0.1455078125, "learning_rate": 4.1792666443260775e-05, "loss": 1.544893741607666, "step": 3579 }, { "epoch": 0.3022276626953558, "grad_norm": 0.1416015625, "learning_rate": 4.1787843358560516e-05, "loss": 1.5748813152313232, "step": 3580 }, { "epoch": 0.3023120838301869, "grad_norm": 0.1396484375, "learning_rate": 4.1783019135604115e-05, "loss": 1.4966230392456055, "step": 3581 }, { "epoch": 0.30239650496501796, "grad_norm": 0.140625, "learning_rate": 4.1778193774718675e-05, "loss": 1.5310180187225342, "step": 3582 }, { "epoch": 0.3024809260998491, "grad_norm": 0.1494140625, "learning_rate": 4.177336727623137e-05, "loss": 1.5751267671585083, "step": 3583 }, { "epoch": 0.3025653472346802, "grad_norm": 0.1376953125, "learning_rate": 4.1768539640469447e-05, "loss": 1.5502301454544067, "step": 3584 }, { "epoch": 0.3026497683695113, "grad_norm": 0.1337890625, "learning_rate": 4.176371086776023e-05, "loss": 1.5951168537139893, "step": 3585 }, { "epoch": 0.3027341895043424, "grad_norm": 0.1435546875, "learning_rate": 4.175888095843112e-05, "loss": 1.6033014059066772, "step": 3586 }, { "epoch": 0.30281861063917354, "grad_norm": 0.1376953125, "learning_rate": 4.17540499128096e-05, "loss": 1.5047131776809692, "step": 3587 }, { "epoch": 0.3029030317740046, "grad_norm": 0.140625, "learning_rate": 4.174921773122322e-05, "loss": 1.5217931270599365, "step": 3588 }, { "epoch": 0.3029874529088357, "grad_norm": 0.1513671875, "learning_rate": 4.1744384413999614e-05, "loss": 1.5352771282196045, "step": 3589 }, { "epoch": 0.3030718740436668, "grad_norm": 0.1416015625, "learning_rate": 4.1739549961466505e-05, "loss": 1.5598071813583374, "step": 3590 }, { "epoch": 0.30315629517849796, "grad_norm": 0.1357421875, "learning_rate": 4.173471437395168e-05, "loss": 1.4892770051956177, "step": 3591 }, { "epoch": 0.30324071631332905, "grad_norm": 0.1376953125, "learning_rate": 4.1729877651782975e-05, "loss": 1.5696840286254883, "step": 3592 }, { "epoch": 0.30332513744816014, "grad_norm": 0.140625, "learning_rate": 4.1725039795288366e-05, "loss": 1.5074743032455444, "step": 3593 }, { "epoch": 0.30340955858299123, "grad_norm": 0.1396484375, "learning_rate": 4.1720200804795853e-05, "loss": 1.562816858291626, "step": 3594 }, { "epoch": 0.3034939797178224, "grad_norm": 0.1494140625, "learning_rate": 4.171536068063354e-05, "loss": 1.581425666809082, "step": 3595 }, { "epoch": 0.3035784008526535, "grad_norm": 0.13671875, "learning_rate": 4.171051942312959e-05, "loss": 1.5971516370773315, "step": 3596 }, { "epoch": 0.30366282198748457, "grad_norm": 0.1494140625, "learning_rate": 4.170567703261226e-05, "loss": 1.4877147674560547, "step": 3597 }, { "epoch": 0.30374724312231566, "grad_norm": 0.130859375, "learning_rate": 4.1700833509409866e-05, "loss": 1.494905948638916, "step": 3598 }, { "epoch": 0.30383166425714675, "grad_norm": 0.1357421875, "learning_rate": 4.169598885385082e-05, "loss": 1.5624899864196777, "step": 3599 }, { "epoch": 0.3039160853919779, "grad_norm": 0.13671875, "learning_rate": 4.169114306626359e-05, "loss": 1.6306043863296509, "step": 3600 }, { "epoch": 0.304000506526809, "grad_norm": 0.146484375, "learning_rate": 4.168629614697675e-05, "loss": 1.5696660280227661, "step": 3601 }, { "epoch": 0.3040849276616401, "grad_norm": 0.1494140625, "learning_rate": 4.1681448096318924e-05, "loss": 1.6076699495315552, "step": 3602 }, { "epoch": 0.3041693487964712, "grad_norm": 0.138671875, "learning_rate": 4.167659891461881e-05, "loss": 1.4219765663146973, "step": 3603 }, { "epoch": 0.3042537699313023, "grad_norm": 0.1396484375, "learning_rate": 4.167174860220522e-05, "loss": 1.4948679208755493, "step": 3604 }, { "epoch": 0.3043381910661334, "grad_norm": 0.1396484375, "learning_rate": 4.1666897159406984e-05, "loss": 1.5673315525054932, "step": 3605 }, { "epoch": 0.3044226122009645, "grad_norm": 0.13671875, "learning_rate": 4.1662044586553066e-05, "loss": 1.5256695747375488, "step": 3606 }, { "epoch": 0.3045070333357956, "grad_norm": 0.138671875, "learning_rate": 4.165719088397247e-05, "loss": 1.5047577619552612, "step": 3607 }, { "epoch": 0.30459145447062674, "grad_norm": 0.1513671875, "learning_rate": 4.1652336051994304e-05, "loss": 1.555221438407898, "step": 3608 }, { "epoch": 0.30467587560545784, "grad_norm": 0.1513671875, "learning_rate": 4.164748009094772e-05, "loss": 1.5267975330352783, "step": 3609 }, { "epoch": 0.3047602967402889, "grad_norm": 0.154296875, "learning_rate": 4.1642623001161976e-05, "loss": 1.5004403591156006, "step": 3610 }, { "epoch": 0.30484471787512, "grad_norm": 0.1279296875, "learning_rate": 4.163776478296638e-05, "loss": 1.5228300094604492, "step": 3611 }, { "epoch": 0.30492913900995117, "grad_norm": 0.1396484375, "learning_rate": 4.163290543669035e-05, "loss": 1.4965391159057617, "step": 3612 }, { "epoch": 0.30501356014478226, "grad_norm": 0.150390625, "learning_rate": 4.162804496266334e-05, "loss": 1.6282299757003784, "step": 3613 }, { "epoch": 0.30509798127961335, "grad_norm": 0.1357421875, "learning_rate": 4.162318336121492e-05, "loss": 1.5184258222579956, "step": 3614 }, { "epoch": 0.30518240241444444, "grad_norm": 0.1455078125, "learning_rate": 4.1618320632674715e-05, "loss": 1.5066964626312256, "step": 3615 }, { "epoch": 0.30526682354927553, "grad_norm": 0.1494140625, "learning_rate": 4.161345677737242e-05, "loss": 1.6085929870605469, "step": 3616 }, { "epoch": 0.3053512446841067, "grad_norm": 0.166015625, "learning_rate": 4.1608591795637816e-05, "loss": 1.497205138206482, "step": 3617 }, { "epoch": 0.3054356658189378, "grad_norm": 0.1337890625, "learning_rate": 4.160372568780077e-05, "loss": 1.531397819519043, "step": 3618 }, { "epoch": 0.30552008695376887, "grad_norm": 0.1416015625, "learning_rate": 4.159885845419122e-05, "loss": 1.5550661087036133, "step": 3619 }, { "epoch": 0.30560450808859996, "grad_norm": 0.142578125, "learning_rate": 4.159399009513917e-05, "loss": 1.5717415809631348, "step": 3620 }, { "epoch": 0.3056889292234311, "grad_norm": 0.1513671875, "learning_rate": 4.1589120610974697e-05, "loss": 1.5656102895736694, "step": 3621 }, { "epoch": 0.3057733503582622, "grad_norm": 0.1396484375, "learning_rate": 4.158425000202797e-05, "loss": 1.4905855655670166, "step": 3622 }, { "epoch": 0.3058577714930933, "grad_norm": 0.14453125, "learning_rate": 4.157937826862923e-05, "loss": 1.5390400886535645, "step": 3623 }, { "epoch": 0.3059421926279244, "grad_norm": 0.13671875, "learning_rate": 4.1574505411108796e-05, "loss": 1.484196424484253, "step": 3624 }, { "epoch": 0.30602661376275553, "grad_norm": 0.1455078125, "learning_rate": 4.1569631429797054e-05, "loss": 1.4656251668930054, "step": 3625 }, { "epoch": 0.3061110348975866, "grad_norm": 0.126953125, "learning_rate": 4.156475632502448e-05, "loss": 1.4623247385025024, "step": 3626 }, { "epoch": 0.3061954560324177, "grad_norm": 0.15625, "learning_rate": 4.15598800971216e-05, "loss": 1.473431944847107, "step": 3627 }, { "epoch": 0.3062798771672488, "grad_norm": 0.1484375, "learning_rate": 4.155500274641905e-05, "loss": 1.5045641660690308, "step": 3628 }, { "epoch": 0.30636429830207995, "grad_norm": 0.1328125, "learning_rate": 4.1550124273247516e-05, "loss": 1.4933561086654663, "step": 3629 }, { "epoch": 0.30644871943691104, "grad_norm": 0.154296875, "learning_rate": 4.154524467793778e-05, "loss": 1.5181849002838135, "step": 3630 }, { "epoch": 0.30653314057174214, "grad_norm": 0.140625, "learning_rate": 4.154036396082068e-05, "loss": 1.5285885334014893, "step": 3631 }, { "epoch": 0.3066175617065732, "grad_norm": 0.1376953125, "learning_rate": 4.1535482122227145e-05, "loss": 1.4809883832931519, "step": 3632 }, { "epoch": 0.3067019828414043, "grad_norm": 0.1396484375, "learning_rate": 4.153059916248818e-05, "loss": 1.5853439569473267, "step": 3633 }, { "epoch": 0.30678640397623547, "grad_norm": 0.1591796875, "learning_rate": 4.1525715081934855e-05, "loss": 1.448307752609253, "step": 3634 }, { "epoch": 0.30687082511106656, "grad_norm": 0.1357421875, "learning_rate": 4.152082988089834e-05, "loss": 1.523160696029663, "step": 3635 }, { "epoch": 0.30695524624589765, "grad_norm": 0.140625, "learning_rate": 4.151594355970982e-05, "loss": 1.5446631908416748, "step": 3636 }, { "epoch": 0.30703966738072874, "grad_norm": 0.1318359375, "learning_rate": 4.151105611870065e-05, "loss": 1.5288581848144531, "step": 3637 }, { "epoch": 0.3071240885155599, "grad_norm": 0.15625, "learning_rate": 4.150616755820218e-05, "loss": 1.5484974384307861, "step": 3638 }, { "epoch": 0.307208509650391, "grad_norm": 0.13671875, "learning_rate": 4.150127787854588e-05, "loss": 1.4626859426498413, "step": 3639 }, { "epoch": 0.3072929307852221, "grad_norm": 0.1357421875, "learning_rate": 4.149638708006327e-05, "loss": 1.4794508218765259, "step": 3640 }, { "epoch": 0.30737735192005317, "grad_norm": 0.1435546875, "learning_rate": 4.1491495163085955e-05, "loss": 1.5659663677215576, "step": 3641 }, { "epoch": 0.3074617730548843, "grad_norm": 0.14453125, "learning_rate": 4.1486602127945644e-05, "loss": 1.561874270439148, "step": 3642 }, { "epoch": 0.3075461941897154, "grad_norm": 0.140625, "learning_rate": 4.1481707974974074e-05, "loss": 1.5427865982055664, "step": 3643 }, { "epoch": 0.3076306153245465, "grad_norm": 0.138671875, "learning_rate": 4.147681270450309e-05, "loss": 1.6300748586654663, "step": 3644 }, { "epoch": 0.3077150364593776, "grad_norm": 0.142578125, "learning_rate": 4.147191631686459e-05, "loss": 1.5565530061721802, "step": 3645 }, { "epoch": 0.30779945759420874, "grad_norm": 0.1337890625, "learning_rate": 4.146701881239058e-05, "loss": 1.589907169342041, "step": 3646 }, { "epoch": 0.30788387872903983, "grad_norm": 0.1416015625, "learning_rate": 4.1462120191413114e-05, "loss": 1.5178654193878174, "step": 3647 }, { "epoch": 0.3079682998638709, "grad_norm": 0.1328125, "learning_rate": 4.145722045426432e-05, "loss": 1.5477043390274048, "step": 3648 }, { "epoch": 0.308052720998702, "grad_norm": 0.1611328125, "learning_rate": 4.145231960127642e-05, "loss": 1.5012829303741455, "step": 3649 }, { "epoch": 0.3081371421335331, "grad_norm": 0.138671875, "learning_rate": 4.1447417632781715e-05, "loss": 1.4765124320983887, "step": 3650 }, { "epoch": 0.30822156326836425, "grad_norm": 0.1513671875, "learning_rate": 4.1442514549112554e-05, "loss": 1.6136149168014526, "step": 3651 }, { "epoch": 0.30830598440319534, "grad_norm": 0.1533203125, "learning_rate": 4.143761035060139e-05, "loss": 1.4851518869400024, "step": 3652 }, { "epoch": 0.30839040553802644, "grad_norm": 0.140625, "learning_rate": 4.1432705037580725e-05, "loss": 1.469470500946045, "step": 3653 }, { "epoch": 0.3084748266728575, "grad_norm": 0.13671875, "learning_rate": 4.142779861038316e-05, "loss": 1.61003839969635, "step": 3654 }, { "epoch": 0.3085592478076887, "grad_norm": 0.1484375, "learning_rate": 4.142289106934137e-05, "loss": 1.553074836730957, "step": 3655 }, { "epoch": 0.30864366894251977, "grad_norm": 0.1318359375, "learning_rate": 4.141798241478809e-05, "loss": 1.4956413507461548, "step": 3656 }, { "epoch": 0.30872809007735086, "grad_norm": 0.138671875, "learning_rate": 4.141307264705613e-05, "loss": 1.4932459592819214, "step": 3657 }, { "epoch": 0.30881251121218195, "grad_norm": 0.142578125, "learning_rate": 4.14081617664784e-05, "loss": 1.5479326248168945, "step": 3658 }, { "epoch": 0.3088969323470131, "grad_norm": 0.1455078125, "learning_rate": 4.1403249773387855e-05, "loss": 1.503087043762207, "step": 3659 }, { "epoch": 0.3089813534818442, "grad_norm": 0.1298828125, "learning_rate": 4.139833666811756e-05, "loss": 1.5323642492294312, "step": 3660 }, { "epoch": 0.3090657746166753, "grad_norm": 0.14453125, "learning_rate": 4.139342245100061e-05, "loss": 1.6208336353302002, "step": 3661 }, { "epoch": 0.3091501957515064, "grad_norm": 0.1376953125, "learning_rate": 4.138850712237021e-05, "loss": 1.4568427801132202, "step": 3662 }, { "epoch": 0.3092346168863375, "grad_norm": 0.1376953125, "learning_rate": 4.138359068255964e-05, "loss": 1.578378677368164, "step": 3663 }, { "epoch": 0.3093190380211686, "grad_norm": 0.1455078125, "learning_rate": 4.1378673131902244e-05, "loss": 1.589228630065918, "step": 3664 }, { "epoch": 0.3094034591559997, "grad_norm": 0.1337890625, "learning_rate": 4.137375447073144e-05, "loss": 1.5745943784713745, "step": 3665 }, { "epoch": 0.3094878802908308, "grad_norm": 0.1337890625, "learning_rate": 4.136883469938072e-05, "loss": 1.5125768184661865, "step": 3666 }, { "epoch": 0.3095723014256619, "grad_norm": 0.1396484375, "learning_rate": 4.136391381818368e-05, "loss": 1.5229209661483765, "step": 3667 }, { "epoch": 0.30965672256049304, "grad_norm": 0.138671875, "learning_rate": 4.1358991827473923e-05, "loss": 1.473861575126648, "step": 3668 }, { "epoch": 0.30974114369532413, "grad_norm": 0.1484375, "learning_rate": 4.135406872758522e-05, "loss": 1.4960845708847046, "step": 3669 }, { "epoch": 0.3098255648301552, "grad_norm": 0.146484375, "learning_rate": 4.134914451885133e-05, "loss": 1.5140695571899414, "step": 3670 }, { "epoch": 0.3099099859649863, "grad_norm": 0.1357421875, "learning_rate": 4.134421920160615e-05, "loss": 1.531445026397705, "step": 3671 }, { "epoch": 0.30999440709981746, "grad_norm": 0.1337890625, "learning_rate": 4.1339292776183626e-05, "loss": 1.559500813484192, "step": 3672 }, { "epoch": 0.31007882823464855, "grad_norm": 0.1669921875, "learning_rate": 4.133436524291777e-05, "loss": 1.5434216260910034, "step": 3673 }, { "epoch": 0.31016324936947964, "grad_norm": 0.1279296875, "learning_rate": 4.1329436602142694e-05, "loss": 1.4960695505142212, "step": 3674 }, { "epoch": 0.31024767050431074, "grad_norm": 0.138671875, "learning_rate": 4.132450685419257e-05, "loss": 1.476182222366333, "step": 3675 }, { "epoch": 0.3103320916391419, "grad_norm": 0.140625, "learning_rate": 4.131957599940163e-05, "loss": 1.4704939126968384, "step": 3676 }, { "epoch": 0.310416512773973, "grad_norm": 0.146484375, "learning_rate": 4.131464403810422e-05, "loss": 1.4860936403274536, "step": 3677 }, { "epoch": 0.31050093390880407, "grad_norm": 0.1513671875, "learning_rate": 4.130971097063472e-05, "loss": 1.5504368543624878, "step": 3678 }, { "epoch": 0.31058535504363516, "grad_norm": 0.1357421875, "learning_rate": 4.130477679732762e-05, "loss": 1.5413610935211182, "step": 3679 }, { "epoch": 0.3106697761784663, "grad_norm": 0.140625, "learning_rate": 4.1299841518517466e-05, "loss": 1.5458275079727173, "step": 3680 }, { "epoch": 0.3107541973132974, "grad_norm": 0.1376953125, "learning_rate": 4.129490513453886e-05, "loss": 1.5882580280303955, "step": 3681 }, { "epoch": 0.3108386184481285, "grad_norm": 0.1318359375, "learning_rate": 4.128996764572654e-05, "loss": 1.5472185611724854, "step": 3682 }, { "epoch": 0.3109230395829596, "grad_norm": 0.1728515625, "learning_rate": 4.128502905241524e-05, "loss": 1.4584598541259766, "step": 3683 }, { "epoch": 0.3110074607177907, "grad_norm": 0.1474609375, "learning_rate": 4.1280089354939834e-05, "loss": 1.6955280303955078, "step": 3684 }, { "epoch": 0.3110918818526218, "grad_norm": 0.1494140625, "learning_rate": 4.127514855363524e-05, "loss": 1.5265971422195435, "step": 3685 }, { "epoch": 0.3111763029874529, "grad_norm": 0.146484375, "learning_rate": 4.1270206648836446e-05, "loss": 1.5641891956329346, "step": 3686 }, { "epoch": 0.311260724122284, "grad_norm": 0.1455078125, "learning_rate": 4.1265263640878536e-05, "loss": 1.511520504951477, "step": 3687 }, { "epoch": 0.3113451452571151, "grad_norm": 0.1513671875, "learning_rate": 4.126031953009666e-05, "loss": 1.5366251468658447, "step": 3688 }, { "epoch": 0.31142956639194624, "grad_norm": 0.140625, "learning_rate": 4.1255374316826033e-05, "loss": 1.5291379690170288, "step": 3689 }, { "epoch": 0.31151398752677734, "grad_norm": 0.2294921875, "learning_rate": 4.1250428001401945e-05, "loss": 1.5562925338745117, "step": 3690 }, { "epoch": 0.31159840866160843, "grad_norm": 0.1455078125, "learning_rate": 4.124548058415979e-05, "loss": 1.5949697494506836, "step": 3691 }, { "epoch": 0.3116828297964395, "grad_norm": 0.138671875, "learning_rate": 4.1240532065435e-05, "loss": 1.4975967407226562, "step": 3692 }, { "epoch": 0.31176725093127067, "grad_norm": 0.140625, "learning_rate": 4.1235582445563094e-05, "loss": 1.5106375217437744, "step": 3693 }, { "epoch": 0.31185167206610176, "grad_norm": 0.140625, "learning_rate": 4.123063172487968e-05, "loss": 1.5458682775497437, "step": 3694 }, { "epoch": 0.31193609320093285, "grad_norm": 0.1376953125, "learning_rate": 4.122567990372041e-05, "loss": 1.52436363697052, "step": 3695 }, { "epoch": 0.31202051433576394, "grad_norm": 0.1337890625, "learning_rate": 4.122072698242105e-05, "loss": 1.6025927066802979, "step": 3696 }, { "epoch": 0.3121049354705951, "grad_norm": 0.1533203125, "learning_rate": 4.1215772961317414e-05, "loss": 1.568768858909607, "step": 3697 }, { "epoch": 0.3121893566054262, "grad_norm": 0.1435546875, "learning_rate": 4.121081784074538e-05, "loss": 1.580678939819336, "step": 3698 }, { "epoch": 0.3122737777402573, "grad_norm": 0.138671875, "learning_rate": 4.120586162104094e-05, "loss": 1.5438470840454102, "step": 3699 }, { "epoch": 0.31235819887508837, "grad_norm": 0.1357421875, "learning_rate": 4.1200904302540136e-05, "loss": 1.501114845275879, "step": 3700 }, { "epoch": 0.31244262000991946, "grad_norm": 0.1337890625, "learning_rate": 4.1195945885579065e-05, "loss": 1.4780516624450684, "step": 3701 }, { "epoch": 0.3125270411447506, "grad_norm": 0.1396484375, "learning_rate": 4.119098637049395e-05, "loss": 1.6010627746582031, "step": 3702 }, { "epoch": 0.3126114622795817, "grad_norm": 0.1484375, "learning_rate": 4.118602575762102e-05, "loss": 1.534578800201416, "step": 3703 }, { "epoch": 0.3126958834144128, "grad_norm": 0.142578125, "learning_rate": 4.1181064047296645e-05, "loss": 1.5341060161590576, "step": 3704 }, { "epoch": 0.3127803045492439, "grad_norm": 0.1337890625, "learning_rate": 4.1176101239857237e-05, "loss": 1.4992775917053223, "step": 3705 }, { "epoch": 0.31286472568407503, "grad_norm": 0.140625, "learning_rate": 4.117113733563928e-05, "loss": 1.4521691799163818, "step": 3706 }, { "epoch": 0.3129491468189061, "grad_norm": 0.13671875, "learning_rate": 4.116617233497935e-05, "loss": 1.5156699419021606, "step": 3707 }, { "epoch": 0.3130335679537372, "grad_norm": 0.1533203125, "learning_rate": 4.116120623821406e-05, "loss": 1.523995280265808, "step": 3708 }, { "epoch": 0.3131179890885683, "grad_norm": 0.1396484375, "learning_rate": 4.115623904568016e-05, "loss": 1.5142550468444824, "step": 3709 }, { "epoch": 0.31320241022339945, "grad_norm": 0.140625, "learning_rate": 4.1151270757714405e-05, "loss": 1.5664023160934448, "step": 3710 }, { "epoch": 0.31328683135823054, "grad_norm": 0.134765625, "learning_rate": 4.1146301374653676e-05, "loss": 1.5157281160354614, "step": 3711 }, { "epoch": 0.31337125249306164, "grad_norm": 0.14453125, "learning_rate": 4.1141330896834894e-05, "loss": 1.551013708114624, "step": 3712 }, { "epoch": 0.31345567362789273, "grad_norm": 0.134765625, "learning_rate": 4.113635932459508e-05, "loss": 1.4552435874938965, "step": 3713 }, { "epoch": 0.3135400947627239, "grad_norm": 0.1298828125, "learning_rate": 4.113138665827133e-05, "loss": 1.4560168981552124, "step": 3714 }, { "epoch": 0.31362451589755497, "grad_norm": 0.181640625, "learning_rate": 4.1126412898200784e-05, "loss": 1.484060525894165, "step": 3715 }, { "epoch": 0.31370893703238606, "grad_norm": 0.1591796875, "learning_rate": 4.112143804472068e-05, "loss": 1.5588905811309814, "step": 3716 }, { "epoch": 0.31379335816721715, "grad_norm": 0.1435546875, "learning_rate": 4.111646209816833e-05, "loss": 1.5551851987838745, "step": 3717 }, { "epoch": 0.31387777930204824, "grad_norm": 0.1455078125, "learning_rate": 4.11114850588811e-05, "loss": 1.5445821285247803, "step": 3718 }, { "epoch": 0.3139622004368794, "grad_norm": 0.1591796875, "learning_rate": 4.1106506927196464e-05, "loss": 1.5264365673065186, "step": 3719 }, { "epoch": 0.3140466215717105, "grad_norm": 0.15625, "learning_rate": 4.1101527703451945e-05, "loss": 1.5105564594268799, "step": 3720 }, { "epoch": 0.3141310427065416, "grad_norm": 0.1455078125, "learning_rate": 4.109654738798513e-05, "loss": 1.508318305015564, "step": 3721 }, { "epoch": 0.31421546384137267, "grad_norm": 0.1416015625, "learning_rate": 4.109156598113373e-05, "loss": 1.5122743844985962, "step": 3722 }, { "epoch": 0.3142998849762038, "grad_norm": 0.1494140625, "learning_rate": 4.108658348323547e-05, "loss": 1.5961308479309082, "step": 3723 }, { "epoch": 0.3143843061110349, "grad_norm": 0.1572265625, "learning_rate": 4.108159989462818e-05, "loss": 1.5287365913391113, "step": 3724 }, { "epoch": 0.314468727245866, "grad_norm": 0.1416015625, "learning_rate": 4.1076615215649764e-05, "loss": 1.6013538837432861, "step": 3725 }, { "epoch": 0.3145531483806971, "grad_norm": 0.1337890625, "learning_rate": 4.107162944663819e-05, "loss": 1.5087984800338745, "step": 3726 }, { "epoch": 0.31463756951552824, "grad_norm": 0.13671875, "learning_rate": 4.106664258793152e-05, "loss": 1.4675558805465698, "step": 3727 }, { "epoch": 0.31472199065035933, "grad_norm": 0.1767578125, "learning_rate": 4.106165463986785e-05, "loss": 1.543849229812622, "step": 3728 }, { "epoch": 0.3148064117851904, "grad_norm": 0.1416015625, "learning_rate": 4.105666560278539e-05, "loss": 1.5958192348480225, "step": 3729 }, { "epoch": 0.3148908329200215, "grad_norm": 0.1376953125, "learning_rate": 4.105167547702242e-05, "loss": 1.549005389213562, "step": 3730 }, { "epoch": 0.3149752540548526, "grad_norm": 0.1376953125, "learning_rate": 4.1046684262917256e-05, "loss": 1.5624637603759766, "step": 3731 }, { "epoch": 0.31505967518968375, "grad_norm": 0.134765625, "learning_rate": 4.1041691960808336e-05, "loss": 1.540266513824463, "step": 3732 }, { "epoch": 0.31514409632451484, "grad_norm": 0.134765625, "learning_rate": 4.103669857103414e-05, "loss": 1.464776873588562, "step": 3733 }, { "epoch": 0.31522851745934594, "grad_norm": 0.1484375, "learning_rate": 4.103170409393323e-05, "loss": 1.6127678155899048, "step": 3734 }, { "epoch": 0.31531293859417703, "grad_norm": 0.1455078125, "learning_rate": 4.102670852984425e-05, "loss": 1.519802212715149, "step": 3735 }, { "epoch": 0.3153973597290082, "grad_norm": 0.14453125, "learning_rate": 4.102171187910591e-05, "loss": 1.5720244646072388, "step": 3736 }, { "epoch": 0.31548178086383927, "grad_norm": 0.146484375, "learning_rate": 4.101671414205699e-05, "loss": 1.5195753574371338, "step": 3737 }, { "epoch": 0.31556620199867036, "grad_norm": 0.1455078125, "learning_rate": 4.101171531903635e-05, "loss": 1.5322458744049072, "step": 3738 }, { "epoch": 0.31565062313350145, "grad_norm": 0.162109375, "learning_rate": 4.1006715410382926e-05, "loss": 1.5189361572265625, "step": 3739 }, { "epoch": 0.3157350442683326, "grad_norm": 0.140625, "learning_rate": 4.100171441643572e-05, "loss": 1.5265535116195679, "step": 3740 }, { "epoch": 0.3158194654031637, "grad_norm": 0.14453125, "learning_rate": 4.099671233753382e-05, "loss": 1.476507544517517, "step": 3741 }, { "epoch": 0.3159038865379948, "grad_norm": 0.1337890625, "learning_rate": 4.099170917401637e-05, "loss": 1.465566873550415, "step": 3742 }, { "epoch": 0.3159883076728259, "grad_norm": 0.14453125, "learning_rate": 4.09867049262226e-05, "loss": 1.5557739734649658, "step": 3743 }, { "epoch": 0.316072728807657, "grad_norm": 0.1298828125, "learning_rate": 4.098169959449181e-05, "loss": 1.5390141010284424, "step": 3744 }, { "epoch": 0.3161571499424881, "grad_norm": 0.134765625, "learning_rate": 4.097669317916337e-05, "loss": 1.5862294435501099, "step": 3745 }, { "epoch": 0.3162415710773192, "grad_norm": 0.1416015625, "learning_rate": 4.0971685680576735e-05, "loss": 1.5201421976089478, "step": 3746 }, { "epoch": 0.3163259922121503, "grad_norm": 0.140625, "learning_rate": 4.0966677099071405e-05, "loss": 1.502816915512085, "step": 3747 }, { "epoch": 0.3164104133469814, "grad_norm": 0.1298828125, "learning_rate": 4.0961667434987e-05, "loss": 1.5374209880828857, "step": 3748 }, { "epoch": 0.31649483448181254, "grad_norm": 0.1318359375, "learning_rate": 4.095665668866318e-05, "loss": 1.5437153577804565, "step": 3749 }, { "epoch": 0.31657925561664363, "grad_norm": 0.1337890625, "learning_rate": 4.095164486043967e-05, "loss": 1.5639543533325195, "step": 3750 }, { "epoch": 0.3166636767514747, "grad_norm": 0.1328125, "learning_rate": 4.0946631950656305e-05, "loss": 1.4483132362365723, "step": 3751 }, { "epoch": 0.3167480978863058, "grad_norm": 0.1337890625, "learning_rate": 4.094161795965296e-05, "loss": 1.4909709692001343, "step": 3752 }, { "epoch": 0.31683251902113696, "grad_norm": 0.1416015625, "learning_rate": 4.09366028877696e-05, "loss": 1.4956880807876587, "step": 3753 }, { "epoch": 0.31691694015596805, "grad_norm": 0.1416015625, "learning_rate": 4.093158673534625e-05, "loss": 1.4542956352233887, "step": 3754 }, { "epoch": 0.31700136129079914, "grad_norm": 0.1455078125, "learning_rate": 4.092656950272303e-05, "loss": 1.4885735511779785, "step": 3755 }, { "epoch": 0.31708578242563024, "grad_norm": 0.1455078125, "learning_rate": 4.092155119024013e-05, "loss": 1.48542058467865, "step": 3756 }, { "epoch": 0.3171702035604614, "grad_norm": 0.140625, "learning_rate": 4.091653179823777e-05, "loss": 1.5514709949493408, "step": 3757 }, { "epoch": 0.3172546246952925, "grad_norm": 0.1318359375, "learning_rate": 4.0911511327056293e-05, "loss": 1.5005391836166382, "step": 3758 }, { "epoch": 0.31733904583012357, "grad_norm": 0.13671875, "learning_rate": 4.090648977703612e-05, "loss": 1.5354478359222412, "step": 3759 }, { "epoch": 0.31742346696495466, "grad_norm": 0.1318359375, "learning_rate": 4.090146714851769e-05, "loss": 1.515576720237732, "step": 3760 }, { "epoch": 0.3175078880997858, "grad_norm": 0.13671875, "learning_rate": 4.089644344184158e-05, "loss": 1.5416938066482544, "step": 3761 }, { "epoch": 0.3175923092346169, "grad_norm": 0.1533203125, "learning_rate": 4.089141865734838e-05, "loss": 1.50376558303833, "step": 3762 }, { "epoch": 0.317676730369448, "grad_norm": 0.1416015625, "learning_rate": 4.0886392795378805e-05, "loss": 1.5286015272140503, "step": 3763 }, { "epoch": 0.3177611515042791, "grad_norm": 0.1357421875, "learning_rate": 4.088136585627361e-05, "loss": 1.5174856185913086, "step": 3764 }, { "epoch": 0.3178455726391102, "grad_norm": 0.1376953125, "learning_rate": 4.087633784037364e-05, "loss": 1.5235329866409302, "step": 3765 }, { "epoch": 0.3179299937739413, "grad_norm": 0.1513671875, "learning_rate": 4.0871308748019795e-05, "loss": 1.5918184518814087, "step": 3766 }, { "epoch": 0.3180144149087724, "grad_norm": 0.1455078125, "learning_rate": 4.0866278579553073e-05, "loss": 1.5576812028884888, "step": 3767 }, { "epoch": 0.3180988360436035, "grad_norm": 0.14453125, "learning_rate": 4.086124733531452e-05, "loss": 1.504690170288086, "step": 3768 }, { "epoch": 0.3181832571784346, "grad_norm": 0.1357421875, "learning_rate": 4.0856215015645286e-05, "loss": 1.5551512241363525, "step": 3769 }, { "epoch": 0.31826767831326574, "grad_norm": 0.1396484375, "learning_rate": 4.085118162088655e-05, "loss": 1.5177972316741943, "step": 3770 }, { "epoch": 0.31835209944809684, "grad_norm": 0.1396484375, "learning_rate": 4.08461471513796e-05, "loss": 1.4889708757400513, "step": 3771 }, { "epoch": 0.31843652058292793, "grad_norm": 0.13671875, "learning_rate": 4.084111160746578e-05, "loss": 1.5465879440307617, "step": 3772 }, { "epoch": 0.318520941717759, "grad_norm": 0.1357421875, "learning_rate": 4.0836074989486524e-05, "loss": 1.4901821613311768, "step": 3773 }, { "epoch": 0.31860536285259017, "grad_norm": 0.13671875, "learning_rate": 4.083103729778331e-05, "loss": 1.4807994365692139, "step": 3774 }, { "epoch": 0.31868978398742126, "grad_norm": 0.1318359375, "learning_rate": 4.0825998532697726e-05, "loss": 1.5261846780776978, "step": 3775 }, { "epoch": 0.31877420512225235, "grad_norm": 0.13671875, "learning_rate": 4.0820958694571394e-05, "loss": 1.5177302360534668, "step": 3776 }, { "epoch": 0.31885862625708344, "grad_norm": 0.146484375, "learning_rate": 4.081591778374603e-05, "loss": 1.5244112014770508, "step": 3777 }, { "epoch": 0.3189430473919146, "grad_norm": 0.1611328125, "learning_rate": 4.081087580056343e-05, "loss": 1.5902130603790283, "step": 3778 }, { "epoch": 0.3190274685267457, "grad_norm": 0.1337890625, "learning_rate": 4.080583274536545e-05, "loss": 1.4687376022338867, "step": 3779 }, { "epoch": 0.3191118896615768, "grad_norm": 0.150390625, "learning_rate": 4.080078861849401e-05, "loss": 1.6021349430084229, "step": 3780 }, { "epoch": 0.31919631079640787, "grad_norm": 0.138671875, "learning_rate": 4.079574342029112e-05, "loss": 1.551866054534912, "step": 3781 }, { "epoch": 0.31928073193123896, "grad_norm": 0.1455078125, "learning_rate": 4.079069715109887e-05, "loss": 1.594502329826355, "step": 3782 }, { "epoch": 0.3193651530660701, "grad_norm": 0.1484375, "learning_rate": 4.0785649811259384e-05, "loss": 1.581730604171753, "step": 3783 }, { "epoch": 0.3194495742009012, "grad_norm": 0.1611328125, "learning_rate": 4.07806014011149e-05, "loss": 1.480713963508606, "step": 3784 }, { "epoch": 0.3195339953357323, "grad_norm": 0.15234375, "learning_rate": 4.077555192100772e-05, "loss": 1.482160210609436, "step": 3785 }, { "epoch": 0.3196184164705634, "grad_norm": 0.1455078125, "learning_rate": 4.0770501371280184e-05, "loss": 1.5550463199615479, "step": 3786 }, { "epoch": 0.31970283760539453, "grad_norm": 0.158203125, "learning_rate": 4.0765449752274757e-05, "loss": 1.533324122428894, "step": 3787 }, { "epoch": 0.3197872587402256, "grad_norm": 0.138671875, "learning_rate": 4.0760397064333937e-05, "loss": 1.4959334135055542, "step": 3788 }, { "epoch": 0.3198716798750567, "grad_norm": 0.142578125, "learning_rate": 4.075534330780032e-05, "loss": 1.5053836107254028, "step": 3789 }, { "epoch": 0.3199561010098878, "grad_norm": 0.1357421875, "learning_rate": 4.075028848301655e-05, "loss": 1.463654637336731, "step": 3790 }, { "epoch": 0.32004052214471895, "grad_norm": 0.1474609375, "learning_rate": 4.074523259032537e-05, "loss": 1.573746919631958, "step": 3791 }, { "epoch": 0.32012494327955004, "grad_norm": 0.1416015625, "learning_rate": 4.074017563006956e-05, "loss": 1.614399790763855, "step": 3792 }, { "epoch": 0.32020936441438114, "grad_norm": 0.1318359375, "learning_rate": 4.073511760259202e-05, "loss": 1.5316786766052246, "step": 3793 }, { "epoch": 0.32029378554921223, "grad_norm": 0.1318359375, "learning_rate": 4.073005850823568e-05, "loss": 1.4940292835235596, "step": 3794 }, { "epoch": 0.3203782066840434, "grad_norm": 0.15625, "learning_rate": 4.072499834734357e-05, "loss": 1.5186080932617188, "step": 3795 }, { "epoch": 0.32046262781887447, "grad_norm": 0.1376953125, "learning_rate": 4.071993712025877e-05, "loss": 1.5083104372024536, "step": 3796 }, { "epoch": 0.32054704895370556, "grad_norm": 0.146484375, "learning_rate": 4.0714874827324436e-05, "loss": 1.6228660345077515, "step": 3797 }, { "epoch": 0.32063147008853665, "grad_norm": 0.1376953125, "learning_rate": 4.070981146888383e-05, "loss": 1.531261682510376, "step": 3798 }, { "epoch": 0.32071589122336774, "grad_norm": 0.1376953125, "learning_rate": 4.070474704528023e-05, "loss": 1.5586479902267456, "step": 3799 }, { "epoch": 0.3208003123581989, "grad_norm": 0.146484375, "learning_rate": 4.069968155685705e-05, "loss": 1.5564687252044678, "step": 3800 }, { "epoch": 0.32088473349303, "grad_norm": 0.1455078125, "learning_rate": 4.069461500395771e-05, "loss": 1.5300323963165283, "step": 3801 }, { "epoch": 0.3209691546278611, "grad_norm": 0.146484375, "learning_rate": 4.0689547386925754e-05, "loss": 1.6335102319717407, "step": 3802 }, { "epoch": 0.32105357576269217, "grad_norm": 0.1572265625, "learning_rate": 4.0684478706104764e-05, "loss": 1.6640983819961548, "step": 3803 }, { "epoch": 0.3211379968975233, "grad_norm": 0.142578125, "learning_rate": 4.067940896183843e-05, "loss": 1.5122238397598267, "step": 3804 }, { "epoch": 0.3212224180323544, "grad_norm": 0.142578125, "learning_rate": 4.067433815447047e-05, "loss": 1.5262161493301392, "step": 3805 }, { "epoch": 0.3213068391671855, "grad_norm": 0.138671875, "learning_rate": 4.066926628434471e-05, "loss": 1.5703119039535522, "step": 3806 }, { "epoch": 0.3213912603020166, "grad_norm": 0.1416015625, "learning_rate": 4.0664193351805035e-05, "loss": 1.5228807926177979, "step": 3807 }, { "epoch": 0.32147568143684774, "grad_norm": 0.1552734375, "learning_rate": 4.06591193571954e-05, "loss": 1.5768351554870605, "step": 3808 }, { "epoch": 0.32156010257167883, "grad_norm": 0.1318359375, "learning_rate": 4.065404430085983e-05, "loss": 1.5499639511108398, "step": 3809 }, { "epoch": 0.3216445237065099, "grad_norm": 0.13671875, "learning_rate": 4.0648968183142424e-05, "loss": 1.584671974182129, "step": 3810 }, { "epoch": 0.321728944841341, "grad_norm": 0.1396484375, "learning_rate": 4.064389100438736e-05, "loss": 1.5846431255340576, "step": 3811 }, { "epoch": 0.32181336597617216, "grad_norm": 0.140625, "learning_rate": 4.0638812764938894e-05, "loss": 1.5260980129241943, "step": 3812 }, { "epoch": 0.32189778711100325, "grad_norm": 0.1533203125, "learning_rate": 4.063373346514132e-05, "loss": 1.515587568283081, "step": 3813 }, { "epoch": 0.32198220824583434, "grad_norm": 0.1337890625, "learning_rate": 4.062865310533904e-05, "loss": 1.5100419521331787, "step": 3814 }, { "epoch": 0.32206662938066544, "grad_norm": 0.1416015625, "learning_rate": 4.0623571685876515e-05, "loss": 1.663177251815796, "step": 3815 }, { "epoch": 0.32215105051549653, "grad_norm": 0.15625, "learning_rate": 4.061848920709829e-05, "loss": 1.510561227798462, "step": 3816 }, { "epoch": 0.3222354716503277, "grad_norm": 0.13671875, "learning_rate": 4.0613405669348935e-05, "loss": 1.4777323007583618, "step": 3817 }, { "epoch": 0.32231989278515877, "grad_norm": 0.1455078125, "learning_rate": 4.0608321072973155e-05, "loss": 1.5337636470794678, "step": 3818 }, { "epoch": 0.32240431391998986, "grad_norm": 0.1376953125, "learning_rate": 4.060323541831569e-05, "loss": 1.5537433624267578, "step": 3819 }, { "epoch": 0.32248873505482095, "grad_norm": 0.1474609375, "learning_rate": 4.059814870572135e-05, "loss": 1.6376216411590576, "step": 3820 }, { "epoch": 0.3225731561896521, "grad_norm": 0.138671875, "learning_rate": 4.059306093553504e-05, "loss": 1.5367934703826904, "step": 3821 }, { "epoch": 0.3226575773244832, "grad_norm": 0.1357421875, "learning_rate": 4.058797210810172e-05, "loss": 1.5200459957122803, "step": 3822 }, { "epoch": 0.3227419984593143, "grad_norm": 0.1455078125, "learning_rate": 4.0582882223766424e-05, "loss": 1.6956790685653687, "step": 3823 }, { "epoch": 0.3228264195941454, "grad_norm": 0.1474609375, "learning_rate": 4.057779128287425e-05, "loss": 1.5478649139404297, "step": 3824 }, { "epoch": 0.3229108407289765, "grad_norm": 0.150390625, "learning_rate": 4.057269928577038e-05, "loss": 1.5998591184616089, "step": 3825 }, { "epoch": 0.3229952618638076, "grad_norm": 0.1455078125, "learning_rate": 4.056760623280008e-05, "loss": 1.5354880094528198, "step": 3826 }, { "epoch": 0.3230796829986387, "grad_norm": 0.1328125, "learning_rate": 4.056251212430865e-05, "loss": 1.5069546699523926, "step": 3827 }, { "epoch": 0.3231641041334698, "grad_norm": 0.1416015625, "learning_rate": 4.0557416960641495e-05, "loss": 1.5652164220809937, "step": 3828 }, { "epoch": 0.32324852526830095, "grad_norm": 0.15625, "learning_rate": 4.055232074214407e-05, "loss": 1.5832314491271973, "step": 3829 }, { "epoch": 0.32333294640313204, "grad_norm": 0.1474609375, "learning_rate": 4.0547223469161914e-05, "loss": 1.543776512145996, "step": 3830 }, { "epoch": 0.32341736753796313, "grad_norm": 0.1455078125, "learning_rate": 4.0542125142040637e-05, "loss": 1.600203275680542, "step": 3831 }, { "epoch": 0.3235017886727942, "grad_norm": 0.14453125, "learning_rate": 4.053702576112593e-05, "loss": 1.4742118120193481, "step": 3832 }, { "epoch": 0.3235862098076253, "grad_norm": 0.138671875, "learning_rate": 4.053192532676351e-05, "loss": 1.5707170963287354, "step": 3833 }, { "epoch": 0.32367063094245646, "grad_norm": 0.12890625, "learning_rate": 4.052682383929923e-05, "loss": 1.4764184951782227, "step": 3834 }, { "epoch": 0.32375505207728755, "grad_norm": 0.150390625, "learning_rate": 4.052172129907897e-05, "loss": 1.443353295326233, "step": 3835 }, { "epoch": 0.32383947321211864, "grad_norm": 0.150390625, "learning_rate": 4.05166177064487e-05, "loss": 1.6055101156234741, "step": 3836 }, { "epoch": 0.32392389434694974, "grad_norm": 0.1298828125, "learning_rate": 4.0511513061754444e-05, "loss": 1.521208643913269, "step": 3837 }, { "epoch": 0.3240083154817809, "grad_norm": 0.154296875, "learning_rate": 4.050640736534233e-05, "loss": 1.5190995931625366, "step": 3838 }, { "epoch": 0.324092736616612, "grad_norm": 0.173828125, "learning_rate": 4.050130061755851e-05, "loss": 1.5502597093582153, "step": 3839 }, { "epoch": 0.32417715775144307, "grad_norm": 0.15234375, "learning_rate": 4.0496192818749255e-05, "loss": 1.5759313106536865, "step": 3840 }, { "epoch": 0.32426157888627416, "grad_norm": 0.12890625, "learning_rate": 4.049108396926088e-05, "loss": 1.4722102880477905, "step": 3841 }, { "epoch": 0.3243460000211053, "grad_norm": 0.150390625, "learning_rate": 4.048597406943978e-05, "loss": 1.598966360092163, "step": 3842 }, { "epoch": 0.3244304211559364, "grad_norm": 0.1494140625, "learning_rate": 4.0480863119632405e-05, "loss": 1.6096140146255493, "step": 3843 }, { "epoch": 0.3245148422907675, "grad_norm": 0.1298828125, "learning_rate": 4.0475751120185304e-05, "loss": 1.468322992324829, "step": 3844 }, { "epoch": 0.3245992634255986, "grad_norm": 0.1474609375, "learning_rate": 4.0470638071445083e-05, "loss": 1.509218692779541, "step": 3845 }, { "epoch": 0.32468368456042973, "grad_norm": 0.146484375, "learning_rate": 4.046552397375841e-05, "loss": 1.5145080089569092, "step": 3846 }, { "epoch": 0.3247681056952608, "grad_norm": 0.1484375, "learning_rate": 4.046040882747204e-05, "loss": 1.4966281652450562, "step": 3847 }, { "epoch": 0.3248525268300919, "grad_norm": 0.1455078125, "learning_rate": 4.045529263293278e-05, "loss": 1.5839924812316895, "step": 3848 }, { "epoch": 0.324936947964923, "grad_norm": 0.1435546875, "learning_rate": 4.045017539048754e-05, "loss": 1.6616246700286865, "step": 3849 }, { "epoch": 0.3250213690997541, "grad_norm": 0.1376953125, "learning_rate": 4.0445057100483274e-05, "loss": 1.5306721925735474, "step": 3850 }, { "epoch": 0.32510579023458525, "grad_norm": 0.1376953125, "learning_rate": 4.0439937763267e-05, "loss": 1.5038083791732788, "step": 3851 }, { "epoch": 0.32519021136941634, "grad_norm": 0.13671875, "learning_rate": 4.043481737918584e-05, "loss": 1.5553936958312988, "step": 3852 }, { "epoch": 0.32527463250424743, "grad_norm": 0.14453125, "learning_rate": 4.042969594858696e-05, "loss": 1.4974043369293213, "step": 3853 }, { "epoch": 0.3253590536390785, "grad_norm": 0.1435546875, "learning_rate": 4.0424573471817605e-05, "loss": 1.5981475114822388, "step": 3854 }, { "epoch": 0.32544347477390967, "grad_norm": 0.1552734375, "learning_rate": 4.0419449949225096e-05, "loss": 1.5874271392822266, "step": 3855 }, { "epoch": 0.32552789590874076, "grad_norm": 0.138671875, "learning_rate": 4.0414325381156815e-05, "loss": 1.5432475805282593, "step": 3856 }, { "epoch": 0.32561231704357185, "grad_norm": 0.134765625, "learning_rate": 4.040919976796022e-05, "loss": 1.482358455657959, "step": 3857 }, { "epoch": 0.32569673817840294, "grad_norm": 0.142578125, "learning_rate": 4.0404073109982845e-05, "loss": 1.5745742321014404, "step": 3858 }, { "epoch": 0.3257811593132341, "grad_norm": 0.140625, "learning_rate": 4.0398945407572285e-05, "loss": 1.5254268646240234, "step": 3859 }, { "epoch": 0.3258655804480652, "grad_norm": 0.154296875, "learning_rate": 4.039381666107621e-05, "loss": 1.4136899709701538, "step": 3860 }, { "epoch": 0.3259500015828963, "grad_norm": 0.1455078125, "learning_rate": 4.0388686870842376e-05, "loss": 1.577659010887146, "step": 3861 }, { "epoch": 0.32603442271772737, "grad_norm": 0.1416015625, "learning_rate": 4.038355603721857e-05, "loss": 1.4848281145095825, "step": 3862 }, { "epoch": 0.3261188438525585, "grad_norm": 0.1396484375, "learning_rate": 4.037842416055269e-05, "loss": 1.6014776229858398, "step": 3863 }, { "epoch": 0.3262032649873896, "grad_norm": 0.1435546875, "learning_rate": 4.037329124119268e-05, "loss": 1.580394983291626, "step": 3864 }, { "epoch": 0.3262876861222207, "grad_norm": 0.138671875, "learning_rate": 4.0368157279486585e-05, "loss": 1.5346732139587402, "step": 3865 }, { "epoch": 0.3263721072570518, "grad_norm": 0.1591796875, "learning_rate": 4.036302227578248e-05, "loss": 1.5856682062149048, "step": 3866 }, { "epoch": 0.3264565283918829, "grad_norm": 0.14453125, "learning_rate": 4.035788623042854e-05, "loss": 1.4980220794677734, "step": 3867 }, { "epoch": 0.32654094952671403, "grad_norm": 0.13671875, "learning_rate": 4.035274914377299e-05, "loss": 1.5229012966156006, "step": 3868 }, { "epoch": 0.3266253706615451, "grad_norm": 0.1513671875, "learning_rate": 4.0347611016164157e-05, "loss": 1.5990102291107178, "step": 3869 }, { "epoch": 0.3267097917963762, "grad_norm": 0.15234375, "learning_rate": 4.034247184795039e-05, "loss": 1.4832271337509155, "step": 3870 }, { "epoch": 0.3267942129312073, "grad_norm": 0.14453125, "learning_rate": 4.033733163948017e-05, "loss": 1.6048437356948853, "step": 3871 }, { "epoch": 0.32687863406603845, "grad_norm": 0.1630859375, "learning_rate": 4.0332190391101986e-05, "loss": 1.5187393426895142, "step": 3872 }, { "epoch": 0.32696305520086955, "grad_norm": 0.1552734375, "learning_rate": 4.0327048103164446e-05, "loss": 1.5865674018859863, "step": 3873 }, { "epoch": 0.32704747633570064, "grad_norm": 0.1328125, "learning_rate": 4.032190477601621e-05, "loss": 1.5042136907577515, "step": 3874 }, { "epoch": 0.32713189747053173, "grad_norm": 0.1416015625, "learning_rate": 4.031676041000599e-05, "loss": 1.4577401876449585, "step": 3875 }, { "epoch": 0.3272163186053629, "grad_norm": 0.1318359375, "learning_rate": 4.0311615005482603e-05, "loss": 1.541722297668457, "step": 3876 }, { "epoch": 0.32730073974019397, "grad_norm": 0.1484375, "learning_rate": 4.030646856279491e-05, "loss": 1.5677541494369507, "step": 3877 }, { "epoch": 0.32738516087502506, "grad_norm": 0.13671875, "learning_rate": 4.030132108229186e-05, "loss": 1.5267008543014526, "step": 3878 }, { "epoch": 0.32746958200985615, "grad_norm": 0.1328125, "learning_rate": 4.029617256432245e-05, "loss": 1.4586364030838013, "step": 3879 }, { "epoch": 0.3275540031446873, "grad_norm": 0.1318359375, "learning_rate": 4.029102300923579e-05, "loss": 1.488094449043274, "step": 3880 }, { "epoch": 0.3276384242795184, "grad_norm": 0.13671875, "learning_rate": 4.028587241738101e-05, "loss": 1.573659896850586, "step": 3881 }, { "epoch": 0.3277228454143495, "grad_norm": 0.134765625, "learning_rate": 4.0280720789107336e-05, "loss": 1.4490753412246704, "step": 3882 }, { "epoch": 0.3278072665491806, "grad_norm": 0.1328125, "learning_rate": 4.027556812476406e-05, "loss": 1.5089163780212402, "step": 3883 }, { "epoch": 0.32789168768401167, "grad_norm": 0.1357421875, "learning_rate": 4.0270414424700556e-05, "loss": 1.5775396823883057, "step": 3884 }, { "epoch": 0.3279761088188428, "grad_norm": 0.1328125, "learning_rate": 4.026525968926624e-05, "loss": 1.5825963020324707, "step": 3885 }, { "epoch": 0.3280605299536739, "grad_norm": 0.1435546875, "learning_rate": 4.026010391881063e-05, "loss": 1.5252984762191772, "step": 3886 }, { "epoch": 0.328144951088505, "grad_norm": 0.14453125, "learning_rate": 4.025494711368328e-05, "loss": 1.5674134492874146, "step": 3887 }, { "epoch": 0.3282293722233361, "grad_norm": 0.14453125, "learning_rate": 4.024978927423386e-05, "loss": 1.512519121170044, "step": 3888 }, { "epoch": 0.32831379335816724, "grad_norm": 0.130859375, "learning_rate": 4.024463040081208e-05, "loss": 1.587641716003418, "step": 3889 }, { "epoch": 0.32839821449299833, "grad_norm": 0.134765625, "learning_rate": 4.0239470493767704e-05, "loss": 1.4937434196472168, "step": 3890 }, { "epoch": 0.3284826356278294, "grad_norm": 0.1435546875, "learning_rate": 4.023430955345059e-05, "loss": 1.4833749532699585, "step": 3891 }, { "epoch": 0.3285670567626605, "grad_norm": 0.1484375, "learning_rate": 4.022914758021068e-05, "loss": 1.5259991884231567, "step": 3892 }, { "epoch": 0.32865147789749166, "grad_norm": 0.1416015625, "learning_rate": 4.022398457439796e-05, "loss": 1.6613178253173828, "step": 3893 }, { "epoch": 0.32873589903232275, "grad_norm": 0.12451171875, "learning_rate": 4.021882053636249e-05, "loss": 1.4596538543701172, "step": 3894 }, { "epoch": 0.32882032016715385, "grad_norm": 0.140625, "learning_rate": 4.0213655466454404e-05, "loss": 1.5337560176849365, "step": 3895 }, { "epoch": 0.32890474130198494, "grad_norm": 0.1357421875, "learning_rate": 4.020848936502391e-05, "loss": 1.4886913299560547, "step": 3896 }, { "epoch": 0.32898916243681603, "grad_norm": 0.1416015625, "learning_rate": 4.020332223242128e-05, "loss": 1.5332432985305786, "step": 3897 }, { "epoch": 0.3290735835716472, "grad_norm": 0.1513671875, "learning_rate": 4.019815406899686e-05, "loss": 1.5072394609451294, "step": 3898 }, { "epoch": 0.32915800470647827, "grad_norm": 0.134765625, "learning_rate": 4.019298487510107e-05, "loss": 1.5279600620269775, "step": 3899 }, { "epoch": 0.32924242584130936, "grad_norm": 0.1396484375, "learning_rate": 4.018781465108437e-05, "loss": 1.5713304281234741, "step": 3900 }, { "epoch": 0.32932684697614045, "grad_norm": 0.14453125, "learning_rate": 4.0182643397297336e-05, "loss": 1.4919209480285645, "step": 3901 }, { "epoch": 0.3294112681109716, "grad_norm": 0.1416015625, "learning_rate": 4.0177471114090595e-05, "loss": 1.546836495399475, "step": 3902 }, { "epoch": 0.3294956892458027, "grad_norm": 0.1376953125, "learning_rate": 4.017229780181482e-05, "loss": 1.4952208995819092, "step": 3903 }, { "epoch": 0.3295801103806338, "grad_norm": 0.1484375, "learning_rate": 4.016712346082079e-05, "loss": 1.564537525177002, "step": 3904 }, { "epoch": 0.3296645315154649, "grad_norm": 0.140625, "learning_rate": 4.016194809145933e-05, "loss": 1.5108274221420288, "step": 3905 }, { "epoch": 0.329748952650296, "grad_norm": 0.134765625, "learning_rate": 4.0156771694081344e-05, "loss": 1.5272216796875, "step": 3906 }, { "epoch": 0.3298333737851271, "grad_norm": 0.1474609375, "learning_rate": 4.0151594269037804e-05, "loss": 1.4653018712997437, "step": 3907 }, { "epoch": 0.3299177949199582, "grad_norm": 0.1435546875, "learning_rate": 4.014641581667976e-05, "loss": 1.6301554441452026, "step": 3908 }, { "epoch": 0.3300022160547893, "grad_norm": 0.1689453125, "learning_rate": 4.014123633735831e-05, "loss": 1.553779125213623, "step": 3909 }, { "epoch": 0.33008663718962045, "grad_norm": 0.130859375, "learning_rate": 4.013605583142464e-05, "loss": 1.4988170862197876, "step": 3910 }, { "epoch": 0.33017105832445154, "grad_norm": 0.1328125, "learning_rate": 4.013087429923001e-05, "loss": 1.5450537204742432, "step": 3911 }, { "epoch": 0.33025547945928263, "grad_norm": 0.1748046875, "learning_rate": 4.0125691741125724e-05, "loss": 1.5800448656082153, "step": 3912 }, { "epoch": 0.3303399005941137, "grad_norm": 0.1572265625, "learning_rate": 4.0120508157463186e-05, "loss": 1.6003775596618652, "step": 3913 }, { "epoch": 0.3304243217289448, "grad_norm": 0.134765625, "learning_rate": 4.011532354859385e-05, "loss": 1.5121312141418457, "step": 3914 }, { "epoch": 0.33050874286377596, "grad_norm": 0.1572265625, "learning_rate": 4.011013791486924e-05, "loss": 1.570050835609436, "step": 3915 }, { "epoch": 0.33059316399860705, "grad_norm": 0.1396484375, "learning_rate": 4.010495125664096e-05, "loss": 1.554733395576477, "step": 3916 }, { "epoch": 0.33067758513343815, "grad_norm": 0.1396484375, "learning_rate": 4.009976357426069e-05, "loss": 1.500137209892273, "step": 3917 }, { "epoch": 0.33076200626826924, "grad_norm": 0.1484375, "learning_rate": 4.009457486808014e-05, "loss": 1.429042100906372, "step": 3918 }, { "epoch": 0.3308464274031004, "grad_norm": 0.1416015625, "learning_rate": 4.008938513845114e-05, "loss": 1.4800055027008057, "step": 3919 }, { "epoch": 0.3309308485379315, "grad_norm": 0.154296875, "learning_rate": 4.008419438572555e-05, "loss": 1.502744436264038, "step": 3920 }, { "epoch": 0.33101526967276257, "grad_norm": 0.1484375, "learning_rate": 4.0079002610255335e-05, "loss": 1.5091532468795776, "step": 3921 }, { "epoch": 0.33109969080759366, "grad_norm": 0.1357421875, "learning_rate": 4.0073809812392485e-05, "loss": 1.563601016998291, "step": 3922 }, { "epoch": 0.3311841119424248, "grad_norm": 0.1484375, "learning_rate": 4.00686159924891e-05, "loss": 1.4704023599624634, "step": 3923 }, { "epoch": 0.3312685330772559, "grad_norm": 0.1630859375, "learning_rate": 4.006342115089733e-05, "loss": 1.619685411453247, "step": 3924 }, { "epoch": 0.331352954212087, "grad_norm": 0.1328125, "learning_rate": 4.005822528796941e-05, "loss": 1.5666064023971558, "step": 3925 }, { "epoch": 0.3314373753469181, "grad_norm": 0.158203125, "learning_rate": 4.005302840405761e-05, "loss": 1.5401453971862793, "step": 3926 }, { "epoch": 0.33152179648174923, "grad_norm": 0.1435546875, "learning_rate": 4.004783049951429e-05, "loss": 1.5287610292434692, "step": 3927 }, { "epoch": 0.3316062176165803, "grad_norm": 0.1474609375, "learning_rate": 4.004263157469191e-05, "loss": 1.662358045578003, "step": 3928 }, { "epoch": 0.3316906387514114, "grad_norm": 0.13671875, "learning_rate": 4.003743162994295e-05, "loss": 1.5100947618484497, "step": 3929 }, { "epoch": 0.3317750598862425, "grad_norm": 0.1484375, "learning_rate": 4.003223066561997e-05, "loss": 1.500321388244629, "step": 3930 }, { "epoch": 0.3318594810210736, "grad_norm": 0.13671875, "learning_rate": 4.002702868207563e-05, "loss": 1.4642760753631592, "step": 3931 }, { "epoch": 0.33194390215590475, "grad_norm": 0.1455078125, "learning_rate": 4.002182567966262e-05, "loss": 1.5075137615203857, "step": 3932 }, { "epoch": 0.33202832329073584, "grad_norm": 0.14453125, "learning_rate": 4.0016621658733725e-05, "loss": 1.5189379453659058, "step": 3933 }, { "epoch": 0.33211274442556693, "grad_norm": 0.142578125, "learning_rate": 4.001141661964178e-05, "loss": 1.5475966930389404, "step": 3934 }, { "epoch": 0.332197165560398, "grad_norm": 0.1376953125, "learning_rate": 4.000621056273971e-05, "loss": 1.5666065216064453, "step": 3935 }, { "epoch": 0.33228158669522917, "grad_norm": 0.1318359375, "learning_rate": 4.000100348838048e-05, "loss": 1.5261305570602417, "step": 3936 }, { "epoch": 0.33236600783006026, "grad_norm": 0.134765625, "learning_rate": 3.999579539691717e-05, "loss": 1.5692005157470703, "step": 3937 }, { "epoch": 0.33245042896489135, "grad_norm": 0.1416015625, "learning_rate": 3.9990586288702884e-05, "loss": 1.5505472421646118, "step": 3938 }, { "epoch": 0.33253485009972245, "grad_norm": 0.1298828125, "learning_rate": 3.998537616409081e-05, "loss": 1.5270979404449463, "step": 3939 }, { "epoch": 0.3326192712345536, "grad_norm": 0.14453125, "learning_rate": 3.998016502343422e-05, "loss": 1.5756316184997559, "step": 3940 }, { "epoch": 0.3327036923693847, "grad_norm": 0.146484375, "learning_rate": 3.997495286708644e-05, "loss": 1.5789337158203125, "step": 3941 }, { "epoch": 0.3327881135042158, "grad_norm": 0.1376953125, "learning_rate": 3.996973969540084e-05, "loss": 1.459035038948059, "step": 3942 }, { "epoch": 0.33287253463904687, "grad_norm": 0.1416015625, "learning_rate": 3.9964525508730924e-05, "loss": 1.522027611732483, "step": 3943 }, { "epoch": 0.332956955773878, "grad_norm": 0.1396484375, "learning_rate": 3.9959310307430204e-05, "loss": 1.5819262266159058, "step": 3944 }, { "epoch": 0.3330413769087091, "grad_norm": 0.1376953125, "learning_rate": 3.995409409185228e-05, "loss": 1.5106571912765503, "step": 3945 }, { "epoch": 0.3331257980435402, "grad_norm": 0.1455078125, "learning_rate": 3.9948876862350834e-05, "loss": 1.5359532833099365, "step": 3946 }, { "epoch": 0.3332102191783713, "grad_norm": 0.1318359375, "learning_rate": 3.994365861927961e-05, "loss": 1.4900842905044556, "step": 3947 }, { "epoch": 0.3332946403132024, "grad_norm": 0.140625, "learning_rate": 3.993843936299242e-05, "loss": 1.5187137126922607, "step": 3948 }, { "epoch": 0.33337906144803353, "grad_norm": 0.1337890625, "learning_rate": 3.993321909384312e-05, "loss": 1.4512630701065063, "step": 3949 }, { "epoch": 0.3334634825828646, "grad_norm": 0.12890625, "learning_rate": 3.9927997812185666e-05, "loss": 1.5058565139770508, "step": 3950 }, { "epoch": 0.3335479037176957, "grad_norm": 0.142578125, "learning_rate": 3.992277551837409e-05, "loss": 1.5422251224517822, "step": 3951 }, { "epoch": 0.3336323248525268, "grad_norm": 0.142578125, "learning_rate": 3.9917552212762466e-05, "loss": 1.5457956790924072, "step": 3952 }, { "epoch": 0.33371674598735795, "grad_norm": 0.13671875, "learning_rate": 3.991232789570494e-05, "loss": 1.5252972841262817, "step": 3953 }, { "epoch": 0.33380116712218905, "grad_norm": 0.14453125, "learning_rate": 3.990710256755573e-05, "loss": 1.4787973165512085, "step": 3954 }, { "epoch": 0.33388558825702014, "grad_norm": 0.1298828125, "learning_rate": 3.990187622866915e-05, "loss": 1.478469967842102, "step": 3955 }, { "epoch": 0.33397000939185123, "grad_norm": 0.140625, "learning_rate": 3.989664887939953e-05, "loss": 1.5381700992584229, "step": 3956 }, { "epoch": 0.3340544305266824, "grad_norm": 0.12890625, "learning_rate": 3.9891420520101307e-05, "loss": 1.5232319831848145, "step": 3957 }, { "epoch": 0.33413885166151347, "grad_norm": 0.1669921875, "learning_rate": 3.988619115112899e-05, "loss": 1.4828824996948242, "step": 3958 }, { "epoch": 0.33422327279634456, "grad_norm": 0.1357421875, "learning_rate": 3.988096077283712e-05, "loss": 1.5256270170211792, "step": 3959 }, { "epoch": 0.33430769393117565, "grad_norm": 0.13671875, "learning_rate": 3.987572938558035e-05, "loss": 1.5127198696136475, "step": 3960 }, { "epoch": 0.3343921150660068, "grad_norm": 0.1376953125, "learning_rate": 3.987049698971337e-05, "loss": 1.528259515762329, "step": 3961 }, { "epoch": 0.3344765362008379, "grad_norm": 0.1318359375, "learning_rate": 3.986526358559095e-05, "loss": 1.5810377597808838, "step": 3962 }, { "epoch": 0.334560957335669, "grad_norm": 0.1328125, "learning_rate": 3.9860029173567914e-05, "loss": 1.4921809434890747, "step": 3963 }, { "epoch": 0.3346453784705001, "grad_norm": 0.1376953125, "learning_rate": 3.9854793753999196e-05, "loss": 1.5330121517181396, "step": 3964 }, { "epoch": 0.33472979960533117, "grad_norm": 0.134765625, "learning_rate": 3.984955732723975e-05, "loss": 1.539823055267334, "step": 3965 }, { "epoch": 0.3348142207401623, "grad_norm": 0.130859375, "learning_rate": 3.9844319893644634e-05, "loss": 1.5398132801055908, "step": 3966 }, { "epoch": 0.3348986418749934, "grad_norm": 0.1318359375, "learning_rate": 3.9839081453568936e-05, "loss": 1.447765588760376, "step": 3967 }, { "epoch": 0.3349830630098245, "grad_norm": 0.13671875, "learning_rate": 3.983384200736785e-05, "loss": 1.5159581899642944, "step": 3968 }, { "epoch": 0.3350674841446556, "grad_norm": 0.138671875, "learning_rate": 3.982860155539661e-05, "loss": 1.5276427268981934, "step": 3969 }, { "epoch": 0.33515190527948674, "grad_norm": 0.130859375, "learning_rate": 3.982336009801056e-05, "loss": 1.500538945198059, "step": 3970 }, { "epoch": 0.33523632641431783, "grad_norm": 0.1474609375, "learning_rate": 3.981811763556506e-05, "loss": 1.5675880908966064, "step": 3971 }, { "epoch": 0.3353207475491489, "grad_norm": 0.1650390625, "learning_rate": 3.9812874168415556e-05, "loss": 1.5771126747131348, "step": 3972 }, { "epoch": 0.33540516868398, "grad_norm": 0.1474609375, "learning_rate": 3.980762969691759e-05, "loss": 1.4427610635757446, "step": 3973 }, { "epoch": 0.33548958981881116, "grad_norm": 0.1396484375, "learning_rate": 3.9802384221426725e-05, "loss": 1.497202754020691, "step": 3974 }, { "epoch": 0.33557401095364225, "grad_norm": 0.13671875, "learning_rate": 3.979713774229864e-05, "loss": 1.5558677911758423, "step": 3975 }, { "epoch": 0.33565843208847335, "grad_norm": 0.12890625, "learning_rate": 3.979189025988904e-05, "loss": 1.4909406900405884, "step": 3976 }, { "epoch": 0.33574285322330444, "grad_norm": 0.1337890625, "learning_rate": 3.9786641774553736e-05, "loss": 1.4877959489822388, "step": 3977 }, { "epoch": 0.3358272743581356, "grad_norm": 0.13671875, "learning_rate": 3.978139228664857e-05, "loss": 1.5261503458023071, "step": 3978 }, { "epoch": 0.3359116954929667, "grad_norm": 0.1416015625, "learning_rate": 3.9776141796529474e-05, "loss": 1.5490061044692993, "step": 3979 }, { "epoch": 0.33599611662779777, "grad_norm": 0.13671875, "learning_rate": 3.977089030455245e-05, "loss": 1.4889724254608154, "step": 3980 }, { "epoch": 0.33608053776262886, "grad_norm": 0.134765625, "learning_rate": 3.9765637811073565e-05, "loss": 1.5346754789352417, "step": 3981 }, { "epoch": 0.33616495889745995, "grad_norm": 0.130859375, "learning_rate": 3.976038431644894e-05, "loss": 1.5150469541549683, "step": 3982 }, { "epoch": 0.3362493800322911, "grad_norm": 0.1474609375, "learning_rate": 3.975512982103479e-05, "loss": 1.6082192659378052, "step": 3983 }, { "epoch": 0.3363338011671222, "grad_norm": 0.150390625, "learning_rate": 3.974987432518735e-05, "loss": 1.5563644170761108, "step": 3984 }, { "epoch": 0.3364182223019533, "grad_norm": 0.1416015625, "learning_rate": 3.974461782926299e-05, "loss": 1.5583044290542603, "step": 3985 }, { "epoch": 0.3365026434367844, "grad_norm": 0.12890625, "learning_rate": 3.9739360333618094e-05, "loss": 1.4558497667312622, "step": 3986 }, { "epoch": 0.3365870645716155, "grad_norm": 0.1396484375, "learning_rate": 3.973410183860914e-05, "loss": 1.6042757034301758, "step": 3987 }, { "epoch": 0.3366714857064466, "grad_norm": 0.13671875, "learning_rate": 3.9728842344592674e-05, "loss": 1.5066999197006226, "step": 3988 }, { "epoch": 0.3367559068412777, "grad_norm": 0.1484375, "learning_rate": 3.972358185192528e-05, "loss": 1.659437894821167, "step": 3989 }, { "epoch": 0.3368403279761088, "grad_norm": 0.140625, "learning_rate": 3.9718320360963657e-05, "loss": 1.561258316040039, "step": 3990 }, { "epoch": 0.33692474911093995, "grad_norm": 0.1328125, "learning_rate": 3.971305787206453e-05, "loss": 1.589410424232483, "step": 3991 }, { "epoch": 0.33700917024577104, "grad_norm": 0.134765625, "learning_rate": 3.9707794385584715e-05, "loss": 1.5909477472305298, "step": 3992 }, { "epoch": 0.33709359138060213, "grad_norm": 0.1396484375, "learning_rate": 3.970252990188108e-05, "loss": 1.46622896194458, "step": 3993 }, { "epoch": 0.3371780125154332, "grad_norm": 0.1318359375, "learning_rate": 3.969726442131059e-05, "loss": 1.512133002281189, "step": 3994 }, { "epoch": 0.33726243365026437, "grad_norm": 0.13671875, "learning_rate": 3.969199794423024e-05, "loss": 1.5418599843978882, "step": 3995 }, { "epoch": 0.33734685478509546, "grad_norm": 0.1552734375, "learning_rate": 3.968673047099711e-05, "loss": 1.5153287649154663, "step": 3996 }, { "epoch": 0.33743127591992655, "grad_norm": 0.1474609375, "learning_rate": 3.968146200196836e-05, "loss": 1.5641757249832153, "step": 3997 }, { "epoch": 0.33751569705475765, "grad_norm": 0.14453125, "learning_rate": 3.967619253750119e-05, "loss": 1.5169918537139893, "step": 3998 }, { "epoch": 0.33760011818958874, "grad_norm": 0.1591796875, "learning_rate": 3.967092207795289e-05, "loss": 1.6113430261611938, "step": 3999 }, { "epoch": 0.3376845393244199, "grad_norm": 0.134765625, "learning_rate": 3.9665650623680813e-05, "loss": 1.5692944526672363, "step": 4000 }, { "epoch": 0.337768960459251, "grad_norm": 0.13671875, "learning_rate": 3.9660378175042364e-05, "loss": 1.5179556608200073, "step": 4001 }, { "epoch": 0.33785338159408207, "grad_norm": 0.142578125, "learning_rate": 3.9655104732395044e-05, "loss": 1.5201444625854492, "step": 4002 }, { "epoch": 0.33793780272891316, "grad_norm": 0.138671875, "learning_rate": 3.964983029609639e-05, "loss": 1.5711499452590942, "step": 4003 }, { "epoch": 0.3380222238637443, "grad_norm": 0.13671875, "learning_rate": 3.9644554866504037e-05, "loss": 1.5058032274246216, "step": 4004 }, { "epoch": 0.3381066449985754, "grad_norm": 0.1455078125, "learning_rate": 3.963927844397566e-05, "loss": 1.5307189226150513, "step": 4005 }, { "epoch": 0.3381910661334065, "grad_norm": 0.15234375, "learning_rate": 3.9634001028869014e-05, "loss": 1.5684690475463867, "step": 4006 }, { "epoch": 0.3382754872682376, "grad_norm": 0.138671875, "learning_rate": 3.9628722621541924e-05, "loss": 1.5690251588821411, "step": 4007 }, { "epoch": 0.33835990840306873, "grad_norm": 0.1376953125, "learning_rate": 3.9623443222352276e-05, "loss": 1.5293394327163696, "step": 4008 }, { "epoch": 0.3384443295378998, "grad_norm": 0.130859375, "learning_rate": 3.961816283165802e-05, "loss": 1.4975688457489014, "step": 4009 }, { "epoch": 0.3385287506727309, "grad_norm": 0.1494140625, "learning_rate": 3.96128814498172e-05, "loss": 1.5025140047073364, "step": 4010 }, { "epoch": 0.338613171807562, "grad_norm": 0.1376953125, "learning_rate": 3.960759907718789e-05, "loss": 1.6241874694824219, "step": 4011 }, { "epoch": 0.33869759294239316, "grad_norm": 0.1376953125, "learning_rate": 3.9602315714128246e-05, "loss": 1.515589714050293, "step": 4012 }, { "epoch": 0.33878201407722425, "grad_norm": 0.134765625, "learning_rate": 3.95970313609965e-05, "loss": 1.5312381982803345, "step": 4013 }, { "epoch": 0.33886643521205534, "grad_norm": 0.1337890625, "learning_rate": 3.959174601815094e-05, "loss": 1.540442705154419, "step": 4014 }, { "epoch": 0.33895085634688643, "grad_norm": 0.140625, "learning_rate": 3.9586459685949926e-05, "loss": 1.5508989095687866, "step": 4015 }, { "epoch": 0.3390352774817175, "grad_norm": 0.1328125, "learning_rate": 3.9581172364751886e-05, "loss": 1.4762327671051025, "step": 4016 }, { "epoch": 0.33911969861654867, "grad_norm": 0.1376953125, "learning_rate": 3.957588405491531e-05, "loss": 1.6691986322402954, "step": 4017 }, { "epoch": 0.33920411975137976, "grad_norm": 0.13671875, "learning_rate": 3.9570594756798765e-05, "loss": 1.563183069229126, "step": 4018 }, { "epoch": 0.33928854088621085, "grad_norm": 0.1357421875, "learning_rate": 3.9565304470760864e-05, "loss": 1.5669207572937012, "step": 4019 }, { "epoch": 0.33937296202104195, "grad_norm": 0.142578125, "learning_rate": 3.9560013197160305e-05, "loss": 1.6438705921173096, "step": 4020 }, { "epoch": 0.3394573831558731, "grad_norm": 0.1396484375, "learning_rate": 3.955472093635587e-05, "loss": 1.5399081707000732, "step": 4021 }, { "epoch": 0.3395418042907042, "grad_norm": 0.1435546875, "learning_rate": 3.9549427688706353e-05, "loss": 1.542073130607605, "step": 4022 }, { "epoch": 0.3396262254255353, "grad_norm": 0.138671875, "learning_rate": 3.954413345457068e-05, "loss": 1.5067702531814575, "step": 4023 }, { "epoch": 0.33971064656036637, "grad_norm": 0.1474609375, "learning_rate": 3.95388382343078e-05, "loss": 1.4824992418289185, "step": 4024 }, { "epoch": 0.3397950676951975, "grad_norm": 0.1328125, "learning_rate": 3.953354202827673e-05, "loss": 1.5722852945327759, "step": 4025 }, { "epoch": 0.3398794888300286, "grad_norm": 0.1318359375, "learning_rate": 3.952824483683658e-05, "loss": 1.4733543395996094, "step": 4026 }, { "epoch": 0.3399639099648597, "grad_norm": 0.1376953125, "learning_rate": 3.9522946660346506e-05, "loss": 1.5891988277435303, "step": 4027 }, { "epoch": 0.3400483310996908, "grad_norm": 0.1328125, "learning_rate": 3.951764749916574e-05, "loss": 1.5224430561065674, "step": 4028 }, { "epoch": 0.34013275223452194, "grad_norm": 0.1455078125, "learning_rate": 3.951234735365359e-05, "loss": 1.6001105308532715, "step": 4029 }, { "epoch": 0.34021717336935303, "grad_norm": 0.1484375, "learning_rate": 3.9507046224169396e-05, "loss": 1.5452593564987183, "step": 4030 }, { "epoch": 0.3403015945041841, "grad_norm": 0.1416015625, "learning_rate": 3.9501744111072605e-05, "loss": 1.4206557273864746, "step": 4031 }, { "epoch": 0.3403860156390152, "grad_norm": 0.1484375, "learning_rate": 3.9496441014722695e-05, "loss": 1.546387791633606, "step": 4032 }, { "epoch": 0.3404704367738463, "grad_norm": 0.13671875, "learning_rate": 3.9491136935479244e-05, "loss": 1.542498230934143, "step": 4033 }, { "epoch": 0.34055485790867746, "grad_norm": 0.1376953125, "learning_rate": 3.948583187370187e-05, "loss": 1.55088472366333, "step": 4034 }, { "epoch": 0.34063927904350855, "grad_norm": 0.134765625, "learning_rate": 3.9480525829750295e-05, "loss": 1.562184453010559, "step": 4035 }, { "epoch": 0.34072370017833964, "grad_norm": 0.1416015625, "learning_rate": 3.9475218803984246e-05, "loss": 1.5430567264556885, "step": 4036 }, { "epoch": 0.34080812131317073, "grad_norm": 0.14453125, "learning_rate": 3.9469910796763575e-05, "loss": 1.5052642822265625, "step": 4037 }, { "epoch": 0.3408925424480019, "grad_norm": 0.16015625, "learning_rate": 3.946460180844817e-05, "loss": 1.5918500423431396, "step": 4038 }, { "epoch": 0.34097696358283297, "grad_norm": 0.146484375, "learning_rate": 3.945929183939799e-05, "loss": 1.5608022212982178, "step": 4039 }, { "epoch": 0.34106138471766406, "grad_norm": 0.150390625, "learning_rate": 3.945398088997306e-05, "loss": 1.569753885269165, "step": 4040 }, { "epoch": 0.34114580585249515, "grad_norm": 0.1513671875, "learning_rate": 3.94486689605335e-05, "loss": 1.5620402097702026, "step": 4041 }, { "epoch": 0.3412302269873263, "grad_norm": 0.142578125, "learning_rate": 3.944335605143945e-05, "loss": 1.5400786399841309, "step": 4042 }, { "epoch": 0.3413146481221574, "grad_norm": 0.1484375, "learning_rate": 3.943804216305114e-05, "loss": 1.5757993459701538, "step": 4043 }, { "epoch": 0.3413990692569885, "grad_norm": 0.1337890625, "learning_rate": 3.943272729572887e-05, "loss": 1.5337677001953125, "step": 4044 }, { "epoch": 0.3414834903918196, "grad_norm": 0.13671875, "learning_rate": 3.9427411449832986e-05, "loss": 1.5368165969848633, "step": 4045 }, { "epoch": 0.34156791152665067, "grad_norm": 0.1396484375, "learning_rate": 3.942209462572394e-05, "loss": 1.4473053216934204, "step": 4046 }, { "epoch": 0.3416523326614818, "grad_norm": 0.1435546875, "learning_rate": 3.941677682376221e-05, "loss": 1.593331217765808, "step": 4047 }, { "epoch": 0.3417367537963129, "grad_norm": 0.15234375, "learning_rate": 3.9411458044308346e-05, "loss": 1.6260101795196533, "step": 4048 }, { "epoch": 0.341821174931144, "grad_norm": 0.1494140625, "learning_rate": 3.9406138287723e-05, "loss": 1.5411319732666016, "step": 4049 }, { "epoch": 0.3419055960659751, "grad_norm": 0.1474609375, "learning_rate": 3.9400817554366845e-05, "loss": 1.5218809843063354, "step": 4050 }, { "epoch": 0.34199001720080624, "grad_norm": 0.1484375, "learning_rate": 3.939549584460065e-05, "loss": 1.5770248174667358, "step": 4051 }, { "epoch": 0.34207443833563733, "grad_norm": 0.1669921875, "learning_rate": 3.9390173158785224e-05, "loss": 1.5457828044891357, "step": 4052 }, { "epoch": 0.3421588594704684, "grad_norm": 0.1416015625, "learning_rate": 3.938484949728147e-05, "loss": 1.4878602027893066, "step": 4053 }, { "epoch": 0.3422432806052995, "grad_norm": 0.1435546875, "learning_rate": 3.937952486045036e-05, "loss": 1.567123532295227, "step": 4054 }, { "epoch": 0.34232770174013066, "grad_norm": 0.140625, "learning_rate": 3.937419924865289e-05, "loss": 1.4722837209701538, "step": 4055 }, { "epoch": 0.34241212287496176, "grad_norm": 0.1484375, "learning_rate": 3.936887266225015e-05, "loss": 1.640110969543457, "step": 4056 }, { "epoch": 0.34249654400979285, "grad_norm": 0.138671875, "learning_rate": 3.9363545101603316e-05, "loss": 1.4761511087417603, "step": 4057 }, { "epoch": 0.34258096514462394, "grad_norm": 0.142578125, "learning_rate": 3.935821656707359e-05, "loss": 1.4366291761398315, "step": 4058 }, { "epoch": 0.3426653862794551, "grad_norm": 0.154296875, "learning_rate": 3.9352887059022284e-05, "loss": 1.60232412815094, "step": 4059 }, { "epoch": 0.3427498074142862, "grad_norm": 0.154296875, "learning_rate": 3.9347556577810724e-05, "loss": 1.4846628904342651, "step": 4060 }, { "epoch": 0.34283422854911727, "grad_norm": 0.1455078125, "learning_rate": 3.9342225123800336e-05, "loss": 1.5427101850509644, "step": 4061 }, { "epoch": 0.34291864968394836, "grad_norm": 0.134765625, "learning_rate": 3.933689269735262e-05, "loss": 1.5684823989868164, "step": 4062 }, { "epoch": 0.34300307081877945, "grad_norm": 0.150390625, "learning_rate": 3.933155929882911e-05, "loss": 1.4651967287063599, "step": 4063 }, { "epoch": 0.3430874919536106, "grad_norm": 0.13671875, "learning_rate": 3.932622492859144e-05, "loss": 1.50910222530365, "step": 4064 }, { "epoch": 0.3431719130884417, "grad_norm": 0.1318359375, "learning_rate": 3.932088958700129e-05, "loss": 1.4437023401260376, "step": 4065 }, { "epoch": 0.3432563342232728, "grad_norm": 0.13671875, "learning_rate": 3.9315553274420384e-05, "loss": 1.5864500999450684, "step": 4066 }, { "epoch": 0.3433407553581039, "grad_norm": 0.15234375, "learning_rate": 3.931021599121057e-05, "loss": 1.5233927965164185, "step": 4067 }, { "epoch": 0.343425176492935, "grad_norm": 0.1484375, "learning_rate": 3.930487773773371e-05, "loss": 1.630296230316162, "step": 4068 }, { "epoch": 0.3435095976277661, "grad_norm": 0.1494140625, "learning_rate": 3.9299538514351754e-05, "loss": 1.5670444965362549, "step": 4069 }, { "epoch": 0.3435940187625972, "grad_norm": 0.138671875, "learning_rate": 3.929419832142671e-05, "loss": 1.5573936700820923, "step": 4070 }, { "epoch": 0.3436784398974283, "grad_norm": 0.1455078125, "learning_rate": 3.928885715932067e-05, "loss": 1.5202234983444214, "step": 4071 }, { "epoch": 0.34376286103225945, "grad_norm": 0.1357421875, "learning_rate": 3.928351502839577e-05, "loss": 1.4968059062957764, "step": 4072 }, { "epoch": 0.34384728216709054, "grad_norm": 0.1494140625, "learning_rate": 3.927817192901422e-05, "loss": 1.512228012084961, "step": 4073 }, { "epoch": 0.34393170330192163, "grad_norm": 0.1455078125, "learning_rate": 3.927282786153828e-05, "loss": 1.6110568046569824, "step": 4074 }, { "epoch": 0.3440161244367527, "grad_norm": 0.138671875, "learning_rate": 3.926748282633031e-05, "loss": 1.5542131662368774, "step": 4075 }, { "epoch": 0.34410054557158387, "grad_norm": 0.140625, "learning_rate": 3.926213682375271e-05, "loss": 1.506567358970642, "step": 4076 }, { "epoch": 0.34418496670641496, "grad_norm": 0.142578125, "learning_rate": 3.925678985416795e-05, "loss": 1.5058567523956299, "step": 4077 }, { "epoch": 0.34426938784124606, "grad_norm": 0.1416015625, "learning_rate": 3.925144191793858e-05, "loss": 1.5462638139724731, "step": 4078 }, { "epoch": 0.34435380897607715, "grad_norm": 0.1689453125, "learning_rate": 3.924609301542718e-05, "loss": 1.518170714378357, "step": 4079 }, { "epoch": 0.34443823011090824, "grad_norm": 0.1318359375, "learning_rate": 3.9240743146996425e-05, "loss": 1.5273282527923584, "step": 4080 }, { "epoch": 0.3445226512457394, "grad_norm": 0.1513671875, "learning_rate": 3.9235392313009064e-05, "loss": 1.493539810180664, "step": 4081 }, { "epoch": 0.3446070723805705, "grad_norm": 0.142578125, "learning_rate": 3.923004051382789e-05, "loss": 1.4624030590057373, "step": 4082 }, { "epoch": 0.34469149351540157, "grad_norm": 0.154296875, "learning_rate": 3.9224687749815766e-05, "loss": 1.4948394298553467, "step": 4083 }, { "epoch": 0.34477591465023266, "grad_norm": 0.1435546875, "learning_rate": 3.921933402133561e-05, "loss": 1.612362027168274, "step": 4084 }, { "epoch": 0.3448603357850638, "grad_norm": 0.1416015625, "learning_rate": 3.921397932875044e-05, "loss": 1.433858036994934, "step": 4085 }, { "epoch": 0.3449447569198949, "grad_norm": 0.138671875, "learning_rate": 3.92086236724233e-05, "loss": 1.5454943180084229, "step": 4086 }, { "epoch": 0.345029178054726, "grad_norm": 0.134765625, "learning_rate": 3.920326705271732e-05, "loss": 1.5806478261947632, "step": 4087 }, { "epoch": 0.3451135991895571, "grad_norm": 0.14453125, "learning_rate": 3.919790946999568e-05, "loss": 1.6064409017562866, "step": 4088 }, { "epoch": 0.34519802032438823, "grad_norm": 0.138671875, "learning_rate": 3.919255092462167e-05, "loss": 1.5228923559188843, "step": 4089 }, { "epoch": 0.3452824414592193, "grad_norm": 0.1484375, "learning_rate": 3.9187191416958594e-05, "loss": 1.5624425411224365, "step": 4090 }, { "epoch": 0.3453668625940504, "grad_norm": 0.1328125, "learning_rate": 3.9181830947369834e-05, "loss": 1.5011932849884033, "step": 4091 }, { "epoch": 0.3454512837288815, "grad_norm": 0.142578125, "learning_rate": 3.917646951621885e-05, "loss": 1.5943236351013184, "step": 4092 }, { "epoch": 0.34553570486371266, "grad_norm": 0.134765625, "learning_rate": 3.917110712386915e-05, "loss": 1.4989073276519775, "step": 4093 }, { "epoch": 0.34562012599854375, "grad_norm": 0.1552734375, "learning_rate": 3.9165743770684326e-05, "loss": 1.5568395853042603, "step": 4094 }, { "epoch": 0.34570454713337484, "grad_norm": 0.13671875, "learning_rate": 3.916037945702803e-05, "loss": 1.4189326763153076, "step": 4095 }, { "epoch": 0.34578896826820593, "grad_norm": 0.140625, "learning_rate": 3.915501418326397e-05, "loss": 1.580084204673767, "step": 4096 }, { "epoch": 0.345873389403037, "grad_norm": 0.1376953125, "learning_rate": 3.9149647949755916e-05, "loss": 1.5589677095413208, "step": 4097 }, { "epoch": 0.34595781053786817, "grad_norm": 0.134765625, "learning_rate": 3.914428075686772e-05, "loss": 1.5135618448257446, "step": 4098 }, { "epoch": 0.34604223167269926, "grad_norm": 0.1396484375, "learning_rate": 3.9138912604963296e-05, "loss": 1.428265929222107, "step": 4099 }, { "epoch": 0.34612665280753036, "grad_norm": 0.1455078125, "learning_rate": 3.913354349440661e-05, "loss": 1.578423023223877, "step": 4100 }, { "epoch": 0.34621107394236145, "grad_norm": 0.140625, "learning_rate": 3.91281734255617e-05, "loss": 1.584320068359375, "step": 4101 }, { "epoch": 0.3462954950771926, "grad_norm": 0.1376953125, "learning_rate": 3.912280239879268e-05, "loss": 1.4772133827209473, "step": 4102 }, { "epoch": 0.3463799162120237, "grad_norm": 0.1982421875, "learning_rate": 3.9117430414463705e-05, "loss": 1.582836627960205, "step": 4103 }, { "epoch": 0.3464643373468548, "grad_norm": 0.15234375, "learning_rate": 3.911205747293901e-05, "loss": 1.5089749097824097, "step": 4104 }, { "epoch": 0.34654875848168587, "grad_norm": 0.142578125, "learning_rate": 3.9106683574582905e-05, "loss": 1.535154938697815, "step": 4105 }, { "epoch": 0.346633179616517, "grad_norm": 0.1435546875, "learning_rate": 3.910130871975974e-05, "loss": 1.5410219430923462, "step": 4106 }, { "epoch": 0.3467176007513481, "grad_norm": 0.16015625, "learning_rate": 3.9095932908833955e-05, "loss": 1.5259360074996948, "step": 4107 }, { "epoch": 0.3468020218861792, "grad_norm": 0.138671875, "learning_rate": 3.909055614217003e-05, "loss": 1.515877366065979, "step": 4108 }, { "epoch": 0.3468864430210103, "grad_norm": 0.140625, "learning_rate": 3.908517842013253e-05, "loss": 1.6090598106384277, "step": 4109 }, { "epoch": 0.34697086415584144, "grad_norm": 0.1513671875, "learning_rate": 3.9079799743086076e-05, "loss": 1.5566792488098145, "step": 4110 }, { "epoch": 0.34705528529067253, "grad_norm": 0.14453125, "learning_rate": 3.907442011139536e-05, "loss": 1.577203631401062, "step": 4111 }, { "epoch": 0.3471397064255036, "grad_norm": 0.140625, "learning_rate": 3.906903952542513e-05, "loss": 1.5107967853546143, "step": 4112 }, { "epoch": 0.3472241275603347, "grad_norm": 0.138671875, "learning_rate": 3.90636579855402e-05, "loss": 1.5500916242599487, "step": 4113 }, { "epoch": 0.3473085486951658, "grad_norm": 0.146484375, "learning_rate": 3.9058275492105465e-05, "loss": 1.5486295223236084, "step": 4114 }, { "epoch": 0.34739296982999696, "grad_norm": 0.1494140625, "learning_rate": 3.9052892045485844e-05, "loss": 1.5195937156677246, "step": 4115 }, { "epoch": 0.34747739096482805, "grad_norm": 0.1396484375, "learning_rate": 3.904750764604637e-05, "loss": 1.5337733030319214, "step": 4116 }, { "epoch": 0.34756181209965914, "grad_norm": 0.1298828125, "learning_rate": 3.904212229415211e-05, "loss": 1.4709174633026123, "step": 4117 }, { "epoch": 0.34764623323449023, "grad_norm": 0.1416015625, "learning_rate": 3.903673599016821e-05, "loss": 1.5635931491851807, "step": 4118 }, { "epoch": 0.3477306543693214, "grad_norm": 0.1259765625, "learning_rate": 3.903134873445986e-05, "loss": 1.4945852756500244, "step": 4119 }, { "epoch": 0.34781507550415247, "grad_norm": 0.1396484375, "learning_rate": 3.902596052739235e-05, "loss": 1.5539568662643433, "step": 4120 }, { "epoch": 0.34789949663898356, "grad_norm": 0.1455078125, "learning_rate": 3.902057136933101e-05, "loss": 1.5352753400802612, "step": 4121 }, { "epoch": 0.34798391777381465, "grad_norm": 0.134765625, "learning_rate": 3.9015181260641206e-05, "loss": 1.5726640224456787, "step": 4122 }, { "epoch": 0.3480683389086458, "grad_norm": 0.138671875, "learning_rate": 3.9009790201688445e-05, "loss": 1.4537259340286255, "step": 4123 }, { "epoch": 0.3481527600434769, "grad_norm": 0.142578125, "learning_rate": 3.900439819283822e-05, "loss": 1.5704973936080933, "step": 4124 }, { "epoch": 0.348237181178308, "grad_norm": 0.154296875, "learning_rate": 3.899900523445614e-05, "loss": 1.5412092208862305, "step": 4125 }, { "epoch": 0.3483216023131391, "grad_norm": 0.1357421875, "learning_rate": 3.899361132690786e-05, "loss": 1.548248052597046, "step": 4126 }, { "epoch": 0.3484060234479702, "grad_norm": 0.13671875, "learning_rate": 3.898821647055909e-05, "loss": 1.5160777568817139, "step": 4127 }, { "epoch": 0.3484904445828013, "grad_norm": 0.142578125, "learning_rate": 3.898282066577562e-05, "loss": 1.5562419891357422, "step": 4128 }, { "epoch": 0.3485748657176324, "grad_norm": 0.1455078125, "learning_rate": 3.897742391292331e-05, "loss": 1.5583800077438354, "step": 4129 }, { "epoch": 0.3486592868524635, "grad_norm": 0.1396484375, "learning_rate": 3.897202621236805e-05, "loss": 1.5090252161026, "step": 4130 }, { "epoch": 0.3487437079872946, "grad_norm": 0.1279296875, "learning_rate": 3.8966627564475835e-05, "loss": 1.4522875547409058, "step": 4131 }, { "epoch": 0.34882812912212574, "grad_norm": 0.138671875, "learning_rate": 3.896122796961269e-05, "loss": 1.4719696044921875, "step": 4132 }, { "epoch": 0.34891255025695683, "grad_norm": 0.146484375, "learning_rate": 3.8955827428144734e-05, "loss": 1.5649656057357788, "step": 4133 }, { "epoch": 0.3489969713917879, "grad_norm": 0.14453125, "learning_rate": 3.895042594043814e-05, "loss": 1.5106489658355713, "step": 4134 }, { "epoch": 0.349081392526619, "grad_norm": 0.138671875, "learning_rate": 3.8945023506859125e-05, "loss": 1.5773258209228516, "step": 4135 }, { "epoch": 0.34916581366145016, "grad_norm": 0.1328125, "learning_rate": 3.893962012777401e-05, "loss": 1.534518837928772, "step": 4136 }, { "epoch": 0.34925023479628126, "grad_norm": 0.14453125, "learning_rate": 3.893421580354913e-05, "loss": 1.5367287397384644, "step": 4137 }, { "epoch": 0.34933465593111235, "grad_norm": 0.1474609375, "learning_rate": 3.892881053455093e-05, "loss": 1.5829716920852661, "step": 4138 }, { "epoch": 0.34941907706594344, "grad_norm": 0.13671875, "learning_rate": 3.892340432114589e-05, "loss": 1.5431925058364868, "step": 4139 }, { "epoch": 0.3495034982007746, "grad_norm": 0.1494140625, "learning_rate": 3.891799716370058e-05, "loss": 1.5337724685668945, "step": 4140 }, { "epoch": 0.3495879193356057, "grad_norm": 0.146484375, "learning_rate": 3.891258906258161e-05, "loss": 1.5448577404022217, "step": 4141 }, { "epoch": 0.34967234047043677, "grad_norm": 0.14453125, "learning_rate": 3.890718001815565e-05, "loss": 1.5720521211624146, "step": 4142 }, { "epoch": 0.34975676160526786, "grad_norm": 0.1396484375, "learning_rate": 3.8901770030789457e-05, "loss": 1.4972087144851685, "step": 4143 }, { "epoch": 0.349841182740099, "grad_norm": 0.1376953125, "learning_rate": 3.889635910084985e-05, "loss": 1.524438500404358, "step": 4144 }, { "epoch": 0.3499256038749301, "grad_norm": 0.142578125, "learning_rate": 3.8890947228703686e-05, "loss": 1.5459909439086914, "step": 4145 }, { "epoch": 0.3500100250097612, "grad_norm": 0.1396484375, "learning_rate": 3.888553441471791e-05, "loss": 1.5448013544082642, "step": 4146 }, { "epoch": 0.3500944461445923, "grad_norm": 0.16796875, "learning_rate": 3.888012065925952e-05, "loss": 1.50883150100708, "step": 4147 }, { "epoch": 0.3501788672794234, "grad_norm": 0.14453125, "learning_rate": 3.88747059626956e-05, "loss": 1.5527710914611816, "step": 4148 }, { "epoch": 0.3502632884142545, "grad_norm": 0.146484375, "learning_rate": 3.886929032539325e-05, "loss": 1.5968058109283447, "step": 4149 }, { "epoch": 0.3503477095490856, "grad_norm": 0.1376953125, "learning_rate": 3.8863873747719695e-05, "loss": 1.5909897089004517, "step": 4150 }, { "epoch": 0.3504321306839167, "grad_norm": 0.1396484375, "learning_rate": 3.8858456230042155e-05, "loss": 1.5564254522323608, "step": 4151 }, { "epoch": 0.3505165518187478, "grad_norm": 0.1435546875, "learning_rate": 3.885303777272798e-05, "loss": 1.5474900007247925, "step": 4152 }, { "epoch": 0.35060097295357895, "grad_norm": 0.1435546875, "learning_rate": 3.884761837614456e-05, "loss": 1.4600648880004883, "step": 4153 }, { "epoch": 0.35068539408841004, "grad_norm": 0.1494140625, "learning_rate": 3.884219804065931e-05, "loss": 1.582540512084961, "step": 4154 }, { "epoch": 0.35076981522324113, "grad_norm": 0.1494140625, "learning_rate": 3.8836776766639764e-05, "loss": 1.504251480102539, "step": 4155 }, { "epoch": 0.3508542363580722, "grad_norm": 0.142578125, "learning_rate": 3.88313545544535e-05, "loss": 1.498350977897644, "step": 4156 }, { "epoch": 0.35093865749290337, "grad_norm": 0.1474609375, "learning_rate": 3.8825931404468155e-05, "loss": 1.5258105993270874, "step": 4157 }, { "epoch": 0.35102307862773446, "grad_norm": 0.1435546875, "learning_rate": 3.8820507317051416e-05, "loss": 1.4847426414489746, "step": 4158 }, { "epoch": 0.35110749976256556, "grad_norm": 0.138671875, "learning_rate": 3.8815082292571066e-05, "loss": 1.452571153640747, "step": 4159 }, { "epoch": 0.35119192089739665, "grad_norm": 0.140625, "learning_rate": 3.880965633139493e-05, "loss": 1.504881501197815, "step": 4160 }, { "epoch": 0.3512763420322278, "grad_norm": 0.1513671875, "learning_rate": 3.8804229433890895e-05, "loss": 1.5394225120544434, "step": 4161 }, { "epoch": 0.3513607631670589, "grad_norm": 0.13671875, "learning_rate": 3.879880160042693e-05, "loss": 1.4760478734970093, "step": 4162 }, { "epoch": 0.35144518430189, "grad_norm": 0.14453125, "learning_rate": 3.879337283137105e-05, "loss": 1.5566091537475586, "step": 4163 }, { "epoch": 0.35152960543672107, "grad_norm": 0.14453125, "learning_rate": 3.878794312709133e-05, "loss": 1.5566586256027222, "step": 4164 }, { "epoch": 0.35161402657155216, "grad_norm": 0.1435546875, "learning_rate": 3.8782512487955924e-05, "loss": 1.573009729385376, "step": 4165 }, { "epoch": 0.3516984477063833, "grad_norm": 0.1591796875, "learning_rate": 3.877708091433305e-05, "loss": 1.5581060647964478, "step": 4166 }, { "epoch": 0.3517828688412144, "grad_norm": 0.1484375, "learning_rate": 3.877164840659097e-05, "loss": 1.457227349281311, "step": 4167 }, { "epoch": 0.3518672899760455, "grad_norm": 0.142578125, "learning_rate": 3.8766214965098024e-05, "loss": 1.6485484838485718, "step": 4168 }, { "epoch": 0.3519517111108766, "grad_norm": 0.1396484375, "learning_rate": 3.8760780590222616e-05, "loss": 1.5643706321716309, "step": 4169 }, { "epoch": 0.35203613224570773, "grad_norm": 0.1318359375, "learning_rate": 3.875534528233321e-05, "loss": 1.470655918121338, "step": 4170 }, { "epoch": 0.3521205533805388, "grad_norm": 0.1376953125, "learning_rate": 3.874990904179833e-05, "loss": 1.4773730039596558, "step": 4171 }, { "epoch": 0.3522049745153699, "grad_norm": 0.1396484375, "learning_rate": 3.8744471868986566e-05, "loss": 1.5805697441101074, "step": 4172 }, { "epoch": 0.352289395650201, "grad_norm": 0.1484375, "learning_rate": 3.8739033764266566e-05, "loss": 1.5270763635635376, "step": 4173 }, { "epoch": 0.35237381678503216, "grad_norm": 0.1318359375, "learning_rate": 3.873359472800705e-05, "loss": 1.4883043766021729, "step": 4174 }, { "epoch": 0.35245823791986325, "grad_norm": 0.1357421875, "learning_rate": 3.8728154760576817e-05, "loss": 1.528584599494934, "step": 4175 }, { "epoch": 0.35254265905469434, "grad_norm": 0.138671875, "learning_rate": 3.872271386234468e-05, "loss": 1.5342185497283936, "step": 4176 }, { "epoch": 0.35262708018952543, "grad_norm": 0.1357421875, "learning_rate": 3.871727203367956e-05, "loss": 1.530784010887146, "step": 4177 }, { "epoch": 0.3527115013243566, "grad_norm": 0.1376953125, "learning_rate": 3.871182927495042e-05, "loss": 1.583929181098938, "step": 4178 }, { "epoch": 0.35279592245918767, "grad_norm": 0.130859375, "learning_rate": 3.870638558652631e-05, "loss": 1.538698673248291, "step": 4179 }, { "epoch": 0.35288034359401876, "grad_norm": 0.1357421875, "learning_rate": 3.87009409687763e-05, "loss": 1.5937175750732422, "step": 4180 }, { "epoch": 0.35296476472884986, "grad_norm": 0.1357421875, "learning_rate": 3.869549542206956e-05, "loss": 1.5150856971740723, "step": 4181 }, { "epoch": 0.35304918586368095, "grad_norm": 0.1298828125, "learning_rate": 3.8690048946775314e-05, "loss": 1.4813687801361084, "step": 4182 }, { "epoch": 0.3531336069985121, "grad_norm": 0.13671875, "learning_rate": 3.8684601543262844e-05, "loss": 1.5641937255859375, "step": 4183 }, { "epoch": 0.3532180281333432, "grad_norm": 0.140625, "learning_rate": 3.867915321190149e-05, "loss": 1.4794632196426392, "step": 4184 }, { "epoch": 0.3533024492681743, "grad_norm": 0.138671875, "learning_rate": 3.867370395306068e-05, "loss": 1.4428844451904297, "step": 4185 }, { "epoch": 0.35338687040300537, "grad_norm": 0.1376953125, "learning_rate": 3.866825376710986e-05, "loss": 1.5031570196151733, "step": 4186 }, { "epoch": 0.3534712915378365, "grad_norm": 0.140625, "learning_rate": 3.866280265441858e-05, "loss": 1.592689037322998, "step": 4187 }, { "epoch": 0.3535557126726676, "grad_norm": 0.1416015625, "learning_rate": 3.865735061535645e-05, "loss": 1.5193283557891846, "step": 4188 }, { "epoch": 0.3536401338074987, "grad_norm": 0.13671875, "learning_rate": 3.865189765029312e-05, "loss": 1.5724318027496338, "step": 4189 }, { "epoch": 0.3537245549423298, "grad_norm": 0.1416015625, "learning_rate": 3.864644375959832e-05, "loss": 1.562955617904663, "step": 4190 }, { "epoch": 0.35380897607716094, "grad_norm": 0.1357421875, "learning_rate": 3.864098894364181e-05, "loss": 1.592862844467163, "step": 4191 }, { "epoch": 0.35389339721199203, "grad_norm": 0.138671875, "learning_rate": 3.8635533202793474e-05, "loss": 1.537570595741272, "step": 4192 }, { "epoch": 0.3539778183468231, "grad_norm": 0.1484375, "learning_rate": 3.863007653742321e-05, "loss": 1.5798419713974, "step": 4193 }, { "epoch": 0.3540622394816542, "grad_norm": 0.1435546875, "learning_rate": 3.8624618947901e-05, "loss": 1.6238263845443726, "step": 4194 }, { "epoch": 0.35414666061648536, "grad_norm": 0.14453125, "learning_rate": 3.8619160434596866e-05, "loss": 1.5706884860992432, "step": 4195 }, { "epoch": 0.35423108175131646, "grad_norm": 0.140625, "learning_rate": 3.861370099788092e-05, "loss": 1.5786099433898926, "step": 4196 }, { "epoch": 0.35431550288614755, "grad_norm": 0.142578125, "learning_rate": 3.860824063812333e-05, "loss": 1.5864981412887573, "step": 4197 }, { "epoch": 0.35439992402097864, "grad_norm": 0.150390625, "learning_rate": 3.860277935569432e-05, "loss": 1.5747785568237305, "step": 4198 }, { "epoch": 0.35448434515580973, "grad_norm": 0.1376953125, "learning_rate": 3.859731715096416e-05, "loss": 1.5528098344802856, "step": 4199 }, { "epoch": 0.3545687662906409, "grad_norm": 0.154296875, "learning_rate": 3.859185402430321e-05, "loss": 1.5115820169448853, "step": 4200 }, { "epoch": 0.35465318742547197, "grad_norm": 0.1416015625, "learning_rate": 3.85863899760819e-05, "loss": 1.5520834922790527, "step": 4201 }, { "epoch": 0.35473760856030306, "grad_norm": 0.1435546875, "learning_rate": 3.8580925006670686e-05, "loss": 1.5937007665634155, "step": 4202 }, { "epoch": 0.35482202969513416, "grad_norm": 0.1416015625, "learning_rate": 3.857545911644011e-05, "loss": 1.5315251350402832, "step": 4203 }, { "epoch": 0.3549064508299653, "grad_norm": 0.1474609375, "learning_rate": 3.8569992305760784e-05, "loss": 1.56178879737854, "step": 4204 }, { "epoch": 0.3549908719647964, "grad_norm": 0.1416015625, "learning_rate": 3.8564524575003355e-05, "loss": 1.5205937623977661, "step": 4205 }, { "epoch": 0.3550752930996275, "grad_norm": 0.1513671875, "learning_rate": 3.8559055924538554e-05, "loss": 1.5571054220199585, "step": 4206 }, { "epoch": 0.3551597142344586, "grad_norm": 0.13671875, "learning_rate": 3.855358635473717e-05, "loss": 1.5635684728622437, "step": 4207 }, { "epoch": 0.3552441353692897, "grad_norm": 0.1396484375, "learning_rate": 3.8548115865970055e-05, "loss": 1.5223383903503418, "step": 4208 }, { "epoch": 0.3553285565041208, "grad_norm": 0.146484375, "learning_rate": 3.854264445860811e-05, "loss": 1.5038105249404907, "step": 4209 }, { "epoch": 0.3554129776389519, "grad_norm": 0.1435546875, "learning_rate": 3.8537172133022334e-05, "loss": 1.614169716835022, "step": 4210 }, { "epoch": 0.355497398773783, "grad_norm": 0.15234375, "learning_rate": 3.853169888958374e-05, "loss": 1.5239009857177734, "step": 4211 }, { "epoch": 0.3555818199086141, "grad_norm": 0.1416015625, "learning_rate": 3.8526224728663436e-05, "loss": 1.436953067779541, "step": 4212 }, { "epoch": 0.35566624104344524, "grad_norm": 0.14453125, "learning_rate": 3.852074965063258e-05, "loss": 1.5444506406784058, "step": 4213 }, { "epoch": 0.35575066217827633, "grad_norm": 0.1533203125, "learning_rate": 3.85152736558624e-05, "loss": 1.533927321434021, "step": 4214 }, { "epoch": 0.3558350833131074, "grad_norm": 0.142578125, "learning_rate": 3.850979674472418e-05, "loss": 1.5496118068695068, "step": 4215 }, { "epoch": 0.3559195044479385, "grad_norm": 0.138671875, "learning_rate": 3.850431891758927e-05, "loss": 1.5004830360412598, "step": 4216 }, { "epoch": 0.35600392558276966, "grad_norm": 0.1318359375, "learning_rate": 3.849884017482908e-05, "loss": 1.5666768550872803, "step": 4217 }, { "epoch": 0.35608834671760076, "grad_norm": 0.1455078125, "learning_rate": 3.849336051681507e-05, "loss": 1.5440768003463745, "step": 4218 }, { "epoch": 0.35617276785243185, "grad_norm": 0.1494140625, "learning_rate": 3.848787994391879e-05, "loss": 1.5481736660003662, "step": 4219 }, { "epoch": 0.35625718898726294, "grad_norm": 0.150390625, "learning_rate": 3.848239845651182e-05, "loss": 1.669451117515564, "step": 4220 }, { "epoch": 0.3563416101220941, "grad_norm": 0.154296875, "learning_rate": 3.847691605496584e-05, "loss": 1.5883976221084595, "step": 4221 }, { "epoch": 0.3564260312569252, "grad_norm": 0.14453125, "learning_rate": 3.847143273965255e-05, "loss": 1.5849924087524414, "step": 4222 }, { "epoch": 0.35651045239175627, "grad_norm": 0.1494140625, "learning_rate": 3.846594851094374e-05, "loss": 1.5977121591567993, "step": 4223 }, { "epoch": 0.35659487352658736, "grad_norm": 0.1435546875, "learning_rate": 3.8460463369211254e-05, "loss": 1.5947600603103638, "step": 4224 }, { "epoch": 0.3566792946614185, "grad_norm": 0.140625, "learning_rate": 3.8454977314826995e-05, "loss": 1.534454107284546, "step": 4225 }, { "epoch": 0.3567637157962496, "grad_norm": 0.1416015625, "learning_rate": 3.844949034816293e-05, "loss": 1.550074577331543, "step": 4226 }, { "epoch": 0.3568481369310807, "grad_norm": 0.1416015625, "learning_rate": 3.844400246959109e-05, "loss": 1.5415791273117065, "step": 4227 }, { "epoch": 0.3569325580659118, "grad_norm": 0.1455078125, "learning_rate": 3.843851367948358e-05, "loss": 1.5513763427734375, "step": 4228 }, { "epoch": 0.3570169792007429, "grad_norm": 0.1455078125, "learning_rate": 3.843302397821253e-05, "loss": 1.5272763967514038, "step": 4229 }, { "epoch": 0.357101400335574, "grad_norm": 0.134765625, "learning_rate": 3.842753336615017e-05, "loss": 1.4959393739700317, "step": 4230 }, { "epoch": 0.3571858214704051, "grad_norm": 0.1279296875, "learning_rate": 3.842204184366877e-05, "loss": 1.4952527284622192, "step": 4231 }, { "epoch": 0.3572702426052362, "grad_norm": 0.1474609375, "learning_rate": 3.841654941114067e-05, "loss": 1.6227062940597534, "step": 4232 }, { "epoch": 0.3573546637400673, "grad_norm": 0.14453125, "learning_rate": 3.841105606893827e-05, "loss": 1.581745982170105, "step": 4233 }, { "epoch": 0.35743908487489845, "grad_norm": 0.140625, "learning_rate": 3.8405561817434035e-05, "loss": 1.5556854009628296, "step": 4234 }, { "epoch": 0.35752350600972954, "grad_norm": 0.1494140625, "learning_rate": 3.840006665700049e-05, "loss": 1.51448655128479, "step": 4235 }, { "epoch": 0.35760792714456063, "grad_norm": 0.1435546875, "learning_rate": 3.839457058801021e-05, "loss": 1.4268620014190674, "step": 4236 }, { "epoch": 0.3576923482793917, "grad_norm": 0.1416015625, "learning_rate": 3.838907361083585e-05, "loss": 1.533915638923645, "step": 4237 }, { "epoch": 0.3577767694142229, "grad_norm": 0.1494140625, "learning_rate": 3.838357572585012e-05, "loss": 1.524922490119934, "step": 4238 }, { "epoch": 0.35786119054905396, "grad_norm": 0.142578125, "learning_rate": 3.837807693342578e-05, "loss": 1.4999244213104248, "step": 4239 }, { "epoch": 0.35794561168388506, "grad_norm": 0.14453125, "learning_rate": 3.837257723393566e-05, "loss": 1.613122582435608, "step": 4240 }, { "epoch": 0.35803003281871615, "grad_norm": 0.1455078125, "learning_rate": 3.836707662775267e-05, "loss": 1.5780361890792847, "step": 4241 }, { "epoch": 0.3581144539535473, "grad_norm": 0.1494140625, "learning_rate": 3.8361575115249756e-05, "loss": 1.5418686866760254, "step": 4242 }, { "epoch": 0.3581988750883784, "grad_norm": 0.1376953125, "learning_rate": 3.835607269679993e-05, "loss": 1.5201349258422852, "step": 4243 }, { "epoch": 0.3582832962232095, "grad_norm": 0.1455078125, "learning_rate": 3.835056937277627e-05, "loss": 1.6287107467651367, "step": 4244 }, { "epoch": 0.35836771735804057, "grad_norm": 0.142578125, "learning_rate": 3.8345065143551916e-05, "loss": 1.568234920501709, "step": 4245 }, { "epoch": 0.35845213849287166, "grad_norm": 0.142578125, "learning_rate": 3.8339560009500076e-05, "loss": 1.4907076358795166, "step": 4246 }, { "epoch": 0.3585365596277028, "grad_norm": 0.1357421875, "learning_rate": 3.833405397099399e-05, "loss": 1.5749998092651367, "step": 4247 }, { "epoch": 0.3586209807625339, "grad_norm": 0.181640625, "learning_rate": 3.8328547028407004e-05, "loss": 1.5183391571044922, "step": 4248 }, { "epoch": 0.358705401897365, "grad_norm": 0.1328125, "learning_rate": 3.832303918211248e-05, "loss": 1.4594600200653076, "step": 4249 }, { "epoch": 0.3587898230321961, "grad_norm": 0.1337890625, "learning_rate": 3.831753043248389e-05, "loss": 1.5642551183700562, "step": 4250 }, { "epoch": 0.35887424416702723, "grad_norm": 0.1513671875, "learning_rate": 3.831202077989472e-05, "loss": 1.4864685535430908, "step": 4251 }, { "epoch": 0.3589586653018583, "grad_norm": 0.150390625, "learning_rate": 3.8306510224718536e-05, "loss": 1.5648010969161987, "step": 4252 }, { "epoch": 0.3590430864366894, "grad_norm": 0.13671875, "learning_rate": 3.8300998767328976e-05, "loss": 1.5139609575271606, "step": 4253 }, { "epoch": 0.3591275075715205, "grad_norm": 0.134765625, "learning_rate": 3.829548640809974e-05, "loss": 1.5306133031845093, "step": 4254 }, { "epoch": 0.35921192870635166, "grad_norm": 0.15234375, "learning_rate": 3.828997314740456e-05, "loss": 1.56240975856781, "step": 4255 }, { "epoch": 0.35929634984118275, "grad_norm": 0.1474609375, "learning_rate": 3.8284458985617256e-05, "loss": 1.5253732204437256, "step": 4256 }, { "epoch": 0.35938077097601384, "grad_norm": 0.154296875, "learning_rate": 3.82789439231117e-05, "loss": 1.541413426399231, "step": 4257 }, { "epoch": 0.35946519211084493, "grad_norm": 0.15234375, "learning_rate": 3.8273427960261824e-05, "loss": 1.4895724058151245, "step": 4258 }, { "epoch": 0.3595496132456761, "grad_norm": 0.14453125, "learning_rate": 3.826791109744163e-05, "loss": 1.4827990531921387, "step": 4259 }, { "epoch": 0.3596340343805072, "grad_norm": 0.1396484375, "learning_rate": 3.8262393335025175e-05, "loss": 1.5309453010559082, "step": 4260 }, { "epoch": 0.35971845551533826, "grad_norm": 0.138671875, "learning_rate": 3.825687467338657e-05, "loss": 1.4829250574111938, "step": 4261 }, { "epoch": 0.35980287665016936, "grad_norm": 0.1435546875, "learning_rate": 3.82513551129e-05, "loss": 1.507392406463623, "step": 4262 }, { "epoch": 0.35988729778500045, "grad_norm": 0.1376953125, "learning_rate": 3.82458346539397e-05, "loss": 1.55986487865448, "step": 4263 }, { "epoch": 0.3599717189198316, "grad_norm": 0.140625, "learning_rate": 3.824031329687997e-05, "loss": 1.552465796470642, "step": 4264 }, { "epoch": 0.3600561400546627, "grad_norm": 0.130859375, "learning_rate": 3.8234791042095177e-05, "loss": 1.5164263248443604, "step": 4265 }, { "epoch": 0.3601405611894938, "grad_norm": 0.146484375, "learning_rate": 3.822926788995974e-05, "loss": 1.5630155801773071, "step": 4266 }, { "epoch": 0.36022498232432487, "grad_norm": 0.1630859375, "learning_rate": 3.822374384084813e-05, "loss": 1.5202362537384033, "step": 4267 }, { "epoch": 0.360309403459156, "grad_norm": 0.1474609375, "learning_rate": 3.8218218895134914e-05, "loss": 1.500826120376587, "step": 4268 }, { "epoch": 0.3603938245939871, "grad_norm": 0.1474609375, "learning_rate": 3.821269305319468e-05, "loss": 1.5291640758514404, "step": 4269 }, { "epoch": 0.3604782457288182, "grad_norm": 0.146484375, "learning_rate": 3.820716631540209e-05, "loss": 1.5384401082992554, "step": 4270 }, { "epoch": 0.3605626668636493, "grad_norm": 0.142578125, "learning_rate": 3.820163868213189e-05, "loss": 1.542315125465393, "step": 4271 }, { "epoch": 0.36064708799848044, "grad_norm": 0.13671875, "learning_rate": 3.819611015375885e-05, "loss": 1.5508623123168945, "step": 4272 }, { "epoch": 0.36073150913331153, "grad_norm": 0.1416015625, "learning_rate": 3.819058073065782e-05, "loss": 1.4852579832077026, "step": 4273 }, { "epoch": 0.3608159302681426, "grad_norm": 0.14453125, "learning_rate": 3.818505041320372e-05, "loss": 1.556171178817749, "step": 4274 }, { "epoch": 0.3609003514029737, "grad_norm": 0.1357421875, "learning_rate": 3.8179519201771496e-05, "loss": 1.529795527458191, "step": 4275 }, { "epoch": 0.36098477253780487, "grad_norm": 0.150390625, "learning_rate": 3.81739870967362e-05, "loss": 1.5467628240585327, "step": 4276 }, { "epoch": 0.36106919367263596, "grad_norm": 0.14453125, "learning_rate": 3.8168454098472906e-05, "loss": 1.5944387912750244, "step": 4277 }, { "epoch": 0.36115361480746705, "grad_norm": 0.1455078125, "learning_rate": 3.816292020735678e-05, "loss": 1.5121206045150757, "step": 4278 }, { "epoch": 0.36123803594229814, "grad_norm": 0.142578125, "learning_rate": 3.8157385423763015e-05, "loss": 1.602317214012146, "step": 4279 }, { "epoch": 0.36132245707712923, "grad_norm": 0.15625, "learning_rate": 3.8151849748066895e-05, "loss": 1.5397443771362305, "step": 4280 }, { "epoch": 0.3614068782119604, "grad_norm": 0.130859375, "learning_rate": 3.8146313180643755e-05, "loss": 1.5571374893188477, "step": 4281 }, { "epoch": 0.3614912993467915, "grad_norm": 0.1318359375, "learning_rate": 3.814077572186897e-05, "loss": 1.542072057723999, "step": 4282 }, { "epoch": 0.36157572048162256, "grad_norm": 0.1318359375, "learning_rate": 3.813523737211802e-05, "loss": 1.50530207157135, "step": 4283 }, { "epoch": 0.36166014161645366, "grad_norm": 0.1328125, "learning_rate": 3.812969813176639e-05, "loss": 1.5168627500534058, "step": 4284 }, { "epoch": 0.3617445627512848, "grad_norm": 0.2041015625, "learning_rate": 3.812415800118968e-05, "loss": 1.5759422779083252, "step": 4285 }, { "epoch": 0.3618289838861159, "grad_norm": 0.1416015625, "learning_rate": 3.81186169807635e-05, "loss": 1.5056719779968262, "step": 4286 }, { "epoch": 0.361913405020947, "grad_norm": 0.1494140625, "learning_rate": 3.811307507086356e-05, "loss": 1.5110524892807007, "step": 4287 }, { "epoch": 0.3619978261557781, "grad_norm": 0.140625, "learning_rate": 3.810753227186561e-05, "loss": 1.531961441040039, "step": 4288 }, { "epoch": 0.3620822472906092, "grad_norm": 0.138671875, "learning_rate": 3.8101988584145467e-05, "loss": 1.4266729354858398, "step": 4289 }, { "epoch": 0.3621666684254403, "grad_norm": 0.14453125, "learning_rate": 3.8096444008079004e-05, "loss": 1.4880362749099731, "step": 4290 }, { "epoch": 0.3622510895602714, "grad_norm": 0.1455078125, "learning_rate": 3.809089854404215e-05, "loss": 1.4893426895141602, "step": 4291 }, { "epoch": 0.3623355106951025, "grad_norm": 0.16015625, "learning_rate": 3.8085352192410915e-05, "loss": 1.4652785062789917, "step": 4292 }, { "epoch": 0.36241993182993365, "grad_norm": 0.1337890625, "learning_rate": 3.807980495356136e-05, "loss": 1.450246810913086, "step": 4293 }, { "epoch": 0.36250435296476474, "grad_norm": 0.138671875, "learning_rate": 3.807425682786957e-05, "loss": 1.5563390254974365, "step": 4294 }, { "epoch": 0.36258877409959583, "grad_norm": 0.138671875, "learning_rate": 3.806870781571175e-05, "loss": 1.4801567792892456, "step": 4295 }, { "epoch": 0.3626731952344269, "grad_norm": 0.1455078125, "learning_rate": 3.8063157917464124e-05, "loss": 1.6428930759429932, "step": 4296 }, { "epoch": 0.362757616369258, "grad_norm": 0.1416015625, "learning_rate": 3.805760713350299e-05, "loss": 1.4878308773040771, "step": 4297 }, { "epoch": 0.36284203750408917, "grad_norm": 0.1474609375, "learning_rate": 3.8052055464204716e-05, "loss": 1.607409119606018, "step": 4298 }, { "epoch": 0.36292645863892026, "grad_norm": 0.1494140625, "learning_rate": 3.80465029099457e-05, "loss": 1.561536192893982, "step": 4299 }, { "epoch": 0.36301087977375135, "grad_norm": 0.1337890625, "learning_rate": 3.804094947110243e-05, "loss": 1.602408766746521, "step": 4300 }, { "epoch": 0.36309530090858244, "grad_norm": 0.134765625, "learning_rate": 3.803539514805144e-05, "loss": 1.570378303527832, "step": 4301 }, { "epoch": 0.3631797220434136, "grad_norm": 0.138671875, "learning_rate": 3.802983994116933e-05, "loss": 1.5122379064559937, "step": 4302 }, { "epoch": 0.3632641431782447, "grad_norm": 0.1376953125, "learning_rate": 3.802428385083274e-05, "loss": 1.4394296407699585, "step": 4303 }, { "epoch": 0.3633485643130758, "grad_norm": 0.1513671875, "learning_rate": 3.8018726877418405e-05, "loss": 1.6114662885665894, "step": 4304 }, { "epoch": 0.36343298544790686, "grad_norm": 0.142578125, "learning_rate": 3.8013169021303095e-05, "loss": 1.5274810791015625, "step": 4305 }, { "epoch": 0.363517406582738, "grad_norm": 0.15234375, "learning_rate": 3.800761028286365e-05, "loss": 1.5882306098937988, "step": 4306 }, { "epoch": 0.3636018277175691, "grad_norm": 0.1591796875, "learning_rate": 3.800205066247695e-05, "loss": 1.5697695016860962, "step": 4307 }, { "epoch": 0.3636862488524002, "grad_norm": 0.134765625, "learning_rate": 3.799649016051997e-05, "loss": 1.3950949907302856, "step": 4308 }, { "epoch": 0.3637706699872313, "grad_norm": 0.146484375, "learning_rate": 3.7990928777369724e-05, "loss": 1.5303713083267212, "step": 4309 }, { "epoch": 0.36385509112206244, "grad_norm": 0.1396484375, "learning_rate": 3.7985366513403275e-05, "loss": 1.502548098564148, "step": 4310 }, { "epoch": 0.3639395122568935, "grad_norm": 0.142578125, "learning_rate": 3.797980336899776e-05, "loss": 1.502594232559204, "step": 4311 }, { "epoch": 0.3640239333917246, "grad_norm": 0.134765625, "learning_rate": 3.797423934453038e-05, "loss": 1.5267540216445923, "step": 4312 }, { "epoch": 0.3641083545265557, "grad_norm": 0.138671875, "learning_rate": 3.796867444037839e-05, "loss": 1.5799369812011719, "step": 4313 }, { "epoch": 0.3641927756613868, "grad_norm": 0.1259765625, "learning_rate": 3.79631086569191e-05, "loss": 1.4631632566452026, "step": 4314 }, { "epoch": 0.36427719679621795, "grad_norm": 0.1708984375, "learning_rate": 3.795754199452988e-05, "loss": 1.5604795217514038, "step": 4315 }, { "epoch": 0.36436161793104904, "grad_norm": 0.13671875, "learning_rate": 3.795197445358817e-05, "loss": 1.498542308807373, "step": 4316 }, { "epoch": 0.36444603906588013, "grad_norm": 0.1611328125, "learning_rate": 3.794640603447145e-05, "loss": 1.588510274887085, "step": 4317 }, { "epoch": 0.3645304602007112, "grad_norm": 0.1328125, "learning_rate": 3.794083673755729e-05, "loss": 1.529616355895996, "step": 4318 }, { "epoch": 0.3646148813355424, "grad_norm": 0.1484375, "learning_rate": 3.79352665632233e-05, "loss": 1.5843331813812256, "step": 4319 }, { "epoch": 0.36469930247037347, "grad_norm": 0.1552734375, "learning_rate": 3.792969551184713e-05, "loss": 1.6175804138183594, "step": 4320 }, { "epoch": 0.36478372360520456, "grad_norm": 0.1474609375, "learning_rate": 3.792412358380654e-05, "loss": 1.523620367050171, "step": 4321 }, { "epoch": 0.36486814474003565, "grad_norm": 0.1376953125, "learning_rate": 3.7918550779479295e-05, "loss": 1.5389771461486816, "step": 4322 }, { "epoch": 0.3649525658748668, "grad_norm": 0.1396484375, "learning_rate": 3.791297709924326e-05, "loss": 1.4838805198669434, "step": 4323 }, { "epoch": 0.3650369870096979, "grad_norm": 0.1494140625, "learning_rate": 3.790740254347634e-05, "loss": 1.440817952156067, "step": 4324 }, { "epoch": 0.365121408144529, "grad_norm": 0.1494140625, "learning_rate": 3.790182711255649e-05, "loss": 1.4943755865097046, "step": 4325 }, { "epoch": 0.3652058292793601, "grad_norm": 0.1376953125, "learning_rate": 3.789625080686177e-05, "loss": 1.4912463426589966, "step": 4326 }, { "epoch": 0.3652902504141912, "grad_norm": 0.1494140625, "learning_rate": 3.7890673626770234e-05, "loss": 1.5335845947265625, "step": 4327 }, { "epoch": 0.3653746715490223, "grad_norm": 0.138671875, "learning_rate": 3.7885095572660037e-05, "loss": 1.5478065013885498, "step": 4328 }, { "epoch": 0.3654590926838534, "grad_norm": 0.1328125, "learning_rate": 3.78795166449094e-05, "loss": 1.5127240419387817, "step": 4329 }, { "epoch": 0.3655435138186845, "grad_norm": 0.1396484375, "learning_rate": 3.787393684389657e-05, "loss": 1.5619654655456543, "step": 4330 }, { "epoch": 0.3656279349535156, "grad_norm": 0.14453125, "learning_rate": 3.786835616999988e-05, "loss": 1.5148543119430542, "step": 4331 }, { "epoch": 0.36571235608834674, "grad_norm": 0.1416015625, "learning_rate": 3.7862774623597706e-05, "loss": 1.498319387435913, "step": 4332 }, { "epoch": 0.3657967772231778, "grad_norm": 0.14453125, "learning_rate": 3.78571922050685e-05, "loss": 1.5573800802230835, "step": 4333 }, { "epoch": 0.3658811983580089, "grad_norm": 0.1357421875, "learning_rate": 3.785160891479075e-05, "loss": 1.5146631002426147, "step": 4334 }, { "epoch": 0.36596561949284, "grad_norm": 0.1494140625, "learning_rate": 3.784602475314303e-05, "loss": 1.5670843124389648, "step": 4335 }, { "epoch": 0.36605004062767116, "grad_norm": 0.1376953125, "learning_rate": 3.784043972050396e-05, "loss": 1.5923855304718018, "step": 4336 }, { "epoch": 0.36613446176250225, "grad_norm": 0.16015625, "learning_rate": 3.78348538172522e-05, "loss": 1.5550603866577148, "step": 4337 }, { "epoch": 0.36621888289733334, "grad_norm": 0.1396484375, "learning_rate": 3.782926704376651e-05, "loss": 1.5754567384719849, "step": 4338 }, { "epoch": 0.36630330403216443, "grad_norm": 0.1328125, "learning_rate": 3.782367940042567e-05, "loss": 1.5055769681930542, "step": 4339 }, { "epoch": 0.3663877251669956, "grad_norm": 0.140625, "learning_rate": 3.7818090887608545e-05, "loss": 1.5811851024627686, "step": 4340 }, { "epoch": 0.3664721463018267, "grad_norm": 0.1533203125, "learning_rate": 3.781250150569405e-05, "loss": 1.5877102613449097, "step": 4341 }, { "epoch": 0.36655656743665777, "grad_norm": 0.1376953125, "learning_rate": 3.780691125506115e-05, "loss": 1.4756803512573242, "step": 4342 }, { "epoch": 0.36664098857148886, "grad_norm": 0.146484375, "learning_rate": 3.780132013608889e-05, "loss": 1.5881564617156982, "step": 4343 }, { "epoch": 0.36672540970632, "grad_norm": 0.142578125, "learning_rate": 3.7795728149156354e-05, "loss": 1.552903175354004, "step": 4344 }, { "epoch": 0.3668098308411511, "grad_norm": 0.12890625, "learning_rate": 3.779013529464268e-05, "loss": 1.4995864629745483, "step": 4345 }, { "epoch": 0.3668942519759822, "grad_norm": 0.1357421875, "learning_rate": 3.7784541572927105e-05, "loss": 1.602548360824585, "step": 4346 }, { "epoch": 0.3669786731108133, "grad_norm": 0.154296875, "learning_rate": 3.777894698438887e-05, "loss": 1.5090855360031128, "step": 4347 }, { "epoch": 0.3670630942456444, "grad_norm": 0.1474609375, "learning_rate": 3.777335152940733e-05, "loss": 1.531537652015686, "step": 4348 }, { "epoch": 0.3671475153804755, "grad_norm": 0.13671875, "learning_rate": 3.776775520836183e-05, "loss": 1.5141760110855103, "step": 4349 }, { "epoch": 0.3672319365153066, "grad_norm": 0.1328125, "learning_rate": 3.776215802163186e-05, "loss": 1.533980369567871, "step": 4350 }, { "epoch": 0.3673163576501377, "grad_norm": 0.1474609375, "learning_rate": 3.775655996959689e-05, "loss": 1.5066958665847778, "step": 4351 }, { "epoch": 0.3674007787849688, "grad_norm": 0.1416015625, "learning_rate": 3.775096105263648e-05, "loss": 1.462054967880249, "step": 4352 }, { "epoch": 0.36748519991979994, "grad_norm": 0.1357421875, "learning_rate": 3.774536127113027e-05, "loss": 1.6174290180206299, "step": 4353 }, { "epoch": 0.36756962105463103, "grad_norm": 0.138671875, "learning_rate": 3.7739760625457935e-05, "loss": 1.54783296585083, "step": 4354 }, { "epoch": 0.3676540421894621, "grad_norm": 0.12890625, "learning_rate": 3.7734159115999214e-05, "loss": 1.461444616317749, "step": 4355 }, { "epoch": 0.3677384633242932, "grad_norm": 0.134765625, "learning_rate": 3.772855674313388e-05, "loss": 1.4184539318084717, "step": 4356 }, { "epoch": 0.36782288445912437, "grad_norm": 0.1337890625, "learning_rate": 3.772295350724181e-05, "loss": 1.5267813205718994, "step": 4357 }, { "epoch": 0.36790730559395546, "grad_norm": 0.1337890625, "learning_rate": 3.7717349408702904e-05, "loss": 1.5071803331375122, "step": 4358 }, { "epoch": 0.36799172672878655, "grad_norm": 0.1298828125, "learning_rate": 3.7711744447897145e-05, "loss": 1.548398494720459, "step": 4359 }, { "epoch": 0.36807614786361764, "grad_norm": 0.1572265625, "learning_rate": 3.7706138625204565e-05, "loss": 1.6080844402313232, "step": 4360 }, { "epoch": 0.36816056899844873, "grad_norm": 0.140625, "learning_rate": 3.7700531941005236e-05, "loss": 1.5178509950637817, "step": 4361 }, { "epoch": 0.3682449901332799, "grad_norm": 0.1455078125, "learning_rate": 3.7694924395679315e-05, "loss": 1.5054571628570557, "step": 4362 }, { "epoch": 0.368329411268111, "grad_norm": 0.1328125, "learning_rate": 3.7689315989607e-05, "loss": 1.4962449073791504, "step": 4363 }, { "epoch": 0.36841383240294207, "grad_norm": 0.1396484375, "learning_rate": 3.7683706723168564e-05, "loss": 1.4789073467254639, "step": 4364 }, { "epoch": 0.36849825353777316, "grad_norm": 0.1435546875, "learning_rate": 3.767809659674433e-05, "loss": 1.6085176467895508, "step": 4365 }, { "epoch": 0.3685826746726043, "grad_norm": 0.138671875, "learning_rate": 3.767248561071467e-05, "loss": 1.618386149406433, "step": 4366 }, { "epoch": 0.3686670958074354, "grad_norm": 0.142578125, "learning_rate": 3.766687376546002e-05, "loss": 1.5755470991134644, "step": 4367 }, { "epoch": 0.3687515169422665, "grad_norm": 0.1455078125, "learning_rate": 3.766126106136089e-05, "loss": 1.5667436122894287, "step": 4368 }, { "epoch": 0.3688359380770976, "grad_norm": 0.1474609375, "learning_rate": 3.765564749879782e-05, "loss": 1.5148295164108276, "step": 4369 }, { "epoch": 0.36892035921192873, "grad_norm": 0.1435546875, "learning_rate": 3.7650033078151424e-05, "loss": 1.5711888074874878, "step": 4370 }, { "epoch": 0.3690047803467598, "grad_norm": 0.1474609375, "learning_rate": 3.764441779980239e-05, "loss": 1.491201400756836, "step": 4371 }, { "epoch": 0.3690892014815909, "grad_norm": 0.13671875, "learning_rate": 3.763880166413143e-05, "loss": 1.5057742595672607, "step": 4372 }, { "epoch": 0.369173622616422, "grad_norm": 0.1494140625, "learning_rate": 3.763318467151934e-05, "loss": 1.5282924175262451, "step": 4373 }, { "epoch": 0.36925804375125315, "grad_norm": 0.1357421875, "learning_rate": 3.762756682234696e-05, "loss": 1.498501181602478, "step": 4374 }, { "epoch": 0.36934246488608424, "grad_norm": 0.1640625, "learning_rate": 3.76219481169952e-05, "loss": 1.568213701248169, "step": 4375 }, { "epoch": 0.36942688602091533, "grad_norm": 0.13671875, "learning_rate": 3.761632855584501e-05, "loss": 1.4974842071533203, "step": 4376 }, { "epoch": 0.3695113071557464, "grad_norm": 0.1455078125, "learning_rate": 3.761070813927743e-05, "loss": 1.561558723449707, "step": 4377 }, { "epoch": 0.3695957282905775, "grad_norm": 0.1513671875, "learning_rate": 3.760508686767352e-05, "loss": 1.563947081565857, "step": 4378 }, { "epoch": 0.36968014942540867, "grad_norm": 0.1435546875, "learning_rate": 3.759946474141442e-05, "loss": 1.557383418083191, "step": 4379 }, { "epoch": 0.36976457056023976, "grad_norm": 0.12890625, "learning_rate": 3.759384176088133e-05, "loss": 1.4880262613296509, "step": 4380 }, { "epoch": 0.36984899169507085, "grad_norm": 0.1416015625, "learning_rate": 3.758821792645549e-05, "loss": 1.5036044120788574, "step": 4381 }, { "epoch": 0.36993341282990194, "grad_norm": 0.1337890625, "learning_rate": 3.7582593238518226e-05, "loss": 1.5481603145599365, "step": 4382 }, { "epoch": 0.3700178339647331, "grad_norm": 0.13671875, "learning_rate": 3.757696769745089e-05, "loss": 1.4896236658096313, "step": 4383 }, { "epoch": 0.3701022550995642, "grad_norm": 0.1357421875, "learning_rate": 3.757134130363492e-05, "loss": 1.5308310985565186, "step": 4384 }, { "epoch": 0.3701866762343953, "grad_norm": 0.12890625, "learning_rate": 3.756571405745178e-05, "loss": 1.5178353786468506, "step": 4385 }, { "epoch": 0.37027109736922637, "grad_norm": 0.134765625, "learning_rate": 3.756008595928304e-05, "loss": 1.5114766359329224, "step": 4386 }, { "epoch": 0.3703555185040575, "grad_norm": 0.1396484375, "learning_rate": 3.7554457009510266e-05, "loss": 1.5596449375152588, "step": 4387 }, { "epoch": 0.3704399396388886, "grad_norm": 0.1416015625, "learning_rate": 3.754882720851513e-05, "loss": 1.5751323699951172, "step": 4388 }, { "epoch": 0.3705243607737197, "grad_norm": 0.15234375, "learning_rate": 3.7543196556679356e-05, "loss": 1.5412267446517944, "step": 4389 }, { "epoch": 0.3706087819085508, "grad_norm": 0.146484375, "learning_rate": 3.75375650543847e-05, "loss": 1.5248947143554688, "step": 4390 }, { "epoch": 0.37069320304338194, "grad_norm": 0.15625, "learning_rate": 3.7531932702013e-05, "loss": 1.5859451293945312, "step": 4391 }, { "epoch": 0.37077762417821303, "grad_norm": 0.1533203125, "learning_rate": 3.752629949994613e-05, "loss": 1.5563273429870605, "step": 4392 }, { "epoch": 0.3708620453130441, "grad_norm": 0.14453125, "learning_rate": 3.752066544856606e-05, "loss": 1.5508612394332886, "step": 4393 }, { "epoch": 0.3709464664478752, "grad_norm": 0.1376953125, "learning_rate": 3.7515030548254765e-05, "loss": 1.5762587785720825, "step": 4394 }, { "epoch": 0.3710308875827063, "grad_norm": 0.1494140625, "learning_rate": 3.750939479939432e-05, "loss": 1.557018756866455, "step": 4395 }, { "epoch": 0.37111530871753745, "grad_norm": 0.13671875, "learning_rate": 3.7503758202366834e-05, "loss": 1.554193139076233, "step": 4396 }, { "epoch": 0.37119972985236854, "grad_norm": 0.1435546875, "learning_rate": 3.7498120757554495e-05, "loss": 1.5181119441986084, "step": 4397 }, { "epoch": 0.37128415098719963, "grad_norm": 0.1337890625, "learning_rate": 3.749248246533953e-05, "loss": 1.5313119888305664, "step": 4398 }, { "epoch": 0.3713685721220307, "grad_norm": 0.13671875, "learning_rate": 3.7486843326104214e-05, "loss": 1.5504372119903564, "step": 4399 }, { "epoch": 0.3714529932568619, "grad_norm": 0.1318359375, "learning_rate": 3.748120334023091e-05, "loss": 1.479963779449463, "step": 4400 }, { "epoch": 0.37153741439169297, "grad_norm": 0.1513671875, "learning_rate": 3.7475562508102024e-05, "loss": 1.5153106451034546, "step": 4401 }, { "epoch": 0.37162183552652406, "grad_norm": 0.142578125, "learning_rate": 3.746992083010001e-05, "loss": 1.5059781074523926, "step": 4402 }, { "epoch": 0.37170625666135515, "grad_norm": 0.1416015625, "learning_rate": 3.7464278306607393e-05, "loss": 1.5797665119171143, "step": 4403 }, { "epoch": 0.3717906777961863, "grad_norm": 0.1484375, "learning_rate": 3.745863493800674e-05, "loss": 1.4620476961135864, "step": 4404 }, { "epoch": 0.3718750989310174, "grad_norm": 0.140625, "learning_rate": 3.74529907246807e-05, "loss": 1.5586512088775635, "step": 4405 }, { "epoch": 0.3719595200658485, "grad_norm": 0.1318359375, "learning_rate": 3.7447345667011943e-05, "loss": 1.5322450399398804, "step": 4406 }, { "epoch": 0.3720439412006796, "grad_norm": 0.1455078125, "learning_rate": 3.744169976538324e-05, "loss": 1.514254093170166, "step": 4407 }, { "epoch": 0.3721283623355107, "grad_norm": 0.1416015625, "learning_rate": 3.743605302017739e-05, "loss": 1.4751437902450562, "step": 4408 }, { "epoch": 0.3722127834703418, "grad_norm": 0.14453125, "learning_rate": 3.743040543177725e-05, "loss": 1.5403048992156982, "step": 4409 }, { "epoch": 0.3722972046051729, "grad_norm": 0.1396484375, "learning_rate": 3.7424757000565734e-05, "loss": 1.5120421648025513, "step": 4410 }, { "epoch": 0.372381625740004, "grad_norm": 0.142578125, "learning_rate": 3.741910772692584e-05, "loss": 1.548033356666565, "step": 4411 }, { "epoch": 0.3724660468748351, "grad_norm": 0.1484375, "learning_rate": 3.7413457611240583e-05, "loss": 1.5506839752197266, "step": 4412 }, { "epoch": 0.37255046800966624, "grad_norm": 0.1474609375, "learning_rate": 3.740780665389307e-05, "loss": 1.5666792392730713, "step": 4413 }, { "epoch": 0.3726348891444973, "grad_norm": 0.1474609375, "learning_rate": 3.7402154855266426e-05, "loss": 1.5034652948379517, "step": 4414 }, { "epoch": 0.3727193102793284, "grad_norm": 0.1494140625, "learning_rate": 3.739650221574389e-05, "loss": 1.613189458847046, "step": 4415 }, { "epoch": 0.3728037314141595, "grad_norm": 0.1474609375, "learning_rate": 3.7390848735708694e-05, "loss": 1.5274161100387573, "step": 4416 }, { "epoch": 0.37288815254899066, "grad_norm": 0.1357421875, "learning_rate": 3.738519441554417e-05, "loss": 1.471890926361084, "step": 4417 }, { "epoch": 0.37297257368382175, "grad_norm": 0.14453125, "learning_rate": 3.737953925563371e-05, "loss": 1.5662221908569336, "step": 4418 }, { "epoch": 0.37305699481865284, "grad_norm": 0.134765625, "learning_rate": 3.7373883256360706e-05, "loss": 1.5310255289077759, "step": 4419 }, { "epoch": 0.37314141595348393, "grad_norm": 0.1337890625, "learning_rate": 3.73682264181087e-05, "loss": 1.5509555339813232, "step": 4420 }, { "epoch": 0.3732258370883151, "grad_norm": 0.1357421875, "learning_rate": 3.73625687412612e-05, "loss": 1.5563786029815674, "step": 4421 }, { "epoch": 0.3733102582231462, "grad_norm": 0.14453125, "learning_rate": 3.7356910226201824e-05, "loss": 1.577713131904602, "step": 4422 }, { "epoch": 0.37339467935797727, "grad_norm": 0.1240234375, "learning_rate": 3.735125087331424e-05, "loss": 1.524016261100769, "step": 4423 }, { "epoch": 0.37347910049280836, "grad_norm": 0.1328125, "learning_rate": 3.7345590682982143e-05, "loss": 1.5718128681182861, "step": 4424 }, { "epoch": 0.3735635216276395, "grad_norm": 0.140625, "learning_rate": 3.733992965558934e-05, "loss": 1.5215743780136108, "step": 4425 }, { "epoch": 0.3736479427624706, "grad_norm": 0.158203125, "learning_rate": 3.733426779151964e-05, "loss": 1.4683995246887207, "step": 4426 }, { "epoch": 0.3737323638973017, "grad_norm": 0.1474609375, "learning_rate": 3.7328605091156934e-05, "loss": 1.4996095895767212, "step": 4427 }, { "epoch": 0.3738167850321328, "grad_norm": 0.150390625, "learning_rate": 3.7322941554885165e-05, "loss": 1.6225032806396484, "step": 4428 }, { "epoch": 0.3739012061669639, "grad_norm": 0.14453125, "learning_rate": 3.731727718308834e-05, "loss": 1.5734401941299438, "step": 4429 }, { "epoch": 0.373985627301795, "grad_norm": 0.150390625, "learning_rate": 3.7311611976150523e-05, "loss": 1.4987293481826782, "step": 4430 }, { "epoch": 0.3740700484366261, "grad_norm": 0.1396484375, "learning_rate": 3.7305945934455815e-05, "loss": 1.5719459056854248, "step": 4431 }, { "epoch": 0.3741544695714572, "grad_norm": 0.150390625, "learning_rate": 3.7300279058388395e-05, "loss": 1.4685006141662598, "step": 4432 }, { "epoch": 0.3742388907062883, "grad_norm": 0.142578125, "learning_rate": 3.729461134833248e-05, "loss": 1.494480848312378, "step": 4433 }, { "epoch": 0.37432331184111944, "grad_norm": 0.140625, "learning_rate": 3.728894280467238e-05, "loss": 1.5523388385772705, "step": 4434 }, { "epoch": 0.37440773297595054, "grad_norm": 0.1376953125, "learning_rate": 3.7283273427792407e-05, "loss": 1.5673441886901855, "step": 4435 }, { "epoch": 0.3744921541107816, "grad_norm": 0.154296875, "learning_rate": 3.727760321807697e-05, "loss": 1.5288642644882202, "step": 4436 }, { "epoch": 0.3745765752456127, "grad_norm": 0.1494140625, "learning_rate": 3.727193217591052e-05, "loss": 1.5471599102020264, "step": 4437 }, { "epoch": 0.37466099638044387, "grad_norm": 0.1376953125, "learning_rate": 3.726626030167758e-05, "loss": 1.6180386543273926, "step": 4438 }, { "epoch": 0.37474541751527496, "grad_norm": 0.162109375, "learning_rate": 3.726058759576271e-05, "loss": 1.4604637622833252, "step": 4439 }, { "epoch": 0.37482983865010605, "grad_norm": 0.1416015625, "learning_rate": 3.725491405855052e-05, "loss": 1.5817415714263916, "step": 4440 }, { "epoch": 0.37491425978493714, "grad_norm": 0.1298828125, "learning_rate": 3.7249239690425706e-05, "loss": 1.4951688051223755, "step": 4441 }, { "epoch": 0.3749986809197683, "grad_norm": 0.1533203125, "learning_rate": 3.7243564491772996e-05, "loss": 1.5576626062393188, "step": 4442 }, { "epoch": 0.3750831020545994, "grad_norm": 0.14453125, "learning_rate": 3.723788846297718e-05, "loss": 1.4934985637664795, "step": 4443 }, { "epoch": 0.3751675231894305, "grad_norm": 0.1328125, "learning_rate": 3.723221160442312e-05, "loss": 1.4918040037155151, "step": 4444 }, { "epoch": 0.37525194432426157, "grad_norm": 0.1552734375, "learning_rate": 3.7226533916495704e-05, "loss": 1.5523719787597656, "step": 4445 }, { "epoch": 0.37533636545909266, "grad_norm": 0.142578125, "learning_rate": 3.7220855399579904e-05, "loss": 1.5211091041564941, "step": 4446 }, { "epoch": 0.3754207865939238, "grad_norm": 0.1474609375, "learning_rate": 3.721517605406072e-05, "loss": 1.5139683485031128, "step": 4447 }, { "epoch": 0.3755052077287549, "grad_norm": 0.150390625, "learning_rate": 3.7209495880323256e-05, "loss": 1.5638591051101685, "step": 4448 }, { "epoch": 0.375589628863586, "grad_norm": 0.1416015625, "learning_rate": 3.720381487875261e-05, "loss": 1.5442477464675903, "step": 4449 }, { "epoch": 0.3756740499984171, "grad_norm": 0.1630859375, "learning_rate": 3.719813304973398e-05, "loss": 1.5823928117752075, "step": 4450 }, { "epoch": 0.37575847113324823, "grad_norm": 0.1416015625, "learning_rate": 3.719245039365262e-05, "loss": 1.5082123279571533, "step": 4451 }, { "epoch": 0.3758428922680793, "grad_norm": 0.1318359375, "learning_rate": 3.718676691089381e-05, "loss": 1.530954360961914, "step": 4452 }, { "epoch": 0.3759273134029104, "grad_norm": 0.1513671875, "learning_rate": 3.7181082601842916e-05, "loss": 1.5576494932174683, "step": 4453 }, { "epoch": 0.3760117345377415, "grad_norm": 0.1337890625, "learning_rate": 3.717539746688534e-05, "loss": 1.5209002494812012, "step": 4454 }, { "epoch": 0.37609615567257265, "grad_norm": 0.140625, "learning_rate": 3.716971150640654e-05, "loss": 1.5475764274597168, "step": 4455 }, { "epoch": 0.37618057680740374, "grad_norm": 0.1376953125, "learning_rate": 3.716402472079206e-05, "loss": 1.543933629989624, "step": 4456 }, { "epoch": 0.37626499794223484, "grad_norm": 0.142578125, "learning_rate": 3.715833711042746e-05, "loss": 1.5776772499084473, "step": 4457 }, { "epoch": 0.3763494190770659, "grad_norm": 0.140625, "learning_rate": 3.715264867569838e-05, "loss": 1.5682212114334106, "step": 4458 }, { "epoch": 0.3764338402118971, "grad_norm": 0.1484375, "learning_rate": 3.7146959416990515e-05, "loss": 1.48660147190094, "step": 4459 }, { "epoch": 0.37651826134672817, "grad_norm": 0.138671875, "learning_rate": 3.714126933468959e-05, "loss": 1.514121413230896, "step": 4460 }, { "epoch": 0.37660268248155926, "grad_norm": 0.140625, "learning_rate": 3.7135578429181434e-05, "loss": 1.567413568496704, "step": 4461 }, { "epoch": 0.37668710361639035, "grad_norm": 0.142578125, "learning_rate": 3.7129886700851886e-05, "loss": 1.5945909023284912, "step": 4462 }, { "epoch": 0.37677152475122144, "grad_norm": 0.1455078125, "learning_rate": 3.712419415008686e-05, "loss": 1.5536128282546997, "step": 4463 }, { "epoch": 0.3768559458860526, "grad_norm": 0.146484375, "learning_rate": 3.711850077727233e-05, "loss": 1.5176678895950317, "step": 4464 }, { "epoch": 0.3769403670208837, "grad_norm": 0.1376953125, "learning_rate": 3.7112806582794315e-05, "loss": 1.6181975603103638, "step": 4465 }, { "epoch": 0.3770247881557148, "grad_norm": 0.130859375, "learning_rate": 3.710711156703891e-05, "loss": 1.5124666690826416, "step": 4466 }, { "epoch": 0.37710920929054587, "grad_norm": 0.142578125, "learning_rate": 3.7101415730392226e-05, "loss": 1.4581042528152466, "step": 4467 }, { "epoch": 0.377193630425377, "grad_norm": 0.15625, "learning_rate": 3.709571907324047e-05, "loss": 1.587207555770874, "step": 4468 }, { "epoch": 0.3772780515602081, "grad_norm": 0.1328125, "learning_rate": 3.709002159596989e-05, "loss": 1.408088207244873, "step": 4469 }, { "epoch": 0.3773624726950392, "grad_norm": 0.1494140625, "learning_rate": 3.708432329896678e-05, "loss": 1.588161826133728, "step": 4470 }, { "epoch": 0.3774468938298703, "grad_norm": 0.142578125, "learning_rate": 3.707862418261752e-05, "loss": 1.5044538974761963, "step": 4471 }, { "epoch": 0.37753131496470144, "grad_norm": 0.1396484375, "learning_rate": 3.707292424730848e-05, "loss": 1.5141372680664062, "step": 4472 }, { "epoch": 0.37761573609953253, "grad_norm": 0.134765625, "learning_rate": 3.706722349342618e-05, "loss": 1.482912302017212, "step": 4473 }, { "epoch": 0.3777001572343636, "grad_norm": 0.1513671875, "learning_rate": 3.7061521921357115e-05, "loss": 1.4680335521697998, "step": 4474 }, { "epoch": 0.3777845783691947, "grad_norm": 0.1552734375, "learning_rate": 3.705581953148787e-05, "loss": 1.6009185314178467, "step": 4475 }, { "epoch": 0.37786899950402586, "grad_norm": 0.1474609375, "learning_rate": 3.7050116324205076e-05, "loss": 1.524892807006836, "step": 4476 }, { "epoch": 0.37795342063885695, "grad_norm": 0.13671875, "learning_rate": 3.704441229989543e-05, "loss": 1.565433382987976, "step": 4477 }, { "epoch": 0.37803784177368804, "grad_norm": 0.1337890625, "learning_rate": 3.7038707458945694e-05, "loss": 1.5236985683441162, "step": 4478 }, { "epoch": 0.37812226290851914, "grad_norm": 0.142578125, "learning_rate": 3.7033001801742636e-05, "loss": 1.5600522756576538, "step": 4479 }, { "epoch": 0.3782066840433502, "grad_norm": 0.1416015625, "learning_rate": 3.702729532867315e-05, "loss": 1.5075653791427612, "step": 4480 }, { "epoch": 0.3782911051781814, "grad_norm": 0.140625, "learning_rate": 3.7021588040124125e-05, "loss": 1.6448163986206055, "step": 4481 }, { "epoch": 0.37837552631301247, "grad_norm": 0.1435546875, "learning_rate": 3.7015879936482535e-05, "loss": 1.532613754272461, "step": 4482 }, { "epoch": 0.37845994744784356, "grad_norm": 0.138671875, "learning_rate": 3.7010171018135396e-05, "loss": 1.530230164527893, "step": 4483 }, { "epoch": 0.37854436858267465, "grad_norm": 0.1484375, "learning_rate": 3.7004461285469796e-05, "loss": 1.522857666015625, "step": 4484 }, { "epoch": 0.3786287897175058, "grad_norm": 0.15234375, "learning_rate": 3.6998750738872876e-05, "loss": 1.555238127708435, "step": 4485 }, { "epoch": 0.3787132108523369, "grad_norm": 0.1337890625, "learning_rate": 3.6993039378731805e-05, "loss": 1.4362637996673584, "step": 4486 }, { "epoch": 0.378797631987168, "grad_norm": 0.1455078125, "learning_rate": 3.698732720543384e-05, "loss": 1.5293939113616943, "step": 4487 }, { "epoch": 0.3788820531219991, "grad_norm": 0.1484375, "learning_rate": 3.698161421936627e-05, "loss": 1.6018141508102417, "step": 4488 }, { "epoch": 0.3789664742568302, "grad_norm": 0.1533203125, "learning_rate": 3.697590042091647e-05, "loss": 1.4351223707199097, "step": 4489 }, { "epoch": 0.3790508953916613, "grad_norm": 0.1328125, "learning_rate": 3.697018581047182e-05, "loss": 1.4734615087509155, "step": 4490 }, { "epoch": 0.3791353165264924, "grad_norm": 0.1513671875, "learning_rate": 3.6964470388419805e-05, "loss": 1.5461699962615967, "step": 4491 }, { "epoch": 0.3792197376613235, "grad_norm": 0.1494140625, "learning_rate": 3.6958754155147945e-05, "loss": 1.5834640264511108, "step": 4492 }, { "epoch": 0.37930415879615464, "grad_norm": 0.138671875, "learning_rate": 3.69530371110438e-05, "loss": 1.5363097190856934, "step": 4493 }, { "epoch": 0.37938857993098574, "grad_norm": 0.138671875, "learning_rate": 3.694731925649501e-05, "loss": 1.5248504877090454, "step": 4494 }, { "epoch": 0.37947300106581683, "grad_norm": 0.1455078125, "learning_rate": 3.694160059188926e-05, "loss": 1.5071346759796143, "step": 4495 }, { "epoch": 0.3795574222006479, "grad_norm": 0.146484375, "learning_rate": 3.693588111761428e-05, "loss": 1.540669560432434, "step": 4496 }, { "epoch": 0.379641843335479, "grad_norm": 0.140625, "learning_rate": 3.693016083405788e-05, "loss": 1.5465327501296997, "step": 4497 }, { "epoch": 0.37972626447031016, "grad_norm": 0.1494140625, "learning_rate": 3.6924439741607894e-05, "loss": 1.5563937425613403, "step": 4498 }, { "epoch": 0.37981068560514125, "grad_norm": 0.13671875, "learning_rate": 3.691871784065223e-05, "loss": 1.5788785219192505, "step": 4499 }, { "epoch": 0.37989510673997234, "grad_norm": 0.13671875, "learning_rate": 3.691299513157884e-05, "loss": 1.552337884902954, "step": 4500 }, { "epoch": 0.37997952787480344, "grad_norm": 0.1357421875, "learning_rate": 3.690727161477575e-05, "loss": 1.5846428871154785, "step": 4501 }, { "epoch": 0.3800639490096346, "grad_norm": 0.16015625, "learning_rate": 3.690154729063103e-05, "loss": 1.5854438543319702, "step": 4502 }, { "epoch": 0.3801483701444657, "grad_norm": 0.138671875, "learning_rate": 3.6895822159532794e-05, "loss": 1.4853389263153076, "step": 4503 }, { "epoch": 0.38023279127929677, "grad_norm": 0.1318359375, "learning_rate": 3.689009622186922e-05, "loss": 1.5460072755813599, "step": 4504 }, { "epoch": 0.38031721241412786, "grad_norm": 0.1484375, "learning_rate": 3.688436947802854e-05, "loss": 1.5754855871200562, "step": 4505 }, { "epoch": 0.380401633548959, "grad_norm": 0.154296875, "learning_rate": 3.687864192839904e-05, "loss": 1.5887912511825562, "step": 4506 }, { "epoch": 0.3804860546837901, "grad_norm": 0.162109375, "learning_rate": 3.6872913573369077e-05, "loss": 1.60986328125, "step": 4507 }, { "epoch": 0.3805704758186212, "grad_norm": 0.15234375, "learning_rate": 3.686718441332702e-05, "loss": 1.5067427158355713, "step": 4508 }, { "epoch": 0.3806548969534523, "grad_norm": 0.1455078125, "learning_rate": 3.6861454448661345e-05, "loss": 1.4832488298416138, "step": 4509 }, { "epoch": 0.38073931808828343, "grad_norm": 0.140625, "learning_rate": 3.6855723679760545e-05, "loss": 1.4867923259735107, "step": 4510 }, { "epoch": 0.3808237392231145, "grad_norm": 0.1318359375, "learning_rate": 3.6849992107013186e-05, "loss": 1.411863088607788, "step": 4511 }, { "epoch": 0.3809081603579456, "grad_norm": 0.140625, "learning_rate": 3.6844259730807874e-05, "loss": 1.518635630607605, "step": 4512 }, { "epoch": 0.3809925814927767, "grad_norm": 0.1494140625, "learning_rate": 3.683852655153327e-05, "loss": 1.566923975944519, "step": 4513 }, { "epoch": 0.3810770026276078, "grad_norm": 0.1357421875, "learning_rate": 3.683279256957813e-05, "loss": 1.5054922103881836, "step": 4514 }, { "epoch": 0.38116142376243894, "grad_norm": 0.14453125, "learning_rate": 3.682705778533121e-05, "loss": 1.5749480724334717, "step": 4515 }, { "epoch": 0.38124584489727004, "grad_norm": 0.138671875, "learning_rate": 3.682132219918134e-05, "loss": 1.5004593133926392, "step": 4516 }, { "epoch": 0.38133026603210113, "grad_norm": 0.1357421875, "learning_rate": 3.68155858115174e-05, "loss": 1.555277943611145, "step": 4517 }, { "epoch": 0.3814146871669322, "grad_norm": 0.146484375, "learning_rate": 3.6809848622728356e-05, "loss": 1.5376461744308472, "step": 4518 }, { "epoch": 0.38149910830176337, "grad_norm": 0.1552734375, "learning_rate": 3.6804110633203176e-05, "loss": 1.4799193143844604, "step": 4519 }, { "epoch": 0.38158352943659446, "grad_norm": 0.1416015625, "learning_rate": 3.679837184333092e-05, "loss": 1.5891306400299072, "step": 4520 }, { "epoch": 0.38166795057142555, "grad_norm": 0.15234375, "learning_rate": 3.679263225350072e-05, "loss": 1.4376475811004639, "step": 4521 }, { "epoch": 0.38175237170625664, "grad_norm": 0.1552734375, "learning_rate": 3.678689186410167e-05, "loss": 1.6043893098831177, "step": 4522 }, { "epoch": 0.3818367928410878, "grad_norm": 0.1591796875, "learning_rate": 3.678115067552305e-05, "loss": 1.6189223527908325, "step": 4523 }, { "epoch": 0.3819212139759189, "grad_norm": 0.146484375, "learning_rate": 3.677540868815408e-05, "loss": 1.569374442100525, "step": 4524 }, { "epoch": 0.38200563511075, "grad_norm": 0.1455078125, "learning_rate": 3.6769665902384096e-05, "loss": 1.592971920967102, "step": 4525 }, { "epoch": 0.38209005624558107, "grad_norm": 0.1484375, "learning_rate": 3.6763922318602474e-05, "loss": 1.4643628597259521, "step": 4526 }, { "epoch": 0.38217447738041216, "grad_norm": 0.1572265625, "learning_rate": 3.675817793719864e-05, "loss": 1.5961346626281738, "step": 4527 }, { "epoch": 0.3822588985152433, "grad_norm": 0.1396484375, "learning_rate": 3.6752432758562096e-05, "loss": 1.4970375299453735, "step": 4528 }, { "epoch": 0.3823433196500744, "grad_norm": 0.1416015625, "learning_rate": 3.6746686783082346e-05, "loss": 1.5159298181533813, "step": 4529 }, { "epoch": 0.3824277407849055, "grad_norm": 0.12890625, "learning_rate": 3.6740940011149e-05, "loss": 1.5269910097122192, "step": 4530 }, { "epoch": 0.3825121619197366, "grad_norm": 0.1416015625, "learning_rate": 3.67351924431517e-05, "loss": 1.4527215957641602, "step": 4531 }, { "epoch": 0.38259658305456773, "grad_norm": 0.1455078125, "learning_rate": 3.6729444079480145e-05, "loss": 1.5104607343673706, "step": 4532 }, { "epoch": 0.3826810041893988, "grad_norm": 0.1474609375, "learning_rate": 3.672369492052409e-05, "loss": 1.5439717769622803, "step": 4533 }, { "epoch": 0.3827654253242299, "grad_norm": 0.1298828125, "learning_rate": 3.671794496667333e-05, "loss": 1.4406558275222778, "step": 4534 }, { "epoch": 0.382849846459061, "grad_norm": 0.146484375, "learning_rate": 3.671219421831775e-05, "loss": 1.4688297510147095, "step": 4535 }, { "epoch": 0.38293426759389215, "grad_norm": 0.1494140625, "learning_rate": 3.670644267584724e-05, "loss": 1.5992660522460938, "step": 4536 }, { "epoch": 0.38301868872872324, "grad_norm": 0.14453125, "learning_rate": 3.670069033965178e-05, "loss": 1.5484325885772705, "step": 4537 }, { "epoch": 0.38310310986355434, "grad_norm": 0.140625, "learning_rate": 3.669493721012139e-05, "loss": 1.4810667037963867, "step": 4538 }, { "epoch": 0.38318753099838543, "grad_norm": 0.146484375, "learning_rate": 3.668918328764614e-05, "loss": 1.5707817077636719, "step": 4539 }, { "epoch": 0.3832719521332166, "grad_norm": 0.1376953125, "learning_rate": 3.668342857261618e-05, "loss": 1.58527672290802, "step": 4540 }, { "epoch": 0.38335637326804767, "grad_norm": 0.1357421875, "learning_rate": 3.667767306542167e-05, "loss": 1.526568055152893, "step": 4541 }, { "epoch": 0.38344079440287876, "grad_norm": 0.142578125, "learning_rate": 3.667191676645286e-05, "loss": 1.540309190750122, "step": 4542 }, { "epoch": 0.38352521553770985, "grad_norm": 0.13671875, "learning_rate": 3.666615967610004e-05, "loss": 1.4853272438049316, "step": 4543 }, { "epoch": 0.38360963667254094, "grad_norm": 0.1357421875, "learning_rate": 3.666040179475354e-05, "loss": 1.533695936203003, "step": 4544 }, { "epoch": 0.3836940578073721, "grad_norm": 0.1474609375, "learning_rate": 3.665464312280378e-05, "loss": 1.4558241367340088, "step": 4545 }, { "epoch": 0.3837784789422032, "grad_norm": 0.13671875, "learning_rate": 3.66488836606412e-05, "loss": 1.4774508476257324, "step": 4546 }, { "epoch": 0.3838629000770343, "grad_norm": 0.158203125, "learning_rate": 3.664312340865631e-05, "loss": 1.5575971603393555, "step": 4547 }, { "epoch": 0.38394732121186537, "grad_norm": 0.1484375, "learning_rate": 3.6637362367239664e-05, "loss": 1.5545942783355713, "step": 4548 }, { "epoch": 0.3840317423466965, "grad_norm": 0.146484375, "learning_rate": 3.663160053678187e-05, "loss": 1.5579793453216553, "step": 4549 }, { "epoch": 0.3841161634815276, "grad_norm": 0.1396484375, "learning_rate": 3.662583791767362e-05, "loss": 1.6051806211471558, "step": 4550 }, { "epoch": 0.3842005846163587, "grad_norm": 0.1376953125, "learning_rate": 3.6620074510305605e-05, "loss": 1.5296874046325684, "step": 4551 }, { "epoch": 0.3842850057511898, "grad_norm": 0.150390625, "learning_rate": 3.661431031506861e-05, "loss": 1.5260919332504272, "step": 4552 }, { "epoch": 0.38436942688602094, "grad_norm": 0.1318359375, "learning_rate": 3.6608545332353445e-05, "loss": 1.5756341218948364, "step": 4553 }, { "epoch": 0.38445384802085203, "grad_norm": 0.138671875, "learning_rate": 3.6602779562551007e-05, "loss": 1.5728731155395508, "step": 4554 }, { "epoch": 0.3845382691556831, "grad_norm": 0.138671875, "learning_rate": 3.659701300605224e-05, "loss": 1.5724223852157593, "step": 4555 }, { "epoch": 0.3846226902905142, "grad_norm": 0.1376953125, "learning_rate": 3.65912456632481e-05, "loss": 1.5478523969650269, "step": 4556 }, { "epoch": 0.38470711142534536, "grad_norm": 0.16015625, "learning_rate": 3.658547753452965e-05, "loss": 1.5034018754959106, "step": 4557 }, { "epoch": 0.38479153256017645, "grad_norm": 0.1376953125, "learning_rate": 3.6579708620287974e-05, "loss": 1.5333949327468872, "step": 4558 }, { "epoch": 0.38487595369500754, "grad_norm": 0.1484375, "learning_rate": 3.657393892091422e-05, "loss": 1.6290099620819092, "step": 4559 }, { "epoch": 0.38496037482983864, "grad_norm": 0.138671875, "learning_rate": 3.656816843679959e-05, "loss": 1.5537292957305908, "step": 4560 }, { "epoch": 0.38504479596466973, "grad_norm": 0.1396484375, "learning_rate": 3.656239716833533e-05, "loss": 1.5532056093215942, "step": 4561 }, { "epoch": 0.3851292170995009, "grad_norm": 0.146484375, "learning_rate": 3.655662511591275e-05, "loss": 1.5032685995101929, "step": 4562 }, { "epoch": 0.38521363823433197, "grad_norm": 0.1708984375, "learning_rate": 3.6550852279923204e-05, "loss": 1.5467705726623535, "step": 4563 }, { "epoch": 0.38529805936916306, "grad_norm": 0.1474609375, "learning_rate": 3.654507866075811e-05, "loss": 1.545700192451477, "step": 4564 }, { "epoch": 0.38538248050399415, "grad_norm": 0.142578125, "learning_rate": 3.653930425880894e-05, "loss": 1.595377802848816, "step": 4565 }, { "epoch": 0.3854669016388253, "grad_norm": 0.1474609375, "learning_rate": 3.65335290744672e-05, "loss": 1.5545717477798462, "step": 4566 }, { "epoch": 0.3855513227736564, "grad_norm": 0.1318359375, "learning_rate": 3.6527753108124465e-05, "loss": 1.4762539863586426, "step": 4567 }, { "epoch": 0.3856357439084875, "grad_norm": 0.15234375, "learning_rate": 3.652197636017236e-05, "loss": 1.5605844259262085, "step": 4568 }, { "epoch": 0.3857201650433186, "grad_norm": 0.1416015625, "learning_rate": 3.651619883100256e-05, "loss": 1.5405700206756592, "step": 4569 }, { "epoch": 0.3858045861781497, "grad_norm": 0.140625, "learning_rate": 3.6510420521006805e-05, "loss": 1.5246374607086182, "step": 4570 }, { "epoch": 0.3858890073129808, "grad_norm": 0.138671875, "learning_rate": 3.650464143057687e-05, "loss": 1.6112067699432373, "step": 4571 }, { "epoch": 0.3859734284478119, "grad_norm": 0.1337890625, "learning_rate": 3.6498861560104586e-05, "loss": 1.478070855140686, "step": 4572 }, { "epoch": 0.386057849582643, "grad_norm": 0.134765625, "learning_rate": 3.649308090998185e-05, "loss": 1.5019360780715942, "step": 4573 }, { "epoch": 0.38614227071747415, "grad_norm": 0.1376953125, "learning_rate": 3.6487299480600615e-05, "loss": 1.5618736743927002, "step": 4574 }, { "epoch": 0.38622669185230524, "grad_norm": 0.1396484375, "learning_rate": 3.6481517272352846e-05, "loss": 1.601210117340088, "step": 4575 }, { "epoch": 0.38631111298713633, "grad_norm": 0.1435546875, "learning_rate": 3.6475734285630616e-05, "loss": 1.568255066871643, "step": 4576 }, { "epoch": 0.3863955341219674, "grad_norm": 0.1455078125, "learning_rate": 3.6469950520826015e-05, "loss": 1.557183861732483, "step": 4577 }, { "epoch": 0.3864799552567985, "grad_norm": 0.142578125, "learning_rate": 3.64641659783312e-05, "loss": 1.5210931301116943, "step": 4578 }, { "epoch": 0.38656437639162966, "grad_norm": 0.146484375, "learning_rate": 3.6458380658538384e-05, "loss": 1.585151195526123, "step": 4579 }, { "epoch": 0.38664879752646075, "grad_norm": 0.1396484375, "learning_rate": 3.64525945618398e-05, "loss": 1.5165534019470215, "step": 4580 }, { "epoch": 0.38673321866129184, "grad_norm": 0.1474609375, "learning_rate": 3.6446807688627795e-05, "loss": 1.5361639261245728, "step": 4581 }, { "epoch": 0.38681763979612294, "grad_norm": 0.1337890625, "learning_rate": 3.64410200392947e-05, "loss": 1.4468697309494019, "step": 4582 }, { "epoch": 0.3869020609309541, "grad_norm": 0.1435546875, "learning_rate": 3.6435231614232946e-05, "loss": 1.535609245300293, "step": 4583 }, { "epoch": 0.3869864820657852, "grad_norm": 0.1396484375, "learning_rate": 3.6429442413835004e-05, "loss": 1.5991175174713135, "step": 4584 }, { "epoch": 0.38707090320061627, "grad_norm": 0.146484375, "learning_rate": 3.64236524384934e-05, "loss": 1.5534229278564453, "step": 4585 }, { "epoch": 0.38715532433544736, "grad_norm": 0.1572265625, "learning_rate": 3.6417861688600695e-05, "loss": 1.6596585512161255, "step": 4586 }, { "epoch": 0.3872397454702785, "grad_norm": 0.1376953125, "learning_rate": 3.641207016454953e-05, "loss": 1.5310895442962646, "step": 4587 }, { "epoch": 0.3873241666051096, "grad_norm": 0.15625, "learning_rate": 3.640627786673257e-05, "loss": 1.579463005065918, "step": 4588 }, { "epoch": 0.3874085877399407, "grad_norm": 0.1416015625, "learning_rate": 3.6400484795542554e-05, "loss": 1.479127049446106, "step": 4589 }, { "epoch": 0.3874930088747718, "grad_norm": 0.13671875, "learning_rate": 3.6394690951372266e-05, "loss": 1.4739211797714233, "step": 4590 }, { "epoch": 0.38757743000960293, "grad_norm": 0.1435546875, "learning_rate": 3.638889633461455e-05, "loss": 1.514206886291504, "step": 4591 }, { "epoch": 0.387661851144434, "grad_norm": 0.1435546875, "learning_rate": 3.638310094566228e-05, "loss": 1.524240493774414, "step": 4592 }, { "epoch": 0.3877462722792651, "grad_norm": 0.1435546875, "learning_rate": 3.6377304784908406e-05, "loss": 1.5609716176986694, "step": 4593 }, { "epoch": 0.3878306934140962, "grad_norm": 0.14453125, "learning_rate": 3.6371507852745915e-05, "loss": 1.5316880941390991, "step": 4594 }, { "epoch": 0.3879151145489273, "grad_norm": 0.134765625, "learning_rate": 3.636571014956786e-05, "loss": 1.5073003768920898, "step": 4595 }, { "epoch": 0.38799953568375845, "grad_norm": 0.1279296875, "learning_rate": 3.6359911675767345e-05, "loss": 1.4407176971435547, "step": 4596 }, { "epoch": 0.38808395681858954, "grad_norm": 0.1357421875, "learning_rate": 3.635411243173751e-05, "loss": 1.5118873119354248, "step": 4597 }, { "epoch": 0.38816837795342063, "grad_norm": 0.1416015625, "learning_rate": 3.634831241787155e-05, "loss": 1.53788423538208, "step": 4598 }, { "epoch": 0.3882527990882517, "grad_norm": 0.1376953125, "learning_rate": 3.6342511634562745e-05, "loss": 1.4664833545684814, "step": 4599 }, { "epoch": 0.38833722022308287, "grad_norm": 0.1494140625, "learning_rate": 3.6336710082204386e-05, "loss": 1.589003086090088, "step": 4600 }, { "epoch": 0.38842164135791396, "grad_norm": 0.1357421875, "learning_rate": 3.6330907761189825e-05, "loss": 1.5172933340072632, "step": 4601 }, { "epoch": 0.38850606249274505, "grad_norm": 0.146484375, "learning_rate": 3.632510467191248e-05, "loss": 1.5890730619430542, "step": 4602 }, { "epoch": 0.38859048362757614, "grad_norm": 0.140625, "learning_rate": 3.631930081476582e-05, "loss": 1.5190843343734741, "step": 4603 }, { "epoch": 0.3886749047624073, "grad_norm": 0.142578125, "learning_rate": 3.631349619014336e-05, "loss": 1.5329477787017822, "step": 4604 }, { "epoch": 0.3887593258972384, "grad_norm": 0.12890625, "learning_rate": 3.6307690798438664e-05, "loss": 1.4875752925872803, "step": 4605 }, { "epoch": 0.3888437470320695, "grad_norm": 0.138671875, "learning_rate": 3.6301884640045344e-05, "loss": 1.4630074501037598, "step": 4606 }, { "epoch": 0.38892816816690057, "grad_norm": 0.1396484375, "learning_rate": 3.629607771535709e-05, "loss": 1.582947850227356, "step": 4607 }, { "epoch": 0.3890125893017317, "grad_norm": 0.1494140625, "learning_rate": 3.629027002476761e-05, "loss": 1.543138027191162, "step": 4608 }, { "epoch": 0.3890970104365628, "grad_norm": 0.1318359375, "learning_rate": 3.628446156867068e-05, "loss": 1.4841476678848267, "step": 4609 }, { "epoch": 0.3891814315713939, "grad_norm": 0.1357421875, "learning_rate": 3.627865234746014e-05, "loss": 1.5469273328781128, "step": 4610 }, { "epoch": 0.389265852706225, "grad_norm": 0.158203125, "learning_rate": 3.6272842361529855e-05, "loss": 1.485116958618164, "step": 4611 }, { "epoch": 0.3893502738410561, "grad_norm": 0.1376953125, "learning_rate": 3.626703161127376e-05, "loss": 1.5451576709747314, "step": 4612 }, { "epoch": 0.38943469497588723, "grad_norm": 0.158203125, "learning_rate": 3.6261220097085845e-05, "loss": 1.5132038593292236, "step": 4613 }, { "epoch": 0.3895191161107183, "grad_norm": 0.1455078125, "learning_rate": 3.6255407819360135e-05, "loss": 1.4773681163787842, "step": 4614 }, { "epoch": 0.3896035372455494, "grad_norm": 0.14453125, "learning_rate": 3.624959477849072e-05, "loss": 1.5787413120269775, "step": 4615 }, { "epoch": 0.3896879583803805, "grad_norm": 0.13671875, "learning_rate": 3.624378097487174e-05, "loss": 1.5449851751327515, "step": 4616 }, { "epoch": 0.38977237951521165, "grad_norm": 0.140625, "learning_rate": 3.6237966408897384e-05, "loss": 1.5214033126831055, "step": 4617 }, { "epoch": 0.38985680065004275, "grad_norm": 0.140625, "learning_rate": 3.62321510809619e-05, "loss": 1.5682597160339355, "step": 4618 }, { "epoch": 0.38994122178487384, "grad_norm": 0.1376953125, "learning_rate": 3.622633499145956e-05, "loss": 1.4719361066818237, "step": 4619 }, { "epoch": 0.39002564291970493, "grad_norm": 0.138671875, "learning_rate": 3.622051814078473e-05, "loss": 1.5186978578567505, "step": 4620 }, { "epoch": 0.3901100640545361, "grad_norm": 0.1376953125, "learning_rate": 3.62147005293318e-05, "loss": 1.5298329591751099, "step": 4621 }, { "epoch": 0.39019448518936717, "grad_norm": 0.138671875, "learning_rate": 3.6208882157495215e-05, "loss": 1.6150281429290771, "step": 4622 }, { "epoch": 0.39027890632419826, "grad_norm": 0.1455078125, "learning_rate": 3.620306302566948e-05, "loss": 1.5427554845809937, "step": 4623 }, { "epoch": 0.39036332745902935, "grad_norm": 0.142578125, "learning_rate": 3.6197243134249136e-05, "loss": 1.5679728984832764, "step": 4624 }, { "epoch": 0.3904477485938605, "grad_norm": 0.134765625, "learning_rate": 3.61914224836288e-05, "loss": 1.537893295288086, "step": 4625 }, { "epoch": 0.3905321697286916, "grad_norm": 0.140625, "learning_rate": 3.618560107420312e-05, "loss": 1.4973053932189941, "step": 4626 }, { "epoch": 0.3906165908635227, "grad_norm": 0.142578125, "learning_rate": 3.61797789063668e-05, "loss": 1.5407450199127197, "step": 4627 }, { "epoch": 0.3907010119983538, "grad_norm": 0.138671875, "learning_rate": 3.617395598051459e-05, "loss": 1.576196312904358, "step": 4628 }, { "epoch": 0.39078543313318487, "grad_norm": 0.1611328125, "learning_rate": 3.616813229704132e-05, "loss": 1.7495884895324707, "step": 4629 }, { "epoch": 0.390869854268016, "grad_norm": 0.134765625, "learning_rate": 3.616230785634183e-05, "loss": 1.574243187904358, "step": 4630 }, { "epoch": 0.3909542754028471, "grad_norm": 0.1318359375, "learning_rate": 3.615648265881103e-05, "loss": 1.4853748083114624, "step": 4631 }, { "epoch": 0.3910386965376782, "grad_norm": 0.134765625, "learning_rate": 3.61506567048439e-05, "loss": 1.588152527809143, "step": 4632 }, { "epoch": 0.3911231176725093, "grad_norm": 0.1435546875, "learning_rate": 3.614482999483542e-05, "loss": 1.4618642330169678, "step": 4633 }, { "epoch": 0.39120753880734044, "grad_norm": 0.1416015625, "learning_rate": 3.6139002529180696e-05, "loss": 1.5690202713012695, "step": 4634 }, { "epoch": 0.39129195994217153, "grad_norm": 0.14453125, "learning_rate": 3.6133174308274826e-05, "loss": 1.4911775588989258, "step": 4635 }, { "epoch": 0.3913763810770026, "grad_norm": 0.1298828125, "learning_rate": 3.612734533251298e-05, "loss": 1.5194218158721924, "step": 4636 }, { "epoch": 0.3914608022118337, "grad_norm": 0.1328125, "learning_rate": 3.612151560229037e-05, "loss": 1.5400059223175049, "step": 4637 }, { "epoch": 0.39154522334666486, "grad_norm": 0.1640625, "learning_rate": 3.6115685118002257e-05, "loss": 1.6155186891555786, "step": 4638 }, { "epoch": 0.39162964448149595, "grad_norm": 0.1435546875, "learning_rate": 3.610985388004399e-05, "loss": 1.5370550155639648, "step": 4639 }, { "epoch": 0.39171406561632705, "grad_norm": 0.1416015625, "learning_rate": 3.6104021888810926e-05, "loss": 1.5428723096847534, "step": 4640 }, { "epoch": 0.39179848675115814, "grad_norm": 0.150390625, "learning_rate": 3.609818914469848e-05, "loss": 1.5108121633529663, "step": 4641 }, { "epoch": 0.3918829078859893, "grad_norm": 0.146484375, "learning_rate": 3.609235564810213e-05, "loss": 1.52322518825531, "step": 4642 }, { "epoch": 0.3919673290208204, "grad_norm": 0.1435546875, "learning_rate": 3.6086521399417416e-05, "loss": 1.5752042531967163, "step": 4643 }, { "epoch": 0.39205175015565147, "grad_norm": 0.1376953125, "learning_rate": 3.6080686399039895e-05, "loss": 1.5830137729644775, "step": 4644 }, { "epoch": 0.39213617129048256, "grad_norm": 0.14453125, "learning_rate": 3.60748506473652e-05, "loss": 1.5824882984161377, "step": 4645 }, { "epoch": 0.39222059242531365, "grad_norm": 0.140625, "learning_rate": 3.606901414478902e-05, "loss": 1.557471752166748, "step": 4646 }, { "epoch": 0.3923050135601448, "grad_norm": 0.1435546875, "learning_rate": 3.606317689170706e-05, "loss": 1.4992437362670898, "step": 4647 }, { "epoch": 0.3923894346949759, "grad_norm": 0.1435546875, "learning_rate": 3.605733888851513e-05, "loss": 1.5239604711532593, "step": 4648 }, { "epoch": 0.392473855829807, "grad_norm": 0.1513671875, "learning_rate": 3.605150013560904e-05, "loss": 1.5897397994995117, "step": 4649 }, { "epoch": 0.3925582769646381, "grad_norm": 0.1328125, "learning_rate": 3.604566063338467e-05, "loss": 1.4814000129699707, "step": 4650 }, { "epoch": 0.3926426980994692, "grad_norm": 0.142578125, "learning_rate": 3.6039820382237964e-05, "loss": 1.5697964429855347, "step": 4651 }, { "epoch": 0.3927271192343003, "grad_norm": 0.1357421875, "learning_rate": 3.60339793825649e-05, "loss": 1.5734254121780396, "step": 4652 }, { "epoch": 0.3928115403691314, "grad_norm": 0.1494140625, "learning_rate": 3.602813763476151e-05, "loss": 1.5413906574249268, "step": 4653 }, { "epoch": 0.3928959615039625, "grad_norm": 0.134765625, "learning_rate": 3.602229513922388e-05, "loss": 1.4734879732131958, "step": 4654 }, { "epoch": 0.39298038263879365, "grad_norm": 0.1484375, "learning_rate": 3.601645189634815e-05, "loss": 1.54136061668396, "step": 4655 }, { "epoch": 0.39306480377362474, "grad_norm": 0.13671875, "learning_rate": 3.6010607906530496e-05, "loss": 1.5639424324035645, "step": 4656 }, { "epoch": 0.39314922490845583, "grad_norm": 0.14453125, "learning_rate": 3.600476317016716e-05, "loss": 1.481703281402588, "step": 4657 }, { "epoch": 0.3932336460432869, "grad_norm": 0.1396484375, "learning_rate": 3.5998917687654433e-05, "loss": 1.5104387998580933, "step": 4658 }, { "epoch": 0.39331806717811807, "grad_norm": 0.15234375, "learning_rate": 3.599307145938865e-05, "loss": 1.5521926879882812, "step": 4659 }, { "epoch": 0.39340248831294916, "grad_norm": 0.146484375, "learning_rate": 3.598722448576619e-05, "loss": 1.5707387924194336, "step": 4660 }, { "epoch": 0.39348690944778025, "grad_norm": 0.1328125, "learning_rate": 3.5981376767183505e-05, "loss": 1.4954949617385864, "step": 4661 }, { "epoch": 0.39357133058261135, "grad_norm": 0.138671875, "learning_rate": 3.5975528304037074e-05, "loss": 1.6062349081039429, "step": 4662 }, { "epoch": 0.39365575171744244, "grad_norm": 0.142578125, "learning_rate": 3.5969679096723456e-05, "loss": 1.4353808164596558, "step": 4663 }, { "epoch": 0.3937401728522736, "grad_norm": 0.14453125, "learning_rate": 3.596382914563921e-05, "loss": 1.5396422147750854, "step": 4664 }, { "epoch": 0.3938245939871047, "grad_norm": 0.138671875, "learning_rate": 3.5957978451181014e-05, "loss": 1.5857168436050415, "step": 4665 }, { "epoch": 0.39390901512193577, "grad_norm": 0.1455078125, "learning_rate": 3.595212701374553e-05, "loss": 1.5458322763442993, "step": 4666 }, { "epoch": 0.39399343625676686, "grad_norm": 0.1376953125, "learning_rate": 3.59462748337295e-05, "loss": 1.4954040050506592, "step": 4667 }, { "epoch": 0.394077857391598, "grad_norm": 0.12890625, "learning_rate": 3.5940421911529746e-05, "loss": 1.4617019891738892, "step": 4668 }, { "epoch": 0.3941622785264291, "grad_norm": 0.1416015625, "learning_rate": 3.593456824754307e-05, "loss": 1.5584279298782349, "step": 4669 }, { "epoch": 0.3942466996612602, "grad_norm": 0.1376953125, "learning_rate": 3.5928713842166387e-05, "loss": 1.529482364654541, "step": 4670 }, { "epoch": 0.3943311207960913, "grad_norm": 0.138671875, "learning_rate": 3.5922858695796644e-05, "loss": 1.529134750366211, "step": 4671 }, { "epoch": 0.39441554193092243, "grad_norm": 0.142578125, "learning_rate": 3.591700280883082e-05, "loss": 1.600324273109436, "step": 4672 }, { "epoch": 0.3944999630657535, "grad_norm": 0.1298828125, "learning_rate": 3.591114618166597e-05, "loss": 1.4507845640182495, "step": 4673 }, { "epoch": 0.3945843842005846, "grad_norm": 0.1796875, "learning_rate": 3.590528881469917e-05, "loss": 1.5052640438079834, "step": 4674 }, { "epoch": 0.3946688053354157, "grad_norm": 0.138671875, "learning_rate": 3.589943070832759e-05, "loss": 1.5440043210983276, "step": 4675 }, { "epoch": 0.3947532264702468, "grad_norm": 0.140625, "learning_rate": 3.58935718629484e-05, "loss": 1.579004168510437, "step": 4676 }, { "epoch": 0.39483764760507795, "grad_norm": 0.1298828125, "learning_rate": 3.5887712278958854e-05, "loss": 1.5203684568405151, "step": 4677 }, { "epoch": 0.39492206873990904, "grad_norm": 0.1513671875, "learning_rate": 3.588185195675624e-05, "loss": 1.512269139289856, "step": 4678 }, { "epoch": 0.39500648987474013, "grad_norm": 0.140625, "learning_rate": 3.587599089673792e-05, "loss": 1.5206029415130615, "step": 4679 }, { "epoch": 0.3950909110095712, "grad_norm": 0.134765625, "learning_rate": 3.587012909930127e-05, "loss": 1.5553010702133179, "step": 4680 }, { "epoch": 0.39517533214440237, "grad_norm": 0.1396484375, "learning_rate": 3.586426656484373e-05, "loss": 1.520821213722229, "step": 4681 }, { "epoch": 0.39525975327923346, "grad_norm": 0.1474609375, "learning_rate": 3.585840329376282e-05, "loss": 1.5797226428985596, "step": 4682 }, { "epoch": 0.39534417441406455, "grad_norm": 0.14453125, "learning_rate": 3.585253928645605e-05, "loss": 1.5277366638183594, "step": 4683 }, { "epoch": 0.39542859554889564, "grad_norm": 0.134765625, "learning_rate": 3.5846674543321036e-05, "loss": 1.5630741119384766, "step": 4684 }, { "epoch": 0.3955130166837268, "grad_norm": 0.134765625, "learning_rate": 3.584080906475542e-05, "loss": 1.5280044078826904, "step": 4685 }, { "epoch": 0.3955974378185579, "grad_norm": 0.142578125, "learning_rate": 3.5834942851156886e-05, "loss": 1.4991207122802734, "step": 4686 }, { "epoch": 0.395681858953389, "grad_norm": 0.13671875, "learning_rate": 3.582907590292318e-05, "loss": 1.4569387435913086, "step": 4687 }, { "epoch": 0.39576628008822007, "grad_norm": 0.1396484375, "learning_rate": 3.58232082204521e-05, "loss": 1.5289329290390015, "step": 4688 }, { "epoch": 0.3958507012230512, "grad_norm": 0.13671875, "learning_rate": 3.5817339804141496e-05, "loss": 1.539659857749939, "step": 4689 }, { "epoch": 0.3959351223578823, "grad_norm": 0.1416015625, "learning_rate": 3.581147065438925e-05, "loss": 1.4477126598358154, "step": 4690 }, { "epoch": 0.3960195434927134, "grad_norm": 0.1630859375, "learning_rate": 3.5805600771593294e-05, "loss": 1.5423043966293335, "step": 4691 }, { "epoch": 0.3961039646275445, "grad_norm": 0.1416015625, "learning_rate": 3.5799730156151646e-05, "loss": 1.4776018857955933, "step": 4692 }, { "epoch": 0.3961883857623756, "grad_norm": 0.1416015625, "learning_rate": 3.579385880846232e-05, "loss": 1.5203453302383423, "step": 4693 }, { "epoch": 0.39627280689720673, "grad_norm": 0.138671875, "learning_rate": 3.578798672892344e-05, "loss": 1.4982883930206299, "step": 4694 }, { "epoch": 0.3963572280320378, "grad_norm": 0.134765625, "learning_rate": 3.578211391793312e-05, "loss": 1.5178921222686768, "step": 4695 }, { "epoch": 0.3964416491668689, "grad_norm": 0.1435546875, "learning_rate": 3.577624037588956e-05, "loss": 1.5554951429367065, "step": 4696 }, { "epoch": 0.3965260703017, "grad_norm": 0.140625, "learning_rate": 3.5770366103190994e-05, "loss": 1.5756280422210693, "step": 4697 }, { "epoch": 0.39661049143653115, "grad_norm": 0.130859375, "learning_rate": 3.576449110023572e-05, "loss": 1.4789520502090454, "step": 4698 }, { "epoch": 0.39669491257136225, "grad_norm": 0.1513671875, "learning_rate": 3.5758615367422084e-05, "loss": 1.567209005355835, "step": 4699 }, { "epoch": 0.39677933370619334, "grad_norm": 0.1328125, "learning_rate": 3.575273890514845e-05, "loss": 1.5822128057479858, "step": 4700 }, { "epoch": 0.39686375484102443, "grad_norm": 0.142578125, "learning_rate": 3.574686171381329e-05, "loss": 1.5693827867507935, "step": 4701 }, { "epoch": 0.3969481759758556, "grad_norm": 0.146484375, "learning_rate": 3.574098379381506e-05, "loss": 1.5814746618270874, "step": 4702 }, { "epoch": 0.39703259711068667, "grad_norm": 0.1318359375, "learning_rate": 3.5735105145552315e-05, "loss": 1.4677056074142456, "step": 4703 }, { "epoch": 0.39711701824551776, "grad_norm": 0.13671875, "learning_rate": 3.572922576942364e-05, "loss": 1.5006983280181885, "step": 4704 }, { "epoch": 0.39720143938034885, "grad_norm": 0.142578125, "learning_rate": 3.5723345665827664e-05, "loss": 1.5580265522003174, "step": 4705 }, { "epoch": 0.39728586051518, "grad_norm": 0.1494140625, "learning_rate": 3.571746483516308e-05, "loss": 1.4464057683944702, "step": 4706 }, { "epoch": 0.3973702816500111, "grad_norm": 0.1396484375, "learning_rate": 3.571158327782862e-05, "loss": 1.5452187061309814, "step": 4707 }, { "epoch": 0.3974547027848422, "grad_norm": 0.140625, "learning_rate": 3.570570099422306e-05, "loss": 1.5953474044799805, "step": 4708 }, { "epoch": 0.3975391239196733, "grad_norm": 0.1484375, "learning_rate": 3.5699817984745244e-05, "loss": 1.5012662410736084, "step": 4709 }, { "epoch": 0.39762354505450437, "grad_norm": 0.1396484375, "learning_rate": 3.569393424979405e-05, "loss": 1.5406036376953125, "step": 4710 }, { "epoch": 0.3977079661893355, "grad_norm": 0.138671875, "learning_rate": 3.5688049789768406e-05, "loss": 1.4698445796966553, "step": 4711 }, { "epoch": 0.3977923873241666, "grad_norm": 0.1376953125, "learning_rate": 3.56821646050673e-05, "loss": 1.4986002445220947, "step": 4712 }, { "epoch": 0.3978768084589977, "grad_norm": 0.1494140625, "learning_rate": 3.567627869608976e-05, "loss": 1.6195390224456787, "step": 4713 }, { "epoch": 0.3979612295938288, "grad_norm": 0.140625, "learning_rate": 3.5670392063234846e-05, "loss": 1.5371662378311157, "step": 4714 }, { "epoch": 0.39804565072865994, "grad_norm": 0.1474609375, "learning_rate": 3.5664504706901715e-05, "loss": 1.5796700716018677, "step": 4715 }, { "epoch": 0.39813007186349103, "grad_norm": 0.140625, "learning_rate": 3.565861662748953e-05, "loss": 1.5601956844329834, "step": 4716 }, { "epoch": 0.3982144929983221, "grad_norm": 0.1376953125, "learning_rate": 3.565272782539752e-05, "loss": 1.5676571130752563, "step": 4717 }, { "epoch": 0.3982989141331532, "grad_norm": 0.1689453125, "learning_rate": 3.5646838301024955e-05, "loss": 1.5638986825942993, "step": 4718 }, { "epoch": 0.39838333526798436, "grad_norm": 0.1357421875, "learning_rate": 3.5640948054771154e-05, "loss": 1.5228041410446167, "step": 4719 }, { "epoch": 0.39846775640281545, "grad_norm": 0.138671875, "learning_rate": 3.563505708703551e-05, "loss": 1.5840801000595093, "step": 4720 }, { "epoch": 0.39855217753764655, "grad_norm": 0.13671875, "learning_rate": 3.562916539821742e-05, "loss": 1.5505012273788452, "step": 4721 }, { "epoch": 0.39863659867247764, "grad_norm": 0.1318359375, "learning_rate": 3.562327298871638e-05, "loss": 1.5102068185806274, "step": 4722 }, { "epoch": 0.3987210198073088, "grad_norm": 0.13671875, "learning_rate": 3.561737985893189e-05, "loss": 1.5245980024337769, "step": 4723 }, { "epoch": 0.3988054409421399, "grad_norm": 0.1513671875, "learning_rate": 3.5611486009263516e-05, "loss": 1.5185015201568604, "step": 4724 }, { "epoch": 0.39888986207697097, "grad_norm": 0.1435546875, "learning_rate": 3.56055914401109e-05, "loss": 1.5532644987106323, "step": 4725 }, { "epoch": 0.39897428321180206, "grad_norm": 0.15234375, "learning_rate": 3.5599696151873685e-05, "loss": 1.5306230783462524, "step": 4726 }, { "epoch": 0.39905870434663315, "grad_norm": 0.1455078125, "learning_rate": 3.559380014495159e-05, "loss": 1.5165406465530396, "step": 4727 }, { "epoch": 0.3991431254814643, "grad_norm": 0.1455078125, "learning_rate": 3.558790341974438e-05, "loss": 1.4827406406402588, "step": 4728 }, { "epoch": 0.3992275466162954, "grad_norm": 0.130859375, "learning_rate": 3.5582005976651864e-05, "loss": 1.4818415641784668, "step": 4729 }, { "epoch": 0.3993119677511265, "grad_norm": 0.1474609375, "learning_rate": 3.5576107816073926e-05, "loss": 1.481766939163208, "step": 4730 }, { "epoch": 0.3993963888859576, "grad_norm": 0.142578125, "learning_rate": 3.5570208938410444e-05, "loss": 1.4980696439743042, "step": 4731 }, { "epoch": 0.3994808100207887, "grad_norm": 0.1572265625, "learning_rate": 3.556430934406139e-05, "loss": 1.5378285646438599, "step": 4732 }, { "epoch": 0.3995652311556198, "grad_norm": 0.1474609375, "learning_rate": 3.555840903342676e-05, "loss": 1.5252134799957275, "step": 4733 }, { "epoch": 0.3996496522904509, "grad_norm": 0.138671875, "learning_rate": 3.555250800690663e-05, "loss": 1.544312596321106, "step": 4734 }, { "epoch": 0.399734073425282, "grad_norm": 0.1376953125, "learning_rate": 3.554660626490109e-05, "loss": 1.557704210281372, "step": 4735 }, { "epoch": 0.39981849456011315, "grad_norm": 0.1435546875, "learning_rate": 3.5540703807810285e-05, "loss": 1.5531407594680786, "step": 4736 }, { "epoch": 0.39990291569494424, "grad_norm": 0.1494140625, "learning_rate": 3.5534800636034435e-05, "loss": 1.5428451299667358, "step": 4737 }, { "epoch": 0.39998733682977533, "grad_norm": 0.1357421875, "learning_rate": 3.552889674997379e-05, "loss": 1.5349329710006714, "step": 4738 }, { "epoch": 0.4000717579646064, "grad_norm": 0.1474609375, "learning_rate": 3.5522992150028614e-05, "loss": 1.5622155666351318, "step": 4739 }, { "epoch": 0.40015617909943757, "grad_norm": 0.162109375, "learning_rate": 3.551708683659929e-05, "loss": 1.6331981420516968, "step": 4740 }, { "epoch": 0.40024060023426866, "grad_norm": 0.1455078125, "learning_rate": 3.5511180810086195e-05, "loss": 1.4883953332901, "step": 4741 }, { "epoch": 0.40032502136909975, "grad_norm": 0.14453125, "learning_rate": 3.5505274070889776e-05, "loss": 1.5380849838256836, "step": 4742 }, { "epoch": 0.40040944250393085, "grad_norm": 0.138671875, "learning_rate": 3.549936661941052e-05, "loss": 1.4937078952789307, "step": 4743 }, { "epoch": 0.40049386363876194, "grad_norm": 0.142578125, "learning_rate": 3.5493458456048976e-05, "loss": 1.5444562435150146, "step": 4744 }, { "epoch": 0.4005782847735931, "grad_norm": 0.138671875, "learning_rate": 3.548754958120573e-05, "loss": 1.5647425651550293, "step": 4745 }, { "epoch": 0.4006627059084242, "grad_norm": 0.15234375, "learning_rate": 3.54816399952814e-05, "loss": 1.6149851083755493, "step": 4746 }, { "epoch": 0.40074712704325527, "grad_norm": 0.1611328125, "learning_rate": 3.5475729698676694e-05, "loss": 1.5571619272232056, "step": 4747 }, { "epoch": 0.40083154817808636, "grad_norm": 0.1533203125, "learning_rate": 3.546981869179233e-05, "loss": 1.5355876684188843, "step": 4748 }, { "epoch": 0.4009159693129175, "grad_norm": 0.138671875, "learning_rate": 3.54639069750291e-05, "loss": 1.54104483127594, "step": 4749 }, { "epoch": 0.4010003904477486, "grad_norm": 0.1328125, "learning_rate": 3.545799454878782e-05, "loss": 1.5150604248046875, "step": 4750 }, { "epoch": 0.4010848115825797, "grad_norm": 0.13671875, "learning_rate": 3.545208141346937e-05, "loss": 1.482905626296997, "step": 4751 }, { "epoch": 0.4011692327174108, "grad_norm": 0.1396484375, "learning_rate": 3.544616756947468e-05, "loss": 1.5350921154022217, "step": 4752 }, { "epoch": 0.40125365385224193, "grad_norm": 0.1357421875, "learning_rate": 3.5440253017204715e-05, "loss": 1.5484704971313477, "step": 4753 }, { "epoch": 0.401338074987073, "grad_norm": 0.1396484375, "learning_rate": 3.5434337757060506e-05, "loss": 1.5052977800369263, "step": 4754 }, { "epoch": 0.4014224961219041, "grad_norm": 0.1416015625, "learning_rate": 3.5428421789443115e-05, "loss": 1.5064805746078491, "step": 4755 }, { "epoch": 0.4015069172567352, "grad_norm": 0.1357421875, "learning_rate": 3.5422505114753654e-05, "loss": 1.567582368850708, "step": 4756 }, { "epoch": 0.40159133839156635, "grad_norm": 0.1376953125, "learning_rate": 3.54165877333933e-05, "loss": 1.5587279796600342, "step": 4757 }, { "epoch": 0.40167575952639745, "grad_norm": 0.146484375, "learning_rate": 3.541066964576325e-05, "loss": 1.5265151262283325, "step": 4758 }, { "epoch": 0.40176018066122854, "grad_norm": 0.146484375, "learning_rate": 3.5404750852264785e-05, "loss": 1.621708631515503, "step": 4759 }, { "epoch": 0.40184460179605963, "grad_norm": 0.1455078125, "learning_rate": 3.53988313532992e-05, "loss": 1.5604121685028076, "step": 4760 }, { "epoch": 0.4019290229308907, "grad_norm": 0.140625, "learning_rate": 3.5392911149267854e-05, "loss": 1.5244791507720947, "step": 4761 }, { "epoch": 0.40201344406572187, "grad_norm": 0.1494140625, "learning_rate": 3.538699024057215e-05, "loss": 1.5350018739700317, "step": 4762 }, { "epoch": 0.40209786520055296, "grad_norm": 0.1474609375, "learning_rate": 3.538106862761353e-05, "loss": 1.5757896900177002, "step": 4763 }, { "epoch": 0.40218228633538405, "grad_norm": 0.1396484375, "learning_rate": 3.5375146310793524e-05, "loss": 1.5745700597763062, "step": 4764 }, { "epoch": 0.40226670747021515, "grad_norm": 0.142578125, "learning_rate": 3.536922329051365e-05, "loss": 1.5926289558410645, "step": 4765 }, { "epoch": 0.4023511286050463, "grad_norm": 0.1630859375, "learning_rate": 3.536329956717551e-05, "loss": 1.5128018856048584, "step": 4766 }, { "epoch": 0.4024355497398774, "grad_norm": 0.1357421875, "learning_rate": 3.535737514118075e-05, "loss": 1.5159213542938232, "step": 4767 }, { "epoch": 0.4025199708747085, "grad_norm": 0.1416015625, "learning_rate": 3.535145001293107e-05, "loss": 1.4377440214157104, "step": 4768 }, { "epoch": 0.40260439200953957, "grad_norm": 0.13671875, "learning_rate": 3.534552418282818e-05, "loss": 1.4141932725906372, "step": 4769 }, { "epoch": 0.4026888131443707, "grad_norm": 0.142578125, "learning_rate": 3.533959765127389e-05, "loss": 1.5411407947540283, "step": 4770 }, { "epoch": 0.4027732342792018, "grad_norm": 0.140625, "learning_rate": 3.533367041867004e-05, "loss": 1.5294338464736938, "step": 4771 }, { "epoch": 0.4028576554140329, "grad_norm": 0.150390625, "learning_rate": 3.5327742485418474e-05, "loss": 1.5829941034317017, "step": 4772 }, { "epoch": 0.402942076548864, "grad_norm": 0.1357421875, "learning_rate": 3.532181385192116e-05, "loss": 1.565880537033081, "step": 4773 }, { "epoch": 0.40302649768369514, "grad_norm": 0.1396484375, "learning_rate": 3.531588451858005e-05, "loss": 1.5313522815704346, "step": 4774 }, { "epoch": 0.40311091881852623, "grad_norm": 0.1396484375, "learning_rate": 3.530995448579717e-05, "loss": 1.5658457279205322, "step": 4775 }, { "epoch": 0.4031953399533573, "grad_norm": 0.15625, "learning_rate": 3.5304023753974596e-05, "loss": 1.5876896381378174, "step": 4776 }, { "epoch": 0.4032797610881884, "grad_norm": 0.140625, "learning_rate": 3.529809232351445e-05, "loss": 1.4758470058441162, "step": 4777 }, { "epoch": 0.4033641822230195, "grad_norm": 0.12890625, "learning_rate": 3.5292160194818884e-05, "loss": 1.4503971338272095, "step": 4778 }, { "epoch": 0.40344860335785065, "grad_norm": 0.1376953125, "learning_rate": 3.5286227368290124e-05, "loss": 1.54729425907135, "step": 4779 }, { "epoch": 0.40353302449268175, "grad_norm": 0.13671875, "learning_rate": 3.528029384433041e-05, "loss": 1.4940091371536255, "step": 4780 }, { "epoch": 0.40361744562751284, "grad_norm": 0.1513671875, "learning_rate": 3.527435962334208e-05, "loss": 1.5902286767959595, "step": 4781 }, { "epoch": 0.40370186676234393, "grad_norm": 0.140625, "learning_rate": 3.5268424705727464e-05, "loss": 1.5233995914459229, "step": 4782 }, { "epoch": 0.4037862878971751, "grad_norm": 0.1728515625, "learning_rate": 3.526248909188897e-05, "loss": 1.5369396209716797, "step": 4783 }, { "epoch": 0.40387070903200617, "grad_norm": 0.1435546875, "learning_rate": 3.525655278222905e-05, "loss": 1.59629487991333, "step": 4784 }, { "epoch": 0.40395513016683726, "grad_norm": 0.1513671875, "learning_rate": 3.52506157771502e-05, "loss": 1.5717238187789917, "step": 4785 }, { "epoch": 0.40403955130166835, "grad_norm": 0.134765625, "learning_rate": 3.524467807705496e-05, "loss": 1.5450183153152466, "step": 4786 }, { "epoch": 0.4041239724364995, "grad_norm": 0.14453125, "learning_rate": 3.523873968234591e-05, "loss": 1.590886116027832, "step": 4787 }, { "epoch": 0.4042083935713306, "grad_norm": 0.15625, "learning_rate": 3.523280059342571e-05, "loss": 1.5385780334472656, "step": 4788 }, { "epoch": 0.4042928147061617, "grad_norm": 0.146484375, "learning_rate": 3.522686081069703e-05, "loss": 1.497619867324829, "step": 4789 }, { "epoch": 0.4043772358409928, "grad_norm": 0.1494140625, "learning_rate": 3.5220920334562607e-05, "loss": 1.627310872077942, "step": 4790 }, { "epoch": 0.4044616569758239, "grad_norm": 0.1435546875, "learning_rate": 3.521497916542521e-05, "loss": 1.5443819761276245, "step": 4791 }, { "epoch": 0.404546078110655, "grad_norm": 0.1494140625, "learning_rate": 3.520903730368769e-05, "loss": 1.559581995010376, "step": 4792 }, { "epoch": 0.4046304992454861, "grad_norm": 0.146484375, "learning_rate": 3.5203094749752886e-05, "loss": 1.6012260913848877, "step": 4793 }, { "epoch": 0.4047149203803172, "grad_norm": 0.140625, "learning_rate": 3.519715150402373e-05, "loss": 1.5136617422103882, "step": 4794 }, { "epoch": 0.4047993415151483, "grad_norm": 0.13671875, "learning_rate": 3.519120756690321e-05, "loss": 1.5404082536697388, "step": 4795 }, { "epoch": 0.40488376264997944, "grad_norm": 0.138671875, "learning_rate": 3.51852629387943e-05, "loss": 1.4970266819000244, "step": 4796 }, { "epoch": 0.40496818378481053, "grad_norm": 0.1396484375, "learning_rate": 3.517931762010009e-05, "loss": 1.62152898311615, "step": 4797 }, { "epoch": 0.4050526049196416, "grad_norm": 0.140625, "learning_rate": 3.517337161122368e-05, "loss": 1.5735125541687012, "step": 4798 }, { "epoch": 0.4051370260544727, "grad_norm": 0.1474609375, "learning_rate": 3.5167424912568215e-05, "loss": 1.5226402282714844, "step": 4799 }, { "epoch": 0.40522144718930386, "grad_norm": 0.1533203125, "learning_rate": 3.516147752453691e-05, "loss": 1.616433024406433, "step": 4800 }, { "epoch": 0.40530586832413495, "grad_norm": 0.1357421875, "learning_rate": 3.5155529447533e-05, "loss": 1.5103472471237183, "step": 4801 }, { "epoch": 0.40539028945896605, "grad_norm": 0.1552734375, "learning_rate": 3.5149580681959783e-05, "loss": 1.5633355379104614, "step": 4802 }, { "epoch": 0.40547471059379714, "grad_norm": 0.1435546875, "learning_rate": 3.514363122822059e-05, "loss": 1.5612330436706543, "step": 4803 }, { "epoch": 0.4055591317286283, "grad_norm": 0.1298828125, "learning_rate": 3.513768108671883e-05, "loss": 1.5243849754333496, "step": 4804 }, { "epoch": 0.4056435528634594, "grad_norm": 0.13671875, "learning_rate": 3.513173025785792e-05, "loss": 1.5067687034606934, "step": 4805 }, { "epoch": 0.40572797399829047, "grad_norm": 0.140625, "learning_rate": 3.5125778742041345e-05, "loss": 1.6108635663986206, "step": 4806 }, { "epoch": 0.40581239513312156, "grad_norm": 0.142578125, "learning_rate": 3.5119826539672636e-05, "loss": 1.5928478240966797, "step": 4807 }, { "epoch": 0.4058968162679527, "grad_norm": 0.1435546875, "learning_rate": 3.511387365115535e-05, "loss": 1.4672892093658447, "step": 4808 }, { "epoch": 0.4059812374027838, "grad_norm": 0.146484375, "learning_rate": 3.5107920076893134e-05, "loss": 1.524882435798645, "step": 4809 }, { "epoch": 0.4060656585376149, "grad_norm": 0.1806640625, "learning_rate": 3.510196581728963e-05, "loss": 1.550640344619751, "step": 4810 }, { "epoch": 0.406150079672446, "grad_norm": 0.146484375, "learning_rate": 3.509601087274857e-05, "loss": 1.5753650665283203, "step": 4811 }, { "epoch": 0.4062345008072771, "grad_norm": 0.1318359375, "learning_rate": 3.50900552436737e-05, "loss": 1.4365355968475342, "step": 4812 }, { "epoch": 0.4063189219421082, "grad_norm": 0.138671875, "learning_rate": 3.5084098930468836e-05, "loss": 1.5837998390197754, "step": 4813 }, { "epoch": 0.4064033430769393, "grad_norm": 0.13671875, "learning_rate": 3.5078141933537824e-05, "loss": 1.4958195686340332, "step": 4814 }, { "epoch": 0.4064877642117704, "grad_norm": 0.1337890625, "learning_rate": 3.5072184253284565e-05, "loss": 1.4943854808807373, "step": 4815 }, { "epoch": 0.4065721853466015, "grad_norm": 0.1416015625, "learning_rate": 3.5066225890113004e-05, "loss": 1.510719895362854, "step": 4816 }, { "epoch": 0.40665660648143265, "grad_norm": 0.1513671875, "learning_rate": 3.506026684442712e-05, "loss": 1.5075660943984985, "step": 4817 }, { "epoch": 0.40674102761626374, "grad_norm": 0.13671875, "learning_rate": 3.5054307116630975e-05, "loss": 1.491492748260498, "step": 4818 }, { "epoch": 0.40682544875109483, "grad_norm": 0.146484375, "learning_rate": 3.5048346707128644e-05, "loss": 1.4634644985198975, "step": 4819 }, { "epoch": 0.4069098698859259, "grad_norm": 0.1357421875, "learning_rate": 3.504238561632424e-05, "loss": 1.4729843139648438, "step": 4820 }, { "epoch": 0.40699429102075707, "grad_norm": 0.1318359375, "learning_rate": 3.503642384462196e-05, "loss": 1.536321759223938, "step": 4821 }, { "epoch": 0.40707871215558816, "grad_norm": 0.134765625, "learning_rate": 3.503046139242602e-05, "loss": 1.4725772142410278, "step": 4822 }, { "epoch": 0.40716313329041925, "grad_norm": 0.138671875, "learning_rate": 3.5024498260140675e-05, "loss": 1.4993932247161865, "step": 4823 }, { "epoch": 0.40724755442525035, "grad_norm": 0.1455078125, "learning_rate": 3.501853444817027e-05, "loss": 1.5821945667266846, "step": 4824 }, { "epoch": 0.4073319755600815, "grad_norm": 0.14453125, "learning_rate": 3.501256995691914e-05, "loss": 1.5767128467559814, "step": 4825 }, { "epoch": 0.4074163966949126, "grad_norm": 0.1357421875, "learning_rate": 3.5006604786791695e-05, "loss": 1.5693538188934326, "step": 4826 }, { "epoch": 0.4075008178297437, "grad_norm": 0.134765625, "learning_rate": 3.50006389381924e-05, "loss": 1.4962825775146484, "step": 4827 }, { "epoch": 0.40758523896457477, "grad_norm": 0.1376953125, "learning_rate": 3.499467241152574e-05, "loss": 1.5716549158096313, "step": 4828 }, { "epoch": 0.40766966009940586, "grad_norm": 0.1611328125, "learning_rate": 3.498870520719627e-05, "loss": 1.5604616403579712, "step": 4829 }, { "epoch": 0.407754081234237, "grad_norm": 0.13671875, "learning_rate": 3.498273732560858e-05, "loss": 1.5092828273773193, "step": 4830 }, { "epoch": 0.4078385023690681, "grad_norm": 0.1328125, "learning_rate": 3.49767687671673e-05, "loss": 1.492418646812439, "step": 4831 }, { "epoch": 0.4079229235038992, "grad_norm": 0.13671875, "learning_rate": 3.497079953227712e-05, "loss": 1.4516905546188354, "step": 4832 }, { "epoch": 0.4080073446387303, "grad_norm": 0.1484375, "learning_rate": 3.496482962134277e-05, "loss": 1.573119044303894, "step": 4833 }, { "epoch": 0.40809176577356143, "grad_norm": 0.14453125, "learning_rate": 3.495885903476901e-05, "loss": 1.4865772724151611, "step": 4834 }, { "epoch": 0.4081761869083925, "grad_norm": 0.134765625, "learning_rate": 3.495288777296067e-05, "loss": 1.5509493350982666, "step": 4835 }, { "epoch": 0.4082606080432236, "grad_norm": 0.1376953125, "learning_rate": 3.494691583632262e-05, "loss": 1.493127465248108, "step": 4836 }, { "epoch": 0.4083450291780547, "grad_norm": 0.1318359375, "learning_rate": 3.4940943225259766e-05, "loss": 1.523097038269043, "step": 4837 }, { "epoch": 0.40842945031288586, "grad_norm": 0.1494140625, "learning_rate": 3.4934969940177066e-05, "loss": 1.5958325862884521, "step": 4838 }, { "epoch": 0.40851387144771695, "grad_norm": 0.15234375, "learning_rate": 3.4928995981479516e-05, "loss": 1.6103647947311401, "step": 4839 }, { "epoch": 0.40859829258254804, "grad_norm": 0.140625, "learning_rate": 3.492302134957218e-05, "loss": 1.4855283498764038, "step": 4840 }, { "epoch": 0.40868271371737913, "grad_norm": 0.13671875, "learning_rate": 3.491704604486015e-05, "loss": 1.5056737661361694, "step": 4841 }, { "epoch": 0.4087671348522102, "grad_norm": 0.1328125, "learning_rate": 3.491107006774855e-05, "loss": 1.4626009464263916, "step": 4842 }, { "epoch": 0.40885155598704137, "grad_norm": 0.13671875, "learning_rate": 3.4905093418642585e-05, "loss": 1.584792137145996, "step": 4843 }, { "epoch": 0.40893597712187246, "grad_norm": 0.1357421875, "learning_rate": 3.489911609794747e-05, "loss": 1.5292023420333862, "step": 4844 }, { "epoch": 0.40902039825670355, "grad_norm": 0.1376953125, "learning_rate": 3.48931381060685e-05, "loss": 1.4793850183486938, "step": 4845 }, { "epoch": 0.40910481939153465, "grad_norm": 0.142578125, "learning_rate": 3.488715944341097e-05, "loss": 1.5712703466415405, "step": 4846 }, { "epoch": 0.4091892405263658, "grad_norm": 0.1455078125, "learning_rate": 3.488118011038027e-05, "loss": 1.4730305671691895, "step": 4847 }, { "epoch": 0.4092736616611969, "grad_norm": 0.1357421875, "learning_rate": 3.487520010738182e-05, "loss": 1.469247817993164, "step": 4848 }, { "epoch": 0.409358082796028, "grad_norm": 0.1376953125, "learning_rate": 3.486921943482105e-05, "loss": 1.5608093738555908, "step": 4849 }, { "epoch": 0.40944250393085907, "grad_norm": 0.1328125, "learning_rate": 3.486323809310349e-05, "loss": 1.5961052179336548, "step": 4850 }, { "epoch": 0.4095269250656902, "grad_norm": 0.1435546875, "learning_rate": 3.485725608263467e-05, "loss": 1.5320271253585815, "step": 4851 }, { "epoch": 0.4096113462005213, "grad_norm": 0.1328125, "learning_rate": 3.485127340382021e-05, "loss": 1.5564554929733276, "step": 4852 }, { "epoch": 0.4096957673353524, "grad_norm": 0.1435546875, "learning_rate": 3.484529005706572e-05, "loss": 1.5294922590255737, "step": 4853 }, { "epoch": 0.4097801884701835, "grad_norm": 0.1337890625, "learning_rate": 3.48393060427769e-05, "loss": 1.5940614938735962, "step": 4854 }, { "epoch": 0.40986460960501464, "grad_norm": 0.1357421875, "learning_rate": 3.483332136135948e-05, "loss": 1.5370951890945435, "step": 4855 }, { "epoch": 0.40994903073984573, "grad_norm": 0.140625, "learning_rate": 3.482733601321924e-05, "loss": 1.6110665798187256, "step": 4856 }, { "epoch": 0.4100334518746768, "grad_norm": 0.1494140625, "learning_rate": 3.482134999876199e-05, "loss": 1.6484487056732178, "step": 4857 }, { "epoch": 0.4101178730095079, "grad_norm": 0.1533203125, "learning_rate": 3.4815363318393604e-05, "loss": 1.5122909545898438, "step": 4858 }, { "epoch": 0.410202294144339, "grad_norm": 0.1513671875, "learning_rate": 3.4809375972519995e-05, "loss": 1.5170655250549316, "step": 4859 }, { "epoch": 0.41028671527917016, "grad_norm": 0.1376953125, "learning_rate": 3.480338796154712e-05, "loss": 1.5963321924209595, "step": 4860 }, { "epoch": 0.41037113641400125, "grad_norm": 0.14453125, "learning_rate": 3.479739928588097e-05, "loss": 1.4607021808624268, "step": 4861 }, { "epoch": 0.41045555754883234, "grad_norm": 0.134765625, "learning_rate": 3.4791409945927606e-05, "loss": 1.5058728456497192, "step": 4862 }, { "epoch": 0.41053997868366343, "grad_norm": 0.134765625, "learning_rate": 3.47854199420931e-05, "loss": 1.5170040130615234, "step": 4863 }, { "epoch": 0.4106243998184946, "grad_norm": 0.1376953125, "learning_rate": 3.4779429274783614e-05, "loss": 1.5076231956481934, "step": 4864 }, { "epoch": 0.41070882095332567, "grad_norm": 0.1484375, "learning_rate": 3.4773437944405317e-05, "loss": 1.586510181427002, "step": 4865 }, { "epoch": 0.41079324208815676, "grad_norm": 0.1337890625, "learning_rate": 3.4767445951364426e-05, "loss": 1.538981556892395, "step": 4866 }, { "epoch": 0.41087766322298785, "grad_norm": 0.1484375, "learning_rate": 3.476145329606723e-05, "loss": 1.5446540117263794, "step": 4867 }, { "epoch": 0.410962084357819, "grad_norm": 0.138671875, "learning_rate": 3.475545997892003e-05, "loss": 1.526127815246582, "step": 4868 }, { "epoch": 0.4110465054926501, "grad_norm": 0.138671875, "learning_rate": 3.474946600032919e-05, "loss": 1.5325117111206055, "step": 4869 }, { "epoch": 0.4111309266274812, "grad_norm": 0.1435546875, "learning_rate": 3.474347136070113e-05, "loss": 1.5013577938079834, "step": 4870 }, { "epoch": 0.4112153477623123, "grad_norm": 0.1435546875, "learning_rate": 3.4737476060442284e-05, "loss": 1.478777289390564, "step": 4871 }, { "epoch": 0.4112997688971434, "grad_norm": 0.1416015625, "learning_rate": 3.473148009995917e-05, "loss": 1.5326136350631714, "step": 4872 }, { "epoch": 0.4113841900319745, "grad_norm": 0.1484375, "learning_rate": 3.47254834796583e-05, "loss": 1.5311084985733032, "step": 4873 }, { "epoch": 0.4114686111668056, "grad_norm": 0.12890625, "learning_rate": 3.4719486199946275e-05, "loss": 1.5281639099121094, "step": 4874 }, { "epoch": 0.4115530323016367, "grad_norm": 0.1337890625, "learning_rate": 3.4713488261229724e-05, "loss": 1.4887629747390747, "step": 4875 }, { "epoch": 0.4116374534364678, "grad_norm": 0.1318359375, "learning_rate": 3.470748966391532e-05, "loss": 1.5732572078704834, "step": 4876 }, { "epoch": 0.41172187457129894, "grad_norm": 0.1396484375, "learning_rate": 3.470149040840979e-05, "loss": 1.4618757963180542, "step": 4877 }, { "epoch": 0.41180629570613003, "grad_norm": 0.142578125, "learning_rate": 3.469549049511989e-05, "loss": 1.4676367044448853, "step": 4878 }, { "epoch": 0.4118907168409611, "grad_norm": 0.146484375, "learning_rate": 3.468948992445242e-05, "loss": 1.5622189044952393, "step": 4879 }, { "epoch": 0.4119751379757922, "grad_norm": 0.140625, "learning_rate": 3.4683488696814244e-05, "loss": 1.5199817419052124, "step": 4880 }, { "epoch": 0.41205955911062336, "grad_norm": 0.142578125, "learning_rate": 3.4677486812612255e-05, "loss": 1.519569993019104, "step": 4881 }, { "epoch": 0.41214398024545446, "grad_norm": 0.1396484375, "learning_rate": 3.4671484272253416e-05, "loss": 1.4841945171356201, "step": 4882 }, { "epoch": 0.41222840138028555, "grad_norm": 0.1396484375, "learning_rate": 3.466548107614469e-05, "loss": 1.5618634223937988, "step": 4883 }, { "epoch": 0.41231282251511664, "grad_norm": 0.1357421875, "learning_rate": 3.465947722469311e-05, "loss": 1.537745475769043, "step": 4884 }, { "epoch": 0.4123972436499478, "grad_norm": 0.1318359375, "learning_rate": 3.4653472718305745e-05, "loss": 1.4655014276504517, "step": 4885 }, { "epoch": 0.4124816647847789, "grad_norm": 0.134765625, "learning_rate": 3.4647467557389746e-05, "loss": 1.5108871459960938, "step": 4886 }, { "epoch": 0.41256608591960997, "grad_norm": 0.1396484375, "learning_rate": 3.464146174235224e-05, "loss": 1.548172116279602, "step": 4887 }, { "epoch": 0.41265050705444106, "grad_norm": 0.1474609375, "learning_rate": 3.463545527360046e-05, "loss": 1.56820809841156, "step": 4888 }, { "epoch": 0.4127349281892722, "grad_norm": 0.140625, "learning_rate": 3.462944815154166e-05, "loss": 1.5668072700500488, "step": 4889 }, { "epoch": 0.4128193493241033, "grad_norm": 0.1357421875, "learning_rate": 3.462344037658312e-05, "loss": 1.5187608003616333, "step": 4890 }, { "epoch": 0.4129037704589344, "grad_norm": 0.1396484375, "learning_rate": 3.4617431949132194e-05, "loss": 1.4610882997512817, "step": 4891 }, { "epoch": 0.4129881915937655, "grad_norm": 0.16015625, "learning_rate": 3.4611422869596264e-05, "loss": 1.5425631999969482, "step": 4892 }, { "epoch": 0.4130726127285966, "grad_norm": 0.1376953125, "learning_rate": 3.4605413138382755e-05, "loss": 1.5822515487670898, "step": 4893 }, { "epoch": 0.4131570338634277, "grad_norm": 0.1416015625, "learning_rate": 3.459940275589915e-05, "loss": 1.5466265678405762, "step": 4894 }, { "epoch": 0.4132414549982588, "grad_norm": 0.1396484375, "learning_rate": 3.459339172255297e-05, "loss": 1.5405882596969604, "step": 4895 }, { "epoch": 0.4133258761330899, "grad_norm": 0.13671875, "learning_rate": 3.458738003875177e-05, "loss": 1.5148359537124634, "step": 4896 }, { "epoch": 0.413410297267921, "grad_norm": 0.1416015625, "learning_rate": 3.4581367704903153e-05, "loss": 1.5247955322265625, "step": 4897 }, { "epoch": 0.41349471840275215, "grad_norm": 0.130859375, "learning_rate": 3.457535472141478e-05, "loss": 1.549405574798584, "step": 4898 }, { "epoch": 0.41357913953758324, "grad_norm": 0.140625, "learning_rate": 3.456934108869434e-05, "loss": 1.512678861618042, "step": 4899 }, { "epoch": 0.41366356067241433, "grad_norm": 0.138671875, "learning_rate": 3.456332680714957e-05, "loss": 1.5192451477050781, "step": 4900 }, { "epoch": 0.4137479818072454, "grad_norm": 0.158203125, "learning_rate": 3.455731187718826e-05, "loss": 1.6128535270690918, "step": 4901 }, { "epoch": 0.41383240294207657, "grad_norm": 0.1494140625, "learning_rate": 3.4551296299218215e-05, "loss": 1.5181498527526855, "step": 4902 }, { "epoch": 0.41391682407690766, "grad_norm": 0.134765625, "learning_rate": 3.454528007364735e-05, "loss": 1.5275994539260864, "step": 4903 }, { "epoch": 0.41400124521173876, "grad_norm": 0.138671875, "learning_rate": 3.453926320088353e-05, "loss": 1.4872641563415527, "step": 4904 }, { "epoch": 0.41408566634656985, "grad_norm": 0.140625, "learning_rate": 3.453324568133475e-05, "loss": 1.4667764902114868, "step": 4905 }, { "epoch": 0.414170087481401, "grad_norm": 0.1396484375, "learning_rate": 3.452722751540899e-05, "loss": 1.5240023136138916, "step": 4906 }, { "epoch": 0.4142545086162321, "grad_norm": 0.142578125, "learning_rate": 3.45212087035143e-05, "loss": 1.5658366680145264, "step": 4907 }, { "epoch": 0.4143389297510632, "grad_norm": 0.130859375, "learning_rate": 3.451518924605878e-05, "loss": 1.456453561782837, "step": 4908 }, { "epoch": 0.41442335088589427, "grad_norm": 0.142578125, "learning_rate": 3.450916914345056e-05, "loss": 1.4991644620895386, "step": 4909 }, { "epoch": 0.41450777202072536, "grad_norm": 0.1357421875, "learning_rate": 3.450314839609781e-05, "loss": 1.5044432878494263, "step": 4910 }, { "epoch": 0.4145921931555565, "grad_norm": 0.1416015625, "learning_rate": 3.449712700440876e-05, "loss": 1.5107940435409546, "step": 4911 }, { "epoch": 0.4146766142903876, "grad_norm": 0.140625, "learning_rate": 3.449110496879167e-05, "loss": 1.5364502668380737, "step": 4912 }, { "epoch": 0.4147610354252187, "grad_norm": 0.130859375, "learning_rate": 3.448508228965485e-05, "loss": 1.489014744758606, "step": 4913 }, { "epoch": 0.4148454565600498, "grad_norm": 0.1494140625, "learning_rate": 3.4479058967406654e-05, "loss": 1.4854397773742676, "step": 4914 }, { "epoch": 0.41492987769488093, "grad_norm": 0.16015625, "learning_rate": 3.447303500245547e-05, "loss": 1.577170729637146, "step": 4915 }, { "epoch": 0.415014298829712, "grad_norm": 0.1455078125, "learning_rate": 3.4467010395209745e-05, "loss": 1.5522774457931519, "step": 4916 }, { "epoch": 0.4150987199645431, "grad_norm": 0.1396484375, "learning_rate": 3.4460985146077953e-05, "loss": 1.5441038608551025, "step": 4917 }, { "epoch": 0.4151831410993742, "grad_norm": 0.13671875, "learning_rate": 3.4454959255468636e-05, "loss": 1.5311986207962036, "step": 4918 }, { "epoch": 0.41526756223420536, "grad_norm": 0.13671875, "learning_rate": 3.444893272379035e-05, "loss": 1.4676655530929565, "step": 4919 }, { "epoch": 0.41535198336903645, "grad_norm": 0.134765625, "learning_rate": 3.444290555145172e-05, "loss": 1.5005760192871094, "step": 4920 }, { "epoch": 0.41543640450386754, "grad_norm": 0.134765625, "learning_rate": 3.443687773886139e-05, "loss": 1.4394913911819458, "step": 4921 }, { "epoch": 0.41552082563869863, "grad_norm": 0.1533203125, "learning_rate": 3.4430849286428064e-05, "loss": 1.5478724241256714, "step": 4922 }, { "epoch": 0.4156052467735298, "grad_norm": 0.134765625, "learning_rate": 3.442482019456049e-05, "loss": 1.5299962759017944, "step": 4923 }, { "epoch": 0.41568966790836087, "grad_norm": 0.1318359375, "learning_rate": 3.441879046366745e-05, "loss": 1.4905714988708496, "step": 4924 }, { "epoch": 0.41577408904319196, "grad_norm": 0.1494140625, "learning_rate": 3.441276009415778e-05, "loss": 1.4918887615203857, "step": 4925 }, { "epoch": 0.41585851017802306, "grad_norm": 0.1337890625, "learning_rate": 3.440672908644035e-05, "loss": 1.4898152351379395, "step": 4926 }, { "epoch": 0.41594293131285415, "grad_norm": 0.1337890625, "learning_rate": 3.440069744092409e-05, "loss": 1.500747561454773, "step": 4927 }, { "epoch": 0.4160273524476853, "grad_norm": 0.134765625, "learning_rate": 3.439466515801792e-05, "loss": 1.5726940631866455, "step": 4928 }, { "epoch": 0.4161117735825164, "grad_norm": 0.1376953125, "learning_rate": 3.438863223813089e-05, "loss": 1.5435842275619507, "step": 4929 }, { "epoch": 0.4161961947173475, "grad_norm": 0.150390625, "learning_rate": 3.4382598681672024e-05, "loss": 1.5783336162567139, "step": 4930 }, { "epoch": 0.41628061585217857, "grad_norm": 0.1298828125, "learning_rate": 3.437656448905041e-05, "loss": 1.4431713819503784, "step": 4931 }, { "epoch": 0.4163650369870097, "grad_norm": 0.154296875, "learning_rate": 3.4370529660675194e-05, "loss": 1.5911062955856323, "step": 4932 }, { "epoch": 0.4164494581218408, "grad_norm": 0.140625, "learning_rate": 3.436449419695553e-05, "loss": 1.54202401638031, "step": 4933 }, { "epoch": 0.4165338792566719, "grad_norm": 0.1572265625, "learning_rate": 3.435845809830066e-05, "loss": 1.5458976030349731, "step": 4934 }, { "epoch": 0.416618300391503, "grad_norm": 0.142578125, "learning_rate": 3.435242136511984e-05, "loss": 1.551937222480774, "step": 4935 }, { "epoch": 0.41670272152633414, "grad_norm": 0.14453125, "learning_rate": 3.4346383997822356e-05, "loss": 1.5532643795013428, "step": 4936 }, { "epoch": 0.41678714266116523, "grad_norm": 0.1376953125, "learning_rate": 3.434034599681758e-05, "loss": 1.5401568412780762, "step": 4937 }, { "epoch": 0.4168715637959963, "grad_norm": 0.1318359375, "learning_rate": 3.4334307362514896e-05, "loss": 1.499626636505127, "step": 4938 }, { "epoch": 0.4169559849308274, "grad_norm": 0.1328125, "learning_rate": 3.432826809532373e-05, "loss": 1.508469820022583, "step": 4939 }, { "epoch": 0.41704040606565856, "grad_norm": 0.1435546875, "learning_rate": 3.432222819565357e-05, "loss": 1.5425130128860474, "step": 4940 }, { "epoch": 0.41712482720048966, "grad_norm": 0.16015625, "learning_rate": 3.431618766391393e-05, "loss": 1.5122003555297852, "step": 4941 }, { "epoch": 0.41720924833532075, "grad_norm": 0.134765625, "learning_rate": 3.431014650051437e-05, "loss": 1.543686866760254, "step": 4942 }, { "epoch": 0.41729366947015184, "grad_norm": 0.1328125, "learning_rate": 3.4304104705864505e-05, "loss": 1.5075384378433228, "step": 4943 }, { "epoch": 0.41737809060498293, "grad_norm": 0.138671875, "learning_rate": 3.4298062280373976e-05, "loss": 1.5576512813568115, "step": 4944 }, { "epoch": 0.4174625117398141, "grad_norm": 0.14453125, "learning_rate": 3.429201922445247e-05, "loss": 1.537524700164795, "step": 4945 }, { "epoch": 0.41754693287464517, "grad_norm": 0.1376953125, "learning_rate": 3.428597553850973e-05, "loss": 1.5680702924728394, "step": 4946 }, { "epoch": 0.41763135400947626, "grad_norm": 0.1357421875, "learning_rate": 3.427993122295552e-05, "loss": 1.541351556777954, "step": 4947 }, { "epoch": 0.41771577514430736, "grad_norm": 0.1630859375, "learning_rate": 3.4273886278199676e-05, "loss": 1.5657023191452026, "step": 4948 }, { "epoch": 0.4178001962791385, "grad_norm": 0.1416015625, "learning_rate": 3.426784070465205e-05, "loss": 1.5138802528381348, "step": 4949 }, { "epoch": 0.4178846174139696, "grad_norm": 0.134765625, "learning_rate": 3.4261794502722546e-05, "loss": 1.4724541902542114, "step": 4950 }, { "epoch": 0.4179690385488007, "grad_norm": 0.142578125, "learning_rate": 3.4255747672821106e-05, "loss": 1.5313150882720947, "step": 4951 }, { "epoch": 0.4180534596836318, "grad_norm": 0.142578125, "learning_rate": 3.4249700215357725e-05, "loss": 1.4948921203613281, "step": 4952 }, { "epoch": 0.4181378808184629, "grad_norm": 0.138671875, "learning_rate": 3.424365213074244e-05, "loss": 1.5594403743743896, "step": 4953 }, { "epoch": 0.418222301953294, "grad_norm": 0.1513671875, "learning_rate": 3.423760341938533e-05, "loss": 1.5938160419464111, "step": 4954 }, { "epoch": 0.4183067230881251, "grad_norm": 0.150390625, "learning_rate": 3.423155408169649e-05, "loss": 1.6190682649612427, "step": 4955 }, { "epoch": 0.4183911442229562, "grad_norm": 0.1396484375, "learning_rate": 3.422550411808611e-05, "loss": 1.4904779195785522, "step": 4956 }, { "epoch": 0.41847556535778735, "grad_norm": 0.134765625, "learning_rate": 3.421945352896436e-05, "loss": 1.4580960273742676, "step": 4957 }, { "epoch": 0.41855998649261844, "grad_norm": 0.138671875, "learning_rate": 3.421340231474151e-05, "loss": 1.5288562774658203, "step": 4958 }, { "epoch": 0.41864440762744953, "grad_norm": 0.1396484375, "learning_rate": 3.4207350475827836e-05, "loss": 1.5181469917297363, "step": 4959 }, { "epoch": 0.4187288287622806, "grad_norm": 0.14453125, "learning_rate": 3.420129801263367e-05, "loss": 1.4296334981918335, "step": 4960 }, { "epoch": 0.4188132498971117, "grad_norm": 0.142578125, "learning_rate": 3.4195244925569376e-05, "loss": 1.5029382705688477, "step": 4961 }, { "epoch": 0.41889767103194286, "grad_norm": 0.1376953125, "learning_rate": 3.418919121504537e-05, "loss": 1.4698894023895264, "step": 4962 }, { "epoch": 0.41898209216677396, "grad_norm": 0.1318359375, "learning_rate": 3.418313688147212e-05, "loss": 1.488343358039856, "step": 4963 }, { "epoch": 0.41906651330160505, "grad_norm": 0.150390625, "learning_rate": 3.4177081925260116e-05, "loss": 1.5113428831100464, "step": 4964 }, { "epoch": 0.41915093443643614, "grad_norm": 0.134765625, "learning_rate": 3.417102634681989e-05, "loss": 1.5171737670898438, "step": 4965 }, { "epoch": 0.4192353555712673, "grad_norm": 0.1396484375, "learning_rate": 3.4164970146562043e-05, "loss": 1.4954169988632202, "step": 4966 }, { "epoch": 0.4193197767060984, "grad_norm": 0.150390625, "learning_rate": 3.4158913324897185e-05, "loss": 1.6054115295410156, "step": 4967 }, { "epoch": 0.41940419784092947, "grad_norm": 0.1396484375, "learning_rate": 3.415285588223599e-05, "loss": 1.5685943365097046, "step": 4968 }, { "epoch": 0.41948861897576056, "grad_norm": 0.1396484375, "learning_rate": 3.4146797818989165e-05, "loss": 1.5889842510223389, "step": 4969 }, { "epoch": 0.4195730401105917, "grad_norm": 0.150390625, "learning_rate": 3.4140739135567464e-05, "loss": 1.5146427154541016, "step": 4970 }, { "epoch": 0.4196574612454228, "grad_norm": 0.138671875, "learning_rate": 3.4134679832381676e-05, "loss": 1.5972472429275513, "step": 4971 }, { "epoch": 0.4197418823802539, "grad_norm": 0.1455078125, "learning_rate": 3.412861990984264e-05, "loss": 1.4620671272277832, "step": 4972 }, { "epoch": 0.419826303515085, "grad_norm": 0.1337890625, "learning_rate": 3.412255936836123e-05, "loss": 1.4767189025878906, "step": 4973 }, { "epoch": 0.41991072464991613, "grad_norm": 0.134765625, "learning_rate": 3.4116498208348366e-05, "loss": 1.5987287759780884, "step": 4974 }, { "epoch": 0.4199951457847472, "grad_norm": 0.1396484375, "learning_rate": 3.4110436430215017e-05, "loss": 1.5439577102661133, "step": 4975 }, { "epoch": 0.4200795669195783, "grad_norm": 0.1455078125, "learning_rate": 3.410437403437217e-05, "loss": 1.5011100769042969, "step": 4976 }, { "epoch": 0.4201639880544094, "grad_norm": 0.1337890625, "learning_rate": 3.409831102123088e-05, "loss": 1.5120593309402466, "step": 4977 }, { "epoch": 0.4202484091892405, "grad_norm": 0.1357421875, "learning_rate": 3.4092247391202235e-05, "loss": 1.4806373119354248, "step": 4978 }, { "epoch": 0.42033283032407165, "grad_norm": 0.158203125, "learning_rate": 3.408618314469737e-05, "loss": 1.6140581369400024, "step": 4979 }, { "epoch": 0.42041725145890274, "grad_norm": 0.1435546875, "learning_rate": 3.4080118282127445e-05, "loss": 1.5933278799057007, "step": 4980 }, { "epoch": 0.42050167259373383, "grad_norm": 0.12890625, "learning_rate": 3.4074052803903664e-05, "loss": 1.4700920581817627, "step": 4981 }, { "epoch": 0.4205860937285649, "grad_norm": 0.140625, "learning_rate": 3.4067986710437305e-05, "loss": 1.5055419206619263, "step": 4982 }, { "epoch": 0.4206705148633961, "grad_norm": 0.150390625, "learning_rate": 3.406192000213964e-05, "loss": 1.4983954429626465, "step": 4983 }, { "epoch": 0.42075493599822716, "grad_norm": 0.1376953125, "learning_rate": 3.405585267942202e-05, "loss": 1.5570714473724365, "step": 4984 }, { "epoch": 0.42083935713305826, "grad_norm": 0.1357421875, "learning_rate": 3.404978474269583e-05, "loss": 1.5360589027404785, "step": 4985 }, { "epoch": 0.42092377826788935, "grad_norm": 0.1953125, "learning_rate": 3.404371619237246e-05, "loss": 1.5718276500701904, "step": 4986 }, { "epoch": 0.4210081994027205, "grad_norm": 0.146484375, "learning_rate": 3.4037647028863416e-05, "loss": 1.5348836183547974, "step": 4987 }, { "epoch": 0.4210926205375516, "grad_norm": 0.13671875, "learning_rate": 3.4031577252580175e-05, "loss": 1.5123028755187988, "step": 4988 }, { "epoch": 0.4211770416723827, "grad_norm": 0.1396484375, "learning_rate": 3.402550686393429e-05, "loss": 1.4688918590545654, "step": 4989 }, { "epoch": 0.42126146280721377, "grad_norm": 0.12890625, "learning_rate": 3.401943586333733e-05, "loss": 1.5257484912872314, "step": 4990 }, { "epoch": 0.4213458839420449, "grad_norm": 0.1484375, "learning_rate": 3.401336425120095e-05, "loss": 1.4853955507278442, "step": 4991 }, { "epoch": 0.421430305076876, "grad_norm": 0.1376953125, "learning_rate": 3.400729202793681e-05, "loss": 1.539262056350708, "step": 4992 }, { "epoch": 0.4215147262117071, "grad_norm": 0.1435546875, "learning_rate": 3.4001219193956614e-05, "loss": 1.5839015245437622, "step": 4993 }, { "epoch": 0.4215991473465382, "grad_norm": 0.1455078125, "learning_rate": 3.399514574967212e-05, "loss": 1.5302730798721313, "step": 4994 }, { "epoch": 0.4216835684813693, "grad_norm": 0.1474609375, "learning_rate": 3.398907169549513e-05, "loss": 1.5711874961853027, "step": 4995 }, { "epoch": 0.42176798961620043, "grad_norm": 0.12890625, "learning_rate": 3.398299703183746e-05, "loss": 1.4582321643829346, "step": 4996 }, { "epoch": 0.4218524107510315, "grad_norm": 0.13671875, "learning_rate": 3.3976921759111016e-05, "loss": 1.4518550634384155, "step": 4997 }, { "epoch": 0.4219368318858626, "grad_norm": 0.1435546875, "learning_rate": 3.3970845877727686e-05, "loss": 1.5435446500778198, "step": 4998 }, { "epoch": 0.4220212530206937, "grad_norm": 0.13671875, "learning_rate": 3.396476938809945e-05, "loss": 1.489885926246643, "step": 4999 }, { "epoch": 0.42210567415552486, "grad_norm": 0.13671875, "learning_rate": 3.39586922906383e-05, "loss": 1.4584691524505615, "step": 5000 }, { "epoch": 0.42219009529035595, "grad_norm": 0.1494140625, "learning_rate": 3.395261458575627e-05, "loss": 1.5048117637634277, "step": 5001 }, { "epoch": 0.42227451642518704, "grad_norm": 0.138671875, "learning_rate": 3.394653627386546e-05, "loss": 1.5336350202560425, "step": 5002 }, { "epoch": 0.42235893756001813, "grad_norm": 0.1494140625, "learning_rate": 3.394045735537798e-05, "loss": 1.5826125144958496, "step": 5003 }, { "epoch": 0.4224433586948493, "grad_norm": 0.1787109375, "learning_rate": 3.3934377830706e-05, "loss": 1.543452501296997, "step": 5004 }, { "epoch": 0.42252777982968037, "grad_norm": 0.13671875, "learning_rate": 3.392829770026174e-05, "loss": 1.5135217905044556, "step": 5005 }, { "epoch": 0.42261220096451146, "grad_norm": 0.138671875, "learning_rate": 3.3922216964457425e-05, "loss": 1.527640700340271, "step": 5006 }, { "epoch": 0.42269662209934256, "grad_norm": 0.1494140625, "learning_rate": 3.391613562370536e-05, "loss": 1.5874087810516357, "step": 5007 }, { "epoch": 0.42278104323417365, "grad_norm": 0.14453125, "learning_rate": 3.391005367841786e-05, "loss": 1.5342512130737305, "step": 5008 }, { "epoch": 0.4228654643690048, "grad_norm": 0.1435546875, "learning_rate": 3.390397112900731e-05, "loss": 1.505043625831604, "step": 5009 }, { "epoch": 0.4229498855038359, "grad_norm": 0.1318359375, "learning_rate": 3.389788797588611e-05, "loss": 1.4381351470947266, "step": 5010 }, { "epoch": 0.423034306638667, "grad_norm": 0.1416015625, "learning_rate": 3.389180421946673e-05, "loss": 1.5029172897338867, "step": 5011 }, { "epoch": 0.42311872777349807, "grad_norm": 0.1416015625, "learning_rate": 3.388571986016164e-05, "loss": 1.5594731569290161, "step": 5012 }, { "epoch": 0.4232031489083292, "grad_norm": 0.1435546875, "learning_rate": 3.387963489838338e-05, "loss": 1.575353980064392, "step": 5013 }, { "epoch": 0.4232875700431603, "grad_norm": 0.1455078125, "learning_rate": 3.387354933454454e-05, "loss": 1.502008318901062, "step": 5014 }, { "epoch": 0.4233719911779914, "grad_norm": 0.1357421875, "learning_rate": 3.386746316905772e-05, "loss": 1.5134443044662476, "step": 5015 }, { "epoch": 0.4234564123128225, "grad_norm": 0.1435546875, "learning_rate": 3.386137640233559e-05, "loss": 1.5372912883758545, "step": 5016 }, { "epoch": 0.42354083344765364, "grad_norm": 0.1357421875, "learning_rate": 3.385528903479084e-05, "loss": 1.507135033607483, "step": 5017 }, { "epoch": 0.42362525458248473, "grad_norm": 0.1396484375, "learning_rate": 3.38492010668362e-05, "loss": 1.5654149055480957, "step": 5018 }, { "epoch": 0.4237096757173158, "grad_norm": 0.1396484375, "learning_rate": 3.3843112498884456e-05, "loss": 1.448346495628357, "step": 5019 }, { "epoch": 0.4237940968521469, "grad_norm": 0.1455078125, "learning_rate": 3.383702333134843e-05, "loss": 1.5373624563217163, "step": 5020 }, { "epoch": 0.42387851798697807, "grad_norm": 0.1416015625, "learning_rate": 3.383093356464099e-05, "loss": 1.5951642990112305, "step": 5021 }, { "epoch": 0.42396293912180916, "grad_norm": 0.1396484375, "learning_rate": 3.382484319917501e-05, "loss": 1.5202934741973877, "step": 5022 }, { "epoch": 0.42404736025664025, "grad_norm": 0.12890625, "learning_rate": 3.381875223536347e-05, "loss": 1.4732329845428467, "step": 5023 }, { "epoch": 0.42413178139147134, "grad_norm": 0.1416015625, "learning_rate": 3.381266067361932e-05, "loss": 1.521925449371338, "step": 5024 }, { "epoch": 0.42421620252630243, "grad_norm": 0.1328125, "learning_rate": 3.3806568514355595e-05, "loss": 1.5339264869689941, "step": 5025 }, { "epoch": 0.4243006236611336, "grad_norm": 0.1337890625, "learning_rate": 3.3800475757985364e-05, "loss": 1.5345250368118286, "step": 5026 }, { "epoch": 0.42438504479596467, "grad_norm": 0.1513671875, "learning_rate": 3.37943824049217e-05, "loss": 1.5321733951568604, "step": 5027 }, { "epoch": 0.42446946593079576, "grad_norm": 0.15625, "learning_rate": 3.378828845557779e-05, "loss": 1.5511971712112427, "step": 5028 }, { "epoch": 0.42455388706562686, "grad_norm": 0.1376953125, "learning_rate": 3.37821939103668e-05, "loss": 1.4572819471359253, "step": 5029 }, { "epoch": 0.424638308200458, "grad_norm": 0.1396484375, "learning_rate": 3.377609876970194e-05, "loss": 1.5247310400009155, "step": 5030 }, { "epoch": 0.4247227293352891, "grad_norm": 0.1435546875, "learning_rate": 3.37700030339965e-05, "loss": 1.4612125158309937, "step": 5031 }, { "epoch": 0.4248071504701202, "grad_norm": 0.1396484375, "learning_rate": 3.3763906703663765e-05, "loss": 1.55146062374115, "step": 5032 }, { "epoch": 0.4248915716049513, "grad_norm": 0.130859375, "learning_rate": 3.37578097791171e-05, "loss": 1.5060843229293823, "step": 5033 }, { "epoch": 0.4249759927397824, "grad_norm": 0.142578125, "learning_rate": 3.375171226076988e-05, "loss": 1.5205013751983643, "step": 5034 }, { "epoch": 0.4250604138746135, "grad_norm": 0.1376953125, "learning_rate": 3.374561414903552e-05, "loss": 1.474226474761963, "step": 5035 }, { "epoch": 0.4251448350094446, "grad_norm": 0.1455078125, "learning_rate": 3.373951544432751e-05, "loss": 1.5164012908935547, "step": 5036 }, { "epoch": 0.4252292561442757, "grad_norm": 0.1357421875, "learning_rate": 3.373341614705934e-05, "loss": 1.5308138132095337, "step": 5037 }, { "epoch": 0.42531367727910685, "grad_norm": 0.140625, "learning_rate": 3.372731625764456e-05, "loss": 1.56615149974823, "step": 5038 }, { "epoch": 0.42539809841393794, "grad_norm": 0.138671875, "learning_rate": 3.372121577649677e-05, "loss": 1.5478023290634155, "step": 5039 }, { "epoch": 0.42548251954876903, "grad_norm": 0.1376953125, "learning_rate": 3.3715114704029584e-05, "loss": 1.5249497890472412, "step": 5040 }, { "epoch": 0.4255669406836001, "grad_norm": 0.14453125, "learning_rate": 3.370901304065667e-05, "loss": 1.5075610876083374, "step": 5041 }, { "epoch": 0.4256513618184312, "grad_norm": 0.1435546875, "learning_rate": 3.370291078679173e-05, "loss": 1.5644844770431519, "step": 5042 }, { "epoch": 0.42573578295326236, "grad_norm": 0.1337890625, "learning_rate": 3.369680794284854e-05, "loss": 1.4897878170013428, "step": 5043 }, { "epoch": 0.42582020408809346, "grad_norm": 0.1337890625, "learning_rate": 3.369070450924085e-05, "loss": 1.4994189739227295, "step": 5044 }, { "epoch": 0.42590462522292455, "grad_norm": 0.134765625, "learning_rate": 3.368460048638251e-05, "loss": 1.5954028367996216, "step": 5045 }, { "epoch": 0.42598904635775564, "grad_norm": 0.134765625, "learning_rate": 3.3678495874687386e-05, "loss": 1.491758108139038, "step": 5046 }, { "epoch": 0.4260734674925868, "grad_norm": 0.1572265625, "learning_rate": 3.367239067456938e-05, "loss": 1.5497909784317017, "step": 5047 }, { "epoch": 0.4261578886274179, "grad_norm": 0.1328125, "learning_rate": 3.366628488644244e-05, "loss": 1.5520331859588623, "step": 5048 }, { "epoch": 0.42624230976224897, "grad_norm": 0.1416015625, "learning_rate": 3.366017851072055e-05, "loss": 1.6502225399017334, "step": 5049 }, { "epoch": 0.42632673089708006, "grad_norm": 0.1337890625, "learning_rate": 3.3654071547817746e-05, "loss": 1.5224822759628296, "step": 5050 }, { "epoch": 0.4264111520319112, "grad_norm": 0.1396484375, "learning_rate": 3.364796399814808e-05, "loss": 1.5443812608718872, "step": 5051 }, { "epoch": 0.4264955731667423, "grad_norm": 0.14453125, "learning_rate": 3.364185586212568e-05, "loss": 1.506036639213562, "step": 5052 }, { "epoch": 0.4265799943015734, "grad_norm": 0.1416015625, "learning_rate": 3.363574714016468e-05, "loss": 1.5484983921051025, "step": 5053 }, { "epoch": 0.4266644154364045, "grad_norm": 0.140625, "learning_rate": 3.362963783267925e-05, "loss": 1.556201457977295, "step": 5054 }, { "epoch": 0.42674883657123563, "grad_norm": 0.1435546875, "learning_rate": 3.3623527940083645e-05, "loss": 1.53243887424469, "step": 5055 }, { "epoch": 0.4268332577060667, "grad_norm": 0.142578125, "learning_rate": 3.361741746279212e-05, "loss": 1.5245943069458008, "step": 5056 }, { "epoch": 0.4269176788408978, "grad_norm": 0.146484375, "learning_rate": 3.361130640121897e-05, "loss": 1.5458564758300781, "step": 5057 }, { "epoch": 0.4270020999757289, "grad_norm": 0.150390625, "learning_rate": 3.360519475577855e-05, "loss": 1.5391016006469727, "step": 5058 }, { "epoch": 0.42708652111056, "grad_norm": 0.14453125, "learning_rate": 3.3599082526885236e-05, "loss": 1.5842132568359375, "step": 5059 }, { "epoch": 0.42717094224539115, "grad_norm": 0.14453125, "learning_rate": 3.3592969714953464e-05, "loss": 1.5797560214996338, "step": 5060 }, { "epoch": 0.42725536338022224, "grad_norm": 0.150390625, "learning_rate": 3.3586856320397695e-05, "loss": 1.634702205657959, "step": 5061 }, { "epoch": 0.42733978451505333, "grad_norm": 0.138671875, "learning_rate": 3.3580742343632414e-05, "loss": 1.5412938594818115, "step": 5062 }, { "epoch": 0.4274242056498844, "grad_norm": 0.1376953125, "learning_rate": 3.3574627785072185e-05, "loss": 1.6087315082550049, "step": 5063 }, { "epoch": 0.4275086267847156, "grad_norm": 0.1337890625, "learning_rate": 3.356851264513158e-05, "loss": 1.5582020282745361, "step": 5064 }, { "epoch": 0.42759304791954666, "grad_norm": 0.146484375, "learning_rate": 3.3562396924225226e-05, "loss": 1.5536662340164185, "step": 5065 }, { "epoch": 0.42767746905437776, "grad_norm": 0.15234375, "learning_rate": 3.3556280622767776e-05, "loss": 1.5712833404541016, "step": 5066 }, { "epoch": 0.42776189018920885, "grad_norm": 0.138671875, "learning_rate": 3.355016374117393e-05, "loss": 1.528471827507019, "step": 5067 }, { "epoch": 0.42784631132404, "grad_norm": 0.140625, "learning_rate": 3.3544046279858434e-05, "loss": 1.6065409183502197, "step": 5068 }, { "epoch": 0.4279307324588711, "grad_norm": 0.142578125, "learning_rate": 3.3537928239236066e-05, "loss": 1.547894835472107, "step": 5069 }, { "epoch": 0.4280151535937022, "grad_norm": 0.140625, "learning_rate": 3.3531809619721635e-05, "loss": 1.4821597337722778, "step": 5070 }, { "epoch": 0.42809957472853327, "grad_norm": 0.140625, "learning_rate": 3.352569042173e-05, "loss": 1.501200556755066, "step": 5071 }, { "epoch": 0.4281839958633644, "grad_norm": 0.142578125, "learning_rate": 3.351957064567607e-05, "loss": 1.546960711479187, "step": 5072 }, { "epoch": 0.4282684169981955, "grad_norm": 0.1513671875, "learning_rate": 3.351345029197477e-05, "loss": 1.5831294059753418, "step": 5073 }, { "epoch": 0.4283528381330266, "grad_norm": 0.1552734375, "learning_rate": 3.350732936104108e-05, "loss": 1.5145295858383179, "step": 5074 }, { "epoch": 0.4284372592678577, "grad_norm": 0.1484375, "learning_rate": 3.350120785329001e-05, "loss": 1.5492603778839111, "step": 5075 }, { "epoch": 0.4285216804026888, "grad_norm": 0.1494140625, "learning_rate": 3.34950857691366e-05, "loss": 1.5931828022003174, "step": 5076 }, { "epoch": 0.42860610153751993, "grad_norm": 0.1572265625, "learning_rate": 3.348896310899597e-05, "loss": 1.5599844455718994, "step": 5077 }, { "epoch": 0.428690522672351, "grad_norm": 0.1396484375, "learning_rate": 3.348283987328323e-05, "loss": 1.437515377998352, "step": 5078 }, { "epoch": 0.4287749438071821, "grad_norm": 0.1484375, "learning_rate": 3.347671606241356e-05, "loss": 1.568233847618103, "step": 5079 }, { "epoch": 0.4288593649420132, "grad_norm": 0.134765625, "learning_rate": 3.347059167680216e-05, "loss": 1.5705533027648926, "step": 5080 }, { "epoch": 0.42894378607684436, "grad_norm": 0.1435546875, "learning_rate": 3.346446671686429e-05, "loss": 1.5184521675109863, "step": 5081 }, { "epoch": 0.42902820721167545, "grad_norm": 0.130859375, "learning_rate": 3.345834118301523e-05, "loss": 1.5179259777069092, "step": 5082 }, { "epoch": 0.42911262834650654, "grad_norm": 0.142578125, "learning_rate": 3.3452215075670304e-05, "loss": 1.5869050025939941, "step": 5083 }, { "epoch": 0.42919704948133763, "grad_norm": 0.146484375, "learning_rate": 3.344608839524488e-05, "loss": 1.6076788902282715, "step": 5084 }, { "epoch": 0.4292814706161688, "grad_norm": 0.1611328125, "learning_rate": 3.343996114215436e-05, "loss": 1.6060305833816528, "step": 5085 }, { "epoch": 0.4293658917509999, "grad_norm": 0.138671875, "learning_rate": 3.343383331681419e-05, "loss": 1.5492026805877686, "step": 5086 }, { "epoch": 0.42945031288583096, "grad_norm": 0.1826171875, "learning_rate": 3.342770491963985e-05, "loss": 1.4810041189193726, "step": 5087 }, { "epoch": 0.42953473402066206, "grad_norm": 0.1318359375, "learning_rate": 3.3421575951046855e-05, "loss": 1.5234330892562866, "step": 5088 }, { "epoch": 0.4296191551554932, "grad_norm": 0.13671875, "learning_rate": 3.3415446411450765e-05, "loss": 1.4819673299789429, "step": 5089 }, { "epoch": 0.4297035762903243, "grad_norm": 0.14453125, "learning_rate": 3.340931630126718e-05, "loss": 1.5410497188568115, "step": 5090 }, { "epoch": 0.4297879974251554, "grad_norm": 0.1552734375, "learning_rate": 3.340318562091175e-05, "loss": 1.5441854000091553, "step": 5091 }, { "epoch": 0.4298724185599865, "grad_norm": 0.138671875, "learning_rate": 3.3397054370800125e-05, "loss": 1.51870596408844, "step": 5092 }, { "epoch": 0.42995683969481757, "grad_norm": 0.15625, "learning_rate": 3.3390922551348036e-05, "loss": 1.600662112236023, "step": 5093 }, { "epoch": 0.4300412608296487, "grad_norm": 0.162109375, "learning_rate": 3.338479016297122e-05, "loss": 1.6240588426589966, "step": 5094 }, { "epoch": 0.4301256819644798, "grad_norm": 0.140625, "learning_rate": 3.337865720608548e-05, "loss": 1.5663715600967407, "step": 5095 }, { "epoch": 0.4302101030993109, "grad_norm": 0.1416015625, "learning_rate": 3.337252368110665e-05, "loss": 1.5410988330841064, "step": 5096 }, { "epoch": 0.430294524234142, "grad_norm": 0.1396484375, "learning_rate": 3.3366389588450576e-05, "loss": 1.5105299949645996, "step": 5097 }, { "epoch": 0.43037894536897314, "grad_norm": 0.1435546875, "learning_rate": 3.3360254928533184e-05, "loss": 1.455936074256897, "step": 5098 }, { "epoch": 0.43046336650380423, "grad_norm": 0.1396484375, "learning_rate": 3.3354119701770414e-05, "loss": 1.4702061414718628, "step": 5099 }, { "epoch": 0.4305477876386353, "grad_norm": 0.14453125, "learning_rate": 3.334798390857825e-05, "loss": 1.599697470664978, "step": 5100 }, { "epoch": 0.4306322087734664, "grad_norm": 0.146484375, "learning_rate": 3.334184754937271e-05, "loss": 1.5874297618865967, "step": 5101 }, { "epoch": 0.43071662990829757, "grad_norm": 0.1455078125, "learning_rate": 3.333571062456985e-05, "loss": 1.5729013681411743, "step": 5102 }, { "epoch": 0.43080105104312866, "grad_norm": 0.15625, "learning_rate": 3.3329573134585776e-05, "loss": 1.616184115409851, "step": 5103 }, { "epoch": 0.43088547217795975, "grad_norm": 0.1337890625, "learning_rate": 3.332343507983662e-05, "loss": 1.5153043270111084, "step": 5104 }, { "epoch": 0.43096989331279084, "grad_norm": 0.1396484375, "learning_rate": 3.331729646073856e-05, "loss": 1.4973493814468384, "step": 5105 }, { "epoch": 0.431054314447622, "grad_norm": 0.16015625, "learning_rate": 3.3311157277707805e-05, "loss": 1.568939208984375, "step": 5106 }, { "epoch": 0.4311387355824531, "grad_norm": 0.1357421875, "learning_rate": 3.330501753116061e-05, "loss": 1.5001344680786133, "step": 5107 }, { "epoch": 0.4312231567172842, "grad_norm": 0.13671875, "learning_rate": 3.329887722151327e-05, "loss": 1.4832533597946167, "step": 5108 }, { "epoch": 0.43130757785211526, "grad_norm": 0.1435546875, "learning_rate": 3.32927363491821e-05, "loss": 1.4564892053604126, "step": 5109 }, { "epoch": 0.43139199898694636, "grad_norm": 0.146484375, "learning_rate": 3.328659491458348e-05, "loss": 1.6332547664642334, "step": 5110 }, { "epoch": 0.4314764201217775, "grad_norm": 0.140625, "learning_rate": 3.32804529181338e-05, "loss": 1.5362203121185303, "step": 5111 }, { "epoch": 0.4315608412566086, "grad_norm": 0.140625, "learning_rate": 3.327431036024951e-05, "loss": 1.4982000589370728, "step": 5112 }, { "epoch": 0.4316452623914397, "grad_norm": 0.138671875, "learning_rate": 3.326816724134709e-05, "loss": 1.5606889724731445, "step": 5113 }, { "epoch": 0.4317296835262708, "grad_norm": 0.1357421875, "learning_rate": 3.326202356184305e-05, "loss": 1.502031922340393, "step": 5114 }, { "epoch": 0.4318141046611019, "grad_norm": 0.12890625, "learning_rate": 3.325587932215396e-05, "loss": 1.4984652996063232, "step": 5115 }, { "epoch": 0.431898525795933, "grad_norm": 0.1337890625, "learning_rate": 3.324973452269641e-05, "loss": 1.4346849918365479, "step": 5116 }, { "epoch": 0.4319829469307641, "grad_norm": 0.1416015625, "learning_rate": 3.324358916388702e-05, "loss": 1.4797998666763306, "step": 5117 }, { "epoch": 0.4320673680655952, "grad_norm": 0.1328125, "learning_rate": 3.323744324614248e-05, "loss": 1.4555795192718506, "step": 5118 }, { "epoch": 0.43215178920042635, "grad_norm": 0.1494140625, "learning_rate": 3.3231296769879485e-05, "loss": 1.5683218240737915, "step": 5119 }, { "epoch": 0.43223621033525744, "grad_norm": 0.154296875, "learning_rate": 3.322514973551478e-05, "loss": 1.5374317169189453, "step": 5120 }, { "epoch": 0.43232063147008853, "grad_norm": 0.134765625, "learning_rate": 3.321900214346515e-05, "loss": 1.509763240814209, "step": 5121 }, { "epoch": 0.4324050526049196, "grad_norm": 0.13671875, "learning_rate": 3.321285399414743e-05, "loss": 1.5083166360855103, "step": 5122 }, { "epoch": 0.4324894737397508, "grad_norm": 0.14453125, "learning_rate": 3.320670528797846e-05, "loss": 1.5830761194229126, "step": 5123 }, { "epoch": 0.43257389487458187, "grad_norm": 0.134765625, "learning_rate": 3.3200556025375144e-05, "loss": 1.5593260526657104, "step": 5124 }, { "epoch": 0.43265831600941296, "grad_norm": 0.1455078125, "learning_rate": 3.319440620675442e-05, "loss": 1.520521640777588, "step": 5125 }, { "epoch": 0.43274273714424405, "grad_norm": 0.140625, "learning_rate": 3.318825583253325e-05, "loss": 1.5744799375534058, "step": 5126 }, { "epoch": 0.43282715827907514, "grad_norm": 0.1474609375, "learning_rate": 3.318210490312867e-05, "loss": 1.4847711324691772, "step": 5127 }, { "epoch": 0.4329115794139063, "grad_norm": 0.1435546875, "learning_rate": 3.317595341895771e-05, "loss": 1.5411914587020874, "step": 5128 }, { "epoch": 0.4329960005487374, "grad_norm": 0.1650390625, "learning_rate": 3.316980138043744e-05, "loss": 1.510990023612976, "step": 5129 }, { "epoch": 0.4330804216835685, "grad_norm": 0.138671875, "learning_rate": 3.3163648787985e-05, "loss": 1.5798612833023071, "step": 5130 }, { "epoch": 0.43316484281839956, "grad_norm": 0.142578125, "learning_rate": 3.315749564201756e-05, "loss": 1.515726923942566, "step": 5131 }, { "epoch": 0.4332492639532307, "grad_norm": 0.1484375, "learning_rate": 3.315134194295231e-05, "loss": 1.5405646562576294, "step": 5132 }, { "epoch": 0.4333336850880618, "grad_norm": 0.1455078125, "learning_rate": 3.314518769120647e-05, "loss": 1.5530331134796143, "step": 5133 }, { "epoch": 0.4334181062228929, "grad_norm": 0.146484375, "learning_rate": 3.313903288719733e-05, "loss": 1.5707834959030151, "step": 5134 }, { "epoch": 0.433502527357724, "grad_norm": 0.142578125, "learning_rate": 3.31328775313422e-05, "loss": 1.549254059791565, "step": 5135 }, { "epoch": 0.43358694849255514, "grad_norm": 0.140625, "learning_rate": 3.312672162405843e-05, "loss": 1.540571689605713, "step": 5136 }, { "epoch": 0.4336713696273862, "grad_norm": 0.1455078125, "learning_rate": 3.312056516576339e-05, "loss": 1.5189454555511475, "step": 5137 }, { "epoch": 0.4337557907622173, "grad_norm": 0.138671875, "learning_rate": 3.311440815687451e-05, "loss": 1.5287522077560425, "step": 5138 }, { "epoch": 0.4338402118970484, "grad_norm": 0.1357421875, "learning_rate": 3.310825059780926e-05, "loss": 1.4739549160003662, "step": 5139 }, { "epoch": 0.43392463303187956, "grad_norm": 0.14453125, "learning_rate": 3.310209248898513e-05, "loss": 1.4842711687088013, "step": 5140 }, { "epoch": 0.43400905416671065, "grad_norm": 0.1337890625, "learning_rate": 3.309593383081965e-05, "loss": 1.4959990978240967, "step": 5141 }, { "epoch": 0.43409347530154174, "grad_norm": 0.1455078125, "learning_rate": 3.30897746237304e-05, "loss": 1.508219838142395, "step": 5142 }, { "epoch": 0.43417789643637283, "grad_norm": 0.134765625, "learning_rate": 3.3083614868134985e-05, "loss": 1.518236756324768, "step": 5143 }, { "epoch": 0.4342623175712039, "grad_norm": 0.1279296875, "learning_rate": 3.307745456445105e-05, "loss": 1.500070333480835, "step": 5144 }, { "epoch": 0.4343467387060351, "grad_norm": 0.158203125, "learning_rate": 3.307129371309627e-05, "loss": 1.5636392831802368, "step": 5145 }, { "epoch": 0.43443115984086617, "grad_norm": 0.140625, "learning_rate": 3.3065132314488396e-05, "loss": 1.476768970489502, "step": 5146 }, { "epoch": 0.43451558097569726, "grad_norm": 0.142578125, "learning_rate": 3.305897036904515e-05, "loss": 1.4675424098968506, "step": 5147 }, { "epoch": 0.43460000211052835, "grad_norm": 0.13671875, "learning_rate": 3.305280787718435e-05, "loss": 1.4658228158950806, "step": 5148 }, { "epoch": 0.4346844232453595, "grad_norm": 0.1376953125, "learning_rate": 3.304664483932381e-05, "loss": 1.5745501518249512, "step": 5149 }, { "epoch": 0.4347688443801906, "grad_norm": 0.1416015625, "learning_rate": 3.3040481255881414e-05, "loss": 1.5415910482406616, "step": 5150 }, { "epoch": 0.4348532655150217, "grad_norm": 0.1455078125, "learning_rate": 3.303431712727507e-05, "loss": 1.580854892730713, "step": 5151 }, { "epoch": 0.4349376866498528, "grad_norm": 0.1376953125, "learning_rate": 3.30281524539227e-05, "loss": 1.5157102346420288, "step": 5152 }, { "epoch": 0.4350221077846839, "grad_norm": 0.138671875, "learning_rate": 3.30219872362423e-05, "loss": 1.5750653743743896, "step": 5153 }, { "epoch": 0.435106528919515, "grad_norm": 0.1357421875, "learning_rate": 3.301582147465189e-05, "loss": 1.5726251602172852, "step": 5154 }, { "epoch": 0.4351909500543461, "grad_norm": 0.14453125, "learning_rate": 3.300965516956951e-05, "loss": 1.541027307510376, "step": 5155 }, { "epoch": 0.4352753711891772, "grad_norm": 0.13671875, "learning_rate": 3.3003488321413256e-05, "loss": 1.5123144388198853, "step": 5156 }, { "epoch": 0.4353597923240083, "grad_norm": 0.1435546875, "learning_rate": 3.2997320930601256e-05, "loss": 1.4729101657867432, "step": 5157 }, { "epoch": 0.43544421345883944, "grad_norm": 0.1396484375, "learning_rate": 3.299115299755168e-05, "loss": 1.647083044052124, "step": 5158 }, { "epoch": 0.4355286345936705, "grad_norm": 0.130859375, "learning_rate": 3.298498452268271e-05, "loss": 1.5677403211593628, "step": 5159 }, { "epoch": 0.4356130557285016, "grad_norm": 0.140625, "learning_rate": 3.297881550641261e-05, "loss": 1.548426866531372, "step": 5160 }, { "epoch": 0.4356974768633327, "grad_norm": 0.1396484375, "learning_rate": 3.297264594915963e-05, "loss": 1.599839687347412, "step": 5161 }, { "epoch": 0.43578189799816386, "grad_norm": 0.130859375, "learning_rate": 3.296647585134209e-05, "loss": 1.516944408416748, "step": 5162 }, { "epoch": 0.43586631913299495, "grad_norm": 0.1455078125, "learning_rate": 3.296030521337836e-05, "loss": 1.4526047706604004, "step": 5163 }, { "epoch": 0.43595074026782604, "grad_norm": 0.146484375, "learning_rate": 3.295413403568678e-05, "loss": 1.532936453819275, "step": 5164 }, { "epoch": 0.43603516140265713, "grad_norm": 0.1376953125, "learning_rate": 3.29479623186858e-05, "loss": 1.509353518486023, "step": 5165 }, { "epoch": 0.4361195825374883, "grad_norm": 0.1337890625, "learning_rate": 3.294179006279386e-05, "loss": 1.5020936727523804, "step": 5166 }, { "epoch": 0.4362040036723194, "grad_norm": 0.14453125, "learning_rate": 3.293561726842948e-05, "loss": 1.564732313156128, "step": 5167 }, { "epoch": 0.43628842480715047, "grad_norm": 0.1474609375, "learning_rate": 3.292944393601117e-05, "loss": 1.5145080089569092, "step": 5168 }, { "epoch": 0.43637284594198156, "grad_norm": 0.14453125, "learning_rate": 3.29232700659575e-05, "loss": 1.5339165925979614, "step": 5169 }, { "epoch": 0.4364572670768127, "grad_norm": 0.134765625, "learning_rate": 3.291709565868708e-05, "loss": 1.5478439331054688, "step": 5170 }, { "epoch": 0.4365416882116438, "grad_norm": 0.140625, "learning_rate": 3.2910920714618535e-05, "loss": 1.4605234861373901, "step": 5171 }, { "epoch": 0.4366261093464749, "grad_norm": 0.14453125, "learning_rate": 3.290474523417055e-05, "loss": 1.5349653959274292, "step": 5172 }, { "epoch": 0.436710530481306, "grad_norm": 0.13671875, "learning_rate": 3.289856921776184e-05, "loss": 1.5322595834732056, "step": 5173 }, { "epoch": 0.4367949516161371, "grad_norm": 0.138671875, "learning_rate": 3.289239266581115e-05, "loss": 1.5176540613174438, "step": 5174 }, { "epoch": 0.4368793727509682, "grad_norm": 0.1376953125, "learning_rate": 3.288621557873727e-05, "loss": 1.567078948020935, "step": 5175 }, { "epoch": 0.4369637938857993, "grad_norm": 0.13671875, "learning_rate": 3.288003795695902e-05, "loss": 1.4671077728271484, "step": 5176 }, { "epoch": 0.4370482150206304, "grad_norm": 0.1611328125, "learning_rate": 3.287385980089526e-05, "loss": 1.5963019132614136, "step": 5177 }, { "epoch": 0.4371326361554615, "grad_norm": 0.1376953125, "learning_rate": 3.2867681110964865e-05, "loss": 1.5088419914245605, "step": 5178 }, { "epoch": 0.43721705729029264, "grad_norm": 0.158203125, "learning_rate": 3.286150188758679e-05, "loss": 1.5503464937210083, "step": 5179 }, { "epoch": 0.43730147842512374, "grad_norm": 0.1494140625, "learning_rate": 3.2855322131179976e-05, "loss": 1.4608983993530273, "step": 5180 }, { "epoch": 0.4373858995599548, "grad_norm": 0.1279296875, "learning_rate": 3.284914184216345e-05, "loss": 1.546025276184082, "step": 5181 }, { "epoch": 0.4374703206947859, "grad_norm": 0.140625, "learning_rate": 3.284296102095625e-05, "loss": 1.5892945528030396, "step": 5182 }, { "epoch": 0.43755474182961707, "grad_norm": 0.1337890625, "learning_rate": 3.2836779667977426e-05, "loss": 1.4799250364303589, "step": 5183 }, { "epoch": 0.43763916296444816, "grad_norm": 0.140625, "learning_rate": 3.283059778364611e-05, "loss": 1.505637526512146, "step": 5184 }, { "epoch": 0.43772358409927925, "grad_norm": 0.138671875, "learning_rate": 3.282441536838144e-05, "loss": 1.507837176322937, "step": 5185 }, { "epoch": 0.43780800523411034, "grad_norm": 0.1455078125, "learning_rate": 3.2818232422602604e-05, "loss": 1.4952332973480225, "step": 5186 }, { "epoch": 0.4378924263689415, "grad_norm": 0.130859375, "learning_rate": 3.2812048946728815e-05, "loss": 1.4924689531326294, "step": 5187 }, { "epoch": 0.4379768475037726, "grad_norm": 0.12890625, "learning_rate": 3.280586494117932e-05, "loss": 1.494805932044983, "step": 5188 }, { "epoch": 0.4380612686386037, "grad_norm": 0.14453125, "learning_rate": 3.279968040637344e-05, "loss": 1.60238516330719, "step": 5189 }, { "epoch": 0.43814568977343477, "grad_norm": 0.1328125, "learning_rate": 3.2793495342730466e-05, "loss": 1.5764907598495483, "step": 5190 }, { "epoch": 0.43823011090826586, "grad_norm": 0.1455078125, "learning_rate": 3.278730975066977e-05, "loss": 1.5366977453231812, "step": 5191 }, { "epoch": 0.438314532043097, "grad_norm": 0.1552734375, "learning_rate": 3.278112363061076e-05, "loss": 1.6057437658309937, "step": 5192 }, { "epoch": 0.4383989531779281, "grad_norm": 0.16015625, "learning_rate": 3.277493698297287e-05, "loss": 1.4327082633972168, "step": 5193 }, { "epoch": 0.4384833743127592, "grad_norm": 0.1513671875, "learning_rate": 3.276874980817556e-05, "loss": 1.5077840089797974, "step": 5194 }, { "epoch": 0.4385677954475903, "grad_norm": 0.1533203125, "learning_rate": 3.276256210663834e-05, "loss": 1.6240631341934204, "step": 5195 }, { "epoch": 0.43865221658242143, "grad_norm": 0.134765625, "learning_rate": 3.275637387878075e-05, "loss": 1.5634361505508423, "step": 5196 }, { "epoch": 0.4387366377172525, "grad_norm": 0.12890625, "learning_rate": 3.2750185125022364e-05, "loss": 1.5018043518066406, "step": 5197 }, { "epoch": 0.4388210588520836, "grad_norm": 0.140625, "learning_rate": 3.27439958457828e-05, "loss": 1.5920547246932983, "step": 5198 }, { "epoch": 0.4389054799869147, "grad_norm": 0.158203125, "learning_rate": 3.273780604148171e-05, "loss": 1.5112695693969727, "step": 5199 }, { "epoch": 0.43898990112174585, "grad_norm": 0.138671875, "learning_rate": 3.273161571253876e-05, "loss": 1.5390461683273315, "step": 5200 }, { "epoch": 0.43907432225657694, "grad_norm": 0.1494140625, "learning_rate": 3.272542485937369e-05, "loss": 1.5768005847930908, "step": 5201 }, { "epoch": 0.43915874339140804, "grad_norm": 0.1279296875, "learning_rate": 3.2719233482406236e-05, "loss": 1.5155057907104492, "step": 5202 }, { "epoch": 0.4392431645262391, "grad_norm": 0.1474609375, "learning_rate": 3.27130415820562e-05, "loss": 1.5058259963989258, "step": 5203 }, { "epoch": 0.4393275856610703, "grad_norm": 0.1435546875, "learning_rate": 3.270684915874341e-05, "loss": 1.5191646814346313, "step": 5204 }, { "epoch": 0.43941200679590137, "grad_norm": 0.1318359375, "learning_rate": 3.270065621288773e-05, "loss": 1.5007340908050537, "step": 5205 }, { "epoch": 0.43949642793073246, "grad_norm": 0.1328125, "learning_rate": 3.269446274490903e-05, "loss": 1.507716178894043, "step": 5206 }, { "epoch": 0.43958084906556355, "grad_norm": 0.1376953125, "learning_rate": 3.268826875522727e-05, "loss": 1.56138277053833, "step": 5207 }, { "epoch": 0.43966527020039464, "grad_norm": 0.1357421875, "learning_rate": 3.268207424426241e-05, "loss": 1.5305767059326172, "step": 5208 }, { "epoch": 0.4397496913352258, "grad_norm": 0.1533203125, "learning_rate": 3.2675879212434446e-05, "loss": 1.617167592048645, "step": 5209 }, { "epoch": 0.4398341124700569, "grad_norm": 0.1357421875, "learning_rate": 3.266968366016342e-05, "loss": 1.528671383857727, "step": 5210 }, { "epoch": 0.439918533604888, "grad_norm": 0.1416015625, "learning_rate": 3.2663487587869415e-05, "loss": 1.5259455442428589, "step": 5211 }, { "epoch": 0.44000295473971907, "grad_norm": 0.140625, "learning_rate": 3.265729099597252e-05, "loss": 1.5238573551177979, "step": 5212 }, { "epoch": 0.4400873758745502, "grad_norm": 0.150390625, "learning_rate": 3.2651093884892905e-05, "loss": 1.5456361770629883, "step": 5213 }, { "epoch": 0.4401717970093813, "grad_norm": 0.158203125, "learning_rate": 3.264489625505072e-05, "loss": 1.5187466144561768, "step": 5214 }, { "epoch": 0.4402562181442124, "grad_norm": 0.1494140625, "learning_rate": 3.263869810686619e-05, "loss": 1.5685361623764038, "step": 5215 }, { "epoch": 0.4403406392790435, "grad_norm": 0.146484375, "learning_rate": 3.263249944075958e-05, "loss": 1.5624446868896484, "step": 5216 }, { "epoch": 0.44042506041387464, "grad_norm": 0.142578125, "learning_rate": 3.2626300257151156e-05, "loss": 1.6039259433746338, "step": 5217 }, { "epoch": 0.44050948154870573, "grad_norm": 0.138671875, "learning_rate": 3.2620100556461245e-05, "loss": 1.4270814657211304, "step": 5218 }, { "epoch": 0.4405939026835368, "grad_norm": 0.1435546875, "learning_rate": 3.261390033911019e-05, "loss": 1.4680125713348389, "step": 5219 }, { "epoch": 0.4406783238183679, "grad_norm": 0.162109375, "learning_rate": 3.26076996055184e-05, "loss": 1.6254833936691284, "step": 5220 }, { "epoch": 0.44076274495319906, "grad_norm": 0.142578125, "learning_rate": 3.2601498356106296e-05, "loss": 1.5100687742233276, "step": 5221 }, { "epoch": 0.44084716608803015, "grad_norm": 0.177734375, "learning_rate": 3.259529659129432e-05, "loss": 1.6237717866897583, "step": 5222 }, { "epoch": 0.44093158722286124, "grad_norm": 0.1474609375, "learning_rate": 3.2589094311502986e-05, "loss": 1.5080201625823975, "step": 5223 }, { "epoch": 0.44101600835769234, "grad_norm": 0.146484375, "learning_rate": 3.258289151715281e-05, "loss": 1.5273499488830566, "step": 5224 }, { "epoch": 0.4411004294925234, "grad_norm": 0.1474609375, "learning_rate": 3.2576688208664374e-05, "loss": 1.5740643739700317, "step": 5225 }, { "epoch": 0.4411848506273546, "grad_norm": 0.1376953125, "learning_rate": 3.257048438645825e-05, "loss": 1.580828070640564, "step": 5226 }, { "epoch": 0.44126927176218567, "grad_norm": 0.1337890625, "learning_rate": 3.25642800509551e-05, "loss": 1.4793469905853271, "step": 5227 }, { "epoch": 0.44135369289701676, "grad_norm": 0.1357421875, "learning_rate": 3.255807520257558e-05, "loss": 1.5811939239501953, "step": 5228 }, { "epoch": 0.44143811403184785, "grad_norm": 0.154296875, "learning_rate": 3.2551869841740385e-05, "loss": 1.5305707454681396, "step": 5229 }, { "epoch": 0.441522535166679, "grad_norm": 0.142578125, "learning_rate": 3.254566396887027e-05, "loss": 1.530199408531189, "step": 5230 }, { "epoch": 0.4416069563015101, "grad_norm": 0.3203125, "learning_rate": 3.2539457584386e-05, "loss": 1.5483818054199219, "step": 5231 }, { "epoch": 0.4416913774363412, "grad_norm": 0.14453125, "learning_rate": 3.253325068870837e-05, "loss": 1.5017815828323364, "step": 5232 }, { "epoch": 0.4417757985711723, "grad_norm": 0.140625, "learning_rate": 3.252704328225825e-05, "loss": 1.588253378868103, "step": 5233 }, { "epoch": 0.4418602197060034, "grad_norm": 0.1611328125, "learning_rate": 3.2520835365456496e-05, "loss": 1.5452067852020264, "step": 5234 }, { "epoch": 0.4419446408408345, "grad_norm": 0.13671875, "learning_rate": 3.251462693872403e-05, "loss": 1.5679435729980469, "step": 5235 }, { "epoch": 0.4420290619756656, "grad_norm": 0.1455078125, "learning_rate": 3.25084180024818e-05, "loss": 1.5231226682662964, "step": 5236 }, { "epoch": 0.4421134831104967, "grad_norm": 0.140625, "learning_rate": 3.250220855715078e-05, "loss": 1.4765872955322266, "step": 5237 }, { "epoch": 0.44219790424532784, "grad_norm": 0.134765625, "learning_rate": 3.249599860315198e-05, "loss": 1.4900939464569092, "step": 5238 }, { "epoch": 0.44228232538015894, "grad_norm": 0.1376953125, "learning_rate": 3.248978814090646e-05, "loss": 1.4483462572097778, "step": 5239 }, { "epoch": 0.44236674651499003, "grad_norm": 0.146484375, "learning_rate": 3.24835771708353e-05, "loss": 1.537867546081543, "step": 5240 }, { "epoch": 0.4424511676498211, "grad_norm": 0.140625, "learning_rate": 3.247736569335962e-05, "loss": 1.5050418376922607, "step": 5241 }, { "epoch": 0.4425355887846522, "grad_norm": 0.140625, "learning_rate": 3.247115370890057e-05, "loss": 1.5708680152893066, "step": 5242 }, { "epoch": 0.44262000991948336, "grad_norm": 0.140625, "learning_rate": 3.2464941217879344e-05, "loss": 1.4974223375320435, "step": 5243 }, { "epoch": 0.44270443105431445, "grad_norm": 0.13671875, "learning_rate": 3.245872822071716e-05, "loss": 1.5592172145843506, "step": 5244 }, { "epoch": 0.44278885218914554, "grad_norm": 0.1357421875, "learning_rate": 3.245251471783528e-05, "loss": 1.5512030124664307, "step": 5245 }, { "epoch": 0.44287327332397664, "grad_norm": 0.1416015625, "learning_rate": 3.244630070965497e-05, "loss": 1.509232759475708, "step": 5246 }, { "epoch": 0.4429576944588078, "grad_norm": 0.140625, "learning_rate": 3.24400861965976e-05, "loss": 1.5029406547546387, "step": 5247 }, { "epoch": 0.4430421155936389, "grad_norm": 0.150390625, "learning_rate": 3.243387117908448e-05, "loss": 1.5302512645721436, "step": 5248 }, { "epoch": 0.44312653672846997, "grad_norm": 0.1669921875, "learning_rate": 3.242765565753703e-05, "loss": 1.537744164466858, "step": 5249 }, { "epoch": 0.44321095786330106, "grad_norm": 0.1435546875, "learning_rate": 3.242143963237668e-05, "loss": 1.555265188217163, "step": 5250 }, { "epoch": 0.4432953789981322, "grad_norm": 0.146484375, "learning_rate": 3.241522310402488e-05, "loss": 1.5198415517807007, "step": 5251 }, { "epoch": 0.4433798001329633, "grad_norm": 0.142578125, "learning_rate": 3.2409006072903134e-05, "loss": 1.5644137859344482, "step": 5252 }, { "epoch": 0.4434642212677944, "grad_norm": 0.14453125, "learning_rate": 3.240278853943296e-05, "loss": 1.5480921268463135, "step": 5253 }, { "epoch": 0.4435486424026255, "grad_norm": 0.1494140625, "learning_rate": 3.239657050403593e-05, "loss": 1.5339694023132324, "step": 5254 }, { "epoch": 0.44363306353745663, "grad_norm": 0.1396484375, "learning_rate": 3.239035196713364e-05, "loss": 1.4464746713638306, "step": 5255 }, { "epoch": 0.4437174846722877, "grad_norm": 0.1455078125, "learning_rate": 3.238413292914773e-05, "loss": 1.4940557479858398, "step": 5256 }, { "epoch": 0.4438019058071188, "grad_norm": 0.142578125, "learning_rate": 3.237791339049985e-05, "loss": 1.5079118013381958, "step": 5257 }, { "epoch": 0.4438863269419499, "grad_norm": 0.1328125, "learning_rate": 3.237169335161171e-05, "loss": 1.5683833360671997, "step": 5258 }, { "epoch": 0.443970748076781, "grad_norm": 0.1494140625, "learning_rate": 3.236547281290505e-05, "loss": 1.5177462100982666, "step": 5259 }, { "epoch": 0.44405516921161214, "grad_norm": 0.138671875, "learning_rate": 3.2359251774801616e-05, "loss": 1.5469907522201538, "step": 5260 }, { "epoch": 0.44413959034644324, "grad_norm": 0.1435546875, "learning_rate": 3.2353030237723234e-05, "loss": 1.5456163883209229, "step": 5261 }, { "epoch": 0.44422401148127433, "grad_norm": 0.1513671875, "learning_rate": 3.234680820209172e-05, "loss": 1.5358951091766357, "step": 5262 }, { "epoch": 0.4443084326161054, "grad_norm": 0.15234375, "learning_rate": 3.234058566832896e-05, "loss": 1.567406177520752, "step": 5263 }, { "epoch": 0.44439285375093657, "grad_norm": 0.140625, "learning_rate": 3.2334362636856835e-05, "loss": 1.5408577919006348, "step": 5264 }, { "epoch": 0.44447727488576766, "grad_norm": 0.13671875, "learning_rate": 3.23281391080973e-05, "loss": 1.5359935760498047, "step": 5265 }, { "epoch": 0.44456169602059875, "grad_norm": 0.140625, "learning_rate": 3.232191508247232e-05, "loss": 1.462920904159546, "step": 5266 }, { "epoch": 0.44464611715542984, "grad_norm": 0.154296875, "learning_rate": 3.2315690560403895e-05, "loss": 1.5467162132263184, "step": 5267 }, { "epoch": 0.444730538290261, "grad_norm": 0.140625, "learning_rate": 3.230946554231407e-05, "loss": 1.5537240505218506, "step": 5268 }, { "epoch": 0.4448149594250921, "grad_norm": 0.1337890625, "learning_rate": 3.23032400286249e-05, "loss": 1.4741889238357544, "step": 5269 }, { "epoch": 0.4448993805599232, "grad_norm": 0.13671875, "learning_rate": 3.229701401975851e-05, "loss": 1.5583751201629639, "step": 5270 }, { "epoch": 0.44498380169475427, "grad_norm": 0.1435546875, "learning_rate": 3.2290787516137036e-05, "loss": 1.5579228401184082, "step": 5271 }, { "epoch": 0.4450682228295854, "grad_norm": 0.1455078125, "learning_rate": 3.228456051818263e-05, "loss": 1.6056116819381714, "step": 5272 }, { "epoch": 0.4451526439644165, "grad_norm": 0.1435546875, "learning_rate": 3.227833302631752e-05, "loss": 1.584118127822876, "step": 5273 }, { "epoch": 0.4452370650992476, "grad_norm": 0.146484375, "learning_rate": 3.227210504096393e-05, "loss": 1.510775089263916, "step": 5274 }, { "epoch": 0.4453214862340787, "grad_norm": 0.1494140625, "learning_rate": 3.226587656254414e-05, "loss": 1.5731555223464966, "step": 5275 }, { "epoch": 0.4454059073689098, "grad_norm": 0.14453125, "learning_rate": 3.225964759148046e-05, "loss": 1.5305365324020386, "step": 5276 }, { "epoch": 0.44549032850374093, "grad_norm": 0.1455078125, "learning_rate": 3.225341812819521e-05, "loss": 1.5063846111297607, "step": 5277 }, { "epoch": 0.445574749638572, "grad_norm": 0.1474609375, "learning_rate": 3.224718817311079e-05, "loss": 1.5195536613464355, "step": 5278 }, { "epoch": 0.4456591707734031, "grad_norm": 0.1357421875, "learning_rate": 3.224095772664959e-05, "loss": 1.4971591234207153, "step": 5279 }, { "epoch": 0.4457435919082342, "grad_norm": 0.1474609375, "learning_rate": 3.223472678923405e-05, "loss": 1.5449191331863403, "step": 5280 }, { "epoch": 0.44582801304306535, "grad_norm": 0.15625, "learning_rate": 3.222849536128664e-05, "loss": 1.4859808683395386, "step": 5281 }, { "epoch": 0.44591243417789644, "grad_norm": 0.1357421875, "learning_rate": 3.222226344322987e-05, "loss": 1.4907724857330322, "step": 5282 }, { "epoch": 0.44599685531272754, "grad_norm": 0.14453125, "learning_rate": 3.2216031035486285e-05, "loss": 1.4844223260879517, "step": 5283 }, { "epoch": 0.44608127644755863, "grad_norm": 0.1357421875, "learning_rate": 3.220979813847844e-05, "loss": 1.4743863344192505, "step": 5284 }, { "epoch": 0.4461656975823898, "grad_norm": 0.138671875, "learning_rate": 3.2203564752628956e-05, "loss": 1.5400784015655518, "step": 5285 }, { "epoch": 0.44625011871722087, "grad_norm": 0.140625, "learning_rate": 3.2197330878360474e-05, "loss": 1.499741792678833, "step": 5286 }, { "epoch": 0.44633453985205196, "grad_norm": 0.1455078125, "learning_rate": 3.219109651609565e-05, "loss": 1.5936105251312256, "step": 5287 }, { "epoch": 0.44641896098688305, "grad_norm": 0.134765625, "learning_rate": 3.21848616662572e-05, "loss": 1.4980711936950684, "step": 5288 }, { "epoch": 0.4465033821217142, "grad_norm": 0.1328125, "learning_rate": 3.217862632926786e-05, "loss": 1.522807002067566, "step": 5289 }, { "epoch": 0.4465878032565453, "grad_norm": 0.1416015625, "learning_rate": 3.217239050555039e-05, "loss": 1.5942567586898804, "step": 5290 }, { "epoch": 0.4466722243913764, "grad_norm": 0.138671875, "learning_rate": 3.216615419552761e-05, "loss": 1.5877704620361328, "step": 5291 }, { "epoch": 0.4467566455262075, "grad_norm": 0.13671875, "learning_rate": 3.2159917399622355e-05, "loss": 1.551400065422058, "step": 5292 }, { "epoch": 0.44684106666103857, "grad_norm": 0.1435546875, "learning_rate": 3.215368011825749e-05, "loss": 1.5662355422973633, "step": 5293 }, { "epoch": 0.4469254877958697, "grad_norm": 0.134765625, "learning_rate": 3.214744235185592e-05, "loss": 1.5299551486968994, "step": 5294 }, { "epoch": 0.4470099089307008, "grad_norm": 0.138671875, "learning_rate": 3.214120410084057e-05, "loss": 1.502848505973816, "step": 5295 }, { "epoch": 0.4470943300655319, "grad_norm": 0.1484375, "learning_rate": 3.213496536563442e-05, "loss": 1.5401239395141602, "step": 5296 }, { "epoch": 0.447178751200363, "grad_norm": 0.14453125, "learning_rate": 3.212872614666046e-05, "loss": 1.501165747642517, "step": 5297 }, { "epoch": 0.44726317233519414, "grad_norm": 0.1416015625, "learning_rate": 3.2122486444341745e-05, "loss": 1.5122023820877075, "step": 5298 }, { "epoch": 0.44734759347002523, "grad_norm": 0.146484375, "learning_rate": 3.2116246259101316e-05, "loss": 1.4669559001922607, "step": 5299 }, { "epoch": 0.4474320146048563, "grad_norm": 0.138671875, "learning_rate": 3.21100055913623e-05, "loss": 1.6100071668624878, "step": 5300 }, { "epoch": 0.4475164357396874, "grad_norm": 0.146484375, "learning_rate": 3.21037644415478e-05, "loss": 1.5855112075805664, "step": 5301 }, { "epoch": 0.44760085687451856, "grad_norm": 0.138671875, "learning_rate": 3.2097522810081015e-05, "loss": 1.4331960678100586, "step": 5302 }, { "epoch": 0.44768527800934965, "grad_norm": 0.140625, "learning_rate": 3.209128069738511e-05, "loss": 1.5291616916656494, "step": 5303 }, { "epoch": 0.44776969914418074, "grad_norm": 0.1318359375, "learning_rate": 3.208503810388333e-05, "loss": 1.5140299797058105, "step": 5304 }, { "epoch": 0.44785412027901184, "grad_norm": 0.146484375, "learning_rate": 3.2078795029998934e-05, "loss": 1.5680783987045288, "step": 5305 }, { "epoch": 0.447938541413843, "grad_norm": 0.1455078125, "learning_rate": 3.207255147615522e-05, "loss": 1.5339324474334717, "step": 5306 }, { "epoch": 0.4480229625486741, "grad_norm": 0.140625, "learning_rate": 3.2066307442775523e-05, "loss": 1.5171438455581665, "step": 5307 }, { "epoch": 0.44810738368350517, "grad_norm": 0.1337890625, "learning_rate": 3.2060062930283185e-05, "loss": 1.5084459781646729, "step": 5308 }, { "epoch": 0.44819180481833626, "grad_norm": 0.1826171875, "learning_rate": 3.205381793910162e-05, "loss": 1.6174328327178955, "step": 5309 }, { "epoch": 0.44827622595316735, "grad_norm": 0.1474609375, "learning_rate": 3.204757246965424e-05, "loss": 1.4915156364440918, "step": 5310 }, { "epoch": 0.4483606470879985, "grad_norm": 0.1328125, "learning_rate": 3.2041326522364506e-05, "loss": 1.5455762147903442, "step": 5311 }, { "epoch": 0.4484450682228296, "grad_norm": 0.1494140625, "learning_rate": 3.203508009765591e-05, "loss": 1.54066801071167, "step": 5312 }, { "epoch": 0.4485294893576607, "grad_norm": 0.1533203125, "learning_rate": 3.202883319595197e-05, "loss": 1.5240532159805298, "step": 5313 }, { "epoch": 0.4486139104924918, "grad_norm": 0.1376953125, "learning_rate": 3.2022585817676255e-05, "loss": 1.4890269041061401, "step": 5314 }, { "epoch": 0.4486983316273229, "grad_norm": 0.138671875, "learning_rate": 3.201633796325233e-05, "loss": 1.4489250183105469, "step": 5315 }, { "epoch": 0.448782752762154, "grad_norm": 0.15234375, "learning_rate": 3.201008963310383e-05, "loss": 1.5669875144958496, "step": 5316 }, { "epoch": 0.4488671738969851, "grad_norm": 0.138671875, "learning_rate": 3.2003840827654395e-05, "loss": 1.5404877662658691, "step": 5317 }, { "epoch": 0.4489515950318162, "grad_norm": 0.13671875, "learning_rate": 3.199759154732773e-05, "loss": 1.5243425369262695, "step": 5318 }, { "epoch": 0.44903601616664734, "grad_norm": 0.15625, "learning_rate": 3.199134179254754e-05, "loss": 1.5391509532928467, "step": 5319 }, { "epoch": 0.44912043730147844, "grad_norm": 0.146484375, "learning_rate": 3.1985091563737555e-05, "loss": 1.5506455898284912, "step": 5320 }, { "epoch": 0.44920485843630953, "grad_norm": 0.1357421875, "learning_rate": 3.197884086132158e-05, "loss": 1.556589126586914, "step": 5321 }, { "epoch": 0.4492892795711406, "grad_norm": 0.1396484375, "learning_rate": 3.197258968572342e-05, "loss": 1.600069522857666, "step": 5322 }, { "epoch": 0.4493737007059717, "grad_norm": 0.1318359375, "learning_rate": 3.1966338037366916e-05, "loss": 1.4857633113861084, "step": 5323 }, { "epoch": 0.44945812184080286, "grad_norm": 0.1357421875, "learning_rate": 3.196008591667596e-05, "loss": 1.5615718364715576, "step": 5324 }, { "epoch": 0.44954254297563395, "grad_norm": 0.1455078125, "learning_rate": 3.195383332407444e-05, "loss": 1.5067566633224487, "step": 5325 }, { "epoch": 0.44962696411046504, "grad_norm": 0.1513671875, "learning_rate": 3.1947580259986305e-05, "loss": 1.486728549003601, "step": 5326 }, { "epoch": 0.44971138524529614, "grad_norm": 0.1474609375, "learning_rate": 3.194132672483553e-05, "loss": 1.562896966934204, "step": 5327 }, { "epoch": 0.4497958063801273, "grad_norm": 0.1455078125, "learning_rate": 3.1935072719046115e-05, "loss": 1.519342303276062, "step": 5328 }, { "epoch": 0.4498802275149584, "grad_norm": 0.1435546875, "learning_rate": 3.1928818243042105e-05, "loss": 1.5062707662582397, "step": 5329 }, { "epoch": 0.44996464864978947, "grad_norm": 0.130859375, "learning_rate": 3.192256329724757e-05, "loss": 1.4413758516311646, "step": 5330 }, { "epoch": 0.45004906978462056, "grad_norm": 0.15625, "learning_rate": 3.191630788208659e-05, "loss": 1.5084483623504639, "step": 5331 }, { "epoch": 0.4501334909194517, "grad_norm": 0.1318359375, "learning_rate": 3.1910051997983316e-05, "loss": 1.4376555681228638, "step": 5332 }, { "epoch": 0.4502179120542828, "grad_norm": 0.1396484375, "learning_rate": 3.190379564536191e-05, "loss": 1.491337537765503, "step": 5333 }, { "epoch": 0.4503023331891139, "grad_norm": 0.1376953125, "learning_rate": 3.189753882464656e-05, "loss": 1.4669963121414185, "step": 5334 }, { "epoch": 0.450386754323945, "grad_norm": 0.13671875, "learning_rate": 3.18912815362615e-05, "loss": 1.5994486808776855, "step": 5335 }, { "epoch": 0.45047117545877613, "grad_norm": 0.140625, "learning_rate": 3.188502378063099e-05, "loss": 1.4999799728393555, "step": 5336 }, { "epoch": 0.4505555965936072, "grad_norm": 0.1328125, "learning_rate": 3.187876555817931e-05, "loss": 1.4945356845855713, "step": 5337 }, { "epoch": 0.4506400177284383, "grad_norm": 0.142578125, "learning_rate": 3.1872506869330805e-05, "loss": 1.5682344436645508, "step": 5338 }, { "epoch": 0.4507244388632694, "grad_norm": 0.1396484375, "learning_rate": 3.18662477145098e-05, "loss": 1.5841012001037598, "step": 5339 }, { "epoch": 0.4508088599981005, "grad_norm": 0.1376953125, "learning_rate": 3.18599880941407e-05, "loss": 1.551554799079895, "step": 5340 }, { "epoch": 0.45089328113293164, "grad_norm": 0.13671875, "learning_rate": 3.185372800864793e-05, "loss": 1.4975441694259644, "step": 5341 }, { "epoch": 0.45097770226776274, "grad_norm": 0.1298828125, "learning_rate": 3.184746745845592e-05, "loss": 1.4763963222503662, "step": 5342 }, { "epoch": 0.45106212340259383, "grad_norm": 0.1396484375, "learning_rate": 3.184120644398915e-05, "loss": 1.5299922227859497, "step": 5343 }, { "epoch": 0.4511465445374249, "grad_norm": 0.1396484375, "learning_rate": 3.1834944965672145e-05, "loss": 1.5705537796020508, "step": 5344 }, { "epoch": 0.45123096567225607, "grad_norm": 0.1455078125, "learning_rate": 3.182868302392944e-05, "loss": 1.5888429880142212, "step": 5345 }, { "epoch": 0.45131538680708716, "grad_norm": 0.138671875, "learning_rate": 3.182242061918561e-05, "loss": 1.5593448877334595, "step": 5346 }, { "epoch": 0.45139980794191825, "grad_norm": 0.130859375, "learning_rate": 3.181615775186527e-05, "loss": 1.4773486852645874, "step": 5347 }, { "epoch": 0.45148422907674934, "grad_norm": 0.142578125, "learning_rate": 3.180989442239305e-05, "loss": 1.5318119525909424, "step": 5348 }, { "epoch": 0.4515686502115805, "grad_norm": 0.146484375, "learning_rate": 3.18036306311936e-05, "loss": 1.64675772190094, "step": 5349 }, { "epoch": 0.4516530713464116, "grad_norm": 0.1572265625, "learning_rate": 3.179736637869167e-05, "loss": 1.5016067028045654, "step": 5350 }, { "epoch": 0.4517374924812427, "grad_norm": 0.1435546875, "learning_rate": 3.179110166531194e-05, "loss": 1.4538601636886597, "step": 5351 }, { "epoch": 0.45182191361607377, "grad_norm": 0.12890625, "learning_rate": 3.17848364914792e-05, "loss": 1.5381717681884766, "step": 5352 }, { "epoch": 0.4519063347509049, "grad_norm": 0.134765625, "learning_rate": 3.1778570857618236e-05, "loss": 1.4890635013580322, "step": 5353 }, { "epoch": 0.451990755885736, "grad_norm": 0.1328125, "learning_rate": 3.177230476415387e-05, "loss": 1.4684637784957886, "step": 5354 }, { "epoch": 0.4520751770205671, "grad_norm": 0.1337890625, "learning_rate": 3.1766038211510975e-05, "loss": 1.4061493873596191, "step": 5355 }, { "epoch": 0.4521595981553982, "grad_norm": 0.12890625, "learning_rate": 3.175977120011442e-05, "loss": 1.4872199296951294, "step": 5356 }, { "epoch": 0.4522440192902293, "grad_norm": 0.1435546875, "learning_rate": 3.175350373038912e-05, "loss": 1.5685349702835083, "step": 5357 }, { "epoch": 0.45232844042506043, "grad_norm": 0.142578125, "learning_rate": 3.174723580276004e-05, "loss": 1.6026173830032349, "step": 5358 }, { "epoch": 0.4524128615598915, "grad_norm": 0.142578125, "learning_rate": 3.1740967417652156e-05, "loss": 1.5845627784729004, "step": 5359 }, { "epoch": 0.4524972826947226, "grad_norm": 0.142578125, "learning_rate": 3.173469857549048e-05, "loss": 1.5102707147598267, "step": 5360 }, { "epoch": 0.4525817038295537, "grad_norm": 0.1337890625, "learning_rate": 3.1728429276700055e-05, "loss": 1.5895071029663086, "step": 5361 }, { "epoch": 0.45266612496438485, "grad_norm": 0.1328125, "learning_rate": 3.172215952170595e-05, "loss": 1.5018137693405151, "step": 5362 }, { "epoch": 0.45275054609921594, "grad_norm": 0.1376953125, "learning_rate": 3.171588931093327e-05, "loss": 1.6061588525772095, "step": 5363 }, { "epoch": 0.45283496723404704, "grad_norm": 0.1474609375, "learning_rate": 3.1709618644807146e-05, "loss": 1.5938133001327515, "step": 5364 }, { "epoch": 0.45291938836887813, "grad_norm": 0.1318359375, "learning_rate": 3.170334752375276e-05, "loss": 1.5398765802383423, "step": 5365 }, { "epoch": 0.4530038095037093, "grad_norm": 0.134765625, "learning_rate": 3.169707594819528e-05, "loss": 1.5348316431045532, "step": 5366 }, { "epoch": 0.45308823063854037, "grad_norm": 0.173828125, "learning_rate": 3.1690803918559973e-05, "loss": 1.5201281309127808, "step": 5367 }, { "epoch": 0.45317265177337146, "grad_norm": 0.142578125, "learning_rate": 3.168453143527207e-05, "loss": 1.5829976797103882, "step": 5368 }, { "epoch": 0.45325707290820255, "grad_norm": 0.146484375, "learning_rate": 3.1678258498756875e-05, "loss": 1.5448493957519531, "step": 5369 }, { "epoch": 0.4533414940430337, "grad_norm": 0.1328125, "learning_rate": 3.1671985109439696e-05, "loss": 1.4934762716293335, "step": 5370 }, { "epoch": 0.4534259151778648, "grad_norm": 0.1357421875, "learning_rate": 3.166571126774588e-05, "loss": 1.453305721282959, "step": 5371 }, { "epoch": 0.4535103363126959, "grad_norm": 0.138671875, "learning_rate": 3.1659436974100834e-05, "loss": 1.4765040874481201, "step": 5372 }, { "epoch": 0.453594757447527, "grad_norm": 0.1318359375, "learning_rate": 3.1653162228929946e-05, "loss": 1.5573772192001343, "step": 5373 }, { "epoch": 0.45367917858235807, "grad_norm": 0.140625, "learning_rate": 3.164688703265867e-05, "loss": 1.5310468673706055, "step": 5374 }, { "epoch": 0.4537635997171892, "grad_norm": 0.1328125, "learning_rate": 3.164061138571247e-05, "loss": 1.562353253364563, "step": 5375 }, { "epoch": 0.4538480208520203, "grad_norm": 0.140625, "learning_rate": 3.1634335288516856e-05, "loss": 1.5348081588745117, "step": 5376 }, { "epoch": 0.4539324419868514, "grad_norm": 0.1513671875, "learning_rate": 3.162805874149738e-05, "loss": 1.4361412525177002, "step": 5377 }, { "epoch": 0.4540168631216825, "grad_norm": 0.140625, "learning_rate": 3.162178174507957e-05, "loss": 1.4368319511413574, "step": 5378 }, { "epoch": 0.45410128425651364, "grad_norm": 0.1396484375, "learning_rate": 3.161550429968905e-05, "loss": 1.5841906070709229, "step": 5379 }, { "epoch": 0.45418570539134473, "grad_norm": 0.12890625, "learning_rate": 3.160922640575143e-05, "loss": 1.4900894165039062, "step": 5380 }, { "epoch": 0.4542701265261758, "grad_norm": 0.1337890625, "learning_rate": 3.1602948063692385e-05, "loss": 1.5130785703659058, "step": 5381 }, { "epoch": 0.4543545476610069, "grad_norm": 0.140625, "learning_rate": 3.159666927393758e-05, "loss": 1.5565193891525269, "step": 5382 }, { "epoch": 0.45443896879583806, "grad_norm": 0.1376953125, "learning_rate": 3.159039003691274e-05, "loss": 1.5177881717681885, "step": 5383 }, { "epoch": 0.45452338993066915, "grad_norm": 0.142578125, "learning_rate": 3.158411035304362e-05, "loss": 1.5778613090515137, "step": 5384 }, { "epoch": 0.45460781106550024, "grad_norm": 0.134765625, "learning_rate": 3.157783022275599e-05, "loss": 1.4736137390136719, "step": 5385 }, { "epoch": 0.45469223220033134, "grad_norm": 0.130859375, "learning_rate": 3.157154964647566e-05, "loss": 1.498193383216858, "step": 5386 }, { "epoch": 0.4547766533351625, "grad_norm": 0.14453125, "learning_rate": 3.1565268624628475e-05, "loss": 1.5731079578399658, "step": 5387 }, { "epoch": 0.4548610744699936, "grad_norm": 0.1357421875, "learning_rate": 3.1558987157640284e-05, "loss": 1.506992220878601, "step": 5388 }, { "epoch": 0.45494549560482467, "grad_norm": 0.134765625, "learning_rate": 3.1552705245937006e-05, "loss": 1.515045404434204, "step": 5389 }, { "epoch": 0.45502991673965576, "grad_norm": 0.142578125, "learning_rate": 3.154642288994456e-05, "loss": 1.511239767074585, "step": 5390 }, { "epoch": 0.45511433787448685, "grad_norm": 0.1357421875, "learning_rate": 3.154014009008891e-05, "loss": 1.541938304901123, "step": 5391 }, { "epoch": 0.455198759009318, "grad_norm": 0.1494140625, "learning_rate": 3.1533856846796035e-05, "loss": 1.6093517541885376, "step": 5392 }, { "epoch": 0.4552831801441491, "grad_norm": 0.1455078125, "learning_rate": 3.1527573160491966e-05, "loss": 1.4889037609100342, "step": 5393 }, { "epoch": 0.4553676012789802, "grad_norm": 0.1484375, "learning_rate": 3.152128903160274e-05, "loss": 1.5692802667617798, "step": 5394 }, { "epoch": 0.4554520224138113, "grad_norm": 0.15234375, "learning_rate": 3.151500446055444e-05, "loss": 1.5144175291061401, "step": 5395 }, { "epoch": 0.4555364435486424, "grad_norm": 0.14453125, "learning_rate": 3.150871944777319e-05, "loss": 1.5221117734909058, "step": 5396 }, { "epoch": 0.4556208646834735, "grad_norm": 0.1435546875, "learning_rate": 3.150243399368511e-05, "loss": 1.5578182935714722, "step": 5397 }, { "epoch": 0.4557052858183046, "grad_norm": 0.12890625, "learning_rate": 3.149614809871638e-05, "loss": 1.47509765625, "step": 5398 }, { "epoch": 0.4557897069531357, "grad_norm": 0.1416015625, "learning_rate": 3.148986176329318e-05, "loss": 1.6018898487091064, "step": 5399 }, { "epoch": 0.45587412808796685, "grad_norm": 0.1826171875, "learning_rate": 3.1483574987841767e-05, "loss": 1.4499973058700562, "step": 5400 }, { "epoch": 0.45595854922279794, "grad_norm": 0.1337890625, "learning_rate": 3.147728777278839e-05, "loss": 1.5204088687896729, "step": 5401 }, { "epoch": 0.45604297035762903, "grad_norm": 0.1689453125, "learning_rate": 3.1471000118559314e-05, "loss": 1.4967119693756104, "step": 5402 }, { "epoch": 0.4561273914924601, "grad_norm": 0.150390625, "learning_rate": 3.1464712025580886e-05, "loss": 1.5743657350540161, "step": 5403 }, { "epoch": 0.45621181262729127, "grad_norm": 0.14453125, "learning_rate": 3.145842349427944e-05, "loss": 1.5576186180114746, "step": 5404 }, { "epoch": 0.45629623376212236, "grad_norm": 0.142578125, "learning_rate": 3.1452134525081365e-05, "loss": 1.5355886220932007, "step": 5405 }, { "epoch": 0.45638065489695345, "grad_norm": 0.140625, "learning_rate": 3.144584511841306e-05, "loss": 1.5663373470306396, "step": 5406 }, { "epoch": 0.45646507603178454, "grad_norm": 0.1396484375, "learning_rate": 3.143955527470095e-05, "loss": 1.5543571710586548, "step": 5407 }, { "epoch": 0.45654949716661564, "grad_norm": 0.1357421875, "learning_rate": 3.143326499437153e-05, "loss": 1.4683778285980225, "step": 5408 }, { "epoch": 0.4566339183014468, "grad_norm": 0.1337890625, "learning_rate": 3.142697427785127e-05, "loss": 1.4643168449401855, "step": 5409 }, { "epoch": 0.4567183394362779, "grad_norm": 0.146484375, "learning_rate": 3.14206831255667e-05, "loss": 1.5375112295150757, "step": 5410 }, { "epoch": 0.45680276057110897, "grad_norm": 0.1396484375, "learning_rate": 3.141439153794439e-05, "loss": 1.5408399105072021, "step": 5411 }, { "epoch": 0.45688718170594006, "grad_norm": 0.1396484375, "learning_rate": 3.140809951541091e-05, "loss": 1.5313743352890015, "step": 5412 }, { "epoch": 0.4569716028407712, "grad_norm": 0.140625, "learning_rate": 3.140180705839289e-05, "loss": 1.598752737045288, "step": 5413 }, { "epoch": 0.4570560239756023, "grad_norm": 0.1318359375, "learning_rate": 3.139551416731695e-05, "loss": 1.5174291133880615, "step": 5414 }, { "epoch": 0.4571404451104334, "grad_norm": 0.1337890625, "learning_rate": 3.138922084260979e-05, "loss": 1.4887044429779053, "step": 5415 }, { "epoch": 0.4572248662452645, "grad_norm": 0.1396484375, "learning_rate": 3.1382927084698085e-05, "loss": 1.5271000862121582, "step": 5416 }, { "epoch": 0.45730928738009563, "grad_norm": 0.1943359375, "learning_rate": 3.137663289400859e-05, "loss": 1.472487449645996, "step": 5417 }, { "epoch": 0.4573937085149267, "grad_norm": 0.1708984375, "learning_rate": 3.137033827096806e-05, "loss": 1.4692916870117188, "step": 5418 }, { "epoch": 0.4574781296497578, "grad_norm": 0.1552734375, "learning_rate": 3.136404321600327e-05, "loss": 1.556869626045227, "step": 5419 }, { "epoch": 0.4575625507845889, "grad_norm": 0.1435546875, "learning_rate": 3.135774772954106e-05, "loss": 1.5318242311477661, "step": 5420 }, { "epoch": 0.45764697191942005, "grad_norm": 0.1416015625, "learning_rate": 3.135145181200828e-05, "loss": 1.5465234518051147, "step": 5421 }, { "epoch": 0.45773139305425115, "grad_norm": 0.1494140625, "learning_rate": 3.1345155463831796e-05, "loss": 1.562221884727478, "step": 5422 }, { "epoch": 0.45781581418908224, "grad_norm": 0.140625, "learning_rate": 3.133885868543852e-05, "loss": 1.5115163326263428, "step": 5423 }, { "epoch": 0.45790023532391333, "grad_norm": 0.146484375, "learning_rate": 3.133256147725539e-05, "loss": 1.6040159463882446, "step": 5424 }, { "epoch": 0.4579846564587444, "grad_norm": 0.146484375, "learning_rate": 3.1326263839709355e-05, "loss": 1.5453506708145142, "step": 5425 }, { "epoch": 0.45806907759357557, "grad_norm": 0.1376953125, "learning_rate": 3.131996577322744e-05, "loss": 1.5680333375930786, "step": 5426 }, { "epoch": 0.45815349872840666, "grad_norm": 0.1416015625, "learning_rate": 3.1313667278236657e-05, "loss": 1.5585829019546509, "step": 5427 }, { "epoch": 0.45823791986323775, "grad_norm": 0.13671875, "learning_rate": 3.130736835516405e-05, "loss": 1.5797955989837646, "step": 5428 }, { "epoch": 0.45832234099806884, "grad_norm": 0.1357421875, "learning_rate": 3.1301069004436704e-05, "loss": 1.5650994777679443, "step": 5429 }, { "epoch": 0.4584067621329, "grad_norm": 0.1396484375, "learning_rate": 3.129476922648174e-05, "loss": 1.490064024925232, "step": 5430 }, { "epoch": 0.4584911832677311, "grad_norm": 0.1337890625, "learning_rate": 3.1288469021726286e-05, "loss": 1.5310134887695312, "step": 5431 }, { "epoch": 0.4585756044025622, "grad_norm": 0.142578125, "learning_rate": 3.128216839059753e-05, "loss": 1.5096333026885986, "step": 5432 }, { "epoch": 0.45866002553739327, "grad_norm": 0.142578125, "learning_rate": 3.1275867333522645e-05, "loss": 1.591344952583313, "step": 5433 }, { "epoch": 0.4587444466722244, "grad_norm": 0.1474609375, "learning_rate": 3.1269565850928866e-05, "loss": 1.603539228439331, "step": 5434 }, { "epoch": 0.4588288678070555, "grad_norm": 0.15234375, "learning_rate": 3.126326394324346e-05, "loss": 1.5677506923675537, "step": 5435 }, { "epoch": 0.4589132889418866, "grad_norm": 0.1416015625, "learning_rate": 3.1256961610893696e-05, "loss": 1.50313138961792, "step": 5436 }, { "epoch": 0.4589977100767177, "grad_norm": 0.138671875, "learning_rate": 3.1250658854306914e-05, "loss": 1.5985056161880493, "step": 5437 }, { "epoch": 0.45908213121154884, "grad_norm": 0.13671875, "learning_rate": 3.1244355673910416e-05, "loss": 1.5206443071365356, "step": 5438 }, { "epoch": 0.45916655234637993, "grad_norm": 0.1396484375, "learning_rate": 3.123805207013161e-05, "loss": 1.590381383895874, "step": 5439 }, { "epoch": 0.459250973481211, "grad_norm": 0.138671875, "learning_rate": 3.123174804339786e-05, "loss": 1.4790211915969849, "step": 5440 }, { "epoch": 0.4593353946160421, "grad_norm": 0.154296875, "learning_rate": 3.122544359413663e-05, "loss": 1.573358178138733, "step": 5441 }, { "epoch": 0.4594198157508732, "grad_norm": 0.150390625, "learning_rate": 3.121913872277535e-05, "loss": 1.5643234252929688, "step": 5442 }, { "epoch": 0.45950423688570435, "grad_norm": 0.1357421875, "learning_rate": 3.121283342974152e-05, "loss": 1.506813645362854, "step": 5443 }, { "epoch": 0.45958865802053545, "grad_norm": 0.142578125, "learning_rate": 3.1206527715462656e-05, "loss": 1.5403788089752197, "step": 5444 }, { "epoch": 0.45967307915536654, "grad_norm": 0.1396484375, "learning_rate": 3.120022158036629e-05, "loss": 1.5350943803787231, "step": 5445 }, { "epoch": 0.45975750029019763, "grad_norm": 0.14453125, "learning_rate": 3.1193915024879994e-05, "loss": 1.5788557529449463, "step": 5446 }, { "epoch": 0.4598419214250288, "grad_norm": 0.1494140625, "learning_rate": 3.1187608049431374e-05, "loss": 1.5571192502975464, "step": 5447 }, { "epoch": 0.45992634255985987, "grad_norm": 0.1396484375, "learning_rate": 3.118130065444805e-05, "loss": 1.595607876777649, "step": 5448 }, { "epoch": 0.46001076369469096, "grad_norm": 0.1318359375, "learning_rate": 3.1174992840357694e-05, "loss": 1.5277074575424194, "step": 5449 }, { "epoch": 0.46009518482952205, "grad_norm": 0.14453125, "learning_rate": 3.1168684607587976e-05, "loss": 1.5187969207763672, "step": 5450 }, { "epoch": 0.4601796059643532, "grad_norm": 0.1435546875, "learning_rate": 3.1162375956566616e-05, "loss": 1.5634291172027588, "step": 5451 }, { "epoch": 0.4602640270991843, "grad_norm": 0.1337890625, "learning_rate": 3.1156066887721346e-05, "loss": 1.5090001821517944, "step": 5452 }, { "epoch": 0.4603484482340154, "grad_norm": 0.1455078125, "learning_rate": 3.114975740147995e-05, "loss": 1.6207280158996582, "step": 5453 }, { "epoch": 0.4604328693688465, "grad_norm": 0.1298828125, "learning_rate": 3.114344749827022e-05, "loss": 1.5403457880020142, "step": 5454 }, { "epoch": 0.4605172905036776, "grad_norm": 0.1337890625, "learning_rate": 3.1137137178519985e-05, "loss": 1.465404748916626, "step": 5455 }, { "epoch": 0.4606017116385087, "grad_norm": 0.1357421875, "learning_rate": 3.113082644265709e-05, "loss": 1.5217390060424805, "step": 5456 }, { "epoch": 0.4606861327733398, "grad_norm": 0.1630859375, "learning_rate": 3.112451529110943e-05, "loss": 1.4766467809677124, "step": 5457 }, { "epoch": 0.4607705539081709, "grad_norm": 0.1416015625, "learning_rate": 3.111820372430491e-05, "loss": 1.4924070835113525, "step": 5458 }, { "epoch": 0.460854975043002, "grad_norm": 0.1455078125, "learning_rate": 3.111189174267148e-05, "loss": 1.5473636388778687, "step": 5459 }, { "epoch": 0.46093939617783314, "grad_norm": 0.138671875, "learning_rate": 3.110557934663708e-05, "loss": 1.5252009630203247, "step": 5460 }, { "epoch": 0.46102381731266423, "grad_norm": 0.1484375, "learning_rate": 3.1099266536629744e-05, "loss": 1.5313656330108643, "step": 5461 }, { "epoch": 0.4611082384474953, "grad_norm": 0.13671875, "learning_rate": 3.1092953313077465e-05, "loss": 1.4469505548477173, "step": 5462 }, { "epoch": 0.4611926595823264, "grad_norm": 0.1484375, "learning_rate": 3.108663967640831e-05, "loss": 1.466740608215332, "step": 5463 }, { "epoch": 0.46127708071715756, "grad_norm": 0.140625, "learning_rate": 3.1080325627050356e-05, "loss": 1.5558406114578247, "step": 5464 }, { "epoch": 0.46136150185198865, "grad_norm": 0.1318359375, "learning_rate": 3.1074011165431705e-05, "loss": 1.552196741104126, "step": 5465 }, { "epoch": 0.46144592298681975, "grad_norm": 0.1337890625, "learning_rate": 3.10676962919805e-05, "loss": 1.5003678798675537, "step": 5466 }, { "epoch": 0.46153034412165084, "grad_norm": 0.1533203125, "learning_rate": 3.1061381007124904e-05, "loss": 1.5131375789642334, "step": 5467 }, { "epoch": 0.461614765256482, "grad_norm": 0.1376953125, "learning_rate": 3.10550653112931e-05, "loss": 1.5633151531219482, "step": 5468 }, { "epoch": 0.4616991863913131, "grad_norm": 0.1396484375, "learning_rate": 3.1048749204913317e-05, "loss": 1.5045669078826904, "step": 5469 }, { "epoch": 0.46178360752614417, "grad_norm": 0.1376953125, "learning_rate": 3.10424326884138e-05, "loss": 1.5960874557495117, "step": 5470 }, { "epoch": 0.46186802866097526, "grad_norm": 0.1474609375, "learning_rate": 3.103611576222282e-05, "loss": 1.582151174545288, "step": 5471 }, { "epoch": 0.46195244979580635, "grad_norm": 0.138671875, "learning_rate": 3.102979842676868e-05, "loss": 1.492767572402954, "step": 5472 }, { "epoch": 0.4620368709306375, "grad_norm": 0.12890625, "learning_rate": 3.102348068247972e-05, "loss": 1.575727939605713, "step": 5473 }, { "epoch": 0.4621212920654686, "grad_norm": 0.1357421875, "learning_rate": 3.101716252978428e-05, "loss": 1.5071011781692505, "step": 5474 }, { "epoch": 0.4622057132002997, "grad_norm": 0.1435546875, "learning_rate": 3.101084396911077e-05, "loss": 1.5955628156661987, "step": 5475 }, { "epoch": 0.4622901343351308, "grad_norm": 0.1357421875, "learning_rate": 3.100452500088758e-05, "loss": 1.5008240938186646, "step": 5476 }, { "epoch": 0.4623745554699619, "grad_norm": 0.1513671875, "learning_rate": 3.099820562554317e-05, "loss": 1.4752000570297241, "step": 5477 }, { "epoch": 0.462458976604793, "grad_norm": 0.134765625, "learning_rate": 3.099188584350599e-05, "loss": 1.5829778909683228, "step": 5478 }, { "epoch": 0.4625433977396241, "grad_norm": 0.1337890625, "learning_rate": 3.098556565520456e-05, "loss": 1.4896241426467896, "step": 5479 }, { "epoch": 0.4626278188744552, "grad_norm": 0.1376953125, "learning_rate": 3.097924506106739e-05, "loss": 1.5551284551620483, "step": 5480 }, { "epoch": 0.46271224000928635, "grad_norm": 0.138671875, "learning_rate": 3.097292406152302e-05, "loss": 1.5331650972366333, "step": 5481 }, { "epoch": 0.46279666114411744, "grad_norm": 0.1396484375, "learning_rate": 3.096660265700006e-05, "loss": 1.5388262271881104, "step": 5482 }, { "epoch": 0.46288108227894853, "grad_norm": 0.1396484375, "learning_rate": 3.096028084792708e-05, "loss": 1.551655650138855, "step": 5483 }, { "epoch": 0.4629655034137796, "grad_norm": 0.1669921875, "learning_rate": 3.095395863473274e-05, "loss": 1.4787237644195557, "step": 5484 }, { "epoch": 0.46304992454861077, "grad_norm": 0.1484375, "learning_rate": 3.09476360178457e-05, "loss": 1.5997565984725952, "step": 5485 }, { "epoch": 0.46313434568344186, "grad_norm": 0.146484375, "learning_rate": 3.094131299769463e-05, "loss": 1.5300153493881226, "step": 5486 }, { "epoch": 0.46321876681827295, "grad_norm": 0.1396484375, "learning_rate": 3.093498957470826e-05, "loss": 1.4832333326339722, "step": 5487 }, { "epoch": 0.46330318795310405, "grad_norm": 0.150390625, "learning_rate": 3.0928665749315335e-05, "loss": 1.6238735914230347, "step": 5488 }, { "epoch": 0.46338760908793514, "grad_norm": 0.1337890625, "learning_rate": 3.092234152194462e-05, "loss": 1.5148741006851196, "step": 5489 }, { "epoch": 0.4634720302227663, "grad_norm": 0.1396484375, "learning_rate": 3.0916016893024916e-05, "loss": 1.4649381637573242, "step": 5490 }, { "epoch": 0.4635564513575974, "grad_norm": 0.14453125, "learning_rate": 3.0909691862985046e-05, "loss": 1.572416067123413, "step": 5491 }, { "epoch": 0.46364087249242847, "grad_norm": 0.1337890625, "learning_rate": 3.090336643225386e-05, "loss": 1.5164240598678589, "step": 5492 }, { "epoch": 0.46372529362725956, "grad_norm": 0.142578125, "learning_rate": 3.089704060126024e-05, "loss": 1.5753498077392578, "step": 5493 }, { "epoch": 0.4638097147620907, "grad_norm": 0.14453125, "learning_rate": 3.089071437043309e-05, "loss": 1.5686086416244507, "step": 5494 }, { "epoch": 0.4638941358969218, "grad_norm": 0.146484375, "learning_rate": 3.088438774020136e-05, "loss": 1.6200850009918213, "step": 5495 }, { "epoch": 0.4639785570317529, "grad_norm": 0.1474609375, "learning_rate": 3.087806071099398e-05, "loss": 1.5634413957595825, "step": 5496 }, { "epoch": 0.464062978166584, "grad_norm": 0.14453125, "learning_rate": 3.0871733283239965e-05, "loss": 1.5518770217895508, "step": 5497 }, { "epoch": 0.46414739930141513, "grad_norm": 0.134765625, "learning_rate": 3.086540545736832e-05, "loss": 1.5140539407730103, "step": 5498 }, { "epoch": 0.4642318204362462, "grad_norm": 0.1318359375, "learning_rate": 3.0859077233808084e-05, "loss": 1.5571069717407227, "step": 5499 }, { "epoch": 0.4643162415710773, "grad_norm": 0.140625, "learning_rate": 3.085274861298833e-05, "loss": 1.5307811498641968, "step": 5500 }, { "epoch": 0.4644006627059084, "grad_norm": 0.1455078125, "learning_rate": 3.0846419595338146e-05, "loss": 1.5491645336151123, "step": 5501 }, { "epoch": 0.46448508384073955, "grad_norm": 0.150390625, "learning_rate": 3.084009018128666e-05, "loss": 1.5657222270965576, "step": 5502 }, { "epoch": 0.46456950497557065, "grad_norm": 0.1513671875, "learning_rate": 3.083376037126303e-05, "loss": 1.5471124649047852, "step": 5503 }, { "epoch": 0.46465392611040174, "grad_norm": 0.1376953125, "learning_rate": 3.082743016569643e-05, "loss": 1.5506916046142578, "step": 5504 }, { "epoch": 0.46473834724523283, "grad_norm": 0.140625, "learning_rate": 3.082109956501604e-05, "loss": 1.5166170597076416, "step": 5505 }, { "epoch": 0.4648227683800639, "grad_norm": 0.134765625, "learning_rate": 3.081476856965111e-05, "loss": 1.504343032836914, "step": 5506 }, { "epoch": 0.46490718951489507, "grad_norm": 0.1376953125, "learning_rate": 3.08084371800309e-05, "loss": 1.4831196069717407, "step": 5507 }, { "epoch": 0.46499161064972616, "grad_norm": 0.1591796875, "learning_rate": 3.080210539658469e-05, "loss": 1.544018030166626, "step": 5508 }, { "epoch": 0.46507603178455725, "grad_norm": 0.134765625, "learning_rate": 3.079577321974179e-05, "loss": 1.5279285907745361, "step": 5509 }, { "epoch": 0.46516045291938835, "grad_norm": 0.1298828125, "learning_rate": 3.078944064993152e-05, "loss": 1.47750723361969, "step": 5510 }, { "epoch": 0.4652448740542195, "grad_norm": 0.13671875, "learning_rate": 3.078310768758328e-05, "loss": 1.5582455396652222, "step": 5511 }, { "epoch": 0.4653292951890506, "grad_norm": 0.1376953125, "learning_rate": 3.077677433312642e-05, "loss": 1.516603708267212, "step": 5512 }, { "epoch": 0.4654137163238817, "grad_norm": 0.138671875, "learning_rate": 3.077044058699037e-05, "loss": 1.5401766300201416, "step": 5513 }, { "epoch": 0.46549813745871277, "grad_norm": 0.1318359375, "learning_rate": 3.076410644960459e-05, "loss": 1.574903130531311, "step": 5514 }, { "epoch": 0.4655825585935439, "grad_norm": 0.13671875, "learning_rate": 3.0757771921398536e-05, "loss": 1.4894345998764038, "step": 5515 }, { "epoch": 0.465666979728375, "grad_norm": 0.138671875, "learning_rate": 3.075143700280171e-05, "loss": 1.5242184400558472, "step": 5516 }, { "epoch": 0.4657514008632061, "grad_norm": 0.1474609375, "learning_rate": 3.074510169424362e-05, "loss": 1.5261807441711426, "step": 5517 }, { "epoch": 0.4658358219980372, "grad_norm": 0.1416015625, "learning_rate": 3.073876599615383e-05, "loss": 1.548706293106079, "step": 5518 }, { "epoch": 0.46592024313286834, "grad_norm": 0.1474609375, "learning_rate": 3.073242990896192e-05, "loss": 1.570917010307312, "step": 5519 }, { "epoch": 0.46600466426769943, "grad_norm": 0.1494140625, "learning_rate": 3.072609343309747e-05, "loss": 1.6825312376022339, "step": 5520 }, { "epoch": 0.4660890854025305, "grad_norm": 0.1298828125, "learning_rate": 3.071975656899013e-05, "loss": 1.4869029521942139, "step": 5521 }, { "epoch": 0.4661735065373616, "grad_norm": 0.1376953125, "learning_rate": 3.071341931706955e-05, "loss": 1.6157735586166382, "step": 5522 }, { "epoch": 0.4662579276721927, "grad_norm": 0.1357421875, "learning_rate": 3.070708167776539e-05, "loss": 1.4255763292312622, "step": 5523 }, { "epoch": 0.46634234880702385, "grad_norm": 0.1396484375, "learning_rate": 3.070074365150739e-05, "loss": 1.491732120513916, "step": 5524 }, { "epoch": 0.46642676994185495, "grad_norm": 0.140625, "learning_rate": 3.069440523872526e-05, "loss": 1.5148919820785522, "step": 5525 }, { "epoch": 0.46651119107668604, "grad_norm": 0.1357421875, "learning_rate": 3.0688066439848775e-05, "loss": 1.4964399337768555, "step": 5526 }, { "epoch": 0.46659561221151713, "grad_norm": 0.138671875, "learning_rate": 3.06817272553077e-05, "loss": 1.525092363357544, "step": 5527 }, { "epoch": 0.4666800333463483, "grad_norm": 0.13671875, "learning_rate": 3.067538768553188e-05, "loss": 1.4938703775405884, "step": 5528 }, { "epoch": 0.46676445448117937, "grad_norm": 0.1357421875, "learning_rate": 3.066904773095111e-05, "loss": 1.5123456716537476, "step": 5529 }, { "epoch": 0.46684887561601046, "grad_norm": 0.1376953125, "learning_rate": 3.066270739199529e-05, "loss": 1.6172312498092651, "step": 5530 }, { "epoch": 0.46693329675084155, "grad_norm": 0.1298828125, "learning_rate": 3.06563666690943e-05, "loss": 1.4853384494781494, "step": 5531 }, { "epoch": 0.4670177178856727, "grad_norm": 0.1357421875, "learning_rate": 3.065002556267804e-05, "loss": 1.5134748220443726, "step": 5532 }, { "epoch": 0.4671021390205038, "grad_norm": 0.140625, "learning_rate": 3.064368407317648e-05, "loss": 1.5229872465133667, "step": 5533 }, { "epoch": 0.4671865601553349, "grad_norm": 0.1376953125, "learning_rate": 3.063734220101957e-05, "loss": 1.4875770807266235, "step": 5534 }, { "epoch": 0.467270981290166, "grad_norm": 0.138671875, "learning_rate": 3.063099994663731e-05, "loss": 1.488122582435608, "step": 5535 }, { "epoch": 0.4673554024249971, "grad_norm": 0.1376953125, "learning_rate": 3.0624657310459714e-05, "loss": 1.4904495477676392, "step": 5536 }, { "epoch": 0.4674398235598282, "grad_norm": 0.1396484375, "learning_rate": 3.061831429291683e-05, "loss": 1.5387661457061768, "step": 5537 }, { "epoch": 0.4675242446946593, "grad_norm": 0.138671875, "learning_rate": 3.061197089443875e-05, "loss": 1.5394169092178345, "step": 5538 }, { "epoch": 0.4676086658294904, "grad_norm": 0.14453125, "learning_rate": 3.0605627115455535e-05, "loss": 1.5520033836364746, "step": 5539 }, { "epoch": 0.4676930869643215, "grad_norm": 0.1416015625, "learning_rate": 3.0599282956397336e-05, "loss": 1.5087203979492188, "step": 5540 }, { "epoch": 0.46777750809915264, "grad_norm": 0.142578125, "learning_rate": 3.059293841769428e-05, "loss": 1.5120848417282104, "step": 5541 }, { "epoch": 0.46786192923398373, "grad_norm": 0.1630859375, "learning_rate": 3.0586593499776575e-05, "loss": 1.5292490720748901, "step": 5542 }, { "epoch": 0.4679463503688148, "grad_norm": 0.1376953125, "learning_rate": 3.0580248203074394e-05, "loss": 1.5153096914291382, "step": 5543 }, { "epoch": 0.4680307715036459, "grad_norm": 0.146484375, "learning_rate": 3.057390252801797e-05, "loss": 1.6391016244888306, "step": 5544 }, { "epoch": 0.46811519263847706, "grad_norm": 0.1328125, "learning_rate": 3.056755647503756e-05, "loss": 1.4907046556472778, "step": 5545 }, { "epoch": 0.46819961377330815, "grad_norm": 0.1435546875, "learning_rate": 3.0561210044563435e-05, "loss": 1.544388771057129, "step": 5546 }, { "epoch": 0.46828403490813925, "grad_norm": 0.130859375, "learning_rate": 3.055486323702591e-05, "loss": 1.4315885305404663, "step": 5547 }, { "epoch": 0.46836845604297034, "grad_norm": 0.14453125, "learning_rate": 3.0548516052855294e-05, "loss": 1.5565434694290161, "step": 5548 }, { "epoch": 0.4684528771778015, "grad_norm": 0.1357421875, "learning_rate": 3.054216849248196e-05, "loss": 1.4538460969924927, "step": 5549 }, { "epoch": 0.4685372983126326, "grad_norm": 0.1318359375, "learning_rate": 3.0535820556336276e-05, "loss": 1.4793987274169922, "step": 5550 }, { "epoch": 0.46862171944746367, "grad_norm": 0.1494140625, "learning_rate": 3.052947224484865e-05, "loss": 1.5588117837905884, "step": 5551 }, { "epoch": 0.46870614058229476, "grad_norm": 0.1435546875, "learning_rate": 3.052312355844952e-05, "loss": 1.5656059980392456, "step": 5552 }, { "epoch": 0.4687905617171259, "grad_norm": 0.1357421875, "learning_rate": 3.051677449756934e-05, "loss": 1.5334792137145996, "step": 5553 }, { "epoch": 0.468874982851957, "grad_norm": 0.1474609375, "learning_rate": 3.051042506263858e-05, "loss": 1.5433123111724854, "step": 5554 }, { "epoch": 0.4689594039867881, "grad_norm": 0.150390625, "learning_rate": 3.050407525408776e-05, "loss": 1.6172314882278442, "step": 5555 }, { "epoch": 0.4690438251216192, "grad_norm": 0.140625, "learning_rate": 3.0497725072347404e-05, "loss": 1.5349881649017334, "step": 5556 }, { "epoch": 0.4691282462564503, "grad_norm": 0.1396484375, "learning_rate": 3.0491374517848086e-05, "loss": 1.564676284790039, "step": 5557 }, { "epoch": 0.4692126673912814, "grad_norm": 0.1435546875, "learning_rate": 3.0485023591020366e-05, "loss": 1.44284188747406, "step": 5558 }, { "epoch": 0.4692970885261125, "grad_norm": 0.130859375, "learning_rate": 3.047867229229486e-05, "loss": 1.4201027154922485, "step": 5559 }, { "epoch": 0.4693815096609436, "grad_norm": 0.1396484375, "learning_rate": 3.0472320622102207e-05, "loss": 1.5643434524536133, "step": 5560 }, { "epoch": 0.4694659307957747, "grad_norm": 0.138671875, "learning_rate": 3.0465968580873062e-05, "loss": 1.5088329315185547, "step": 5561 }, { "epoch": 0.46955035193060585, "grad_norm": 0.1328125, "learning_rate": 3.045961616903811e-05, "loss": 1.470008373260498, "step": 5562 }, { "epoch": 0.46963477306543694, "grad_norm": 0.1494140625, "learning_rate": 3.0453263387028053e-05, "loss": 1.5090115070343018, "step": 5563 }, { "epoch": 0.46971919420026803, "grad_norm": 0.1376953125, "learning_rate": 3.044691023527364e-05, "loss": 1.5325284004211426, "step": 5564 }, { "epoch": 0.4698036153350991, "grad_norm": 0.1376953125, "learning_rate": 3.044055671420561e-05, "loss": 1.5440092086791992, "step": 5565 }, { "epoch": 0.46988803646993027, "grad_norm": 0.1416015625, "learning_rate": 3.0434202824254764e-05, "loss": 1.5798556804656982, "step": 5566 }, { "epoch": 0.46997245760476136, "grad_norm": 0.1416015625, "learning_rate": 3.042784856585191e-05, "loss": 1.5764981508255005, "step": 5567 }, { "epoch": 0.47005687873959245, "grad_norm": 0.1416015625, "learning_rate": 3.0421493939427858e-05, "loss": 1.5374863147735596, "step": 5568 }, { "epoch": 0.47014129987442355, "grad_norm": 0.138671875, "learning_rate": 3.04151389454135e-05, "loss": 1.4747072458267212, "step": 5569 }, { "epoch": 0.4702257210092547, "grad_norm": 0.1494140625, "learning_rate": 3.0408783584239704e-05, "loss": 1.498122215270996, "step": 5570 }, { "epoch": 0.4703101421440858, "grad_norm": 0.14453125, "learning_rate": 3.0402427856337373e-05, "loss": 1.5539555549621582, "step": 5571 }, { "epoch": 0.4703945632789169, "grad_norm": 0.1328125, "learning_rate": 3.039607176213745e-05, "loss": 1.5502018928527832, "step": 5572 }, { "epoch": 0.47047898441374797, "grad_norm": 0.138671875, "learning_rate": 3.038971530207089e-05, "loss": 1.5498881340026855, "step": 5573 }, { "epoch": 0.47056340554857906, "grad_norm": 0.1298828125, "learning_rate": 3.038335847656869e-05, "loss": 1.5696325302124023, "step": 5574 }, { "epoch": 0.4706478266834102, "grad_norm": 0.1318359375, "learning_rate": 3.0377001286061834e-05, "loss": 1.5118626356124878, "step": 5575 }, { "epoch": 0.4707322478182413, "grad_norm": 0.1396484375, "learning_rate": 3.0370643730981368e-05, "loss": 1.48312246799469, "step": 5576 }, { "epoch": 0.4708166689530724, "grad_norm": 0.142578125, "learning_rate": 3.0364285811758347e-05, "loss": 1.551628828048706, "step": 5577 }, { "epoch": 0.4709010900879035, "grad_norm": 0.1572265625, "learning_rate": 3.0357927528823855e-05, "loss": 1.488209843635559, "step": 5578 }, { "epoch": 0.47098551122273463, "grad_norm": 0.1357421875, "learning_rate": 3.0351568882609e-05, "loss": 1.531699299812317, "step": 5579 }, { "epoch": 0.4710699323575657, "grad_norm": 0.134765625, "learning_rate": 3.0345209873544913e-05, "loss": 1.466326117515564, "step": 5580 }, { "epoch": 0.4711543534923968, "grad_norm": 0.1357421875, "learning_rate": 3.033885050206274e-05, "loss": 1.562528371810913, "step": 5581 }, { "epoch": 0.4712387746272279, "grad_norm": 0.142578125, "learning_rate": 3.0332490768593675e-05, "loss": 1.4844133853912354, "step": 5582 }, { "epoch": 0.47132319576205906, "grad_norm": 0.15234375, "learning_rate": 3.0326130673568914e-05, "loss": 1.5941202640533447, "step": 5583 }, { "epoch": 0.47140761689689015, "grad_norm": 0.154296875, "learning_rate": 3.0319770217419695e-05, "loss": 1.5788323879241943, "step": 5584 }, { "epoch": 0.47149203803172124, "grad_norm": 0.134765625, "learning_rate": 3.0313409400577264e-05, "loss": 1.473365068435669, "step": 5585 }, { "epoch": 0.47157645916655233, "grad_norm": 0.1337890625, "learning_rate": 3.030704822347291e-05, "loss": 1.5829402208328247, "step": 5586 }, { "epoch": 0.4716608803013835, "grad_norm": 0.1416015625, "learning_rate": 3.030068668653793e-05, "loss": 1.5552458763122559, "step": 5587 }, { "epoch": 0.47174530143621457, "grad_norm": 0.146484375, "learning_rate": 3.0294324790203655e-05, "loss": 1.4953734874725342, "step": 5588 }, { "epoch": 0.47182972257104566, "grad_norm": 0.142578125, "learning_rate": 3.0287962534901426e-05, "loss": 1.5540711879730225, "step": 5589 }, { "epoch": 0.47191414370587675, "grad_norm": 0.1357421875, "learning_rate": 3.0281599921062626e-05, "loss": 1.4883968830108643, "step": 5590 }, { "epoch": 0.47199856484070785, "grad_norm": 0.1416015625, "learning_rate": 3.027523694911866e-05, "loss": 1.4922374486923218, "step": 5591 }, { "epoch": 0.472082985975539, "grad_norm": 0.1533203125, "learning_rate": 3.026887361950094e-05, "loss": 1.491229772567749, "step": 5592 }, { "epoch": 0.4721674071103701, "grad_norm": 0.1396484375, "learning_rate": 3.0262509932640936e-05, "loss": 1.553182601928711, "step": 5593 }, { "epoch": 0.4722518282452012, "grad_norm": 0.1435546875, "learning_rate": 3.02561458889701e-05, "loss": 1.6117266416549683, "step": 5594 }, { "epoch": 0.47233624938003227, "grad_norm": 0.1328125, "learning_rate": 3.0249781488919947e-05, "loss": 1.5198752880096436, "step": 5595 }, { "epoch": 0.4724206705148634, "grad_norm": 0.1396484375, "learning_rate": 3.0243416732921986e-05, "loss": 1.5445146560668945, "step": 5596 }, { "epoch": 0.4725050916496945, "grad_norm": 0.1455078125, "learning_rate": 3.0237051621407763e-05, "loss": 1.5500377416610718, "step": 5597 }, { "epoch": 0.4725895127845256, "grad_norm": 0.1337890625, "learning_rate": 3.023068615480886e-05, "loss": 1.4370182752609253, "step": 5598 }, { "epoch": 0.4726739339193567, "grad_norm": 0.146484375, "learning_rate": 3.0224320333556854e-05, "loss": 1.54189932346344, "step": 5599 }, { "epoch": 0.47275835505418784, "grad_norm": 0.154296875, "learning_rate": 3.0217954158083384e-05, "loss": 1.5801243782043457, "step": 5600 }, { "epoch": 0.47284277618901893, "grad_norm": 0.15234375, "learning_rate": 3.021158762882007e-05, "loss": 1.4944007396697998, "step": 5601 }, { "epoch": 0.47292719732385, "grad_norm": 0.140625, "learning_rate": 3.0205220746198586e-05, "loss": 1.4633442163467407, "step": 5602 }, { "epoch": 0.4730116184586811, "grad_norm": 0.1435546875, "learning_rate": 3.0198853510650625e-05, "loss": 1.483466625213623, "step": 5603 }, { "epoch": 0.47309603959351226, "grad_norm": 0.1474609375, "learning_rate": 3.0192485922607905e-05, "loss": 1.5442728996276855, "step": 5604 }, { "epoch": 0.47318046072834336, "grad_norm": 0.138671875, "learning_rate": 3.018611798250216e-05, "loss": 1.4243440628051758, "step": 5605 }, { "epoch": 0.47326488186317445, "grad_norm": 0.1337890625, "learning_rate": 3.0179749690765142e-05, "loss": 1.4261996746063232, "step": 5606 }, { "epoch": 0.47334930299800554, "grad_norm": 0.13671875, "learning_rate": 3.0173381047828647e-05, "loss": 1.5971555709838867, "step": 5607 }, { "epoch": 0.47343372413283663, "grad_norm": 0.1298828125, "learning_rate": 3.0167012054124484e-05, "loss": 1.4926936626434326, "step": 5608 }, { "epoch": 0.4735181452676678, "grad_norm": 0.1474609375, "learning_rate": 3.016064271008448e-05, "loss": 1.5827548503875732, "step": 5609 }, { "epoch": 0.47360256640249887, "grad_norm": 0.13671875, "learning_rate": 3.0154273016140504e-05, "loss": 1.4896310567855835, "step": 5610 }, { "epoch": 0.47368698753732996, "grad_norm": 0.13671875, "learning_rate": 3.0147902972724422e-05, "loss": 1.491419792175293, "step": 5611 }, { "epoch": 0.47377140867216105, "grad_norm": 0.138671875, "learning_rate": 3.0141532580268144e-05, "loss": 1.5798687934875488, "step": 5612 }, { "epoch": 0.4738558298069922, "grad_norm": 0.1357421875, "learning_rate": 3.0135161839203597e-05, "loss": 1.5450133085250854, "step": 5613 }, { "epoch": 0.4739402509418233, "grad_norm": 0.1416015625, "learning_rate": 3.012879074996274e-05, "loss": 1.4940502643585205, "step": 5614 }, { "epoch": 0.4740246720766544, "grad_norm": 0.1376953125, "learning_rate": 3.012241931297754e-05, "loss": 1.5035203695297241, "step": 5615 }, { "epoch": 0.4741090932114855, "grad_norm": 0.138671875, "learning_rate": 3.0116047528679998e-05, "loss": 1.5914989709854126, "step": 5616 }, { "epoch": 0.4741935143463166, "grad_norm": 0.154296875, "learning_rate": 3.010967539750213e-05, "loss": 1.4250571727752686, "step": 5617 }, { "epoch": 0.4742779354811477, "grad_norm": 0.140625, "learning_rate": 3.010330291987599e-05, "loss": 1.5516231060028076, "step": 5618 }, { "epoch": 0.4743623566159788, "grad_norm": 0.1875, "learning_rate": 3.009693009623365e-05, "loss": 1.53261137008667, "step": 5619 }, { "epoch": 0.4744467777508099, "grad_norm": 0.1689453125, "learning_rate": 3.0090556927007202e-05, "loss": 1.4921597242355347, "step": 5620 }, { "epoch": 0.47453119888564105, "grad_norm": 0.1396484375, "learning_rate": 3.0084183412628742e-05, "loss": 1.5044276714324951, "step": 5621 }, { "epoch": 0.47461562002047214, "grad_norm": 0.1435546875, "learning_rate": 3.0077809553530444e-05, "loss": 1.5960729122161865, "step": 5622 }, { "epoch": 0.47470004115530323, "grad_norm": 0.1396484375, "learning_rate": 3.0071435350144444e-05, "loss": 1.5287108421325684, "step": 5623 }, { "epoch": 0.4747844622901343, "grad_norm": 0.134765625, "learning_rate": 3.0065060802902946e-05, "loss": 1.536426305770874, "step": 5624 }, { "epoch": 0.4748688834249654, "grad_norm": 0.1484375, "learning_rate": 3.005868591223814e-05, "loss": 1.5795881748199463, "step": 5625 }, { "epoch": 0.47495330455979656, "grad_norm": 0.1279296875, "learning_rate": 3.0052310678582263e-05, "loss": 1.4317961931228638, "step": 5626 }, { "epoch": 0.47503772569462765, "grad_norm": 0.1337890625, "learning_rate": 3.0045935102367596e-05, "loss": 1.5066896677017212, "step": 5627 }, { "epoch": 0.47512214682945875, "grad_norm": 0.1396484375, "learning_rate": 3.003955918402639e-05, "loss": 1.5383669137954712, "step": 5628 }, { "epoch": 0.47520656796428984, "grad_norm": 0.12890625, "learning_rate": 3.003318292399096e-05, "loss": 1.5012459754943848, "step": 5629 }, { "epoch": 0.475290989099121, "grad_norm": 0.140625, "learning_rate": 3.0026806322693625e-05, "loss": 1.4508225917816162, "step": 5630 }, { "epoch": 0.4753754102339521, "grad_norm": 0.1337890625, "learning_rate": 3.0020429380566744e-05, "loss": 1.5466891527175903, "step": 5631 }, { "epoch": 0.47545983136878317, "grad_norm": 0.13671875, "learning_rate": 3.0014052098042685e-05, "loss": 1.5274568796157837, "step": 5632 }, { "epoch": 0.47554425250361426, "grad_norm": 0.140625, "learning_rate": 3.0007674475553837e-05, "loss": 1.5908745527267456, "step": 5633 }, { "epoch": 0.4756286736384454, "grad_norm": 0.142578125, "learning_rate": 3.000129651353263e-05, "loss": 1.485214114189148, "step": 5634 }, { "epoch": 0.4757130947732765, "grad_norm": 0.1513671875, "learning_rate": 2.999491821241148e-05, "loss": 1.5448105335235596, "step": 5635 }, { "epoch": 0.4757975159081076, "grad_norm": 0.134765625, "learning_rate": 2.9988539572622888e-05, "loss": 1.5366332530975342, "step": 5636 }, { "epoch": 0.4758819370429387, "grad_norm": 0.1376953125, "learning_rate": 2.9982160594599317e-05, "loss": 1.5194364786148071, "step": 5637 }, { "epoch": 0.4759663581777698, "grad_norm": 0.146484375, "learning_rate": 2.9975781278773278e-05, "loss": 1.556194543838501, "step": 5638 }, { "epoch": 0.4760507793126009, "grad_norm": 0.140625, "learning_rate": 2.996940162557731e-05, "loss": 1.4187699556350708, "step": 5639 }, { "epoch": 0.476135200447432, "grad_norm": 0.1396484375, "learning_rate": 2.9963021635443966e-05, "loss": 1.5305644273757935, "step": 5640 }, { "epoch": 0.4762196215822631, "grad_norm": 0.1435546875, "learning_rate": 2.9956641308805833e-05, "loss": 1.5382541418075562, "step": 5641 }, { "epoch": 0.4763040427170942, "grad_norm": 0.1455078125, "learning_rate": 2.9950260646095496e-05, "loss": 1.5772026777267456, "step": 5642 }, { "epoch": 0.47638846385192535, "grad_norm": 0.1396484375, "learning_rate": 2.9943879647745592e-05, "loss": 1.529844880104065, "step": 5643 }, { "epoch": 0.47647288498675644, "grad_norm": 0.146484375, "learning_rate": 2.9937498314188763e-05, "loss": 1.6181895732879639, "step": 5644 }, { "epoch": 0.47655730612158753, "grad_norm": 0.13671875, "learning_rate": 2.993111664585768e-05, "loss": 1.5057690143585205, "step": 5645 }, { "epoch": 0.4766417272564186, "grad_norm": 0.138671875, "learning_rate": 2.9924734643185037e-05, "loss": 1.5143425464630127, "step": 5646 }, { "epoch": 0.47672614839124977, "grad_norm": 0.1376953125, "learning_rate": 2.991835230660355e-05, "loss": 1.4341139793395996, "step": 5647 }, { "epoch": 0.47681056952608086, "grad_norm": 0.1396484375, "learning_rate": 2.991196963654595e-05, "loss": 1.5099682807922363, "step": 5648 }, { "epoch": 0.47689499066091195, "grad_norm": 0.1484375, "learning_rate": 2.9905586633445003e-05, "loss": 1.5525999069213867, "step": 5649 }, { "epoch": 0.47697941179574305, "grad_norm": 0.140625, "learning_rate": 2.9899203297733492e-05, "loss": 1.5259417295455933, "step": 5650 }, { "epoch": 0.4770638329305742, "grad_norm": 0.1435546875, "learning_rate": 2.989281962984422e-05, "loss": 1.4429970979690552, "step": 5651 }, { "epoch": 0.4771482540654053, "grad_norm": 0.1455078125, "learning_rate": 2.988643563021002e-05, "loss": 1.5737649202346802, "step": 5652 }, { "epoch": 0.4772326752002364, "grad_norm": 0.1416015625, "learning_rate": 2.9880051299263735e-05, "loss": 1.5871697664260864, "step": 5653 }, { "epoch": 0.47731709633506747, "grad_norm": 0.142578125, "learning_rate": 2.987366663743824e-05, "loss": 1.4871383905410767, "step": 5654 }, { "epoch": 0.47740151746989856, "grad_norm": 0.1416015625, "learning_rate": 2.9867281645166435e-05, "loss": 1.482932209968567, "step": 5655 }, { "epoch": 0.4774859386047297, "grad_norm": 0.1416015625, "learning_rate": 2.9860896322881238e-05, "loss": 1.5260539054870605, "step": 5656 }, { "epoch": 0.4775703597395608, "grad_norm": 0.140625, "learning_rate": 2.9854510671015578e-05, "loss": 1.44429612159729, "step": 5657 }, { "epoch": 0.4776547808743919, "grad_norm": 0.1416015625, "learning_rate": 2.9848124690002433e-05, "loss": 1.6358510255813599, "step": 5658 }, { "epoch": 0.477739202009223, "grad_norm": 0.138671875, "learning_rate": 2.9841738380274774e-05, "loss": 1.5037809610366821, "step": 5659 }, { "epoch": 0.47782362314405413, "grad_norm": 0.140625, "learning_rate": 2.9835351742265622e-05, "loss": 1.5464296340942383, "step": 5660 }, { "epoch": 0.4779080442788852, "grad_norm": 0.1474609375, "learning_rate": 2.9828964776407997e-05, "loss": 1.4778192043304443, "step": 5661 }, { "epoch": 0.4779924654137163, "grad_norm": 0.140625, "learning_rate": 2.982257748313495e-05, "loss": 1.5570881366729736, "step": 5662 }, { "epoch": 0.4780768865485474, "grad_norm": 0.1416015625, "learning_rate": 2.9816189862879562e-05, "loss": 1.476912498474121, "step": 5663 }, { "epoch": 0.47816130768337856, "grad_norm": 0.146484375, "learning_rate": 2.9809801916074924e-05, "loss": 1.5908360481262207, "step": 5664 }, { "epoch": 0.47824572881820965, "grad_norm": 0.1474609375, "learning_rate": 2.980341364315416e-05, "loss": 1.5178042650222778, "step": 5665 }, { "epoch": 0.47833014995304074, "grad_norm": 0.1416015625, "learning_rate": 2.979702504455039e-05, "loss": 1.5743250846862793, "step": 5666 }, { "epoch": 0.47841457108787183, "grad_norm": 0.134765625, "learning_rate": 2.9790636120696802e-05, "loss": 1.5264110565185547, "step": 5667 }, { "epoch": 0.478498992222703, "grad_norm": 0.1376953125, "learning_rate": 2.9784246872026573e-05, "loss": 1.575839638710022, "step": 5668 }, { "epoch": 0.47858341335753407, "grad_norm": 0.13671875, "learning_rate": 2.97778572989729e-05, "loss": 1.542514443397522, "step": 5669 }, { "epoch": 0.47866783449236516, "grad_norm": 0.1455078125, "learning_rate": 2.9771467401969017e-05, "loss": 1.5695079565048218, "step": 5670 }, { "epoch": 0.47875225562719625, "grad_norm": 0.1337890625, "learning_rate": 2.9765077181448177e-05, "loss": 1.535280704498291, "step": 5671 }, { "epoch": 0.47883667676202735, "grad_norm": 0.1318359375, "learning_rate": 2.975868663784365e-05, "loss": 1.5492262840270996, "step": 5672 }, { "epoch": 0.4789210978968585, "grad_norm": 0.1455078125, "learning_rate": 2.9752295771588735e-05, "loss": 1.515103816986084, "step": 5673 }, { "epoch": 0.4790055190316896, "grad_norm": 0.1474609375, "learning_rate": 2.9745904583116736e-05, "loss": 1.5307033061981201, "step": 5674 }, { "epoch": 0.4790899401665207, "grad_norm": 0.1396484375, "learning_rate": 2.9739513072861003e-05, "loss": 1.517216682434082, "step": 5675 }, { "epoch": 0.47917436130135177, "grad_norm": 0.1416015625, "learning_rate": 2.9733121241254884e-05, "loss": 1.524726152420044, "step": 5676 }, { "epoch": 0.4792587824361829, "grad_norm": 0.1357421875, "learning_rate": 2.972672908873178e-05, "loss": 1.5901519060134888, "step": 5677 }, { "epoch": 0.479343203571014, "grad_norm": 0.1787109375, "learning_rate": 2.9720336615725074e-05, "loss": 1.568641185760498, "step": 5678 }, { "epoch": 0.4794276247058451, "grad_norm": 0.13671875, "learning_rate": 2.9713943822668205e-05, "loss": 1.4592571258544922, "step": 5679 }, { "epoch": 0.4795120458406762, "grad_norm": 0.1494140625, "learning_rate": 2.9707550709994607e-05, "loss": 1.543664813041687, "step": 5680 }, { "epoch": 0.47959646697550734, "grad_norm": 0.1337890625, "learning_rate": 2.9701157278137758e-05, "loss": 1.4903109073638916, "step": 5681 }, { "epoch": 0.47968088811033843, "grad_norm": 0.1416015625, "learning_rate": 2.9694763527531155e-05, "loss": 1.4540822505950928, "step": 5682 }, { "epoch": 0.4797653092451695, "grad_norm": 0.13671875, "learning_rate": 2.968836945860829e-05, "loss": 1.5024230480194092, "step": 5683 }, { "epoch": 0.4798497303800006, "grad_norm": 0.12890625, "learning_rate": 2.9681975071802708e-05, "loss": 1.4567523002624512, "step": 5684 }, { "epoch": 0.47993415151483176, "grad_norm": 0.138671875, "learning_rate": 2.967558036754796e-05, "loss": 1.5207929611206055, "step": 5685 }, { "epoch": 0.48001857264966286, "grad_norm": 0.1474609375, "learning_rate": 2.966918534627763e-05, "loss": 1.5355154275894165, "step": 5686 }, { "epoch": 0.48010299378449395, "grad_norm": 0.1337890625, "learning_rate": 2.9662790008425307e-05, "loss": 1.4975935220718384, "step": 5687 }, { "epoch": 0.48018741491932504, "grad_norm": 0.138671875, "learning_rate": 2.965639435442461e-05, "loss": 1.5888571739196777, "step": 5688 }, { "epoch": 0.48027183605415613, "grad_norm": 0.1787109375, "learning_rate": 2.964999838470919e-05, "loss": 1.4998890161514282, "step": 5689 }, { "epoch": 0.4803562571889873, "grad_norm": 0.1328125, "learning_rate": 2.96436020997127e-05, "loss": 1.5006765127182007, "step": 5690 }, { "epoch": 0.48044067832381837, "grad_norm": 0.138671875, "learning_rate": 2.9637205499868825e-05, "loss": 1.4784553050994873, "step": 5691 }, { "epoch": 0.48052509945864946, "grad_norm": 0.1376953125, "learning_rate": 2.9630808585611274e-05, "loss": 1.5229077339172363, "step": 5692 }, { "epoch": 0.48060952059348055, "grad_norm": 0.1357421875, "learning_rate": 2.9624411357373762e-05, "loss": 1.600611686706543, "step": 5693 }, { "epoch": 0.4806939417283117, "grad_norm": 0.142578125, "learning_rate": 2.961801381559005e-05, "loss": 1.5270944833755493, "step": 5694 }, { "epoch": 0.4807783628631428, "grad_norm": 0.138671875, "learning_rate": 2.96116159606939e-05, "loss": 1.5331172943115234, "step": 5695 }, { "epoch": 0.4808627839979739, "grad_norm": 0.140625, "learning_rate": 2.96052177931191e-05, "loss": 1.5087894201278687, "step": 5696 }, { "epoch": 0.480947205132805, "grad_norm": 0.1533203125, "learning_rate": 2.959881931329947e-05, "loss": 1.5442538261413574, "step": 5697 }, { "epoch": 0.4810316262676361, "grad_norm": 0.1572265625, "learning_rate": 2.9592420521668828e-05, "loss": 1.5737128257751465, "step": 5698 }, { "epoch": 0.4811160474024672, "grad_norm": 0.1376953125, "learning_rate": 2.958602141866105e-05, "loss": 1.5328831672668457, "step": 5699 }, { "epoch": 0.4812004685372983, "grad_norm": 0.1328125, "learning_rate": 2.957962200470999e-05, "loss": 1.4762308597564697, "step": 5700 }, { "epoch": 0.4812848896721294, "grad_norm": 0.1328125, "learning_rate": 2.957322228024955e-05, "loss": 1.4557503461837769, "step": 5701 }, { "epoch": 0.48136931080696055, "grad_norm": 0.142578125, "learning_rate": 2.956682224571364e-05, "loss": 1.697293758392334, "step": 5702 }, { "epoch": 0.48145373194179164, "grad_norm": 0.134765625, "learning_rate": 2.9560421901536207e-05, "loss": 1.5715727806091309, "step": 5703 }, { "epoch": 0.48153815307662273, "grad_norm": 0.1376953125, "learning_rate": 2.9554021248151213e-05, "loss": 1.5058152675628662, "step": 5704 }, { "epoch": 0.4816225742114538, "grad_norm": 0.150390625, "learning_rate": 2.9547620285992627e-05, "loss": 1.564043402671814, "step": 5705 }, { "epoch": 0.4817069953462849, "grad_norm": 0.142578125, "learning_rate": 2.9541219015494458e-05, "loss": 1.585806965827942, "step": 5706 }, { "epoch": 0.48179141648111606, "grad_norm": 0.14453125, "learning_rate": 2.9534817437090722e-05, "loss": 1.5913835763931274, "step": 5707 }, { "epoch": 0.48187583761594716, "grad_norm": 0.1416015625, "learning_rate": 2.952841555121547e-05, "loss": 1.5640908479690552, "step": 5708 }, { "epoch": 0.48196025875077825, "grad_norm": 0.14453125, "learning_rate": 2.952201335830275e-05, "loss": 1.553600788116455, "step": 5709 }, { "epoch": 0.48204467988560934, "grad_norm": 0.1884765625, "learning_rate": 2.9515610858786657e-05, "loss": 1.497139573097229, "step": 5710 }, { "epoch": 0.4821291010204405, "grad_norm": 0.1328125, "learning_rate": 2.9509208053101296e-05, "loss": 1.5877200365066528, "step": 5711 }, { "epoch": 0.4822135221552716, "grad_norm": 0.1484375, "learning_rate": 2.9502804941680784e-05, "loss": 1.5564885139465332, "step": 5712 }, { "epoch": 0.48229794329010267, "grad_norm": 0.1513671875, "learning_rate": 2.9496401524959285e-05, "loss": 1.5546607971191406, "step": 5713 }, { "epoch": 0.48238236442493376, "grad_norm": 0.1416015625, "learning_rate": 2.9489997803370946e-05, "loss": 1.517285704612732, "step": 5714 }, { "epoch": 0.4824667855597649, "grad_norm": 0.1357421875, "learning_rate": 2.9483593777349967e-05, "loss": 1.4536809921264648, "step": 5715 }, { "epoch": 0.482551206694596, "grad_norm": 0.1357421875, "learning_rate": 2.947718944733055e-05, "loss": 1.5684479475021362, "step": 5716 }, { "epoch": 0.4826356278294271, "grad_norm": 0.1435546875, "learning_rate": 2.9470784813746926e-05, "loss": 1.6239827871322632, "step": 5717 }, { "epoch": 0.4827200489642582, "grad_norm": 0.140625, "learning_rate": 2.9464379877033348e-05, "loss": 1.4959362745285034, "step": 5718 }, { "epoch": 0.48280447009908933, "grad_norm": 0.1435546875, "learning_rate": 2.9457974637624085e-05, "loss": 1.574338436126709, "step": 5719 }, { "epoch": 0.4828888912339204, "grad_norm": 0.162109375, "learning_rate": 2.9451569095953423e-05, "loss": 1.5222053527832031, "step": 5720 }, { "epoch": 0.4829733123687515, "grad_norm": 0.140625, "learning_rate": 2.9445163252455676e-05, "loss": 1.568172812461853, "step": 5721 }, { "epoch": 0.4830577335035826, "grad_norm": 0.1328125, "learning_rate": 2.9438757107565174e-05, "loss": 1.54530930519104, "step": 5722 }, { "epoch": 0.4831421546384137, "grad_norm": 0.1376953125, "learning_rate": 2.943235066171628e-05, "loss": 1.4723944664001465, "step": 5723 }, { "epoch": 0.48322657577324485, "grad_norm": 0.1396484375, "learning_rate": 2.942594391534334e-05, "loss": 1.519835114479065, "step": 5724 }, { "epoch": 0.48331099690807594, "grad_norm": 0.1337890625, "learning_rate": 2.941953686888078e-05, "loss": 1.546875238418579, "step": 5725 }, { "epoch": 0.48339541804290703, "grad_norm": 0.14453125, "learning_rate": 2.941312952276299e-05, "loss": 1.5530681610107422, "step": 5726 }, { "epoch": 0.4834798391777381, "grad_norm": 0.12890625, "learning_rate": 2.940672187742441e-05, "loss": 1.4845300912857056, "step": 5727 }, { "epoch": 0.48356426031256927, "grad_norm": 0.134765625, "learning_rate": 2.94003139332995e-05, "loss": 1.5591272115707397, "step": 5728 }, { "epoch": 0.48364868144740036, "grad_norm": 0.14453125, "learning_rate": 2.939390569082272e-05, "loss": 1.5235110521316528, "step": 5729 }, { "epoch": 0.48373310258223146, "grad_norm": 0.1376953125, "learning_rate": 2.9387497150428584e-05, "loss": 1.4806296825408936, "step": 5730 }, { "epoch": 0.48381752371706255, "grad_norm": 0.1552734375, "learning_rate": 2.9381088312551586e-05, "loss": 1.5294036865234375, "step": 5731 }, { "epoch": 0.4839019448518937, "grad_norm": 0.1328125, "learning_rate": 2.937467917762627e-05, "loss": 1.5091521739959717, "step": 5732 }, { "epoch": 0.4839863659867248, "grad_norm": 0.1455078125, "learning_rate": 2.936826974608719e-05, "loss": 1.5295535326004028, "step": 5733 }, { "epoch": 0.4840707871215559, "grad_norm": 0.1376953125, "learning_rate": 2.9361860018368924e-05, "loss": 1.5577384233474731, "step": 5734 }, { "epoch": 0.48415520825638697, "grad_norm": 0.142578125, "learning_rate": 2.935544999490607e-05, "loss": 1.5186294317245483, "step": 5735 }, { "epoch": 0.4842396293912181, "grad_norm": 0.14453125, "learning_rate": 2.9349039676133228e-05, "loss": 1.561590552330017, "step": 5736 }, { "epoch": 0.4843240505260492, "grad_norm": 0.13671875, "learning_rate": 2.9342629062485043e-05, "loss": 1.4060723781585693, "step": 5737 }, { "epoch": 0.4844084716608803, "grad_norm": 0.130859375, "learning_rate": 2.933621815439617e-05, "loss": 1.4839211702346802, "step": 5738 }, { "epoch": 0.4844928927957114, "grad_norm": 0.134765625, "learning_rate": 2.9329806952301285e-05, "loss": 1.506730318069458, "step": 5739 }, { "epoch": 0.4845773139305425, "grad_norm": 0.1376953125, "learning_rate": 2.932339545663509e-05, "loss": 1.5331549644470215, "step": 5740 }, { "epoch": 0.48466173506537363, "grad_norm": 0.134765625, "learning_rate": 2.9316983667832276e-05, "loss": 1.5030597448349, "step": 5741 }, { "epoch": 0.4847461562002047, "grad_norm": 0.1455078125, "learning_rate": 2.93105715863276e-05, "loss": 1.5453894138336182, "step": 5742 }, { "epoch": 0.4848305773350358, "grad_norm": 0.1357421875, "learning_rate": 2.9304159212555804e-05, "loss": 1.519299030303955, "step": 5743 }, { "epoch": 0.4849149984698669, "grad_norm": 0.13671875, "learning_rate": 2.929774654695167e-05, "loss": 1.5629521608352661, "step": 5744 }, { "epoch": 0.48499941960469806, "grad_norm": 0.1328125, "learning_rate": 2.929133358995e-05, "loss": 1.4655455350875854, "step": 5745 }, { "epoch": 0.48508384073952915, "grad_norm": 0.13671875, "learning_rate": 2.9284920341985578e-05, "loss": 1.6279224157333374, "step": 5746 }, { "epoch": 0.48516826187436024, "grad_norm": 0.1396484375, "learning_rate": 2.9278506803493276e-05, "loss": 1.52908194065094, "step": 5747 }, { "epoch": 0.48525268300919133, "grad_norm": 0.130859375, "learning_rate": 2.9272092974907917e-05, "loss": 1.4804643392562866, "step": 5748 }, { "epoch": 0.4853371041440225, "grad_norm": 0.1455078125, "learning_rate": 2.9265678856664393e-05, "loss": 1.5182267427444458, "step": 5749 }, { "epoch": 0.48542152527885357, "grad_norm": 0.1416015625, "learning_rate": 2.925926444919759e-05, "loss": 1.5605508089065552, "step": 5750 }, { "epoch": 0.48550594641368466, "grad_norm": 0.13671875, "learning_rate": 2.9252849752942403e-05, "loss": 1.485300898551941, "step": 5751 }, { "epoch": 0.48559036754851576, "grad_norm": 0.146484375, "learning_rate": 2.9246434768333796e-05, "loss": 1.5621418952941895, "step": 5752 }, { "epoch": 0.4856747886833469, "grad_norm": 0.134765625, "learning_rate": 2.9240019495806704e-05, "loss": 1.4706242084503174, "step": 5753 }, { "epoch": 0.485759209818178, "grad_norm": 0.142578125, "learning_rate": 2.9233603935796094e-05, "loss": 1.5831682682037354, "step": 5754 }, { "epoch": 0.4858436309530091, "grad_norm": 0.1376953125, "learning_rate": 2.9227188088736958e-05, "loss": 1.5737290382385254, "step": 5755 }, { "epoch": 0.4859280520878402, "grad_norm": 0.1318359375, "learning_rate": 2.922077195506432e-05, "loss": 1.5001819133758545, "step": 5756 }, { "epoch": 0.48601247322267127, "grad_norm": 0.1494140625, "learning_rate": 2.9214355535213183e-05, "loss": 1.4754765033721924, "step": 5757 }, { "epoch": 0.4860968943575024, "grad_norm": 0.138671875, "learning_rate": 2.920793882961862e-05, "loss": 1.5507447719573975, "step": 5758 }, { "epoch": 0.4861813154923335, "grad_norm": 0.1474609375, "learning_rate": 2.9201521838715696e-05, "loss": 1.5576399564743042, "step": 5759 }, { "epoch": 0.4862657366271646, "grad_norm": 0.1328125, "learning_rate": 2.9195104562939474e-05, "loss": 1.475473165512085, "step": 5760 }, { "epoch": 0.4863501577619957, "grad_norm": 0.1337890625, "learning_rate": 2.9188687002725096e-05, "loss": 1.4554885625839233, "step": 5761 }, { "epoch": 0.48643457889682684, "grad_norm": 0.14453125, "learning_rate": 2.9182269158507663e-05, "loss": 1.5400282144546509, "step": 5762 }, { "epoch": 0.48651900003165793, "grad_norm": 0.138671875, "learning_rate": 2.9175851030722328e-05, "loss": 1.6055001020431519, "step": 5763 }, { "epoch": 0.486603421166489, "grad_norm": 0.1376953125, "learning_rate": 2.9169432619804253e-05, "loss": 1.5039751529693604, "step": 5764 }, { "epoch": 0.4866878423013201, "grad_norm": 0.1455078125, "learning_rate": 2.916301392618863e-05, "loss": 1.493513584136963, "step": 5765 }, { "epoch": 0.48677226343615126, "grad_norm": 0.142578125, "learning_rate": 2.9156594950310663e-05, "loss": 1.4799728393554688, "step": 5766 }, { "epoch": 0.48685668457098236, "grad_norm": 0.13671875, "learning_rate": 2.9150175692605552e-05, "loss": 1.534011960029602, "step": 5767 }, { "epoch": 0.48694110570581345, "grad_norm": 0.158203125, "learning_rate": 2.914375615350856e-05, "loss": 1.5725853443145752, "step": 5768 }, { "epoch": 0.48702552684064454, "grad_norm": 0.15234375, "learning_rate": 2.913733633345494e-05, "loss": 1.5512787103652954, "step": 5769 }, { "epoch": 0.4871099479754757, "grad_norm": 0.1474609375, "learning_rate": 2.9130916232879972e-05, "loss": 1.5300723314285278, "step": 5770 }, { "epoch": 0.4871943691103068, "grad_norm": 0.1337890625, "learning_rate": 2.912449585221896e-05, "loss": 1.450385570526123, "step": 5771 }, { "epoch": 0.48727879024513787, "grad_norm": 0.1357421875, "learning_rate": 2.9118075191907206e-05, "loss": 1.5178107023239136, "step": 5772 }, { "epoch": 0.48736321137996896, "grad_norm": 0.1357421875, "learning_rate": 2.9111654252380062e-05, "loss": 1.5449087619781494, "step": 5773 }, { "epoch": 0.48744763251480006, "grad_norm": 0.146484375, "learning_rate": 2.910523303407287e-05, "loss": 1.5250136852264404, "step": 5774 }, { "epoch": 0.4875320536496312, "grad_norm": 0.14453125, "learning_rate": 2.9098811537421016e-05, "loss": 1.5270699262619019, "step": 5775 }, { "epoch": 0.4876164747844623, "grad_norm": 0.1337890625, "learning_rate": 2.909238976285989e-05, "loss": 1.4672988653182983, "step": 5776 }, { "epoch": 0.4877008959192934, "grad_norm": 0.1484375, "learning_rate": 2.9085967710824895e-05, "loss": 1.5511233806610107, "step": 5777 }, { "epoch": 0.4877853170541245, "grad_norm": 0.142578125, "learning_rate": 2.9079545381751473e-05, "loss": 1.5666844844818115, "step": 5778 }, { "epoch": 0.4878697381889556, "grad_norm": 0.1416015625, "learning_rate": 2.9073122776075064e-05, "loss": 1.4789479970932007, "step": 5779 }, { "epoch": 0.4879541593237867, "grad_norm": 0.1328125, "learning_rate": 2.9066699894231136e-05, "loss": 1.5226397514343262, "step": 5780 }, { "epoch": 0.4880385804586178, "grad_norm": 0.1396484375, "learning_rate": 2.906027673665519e-05, "loss": 1.566487193107605, "step": 5781 }, { "epoch": 0.4881230015934489, "grad_norm": 0.13671875, "learning_rate": 2.9053853303782713e-05, "loss": 1.4858349561691284, "step": 5782 }, { "epoch": 0.48820742272828005, "grad_norm": 0.138671875, "learning_rate": 2.9047429596049247e-05, "loss": 1.582663893699646, "step": 5783 }, { "epoch": 0.48829184386311114, "grad_norm": 0.1396484375, "learning_rate": 2.9041005613890322e-05, "loss": 1.5354750156402588, "step": 5784 }, { "epoch": 0.48837626499794223, "grad_norm": 0.130859375, "learning_rate": 2.90345813577415e-05, "loss": 1.448378562927246, "step": 5785 }, { "epoch": 0.4884606861327733, "grad_norm": 0.1416015625, "learning_rate": 2.9028156828038366e-05, "loss": 1.517724871635437, "step": 5786 }, { "epoch": 0.4885451072676044, "grad_norm": 0.1328125, "learning_rate": 2.9021732025216514e-05, "loss": 1.5458098649978638, "step": 5787 }, { "epoch": 0.48862952840243556, "grad_norm": 0.140625, "learning_rate": 2.9015306949711568e-05, "loss": 1.4894847869873047, "step": 5788 }, { "epoch": 0.48871394953726666, "grad_norm": 0.1376953125, "learning_rate": 2.900888160195916e-05, "loss": 1.5058515071868896, "step": 5789 }, { "epoch": 0.48879837067209775, "grad_norm": 0.158203125, "learning_rate": 2.9002455982394944e-05, "loss": 1.61161470413208, "step": 5790 }, { "epoch": 0.48888279180692884, "grad_norm": 0.138671875, "learning_rate": 2.8996030091454585e-05, "loss": 1.5693646669387817, "step": 5791 }, { "epoch": 0.48896721294176, "grad_norm": 0.1337890625, "learning_rate": 2.8989603929573783e-05, "loss": 1.4833520650863647, "step": 5792 }, { "epoch": 0.4890516340765911, "grad_norm": 0.140625, "learning_rate": 2.8983177497188246e-05, "loss": 1.5304057598114014, "step": 5793 }, { "epoch": 0.48913605521142217, "grad_norm": 0.158203125, "learning_rate": 2.8976750794733704e-05, "loss": 1.5400110483169556, "step": 5794 }, { "epoch": 0.48922047634625326, "grad_norm": 0.1328125, "learning_rate": 2.8970323822645895e-05, "loss": 1.5766135454177856, "step": 5795 }, { "epoch": 0.4893048974810844, "grad_norm": 0.1416015625, "learning_rate": 2.8963896581360584e-05, "loss": 1.5221529006958008, "step": 5796 }, { "epoch": 0.4893893186159155, "grad_norm": 0.1357421875, "learning_rate": 2.8957469071313564e-05, "loss": 1.6071476936340332, "step": 5797 }, { "epoch": 0.4894737397507466, "grad_norm": 0.1416015625, "learning_rate": 2.895104129294063e-05, "loss": 1.4988148212432861, "step": 5798 }, { "epoch": 0.4895581608855777, "grad_norm": 0.1396484375, "learning_rate": 2.8944613246677586e-05, "loss": 1.5199089050292969, "step": 5799 }, { "epoch": 0.48964258202040883, "grad_norm": 0.1396484375, "learning_rate": 2.8938184932960292e-05, "loss": 1.4821363687515259, "step": 5800 }, { "epoch": 0.4897270031552399, "grad_norm": 0.1435546875, "learning_rate": 2.8931756352224593e-05, "loss": 1.5493758916854858, "step": 5801 }, { "epoch": 0.489811424290071, "grad_norm": 0.13671875, "learning_rate": 2.8925327504906368e-05, "loss": 1.4959056377410889, "step": 5802 }, { "epoch": 0.4898958454249021, "grad_norm": 0.1416015625, "learning_rate": 2.8918898391441497e-05, "loss": 1.6064305305480957, "step": 5803 }, { "epoch": 0.4899802665597332, "grad_norm": 0.1376953125, "learning_rate": 2.891246901226589e-05, "loss": 1.6303565502166748, "step": 5804 }, { "epoch": 0.49006468769456435, "grad_norm": 0.14453125, "learning_rate": 2.8906039367815486e-05, "loss": 1.6092772483825684, "step": 5805 }, { "epoch": 0.49014910882939544, "grad_norm": 0.1357421875, "learning_rate": 2.8899609458526224e-05, "loss": 1.5789692401885986, "step": 5806 }, { "epoch": 0.49023352996422653, "grad_norm": 0.138671875, "learning_rate": 2.8893179284834072e-05, "loss": 1.488218069076538, "step": 5807 }, { "epoch": 0.4903179510990576, "grad_norm": 0.142578125, "learning_rate": 2.8886748847174995e-05, "loss": 1.5282641649246216, "step": 5808 }, { "epoch": 0.4904023722338888, "grad_norm": 0.1376953125, "learning_rate": 2.8880318145985008e-05, "loss": 1.581513524055481, "step": 5809 }, { "epoch": 0.49048679336871986, "grad_norm": 0.1396484375, "learning_rate": 2.8873887181700127e-05, "loss": 1.4752898216247559, "step": 5810 }, { "epoch": 0.49057121450355096, "grad_norm": 0.1337890625, "learning_rate": 2.886745595475638e-05, "loss": 1.528799057006836, "step": 5811 }, { "epoch": 0.49065563563838205, "grad_norm": 0.1416015625, "learning_rate": 2.8861024465589826e-05, "loss": 1.579378604888916, "step": 5812 }, { "epoch": 0.4907400567732132, "grad_norm": 0.13671875, "learning_rate": 2.8854592714636525e-05, "loss": 1.5197845697402954, "step": 5813 }, { "epoch": 0.4908244779080443, "grad_norm": 0.1435546875, "learning_rate": 2.8848160702332584e-05, "loss": 1.4655530452728271, "step": 5814 }, { "epoch": 0.4909088990428754, "grad_norm": 0.1396484375, "learning_rate": 2.884172842911409e-05, "loss": 1.4900949001312256, "step": 5815 }, { "epoch": 0.49099332017770647, "grad_norm": 0.140625, "learning_rate": 2.883529589541718e-05, "loss": 1.5097163915634155, "step": 5816 }, { "epoch": 0.4910777413125376, "grad_norm": 0.1376953125, "learning_rate": 2.8828863101677987e-05, "loss": 1.5102388858795166, "step": 5817 }, { "epoch": 0.4911621624473687, "grad_norm": 0.14453125, "learning_rate": 2.8822430048332665e-05, "loss": 1.4665333032608032, "step": 5818 }, { "epoch": 0.4912465835821998, "grad_norm": 0.142578125, "learning_rate": 2.881599673581741e-05, "loss": 1.5507184267044067, "step": 5819 }, { "epoch": 0.4913310047170309, "grad_norm": 0.1513671875, "learning_rate": 2.88095631645684e-05, "loss": 1.4665082693099976, "step": 5820 }, { "epoch": 0.491415425851862, "grad_norm": 0.142578125, "learning_rate": 2.8803129335021844e-05, "loss": 1.570966124534607, "step": 5821 }, { "epoch": 0.49149984698669313, "grad_norm": 0.1435546875, "learning_rate": 2.879669524761398e-05, "loss": 1.5362462997436523, "step": 5822 }, { "epoch": 0.4915842681215242, "grad_norm": 0.142578125, "learning_rate": 2.8790260902781053e-05, "loss": 1.475791096687317, "step": 5823 }, { "epoch": 0.4916686892563553, "grad_norm": 0.14453125, "learning_rate": 2.8783826300959332e-05, "loss": 1.5328134298324585, "step": 5824 }, { "epoch": 0.4917531103911864, "grad_norm": 0.138671875, "learning_rate": 2.8777391442585088e-05, "loss": 1.5055335760116577, "step": 5825 }, { "epoch": 0.49183753152601756, "grad_norm": 0.13671875, "learning_rate": 2.8770956328094627e-05, "loss": 1.552043080329895, "step": 5826 }, { "epoch": 0.49192195266084865, "grad_norm": 0.134765625, "learning_rate": 2.8764520957924258e-05, "loss": 1.522213339805603, "step": 5827 }, { "epoch": 0.49200637379567974, "grad_norm": 0.1494140625, "learning_rate": 2.875808533251032e-05, "loss": 1.5596803426742554, "step": 5828 }, { "epoch": 0.49209079493051083, "grad_norm": 0.1416015625, "learning_rate": 2.875164945228917e-05, "loss": 1.444332242012024, "step": 5829 }, { "epoch": 0.492175216065342, "grad_norm": 0.142578125, "learning_rate": 2.8745213317697162e-05, "loss": 1.5422937870025635, "step": 5830 }, { "epoch": 0.4922596372001731, "grad_norm": 0.1435546875, "learning_rate": 2.8738776929170692e-05, "loss": 1.528889536857605, "step": 5831 }, { "epoch": 0.49234405833500416, "grad_norm": 0.150390625, "learning_rate": 2.873234028714616e-05, "loss": 1.4836221933364868, "step": 5832 }, { "epoch": 0.49242847946983526, "grad_norm": 0.1435546875, "learning_rate": 2.8725903392059984e-05, "loss": 1.5760166645050049, "step": 5833 }, { "epoch": 0.4925129006046664, "grad_norm": 0.1357421875, "learning_rate": 2.8719466244348604e-05, "loss": 1.4782658815383911, "step": 5834 }, { "epoch": 0.4925973217394975, "grad_norm": 0.1513671875, "learning_rate": 2.8713028844448464e-05, "loss": 1.6074800491333008, "step": 5835 }, { "epoch": 0.4926817428743286, "grad_norm": 0.142578125, "learning_rate": 2.870659119279605e-05, "loss": 1.5379596948623657, "step": 5836 }, { "epoch": 0.4927661640091597, "grad_norm": 0.1376953125, "learning_rate": 2.8700153289827842e-05, "loss": 1.5047484636306763, "step": 5837 }, { "epoch": 0.49285058514399077, "grad_norm": 0.1396484375, "learning_rate": 2.8693715135980352e-05, "loss": 1.5465142726898193, "step": 5838 }, { "epoch": 0.4929350062788219, "grad_norm": 0.146484375, "learning_rate": 2.8687276731690092e-05, "loss": 1.6514419317245483, "step": 5839 }, { "epoch": 0.493019427413653, "grad_norm": 0.1533203125, "learning_rate": 2.8680838077393606e-05, "loss": 1.5083616971969604, "step": 5840 }, { "epoch": 0.4931038485484841, "grad_norm": 0.1474609375, "learning_rate": 2.8674399173527454e-05, "loss": 1.5855216979980469, "step": 5841 }, { "epoch": 0.4931882696833152, "grad_norm": 0.12890625, "learning_rate": 2.8667960020528207e-05, "loss": 1.456046223640442, "step": 5842 }, { "epoch": 0.49327269081814634, "grad_norm": 0.146484375, "learning_rate": 2.8661520618832454e-05, "loss": 1.4776110649108887, "step": 5843 }, { "epoch": 0.49335711195297743, "grad_norm": 0.13671875, "learning_rate": 2.8655080968876795e-05, "loss": 1.516345739364624, "step": 5844 }, { "epoch": 0.4934415330878085, "grad_norm": 0.13671875, "learning_rate": 2.8648641071097866e-05, "loss": 1.5339446067810059, "step": 5845 }, { "epoch": 0.4935259542226396, "grad_norm": 0.1416015625, "learning_rate": 2.86422009259323e-05, "loss": 1.5060118436813354, "step": 5846 }, { "epoch": 0.49361037535747077, "grad_norm": 0.14453125, "learning_rate": 2.8635760533816757e-05, "loss": 1.624232292175293, "step": 5847 }, { "epoch": 0.49369479649230186, "grad_norm": 0.1416015625, "learning_rate": 2.8629319895187918e-05, "loss": 1.5124558210372925, "step": 5848 }, { "epoch": 0.49377921762713295, "grad_norm": 0.138671875, "learning_rate": 2.8622879010482452e-05, "loss": 1.5020647048950195, "step": 5849 }, { "epoch": 0.49386363876196404, "grad_norm": 0.1494140625, "learning_rate": 2.8616437880137093e-05, "loss": 1.5811489820480347, "step": 5850 }, { "epoch": 0.4939480598967952, "grad_norm": 0.1416015625, "learning_rate": 2.860999650458855e-05, "loss": 1.5060045719146729, "step": 5851 }, { "epoch": 0.4940324810316263, "grad_norm": 0.140625, "learning_rate": 2.860355488427356e-05, "loss": 1.502180576324463, "step": 5852 }, { "epoch": 0.4941169021664574, "grad_norm": 0.1396484375, "learning_rate": 2.8597113019628897e-05, "loss": 1.6024069786071777, "step": 5853 }, { "epoch": 0.49420132330128846, "grad_norm": 0.150390625, "learning_rate": 2.8590670911091317e-05, "loss": 1.5067648887634277, "step": 5854 }, { "epoch": 0.49428574443611956, "grad_norm": 0.140625, "learning_rate": 2.8584228559097625e-05, "loss": 1.5074338912963867, "step": 5855 }, { "epoch": 0.4943701655709507, "grad_norm": 0.130859375, "learning_rate": 2.8577785964084615e-05, "loss": 1.6098182201385498, "step": 5856 }, { "epoch": 0.4944545867057818, "grad_norm": 0.1337890625, "learning_rate": 2.857134312648912e-05, "loss": 1.4724724292755127, "step": 5857 }, { "epoch": 0.4945390078406129, "grad_norm": 0.140625, "learning_rate": 2.8564900046747977e-05, "loss": 1.53104567527771, "step": 5858 }, { "epoch": 0.494623428975444, "grad_norm": 0.1337890625, "learning_rate": 2.8558456725298037e-05, "loss": 1.522346019744873, "step": 5859 }, { "epoch": 0.4947078501102751, "grad_norm": 0.138671875, "learning_rate": 2.8552013162576186e-05, "loss": 1.553999900817871, "step": 5860 }, { "epoch": 0.4947922712451062, "grad_norm": 0.146484375, "learning_rate": 2.8545569359019304e-05, "loss": 1.4852381944656372, "step": 5861 }, { "epoch": 0.4948766923799373, "grad_norm": 0.1484375, "learning_rate": 2.853912531506429e-05, "loss": 1.5036407709121704, "step": 5862 }, { "epoch": 0.4949611135147684, "grad_norm": 0.1474609375, "learning_rate": 2.8532681031148078e-05, "loss": 1.4508768320083618, "step": 5863 }, { "epoch": 0.49504553464959955, "grad_norm": 0.1455078125, "learning_rate": 2.8526236507707595e-05, "loss": 1.6368134021759033, "step": 5864 }, { "epoch": 0.49512995578443064, "grad_norm": 0.1416015625, "learning_rate": 2.8519791745179807e-05, "loss": 1.561327576637268, "step": 5865 }, { "epoch": 0.49521437691926173, "grad_norm": 0.134765625, "learning_rate": 2.851334674400168e-05, "loss": 1.5192701816558838, "step": 5866 }, { "epoch": 0.4952987980540928, "grad_norm": 0.1513671875, "learning_rate": 2.850690150461019e-05, "loss": 1.48004150390625, "step": 5867 }, { "epoch": 0.495383219188924, "grad_norm": 0.154296875, "learning_rate": 2.850045602744236e-05, "loss": 1.6716097593307495, "step": 5868 }, { "epoch": 0.49546764032375507, "grad_norm": 0.1494140625, "learning_rate": 2.8494010312935183e-05, "loss": 1.5903186798095703, "step": 5869 }, { "epoch": 0.49555206145858616, "grad_norm": 0.142578125, "learning_rate": 2.848756436152572e-05, "loss": 1.5396690368652344, "step": 5870 }, { "epoch": 0.49563648259341725, "grad_norm": 0.138671875, "learning_rate": 2.8481118173651007e-05, "loss": 1.514467716217041, "step": 5871 }, { "epoch": 0.49572090372824834, "grad_norm": 0.142578125, "learning_rate": 2.847467174974811e-05, "loss": 1.4922592639923096, "step": 5872 }, { "epoch": 0.4958053248630795, "grad_norm": 0.1494140625, "learning_rate": 2.846822509025412e-05, "loss": 1.5178594589233398, "step": 5873 }, { "epoch": 0.4958897459979106, "grad_norm": 0.1376953125, "learning_rate": 2.8461778195606137e-05, "loss": 1.4803842306137085, "step": 5874 }, { "epoch": 0.4959741671327417, "grad_norm": 0.1416015625, "learning_rate": 2.8455331066241263e-05, "loss": 1.614217758178711, "step": 5875 }, { "epoch": 0.49605858826757276, "grad_norm": 0.1455078125, "learning_rate": 2.844888370259664e-05, "loss": 1.5382949113845825, "step": 5876 }, { "epoch": 0.4961430094024039, "grad_norm": 0.1376953125, "learning_rate": 2.8442436105109415e-05, "loss": 1.592962622642517, "step": 5877 }, { "epoch": 0.496227430537235, "grad_norm": 0.1474609375, "learning_rate": 2.8435988274216746e-05, "loss": 1.5649380683898926, "step": 5878 }, { "epoch": 0.4963118516720661, "grad_norm": 0.1416015625, "learning_rate": 2.8429540210355813e-05, "loss": 1.570400357246399, "step": 5879 }, { "epoch": 0.4963962728068972, "grad_norm": 0.146484375, "learning_rate": 2.842309191396381e-05, "loss": 1.5799616575241089, "step": 5880 }, { "epoch": 0.49648069394172833, "grad_norm": 0.1328125, "learning_rate": 2.8416643385477948e-05, "loss": 1.4698556661605835, "step": 5881 }, { "epoch": 0.4965651150765594, "grad_norm": 0.1328125, "learning_rate": 2.8410194625335444e-05, "loss": 1.471370816230774, "step": 5882 }, { "epoch": 0.4966495362113905, "grad_norm": 0.1416015625, "learning_rate": 2.8403745633973556e-05, "loss": 1.542663335800171, "step": 5883 }, { "epoch": 0.4967339573462216, "grad_norm": 0.1435546875, "learning_rate": 2.8397296411829532e-05, "loss": 1.552844524383545, "step": 5884 }, { "epoch": 0.49681837848105276, "grad_norm": 0.1279296875, "learning_rate": 2.8390846959340638e-05, "loss": 1.4985928535461426, "step": 5885 }, { "epoch": 0.49690279961588385, "grad_norm": 0.15234375, "learning_rate": 2.8384397276944185e-05, "loss": 1.532600998878479, "step": 5886 }, { "epoch": 0.49698722075071494, "grad_norm": 0.1318359375, "learning_rate": 2.837794736507745e-05, "loss": 1.511593222618103, "step": 5887 }, { "epoch": 0.49707164188554603, "grad_norm": 0.1396484375, "learning_rate": 2.8371497224177762e-05, "loss": 1.534597635269165, "step": 5888 }, { "epoch": 0.4971560630203771, "grad_norm": 0.1455078125, "learning_rate": 2.8365046854682464e-05, "loss": 1.4764986038208008, "step": 5889 }, { "epoch": 0.4972404841552083, "grad_norm": 0.146484375, "learning_rate": 2.8358596257028898e-05, "loss": 1.5117262601852417, "step": 5890 }, { "epoch": 0.49732490529003937, "grad_norm": 0.1474609375, "learning_rate": 2.8352145431654436e-05, "loss": 1.6266571283340454, "step": 5891 }, { "epoch": 0.49740932642487046, "grad_norm": 0.1455078125, "learning_rate": 2.8345694378996458e-05, "loss": 1.5689805746078491, "step": 5892 }, { "epoch": 0.49749374755970155, "grad_norm": 0.13671875, "learning_rate": 2.8339243099492353e-05, "loss": 1.5531541109085083, "step": 5893 }, { "epoch": 0.4975781686945327, "grad_norm": 0.1357421875, "learning_rate": 2.8332791593579537e-05, "loss": 1.5398132801055908, "step": 5894 }, { "epoch": 0.4976625898293638, "grad_norm": 0.13671875, "learning_rate": 2.8326339861695444e-05, "loss": 1.4979032278060913, "step": 5895 }, { "epoch": 0.4977470109641949, "grad_norm": 0.1416015625, "learning_rate": 2.831988790427752e-05, "loss": 1.6011930704116821, "step": 5896 }, { "epoch": 0.497831432099026, "grad_norm": 0.1435546875, "learning_rate": 2.8313435721763203e-05, "loss": 1.5719506740570068, "step": 5897 }, { "epoch": 0.4979158532338571, "grad_norm": 0.134765625, "learning_rate": 2.830698331458999e-05, "loss": 1.572759747505188, "step": 5898 }, { "epoch": 0.4980002743686882, "grad_norm": 0.1845703125, "learning_rate": 2.8300530683195352e-05, "loss": 1.5871002674102783, "step": 5899 }, { "epoch": 0.4980846955035193, "grad_norm": 0.142578125, "learning_rate": 2.8294077828016808e-05, "loss": 1.5543991327285767, "step": 5900 }, { "epoch": 0.4981691166383504, "grad_norm": 0.1435546875, "learning_rate": 2.8287624749491864e-05, "loss": 1.4745980501174927, "step": 5901 }, { "epoch": 0.49825353777318154, "grad_norm": 0.1416015625, "learning_rate": 2.8281171448058064e-05, "loss": 1.5081192255020142, "step": 5902 }, { "epoch": 0.49833795890801263, "grad_norm": 0.1494140625, "learning_rate": 2.8274717924152948e-05, "loss": 1.4824296236038208, "step": 5903 }, { "epoch": 0.4984223800428437, "grad_norm": 0.134765625, "learning_rate": 2.8268264178214082e-05, "loss": 1.4574588537216187, "step": 5904 }, { "epoch": 0.4985068011776748, "grad_norm": 0.1337890625, "learning_rate": 2.8261810210679058e-05, "loss": 1.5250324010849, "step": 5905 }, { "epoch": 0.4985912223125059, "grad_norm": 0.1328125, "learning_rate": 2.825535602198546e-05, "loss": 1.4854729175567627, "step": 5906 }, { "epoch": 0.49867564344733706, "grad_norm": 0.1376953125, "learning_rate": 2.824890161257089e-05, "loss": 1.4893263578414917, "step": 5907 }, { "epoch": 0.49876006458216815, "grad_norm": 0.1357421875, "learning_rate": 2.8242446982872988e-05, "loss": 1.4679782390594482, "step": 5908 }, { "epoch": 0.49884448571699924, "grad_norm": 0.142578125, "learning_rate": 2.8235992133329386e-05, "loss": 1.5869296789169312, "step": 5909 }, { "epoch": 0.49892890685183033, "grad_norm": 0.1376953125, "learning_rate": 2.8229537064377735e-05, "loss": 1.5766319036483765, "step": 5910 }, { "epoch": 0.4990133279866615, "grad_norm": 0.1328125, "learning_rate": 2.822308177645572e-05, "loss": 1.5059823989868164, "step": 5911 }, { "epoch": 0.4990977491214926, "grad_norm": 0.1484375, "learning_rate": 2.8216626270001e-05, "loss": 1.6112720966339111, "step": 5912 }, { "epoch": 0.49918217025632367, "grad_norm": 0.1416015625, "learning_rate": 2.82101705454513e-05, "loss": 1.6125996112823486, "step": 5913 }, { "epoch": 0.49926659139115476, "grad_norm": 0.1328125, "learning_rate": 2.820371460324431e-05, "loss": 1.5308479070663452, "step": 5914 }, { "epoch": 0.4993510125259859, "grad_norm": 0.1357421875, "learning_rate": 2.8197258443817777e-05, "loss": 1.4366761445999146, "step": 5915 }, { "epoch": 0.499435433660817, "grad_norm": 0.1435546875, "learning_rate": 2.8190802067609424e-05, "loss": 1.5590121746063232, "step": 5916 }, { "epoch": 0.4995198547956481, "grad_norm": 0.1337890625, "learning_rate": 2.8184345475057033e-05, "loss": 1.5091006755828857, "step": 5917 }, { "epoch": 0.4996042759304792, "grad_norm": 0.134765625, "learning_rate": 2.8177888666598362e-05, "loss": 1.5688413381576538, "step": 5918 }, { "epoch": 0.4996886970653103, "grad_norm": 0.1357421875, "learning_rate": 2.8171431642671196e-05, "loss": 1.4755914211273193, "step": 5919 }, { "epoch": 0.4997731182001414, "grad_norm": 0.1455078125, "learning_rate": 2.8164974403713353e-05, "loss": 1.560448169708252, "step": 5920 }, { "epoch": 0.4998575393349725, "grad_norm": 0.142578125, "learning_rate": 2.8158516950162622e-05, "loss": 1.4771865606307983, "step": 5921 }, { "epoch": 0.4999419604698036, "grad_norm": 0.1494140625, "learning_rate": 2.8152059282456867e-05, "loss": 1.5491732358932495, "step": 5922 }, { "epoch": 0.5000263816046348, "grad_norm": 0.12890625, "learning_rate": 2.8145601401033898e-05, "loss": 1.5226690769195557, "step": 5923 }, { "epoch": 0.5001108027394658, "grad_norm": 0.142578125, "learning_rate": 2.8139143306331607e-05, "loss": 1.5435023307800293, "step": 5924 }, { "epoch": 0.5001952238742969, "grad_norm": 0.15625, "learning_rate": 2.8132684998787847e-05, "loss": 1.5541832447052002, "step": 5925 }, { "epoch": 0.500279645009128, "grad_norm": 0.130859375, "learning_rate": 2.812622647884051e-05, "loss": 1.4339438676834106, "step": 5926 }, { "epoch": 0.5003640661439591, "grad_norm": 0.1513671875, "learning_rate": 2.8119767746927518e-05, "loss": 1.522485375404358, "step": 5927 }, { "epoch": 0.5004484872787902, "grad_norm": 0.1416015625, "learning_rate": 2.8113308803486766e-05, "loss": 1.5118995904922485, "step": 5928 }, { "epoch": 0.5005329084136213, "grad_norm": 0.14453125, "learning_rate": 2.810684964895619e-05, "loss": 1.5754889249801636, "step": 5929 }, { "epoch": 0.5006173295484525, "grad_norm": 0.1376953125, "learning_rate": 2.8100390283773743e-05, "loss": 1.5563597679138184, "step": 5930 }, { "epoch": 0.5007017506832836, "grad_norm": 0.1357421875, "learning_rate": 2.809393070837738e-05, "loss": 1.4731645584106445, "step": 5931 }, { "epoch": 0.5007861718181147, "grad_norm": 0.1337890625, "learning_rate": 2.8087470923205085e-05, "loss": 1.4691643714904785, "step": 5932 }, { "epoch": 0.5008705929529458, "grad_norm": 0.15625, "learning_rate": 2.8081010928694833e-05, "loss": 1.6238206624984741, "step": 5933 }, { "epoch": 0.5009550140877769, "grad_norm": 0.138671875, "learning_rate": 2.8074550725284637e-05, "loss": 1.5789440870285034, "step": 5934 }, { "epoch": 0.501039435222608, "grad_norm": 0.1337890625, "learning_rate": 2.806809031341251e-05, "loss": 1.4842100143432617, "step": 5935 }, { "epoch": 0.5011238563574391, "grad_norm": 0.138671875, "learning_rate": 2.8061629693516488e-05, "loss": 1.525134801864624, "step": 5936 }, { "epoch": 0.5012082774922701, "grad_norm": 0.12890625, "learning_rate": 2.8055168866034615e-05, "loss": 1.4832414388656616, "step": 5937 }, { "epoch": 0.5012926986271012, "grad_norm": 0.142578125, "learning_rate": 2.8048707831404946e-05, "loss": 1.5747489929199219, "step": 5938 }, { "epoch": 0.5013771197619324, "grad_norm": 0.15625, "learning_rate": 2.8042246590065557e-05, "loss": 1.5156068801879883, "step": 5939 }, { "epoch": 0.5014615408967635, "grad_norm": 0.142578125, "learning_rate": 2.8035785142454535e-05, "loss": 1.6039345264434814, "step": 5940 }, { "epoch": 0.5015459620315946, "grad_norm": 0.1435546875, "learning_rate": 2.8029323489009985e-05, "loss": 1.584184169769287, "step": 5941 }, { "epoch": 0.5016303831664257, "grad_norm": 0.1435546875, "learning_rate": 2.8022861630170028e-05, "loss": 1.6257908344268799, "step": 5942 }, { "epoch": 0.5017148043012568, "grad_norm": 0.1396484375, "learning_rate": 2.8016399566372774e-05, "loss": 1.604335069656372, "step": 5943 }, { "epoch": 0.5017992254360879, "grad_norm": 0.12890625, "learning_rate": 2.800993729805639e-05, "loss": 1.5452892780303955, "step": 5944 }, { "epoch": 0.501883646570919, "grad_norm": 0.1376953125, "learning_rate": 2.8003474825659015e-05, "loss": 1.5388312339782715, "step": 5945 }, { "epoch": 0.5019680677057501, "grad_norm": 0.15234375, "learning_rate": 2.799701214961883e-05, "loss": 1.4817463159561157, "step": 5946 }, { "epoch": 0.5020524888405813, "grad_norm": 0.1337890625, "learning_rate": 2.799054927037402e-05, "loss": 1.4658825397491455, "step": 5947 }, { "epoch": 0.5021369099754124, "grad_norm": 0.142578125, "learning_rate": 2.7984086188362774e-05, "loss": 1.5065218210220337, "step": 5948 }, { "epoch": 0.5022213311102435, "grad_norm": 0.13671875, "learning_rate": 2.797762290402332e-05, "loss": 1.5385184288024902, "step": 5949 }, { "epoch": 0.5023057522450746, "grad_norm": 0.14453125, "learning_rate": 2.7971159417793867e-05, "loss": 1.4963358640670776, "step": 5950 }, { "epoch": 0.5023901733799057, "grad_norm": 0.14453125, "learning_rate": 2.7964695730112676e-05, "loss": 1.5276232957839966, "step": 5951 }, { "epoch": 0.5024745945147367, "grad_norm": 0.1416015625, "learning_rate": 2.7958231841417977e-05, "loss": 1.534226655960083, "step": 5952 }, { "epoch": 0.5025590156495678, "grad_norm": 0.1494140625, "learning_rate": 2.795176775214805e-05, "loss": 1.6389455795288086, "step": 5953 }, { "epoch": 0.5026434367843989, "grad_norm": 0.1328125, "learning_rate": 2.794530346274118e-05, "loss": 1.4677636623382568, "step": 5954 }, { "epoch": 0.50272785791923, "grad_norm": 0.142578125, "learning_rate": 2.7938838973635657e-05, "loss": 1.5691637992858887, "step": 5955 }, { "epoch": 0.5028122790540612, "grad_norm": 0.1318359375, "learning_rate": 2.7932374285269786e-05, "loss": 1.5177823305130005, "step": 5956 }, { "epoch": 0.5028967001888923, "grad_norm": 0.1396484375, "learning_rate": 2.7925909398081878e-05, "loss": 1.5218292474746704, "step": 5957 }, { "epoch": 0.5029811213237234, "grad_norm": 0.140625, "learning_rate": 2.7919444312510295e-05, "loss": 1.5178338289260864, "step": 5958 }, { "epoch": 0.5030655424585545, "grad_norm": 0.13671875, "learning_rate": 2.7912979028993363e-05, "loss": 1.5631059408187866, "step": 5959 }, { "epoch": 0.5031499635933856, "grad_norm": 0.1357421875, "learning_rate": 2.790651354796945e-05, "loss": 1.528355360031128, "step": 5960 }, { "epoch": 0.5032343847282167, "grad_norm": 0.1337890625, "learning_rate": 2.7900047869876934e-05, "loss": 1.5110700130462646, "step": 5961 }, { "epoch": 0.5033188058630478, "grad_norm": 0.140625, "learning_rate": 2.78935819951542e-05, "loss": 1.5473506450653076, "step": 5962 }, { "epoch": 0.5034032269978789, "grad_norm": 0.12890625, "learning_rate": 2.788711592423966e-05, "loss": 1.5154387950897217, "step": 5963 }, { "epoch": 0.5034876481327101, "grad_norm": 0.1396484375, "learning_rate": 2.788064965757171e-05, "loss": 1.5611783266067505, "step": 5964 }, { "epoch": 0.5035720692675412, "grad_norm": 0.1376953125, "learning_rate": 2.7874183195588793e-05, "loss": 1.571775197982788, "step": 5965 }, { "epoch": 0.5036564904023723, "grad_norm": 0.1396484375, "learning_rate": 2.7867716538729344e-05, "loss": 1.5524197816848755, "step": 5966 }, { "epoch": 0.5037409115372034, "grad_norm": 0.13671875, "learning_rate": 2.7861249687431822e-05, "loss": 1.4963499307632446, "step": 5967 }, { "epoch": 0.5038253326720344, "grad_norm": 0.1455078125, "learning_rate": 2.7854782642134702e-05, "loss": 1.44430673122406, "step": 5968 }, { "epoch": 0.5039097538068655, "grad_norm": 0.142578125, "learning_rate": 2.784831540327645e-05, "loss": 1.5067092180252075, "step": 5969 }, { "epoch": 0.5039941749416966, "grad_norm": 0.224609375, "learning_rate": 2.7841847971295564e-05, "loss": 1.5478790998458862, "step": 5970 }, { "epoch": 0.5040785960765277, "grad_norm": 0.1416015625, "learning_rate": 2.7835380346630558e-05, "loss": 1.5551103353500366, "step": 5971 }, { "epoch": 0.5041630172113588, "grad_norm": 0.1357421875, "learning_rate": 2.7828912529719948e-05, "loss": 1.5238335132598877, "step": 5972 }, { "epoch": 0.50424743834619, "grad_norm": 0.140625, "learning_rate": 2.782244452100227e-05, "loss": 1.5275707244873047, "step": 5973 }, { "epoch": 0.5043318594810211, "grad_norm": 0.1396484375, "learning_rate": 2.7815976320916064e-05, "loss": 1.5692073106765747, "step": 5974 }, { "epoch": 0.5044162806158522, "grad_norm": 0.1484375, "learning_rate": 2.7809507929899903e-05, "loss": 1.471770167350769, "step": 5975 }, { "epoch": 0.5045007017506833, "grad_norm": 0.1416015625, "learning_rate": 2.7803039348392347e-05, "loss": 1.5370917320251465, "step": 5976 }, { "epoch": 0.5045851228855144, "grad_norm": 0.138671875, "learning_rate": 2.779657057683198e-05, "loss": 1.5891873836517334, "step": 5977 }, { "epoch": 0.5046695440203455, "grad_norm": 0.162109375, "learning_rate": 2.779010161565742e-05, "loss": 1.5760587453842163, "step": 5978 }, { "epoch": 0.5047539651551766, "grad_norm": 0.1328125, "learning_rate": 2.7783632465307253e-05, "loss": 1.5502073764801025, "step": 5979 }, { "epoch": 0.5048383862900077, "grad_norm": 0.1298828125, "learning_rate": 2.7777163126220118e-05, "loss": 1.478554129600525, "step": 5980 }, { "epoch": 0.5049228074248389, "grad_norm": 0.146484375, "learning_rate": 2.7770693598834647e-05, "loss": 1.4613499641418457, "step": 5981 }, { "epoch": 0.50500722855967, "grad_norm": 0.1416015625, "learning_rate": 2.7764223883589484e-05, "loss": 1.5399940013885498, "step": 5982 }, { "epoch": 0.505091649694501, "grad_norm": 0.150390625, "learning_rate": 2.7757753980923308e-05, "loss": 1.539679765701294, "step": 5983 }, { "epoch": 0.5051760708293321, "grad_norm": 0.1435546875, "learning_rate": 2.7751283891274772e-05, "loss": 1.5730329751968384, "step": 5984 }, { "epoch": 0.5052604919641632, "grad_norm": 0.1416015625, "learning_rate": 2.7744813615082588e-05, "loss": 1.5237433910369873, "step": 5985 }, { "epoch": 0.5053449130989943, "grad_norm": 0.146484375, "learning_rate": 2.7738343152785434e-05, "loss": 1.5483542680740356, "step": 5986 }, { "epoch": 0.5054293342338254, "grad_norm": 0.1435546875, "learning_rate": 2.7731872504822033e-05, "loss": 1.4844776391983032, "step": 5987 }, { "epoch": 0.5055137553686565, "grad_norm": 0.1328125, "learning_rate": 2.7725401671631113e-05, "loss": 1.5035003423690796, "step": 5988 }, { "epoch": 0.5055981765034876, "grad_norm": 0.15234375, "learning_rate": 2.7718930653651404e-05, "loss": 1.5396908521652222, "step": 5989 }, { "epoch": 0.5056825976383188, "grad_norm": 0.1337890625, "learning_rate": 2.771245945132167e-05, "loss": 1.4993548393249512, "step": 5990 }, { "epoch": 0.5057670187731499, "grad_norm": 0.130859375, "learning_rate": 2.7705988065080658e-05, "loss": 1.518441915512085, "step": 5991 }, { "epoch": 0.505851439907981, "grad_norm": 0.140625, "learning_rate": 2.769951649536715e-05, "loss": 1.5021107196807861, "step": 5992 }, { "epoch": 0.5059358610428121, "grad_norm": 0.130859375, "learning_rate": 2.7693044742619932e-05, "loss": 1.528467059135437, "step": 5993 }, { "epoch": 0.5060202821776432, "grad_norm": 0.138671875, "learning_rate": 2.7686572807277815e-05, "loss": 1.5533231496810913, "step": 5994 }, { "epoch": 0.5061047033124743, "grad_norm": 0.15234375, "learning_rate": 2.7680100689779603e-05, "loss": 1.531506896018982, "step": 5995 }, { "epoch": 0.5061891244473053, "grad_norm": 0.1484375, "learning_rate": 2.7673628390564123e-05, "loss": 1.4349285364151, "step": 5996 }, { "epoch": 0.5062735455821364, "grad_norm": 0.1396484375, "learning_rate": 2.766715591007021e-05, "loss": 1.5739811658859253, "step": 5997 }, { "epoch": 0.5063579667169676, "grad_norm": 0.140625, "learning_rate": 2.7660683248736708e-05, "loss": 1.5730876922607422, "step": 5998 }, { "epoch": 0.5064423878517987, "grad_norm": 0.1396484375, "learning_rate": 2.76542104070025e-05, "loss": 1.5169119834899902, "step": 5999 }, { "epoch": 0.5065268089866298, "grad_norm": 0.1337890625, "learning_rate": 2.764773738530644e-05, "loss": 1.5373895168304443, "step": 6000 }, { "epoch": 0.5066112301214609, "grad_norm": 0.142578125, "learning_rate": 2.7641264184087413e-05, "loss": 1.5674203634262085, "step": 6001 }, { "epoch": 0.506695651256292, "grad_norm": 0.142578125, "learning_rate": 2.7634790803784334e-05, "loss": 1.5365650653839111, "step": 6002 }, { "epoch": 0.5067800723911231, "grad_norm": 0.1416015625, "learning_rate": 2.7628317244836104e-05, "loss": 1.5772037506103516, "step": 6003 }, { "epoch": 0.5068644935259542, "grad_norm": 0.13671875, "learning_rate": 2.762184350768165e-05, "loss": 1.5561399459838867, "step": 6004 }, { "epoch": 0.5069489146607853, "grad_norm": 0.1376953125, "learning_rate": 2.76153695927599e-05, "loss": 1.6020013093948364, "step": 6005 }, { "epoch": 0.5070333357956164, "grad_norm": 0.1806640625, "learning_rate": 2.7608895500509806e-05, "loss": 1.59530508518219, "step": 6006 }, { "epoch": 0.5071177569304476, "grad_norm": 0.1328125, "learning_rate": 2.7602421231370322e-05, "loss": 1.4929919242858887, "step": 6007 }, { "epoch": 0.5072021780652787, "grad_norm": 0.1484375, "learning_rate": 2.759594678578043e-05, "loss": 1.5265238285064697, "step": 6008 }, { "epoch": 0.5072865992001098, "grad_norm": 0.14453125, "learning_rate": 2.758947216417911e-05, "loss": 1.5682728290557861, "step": 6009 }, { "epoch": 0.5073710203349409, "grad_norm": 0.138671875, "learning_rate": 2.7582997367005337e-05, "loss": 1.548087477684021, "step": 6010 }, { "epoch": 0.507455441469772, "grad_norm": 0.1494140625, "learning_rate": 2.7576522394698146e-05, "loss": 1.612128734588623, "step": 6011 }, { "epoch": 0.507539862604603, "grad_norm": 0.1376953125, "learning_rate": 2.757004724769654e-05, "loss": 1.5684696435928345, "step": 6012 }, { "epoch": 0.5076242837394341, "grad_norm": 0.15234375, "learning_rate": 2.756357192643955e-05, "loss": 1.5581837892532349, "step": 6013 }, { "epoch": 0.5077087048742652, "grad_norm": 0.1328125, "learning_rate": 2.7557096431366236e-05, "loss": 1.5594176054000854, "step": 6014 }, { "epoch": 0.5077931260090964, "grad_norm": 0.134765625, "learning_rate": 2.7550620762915618e-05, "loss": 1.5708224773406982, "step": 6015 }, { "epoch": 0.5078775471439275, "grad_norm": 0.1474609375, "learning_rate": 2.7544144921526794e-05, "loss": 1.531911015510559, "step": 6016 }, { "epoch": 0.5079619682787586, "grad_norm": 0.1494140625, "learning_rate": 2.7537668907638824e-05, "loss": 1.5099974870681763, "step": 6017 }, { "epoch": 0.5080463894135897, "grad_norm": 0.1357421875, "learning_rate": 2.75311927216908e-05, "loss": 1.590507984161377, "step": 6018 }, { "epoch": 0.5081308105484208, "grad_norm": 0.13671875, "learning_rate": 2.7524716364121827e-05, "loss": 1.486850619316101, "step": 6019 }, { "epoch": 0.5082152316832519, "grad_norm": 0.1337890625, "learning_rate": 2.7518239835371018e-05, "loss": 1.4945528507232666, "step": 6020 }, { "epoch": 0.508299652818083, "grad_norm": 0.1455078125, "learning_rate": 2.75117631358775e-05, "loss": 1.5242208242416382, "step": 6021 }, { "epoch": 0.5083840739529141, "grad_norm": 0.14453125, "learning_rate": 2.75052862660804e-05, "loss": 1.5692956447601318, "step": 6022 }, { "epoch": 0.5084684950877452, "grad_norm": 0.158203125, "learning_rate": 2.7498809226418866e-05, "loss": 1.471860647201538, "step": 6023 }, { "epoch": 0.5085529162225764, "grad_norm": 0.1337890625, "learning_rate": 2.749233201733206e-05, "loss": 1.5579813718795776, "step": 6024 }, { "epoch": 0.5086373373574075, "grad_norm": 0.1552734375, "learning_rate": 2.748585463925915e-05, "loss": 1.5674786567687988, "step": 6025 }, { "epoch": 0.5087217584922386, "grad_norm": 0.1357421875, "learning_rate": 2.747937709263933e-05, "loss": 1.4873257875442505, "step": 6026 }, { "epoch": 0.5088061796270696, "grad_norm": 0.1328125, "learning_rate": 2.7472899377911782e-05, "loss": 1.4636818170547485, "step": 6027 }, { "epoch": 0.5088906007619007, "grad_norm": 0.142578125, "learning_rate": 2.7466421495515703e-05, "loss": 1.518917202949524, "step": 6028 }, { "epoch": 0.5089750218967318, "grad_norm": 0.140625, "learning_rate": 2.7459943445890322e-05, "loss": 1.546515703201294, "step": 6029 }, { "epoch": 0.5090594430315629, "grad_norm": 0.142578125, "learning_rate": 2.745346522947486e-05, "loss": 1.5265425443649292, "step": 6030 }, { "epoch": 0.509143864166394, "grad_norm": 0.138671875, "learning_rate": 2.7446986846708573e-05, "loss": 1.5494716167449951, "step": 6031 }, { "epoch": 0.5092282853012252, "grad_norm": 0.1337890625, "learning_rate": 2.744050829803068e-05, "loss": 1.4987852573394775, "step": 6032 }, { "epoch": 0.5093127064360563, "grad_norm": 0.1376953125, "learning_rate": 2.7434029583880466e-05, "loss": 1.5052845478057861, "step": 6033 }, { "epoch": 0.5093971275708874, "grad_norm": 0.1435546875, "learning_rate": 2.742755070469719e-05, "loss": 1.5349946022033691, "step": 6034 }, { "epoch": 0.5094815487057185, "grad_norm": 0.1416015625, "learning_rate": 2.742107166092015e-05, "loss": 1.5496361255645752, "step": 6035 }, { "epoch": 0.5095659698405496, "grad_norm": 0.13671875, "learning_rate": 2.7414592452988624e-05, "loss": 1.4647613763809204, "step": 6036 }, { "epoch": 0.5096503909753807, "grad_norm": 0.1396484375, "learning_rate": 2.7408113081341917e-05, "loss": 1.4984817504882812, "step": 6037 }, { "epoch": 0.5097348121102118, "grad_norm": 0.142578125, "learning_rate": 2.740163354641937e-05, "loss": 1.5607761144638062, "step": 6038 }, { "epoch": 0.5098192332450429, "grad_norm": 0.140625, "learning_rate": 2.7395153848660294e-05, "loss": 1.5746541023254395, "step": 6039 }, { "epoch": 0.509903654379874, "grad_norm": 0.1376953125, "learning_rate": 2.7388673988504028e-05, "loss": 1.5901005268096924, "step": 6040 }, { "epoch": 0.5099880755147052, "grad_norm": 0.1328125, "learning_rate": 2.738219396638992e-05, "loss": 1.4969981908798218, "step": 6041 }, { "epoch": 0.5100724966495362, "grad_norm": 0.140625, "learning_rate": 2.737571378275734e-05, "loss": 1.5710722208023071, "step": 6042 }, { "epoch": 0.5101569177843673, "grad_norm": 0.1318359375, "learning_rate": 2.736923343804565e-05, "loss": 1.4566023349761963, "step": 6043 }, { "epoch": 0.5102413389191984, "grad_norm": 0.14453125, "learning_rate": 2.736275293269424e-05, "loss": 1.554404854774475, "step": 6044 }, { "epoch": 0.5103257600540295, "grad_norm": 0.14453125, "learning_rate": 2.7356272267142507e-05, "loss": 1.5752137899398804, "step": 6045 }, { "epoch": 0.5104101811888606, "grad_norm": 0.1435546875, "learning_rate": 2.7349791441829843e-05, "loss": 1.5730632543563843, "step": 6046 }, { "epoch": 0.5104946023236917, "grad_norm": 0.1416015625, "learning_rate": 2.7343310457195676e-05, "loss": 1.5854624509811401, "step": 6047 }, { "epoch": 0.5105790234585228, "grad_norm": 0.1337890625, "learning_rate": 2.7336829313679423e-05, "loss": 1.5822731256484985, "step": 6048 }, { "epoch": 0.510663444593354, "grad_norm": 0.130859375, "learning_rate": 2.733034801172053e-05, "loss": 1.5532132387161255, "step": 6049 }, { "epoch": 0.5107478657281851, "grad_norm": 0.1376953125, "learning_rate": 2.7323866551758436e-05, "loss": 1.539927363395691, "step": 6050 }, { "epoch": 0.5108322868630162, "grad_norm": 0.1484375, "learning_rate": 2.731738493423261e-05, "loss": 1.5865631103515625, "step": 6051 }, { "epoch": 0.5109167079978473, "grad_norm": 0.138671875, "learning_rate": 2.7310903159582513e-05, "loss": 1.5532554388046265, "step": 6052 }, { "epoch": 0.5110011291326784, "grad_norm": 0.16015625, "learning_rate": 2.730442122824763e-05, "loss": 1.5698659420013428, "step": 6053 }, { "epoch": 0.5110855502675095, "grad_norm": 0.1396484375, "learning_rate": 2.7297939140667437e-05, "loss": 1.5466701984405518, "step": 6054 }, { "epoch": 0.5111699714023406, "grad_norm": 0.1328125, "learning_rate": 2.7291456897281453e-05, "loss": 1.464828610420227, "step": 6055 }, { "epoch": 0.5112543925371716, "grad_norm": 0.1494140625, "learning_rate": 2.7284974498529186e-05, "loss": 1.5406931638717651, "step": 6056 }, { "epoch": 0.5113388136720027, "grad_norm": 0.1416015625, "learning_rate": 2.727849194485016e-05, "loss": 1.5140125751495361, "step": 6057 }, { "epoch": 0.5114232348068339, "grad_norm": 0.138671875, "learning_rate": 2.72720092366839e-05, "loss": 1.4959983825683594, "step": 6058 }, { "epoch": 0.511507655941665, "grad_norm": 0.154296875, "learning_rate": 2.7265526374469945e-05, "loss": 1.5800426006317139, "step": 6059 }, { "epoch": 0.5115920770764961, "grad_norm": 0.1533203125, "learning_rate": 2.7259043358647863e-05, "loss": 1.6070011854171753, "step": 6060 }, { "epoch": 0.5116764982113272, "grad_norm": 0.13671875, "learning_rate": 2.7252560189657207e-05, "loss": 1.569875955581665, "step": 6061 }, { "epoch": 0.5117609193461583, "grad_norm": 0.1484375, "learning_rate": 2.7246076867937565e-05, "loss": 1.610978603363037, "step": 6062 }, { "epoch": 0.5118453404809894, "grad_norm": 0.1328125, "learning_rate": 2.72395933939285e-05, "loss": 1.4927349090576172, "step": 6063 }, { "epoch": 0.5119297616158205, "grad_norm": 0.140625, "learning_rate": 2.7233109768069625e-05, "loss": 1.480108380317688, "step": 6064 }, { "epoch": 0.5120141827506516, "grad_norm": 0.134765625, "learning_rate": 2.722662599080054e-05, "loss": 1.5898175239562988, "step": 6065 }, { "epoch": 0.5120986038854828, "grad_norm": 0.146484375, "learning_rate": 2.722014206256086e-05, "loss": 1.4933940172195435, "step": 6066 }, { "epoch": 0.5121830250203139, "grad_norm": 0.130859375, "learning_rate": 2.721365798379022e-05, "loss": 1.4615529775619507, "step": 6067 }, { "epoch": 0.512267446155145, "grad_norm": 0.1494140625, "learning_rate": 2.7207173754928233e-05, "loss": 1.5609015226364136, "step": 6068 }, { "epoch": 0.5123518672899761, "grad_norm": 0.142578125, "learning_rate": 2.7200689376414573e-05, "loss": 1.595488429069519, "step": 6069 }, { "epoch": 0.5124362884248072, "grad_norm": 0.1474609375, "learning_rate": 2.7194204848688875e-05, "loss": 1.5391640663146973, "step": 6070 }, { "epoch": 0.5125207095596382, "grad_norm": 0.13671875, "learning_rate": 2.7187720172190823e-05, "loss": 1.5153025388717651, "step": 6071 }, { "epoch": 0.5126051306944693, "grad_norm": 0.1435546875, "learning_rate": 2.718123534736008e-05, "loss": 1.5306307077407837, "step": 6072 }, { "epoch": 0.5126895518293004, "grad_norm": 0.1337890625, "learning_rate": 2.7174750374636333e-05, "loss": 1.4382696151733398, "step": 6073 }, { "epoch": 0.5127739729641315, "grad_norm": 0.146484375, "learning_rate": 2.7168265254459292e-05, "loss": 1.546676754951477, "step": 6074 }, { "epoch": 0.5128583940989627, "grad_norm": 0.1337890625, "learning_rate": 2.7161779987268644e-05, "loss": 1.5372394323349, "step": 6075 }, { "epoch": 0.5129428152337938, "grad_norm": 0.1474609375, "learning_rate": 2.7155294573504132e-05, "loss": 1.5417239665985107, "step": 6076 }, { "epoch": 0.5130272363686249, "grad_norm": 0.1396484375, "learning_rate": 2.7148809013605448e-05, "loss": 1.4927978515625, "step": 6077 }, { "epoch": 0.513111657503456, "grad_norm": 0.1318359375, "learning_rate": 2.7142323308012356e-05, "loss": 1.541691541671753, "step": 6078 }, { "epoch": 0.5131960786382871, "grad_norm": 0.142578125, "learning_rate": 2.7135837457164596e-05, "loss": 1.544103741645813, "step": 6079 }, { "epoch": 0.5132804997731182, "grad_norm": 0.1435546875, "learning_rate": 2.7129351461501928e-05, "loss": 1.4175981283187866, "step": 6080 }, { "epoch": 0.5133649209079493, "grad_norm": 0.1494140625, "learning_rate": 2.712286532146411e-05, "loss": 1.561844825744629, "step": 6081 }, { "epoch": 0.5134493420427804, "grad_norm": 0.140625, "learning_rate": 2.7116379037490907e-05, "loss": 1.4845157861709595, "step": 6082 }, { "epoch": 0.5135337631776116, "grad_norm": 0.1865234375, "learning_rate": 2.7109892610022135e-05, "loss": 1.4843512773513794, "step": 6083 }, { "epoch": 0.5136181843124427, "grad_norm": 0.142578125, "learning_rate": 2.7103406039497565e-05, "loss": 1.5291694402694702, "step": 6084 }, { "epoch": 0.5137026054472738, "grad_norm": 0.13671875, "learning_rate": 2.709691932635701e-05, "loss": 1.4949296712875366, "step": 6085 }, { "epoch": 0.5137870265821048, "grad_norm": 0.140625, "learning_rate": 2.7090432471040282e-05, "loss": 1.5461169481277466, "step": 6086 }, { "epoch": 0.5138714477169359, "grad_norm": 0.138671875, "learning_rate": 2.708394547398721e-05, "loss": 1.4869564771652222, "step": 6087 }, { "epoch": 0.513955868851767, "grad_norm": 0.1357421875, "learning_rate": 2.7077458335637633e-05, "loss": 1.5090820789337158, "step": 6088 }, { "epoch": 0.5140402899865981, "grad_norm": 0.1455078125, "learning_rate": 2.707097105643138e-05, "loss": 1.5451974868774414, "step": 6089 }, { "epoch": 0.5141247111214292, "grad_norm": 0.13671875, "learning_rate": 2.7064483636808313e-05, "loss": 1.5311458110809326, "step": 6090 }, { "epoch": 0.5142091322562603, "grad_norm": 0.1357421875, "learning_rate": 2.7057996077208293e-05, "loss": 1.483384370803833, "step": 6091 }, { "epoch": 0.5142935533910915, "grad_norm": 0.1376953125, "learning_rate": 2.705150837807119e-05, "loss": 1.553087592124939, "step": 6092 }, { "epoch": 0.5143779745259226, "grad_norm": 0.134765625, "learning_rate": 2.704502053983689e-05, "loss": 1.4907090663909912, "step": 6093 }, { "epoch": 0.5144623956607537, "grad_norm": 0.1494140625, "learning_rate": 2.703853256294528e-05, "loss": 1.4998180866241455, "step": 6094 }, { "epoch": 0.5145468167955848, "grad_norm": 0.1455078125, "learning_rate": 2.7032044447836262e-05, "loss": 1.6065620183944702, "step": 6095 }, { "epoch": 0.5146312379304159, "grad_norm": 0.1328125, "learning_rate": 2.7025556194949746e-05, "loss": 1.5378292798995972, "step": 6096 }, { "epoch": 0.514715659065247, "grad_norm": 0.14453125, "learning_rate": 2.701906780472565e-05, "loss": 1.5986026525497437, "step": 6097 }, { "epoch": 0.5148000802000781, "grad_norm": 0.15625, "learning_rate": 2.701257927760391e-05, "loss": 1.4785058498382568, "step": 6098 }, { "epoch": 0.5148845013349092, "grad_norm": 0.1455078125, "learning_rate": 2.7006090614024454e-05, "loss": 1.5355250835418701, "step": 6099 }, { "epoch": 0.5149689224697404, "grad_norm": 0.1357421875, "learning_rate": 2.6999601814427235e-05, "loss": 1.5606944561004639, "step": 6100 }, { "epoch": 0.5150533436045714, "grad_norm": 0.134765625, "learning_rate": 2.6993112879252204e-05, "loss": 1.5425761938095093, "step": 6101 }, { "epoch": 0.5151377647394025, "grad_norm": 0.1416015625, "learning_rate": 2.698662380893932e-05, "loss": 1.589705467224121, "step": 6102 }, { "epoch": 0.5152221858742336, "grad_norm": 0.146484375, "learning_rate": 2.698013460392858e-05, "loss": 1.578086495399475, "step": 6103 }, { "epoch": 0.5153066070090647, "grad_norm": 0.1376953125, "learning_rate": 2.6973645264659946e-05, "loss": 1.5698367357254028, "step": 6104 }, { "epoch": 0.5153910281438958, "grad_norm": 0.1474609375, "learning_rate": 2.696715579157343e-05, "loss": 1.5874321460723877, "step": 6105 }, { "epoch": 0.5154754492787269, "grad_norm": 0.12890625, "learning_rate": 2.6960666185109013e-05, "loss": 1.4868780374526978, "step": 6106 }, { "epoch": 0.515559870413558, "grad_norm": 0.1513671875, "learning_rate": 2.6954176445706712e-05, "loss": 1.4849008321762085, "step": 6107 }, { "epoch": 0.5156442915483891, "grad_norm": 0.1328125, "learning_rate": 2.6947686573806557e-05, "loss": 1.5077378749847412, "step": 6108 }, { "epoch": 0.5157287126832203, "grad_norm": 0.1337890625, "learning_rate": 2.694119656984857e-05, "loss": 1.4609344005584717, "step": 6109 }, { "epoch": 0.5158131338180514, "grad_norm": 0.14453125, "learning_rate": 2.6934706434272794e-05, "loss": 1.571043610572815, "step": 6110 }, { "epoch": 0.5158975549528825, "grad_norm": 0.140625, "learning_rate": 2.6928216167519266e-05, "loss": 1.485796570777893, "step": 6111 }, { "epoch": 0.5159819760877136, "grad_norm": 0.1435546875, "learning_rate": 2.692172577002805e-05, "loss": 1.5922757387161255, "step": 6112 }, { "epoch": 0.5160663972225447, "grad_norm": 0.1318359375, "learning_rate": 2.69152352422392e-05, "loss": 1.5446207523345947, "step": 6113 }, { "epoch": 0.5161508183573758, "grad_norm": 0.1416015625, "learning_rate": 2.6908744584592805e-05, "loss": 1.5290560722351074, "step": 6114 }, { "epoch": 0.5162352394922068, "grad_norm": 0.140625, "learning_rate": 2.6902253797528943e-05, "loss": 1.5377519130706787, "step": 6115 }, { "epoch": 0.5163196606270379, "grad_norm": 0.13671875, "learning_rate": 2.689576288148769e-05, "loss": 1.4474802017211914, "step": 6116 }, { "epoch": 0.5164040817618691, "grad_norm": 0.134765625, "learning_rate": 2.6889271836909163e-05, "loss": 1.5148837566375732, "step": 6117 }, { "epoch": 0.5164885028967002, "grad_norm": 0.1396484375, "learning_rate": 2.6882780664233464e-05, "loss": 1.5537227392196655, "step": 6118 }, { "epoch": 0.5165729240315313, "grad_norm": 0.1435546875, "learning_rate": 2.6876289363900708e-05, "loss": 1.552441954612732, "step": 6119 }, { "epoch": 0.5166573451663624, "grad_norm": 0.1328125, "learning_rate": 2.6869797936351026e-05, "loss": 1.465808629989624, "step": 6120 }, { "epoch": 0.5167417663011935, "grad_norm": 0.1318359375, "learning_rate": 2.686330638202455e-05, "loss": 1.4853520393371582, "step": 6121 }, { "epoch": 0.5168261874360246, "grad_norm": 0.1416015625, "learning_rate": 2.6856814701361422e-05, "loss": 1.5810155868530273, "step": 6122 }, { "epoch": 0.5169106085708557, "grad_norm": 0.146484375, "learning_rate": 2.6850322894801787e-05, "loss": 1.5309656858444214, "step": 6123 }, { "epoch": 0.5169950297056868, "grad_norm": 0.138671875, "learning_rate": 2.6843830962785828e-05, "loss": 1.6216621398925781, "step": 6124 }, { "epoch": 0.5170794508405179, "grad_norm": 0.138671875, "learning_rate": 2.6837338905753685e-05, "loss": 1.5539331436157227, "step": 6125 }, { "epoch": 0.5171638719753491, "grad_norm": 0.1474609375, "learning_rate": 2.6830846724145543e-05, "loss": 1.5589702129364014, "step": 6126 }, { "epoch": 0.5172482931101802, "grad_norm": 0.1435546875, "learning_rate": 2.6824354418401605e-05, "loss": 1.5845121145248413, "step": 6127 }, { "epoch": 0.5173327142450113, "grad_norm": 0.15234375, "learning_rate": 2.6817861988962045e-05, "loss": 1.5692899227142334, "step": 6128 }, { "epoch": 0.5174171353798424, "grad_norm": 0.1416015625, "learning_rate": 2.6811369436267075e-05, "loss": 1.3805283308029175, "step": 6129 }, { "epoch": 0.5175015565146734, "grad_norm": 0.13671875, "learning_rate": 2.6804876760756905e-05, "loss": 1.534963846206665, "step": 6130 }, { "epoch": 0.5175859776495045, "grad_norm": 0.1552734375, "learning_rate": 2.6798383962871748e-05, "loss": 1.5188064575195312, "step": 6131 }, { "epoch": 0.5176703987843356, "grad_norm": 0.1455078125, "learning_rate": 2.6791891043051837e-05, "loss": 1.5117969512939453, "step": 6132 }, { "epoch": 0.5177548199191667, "grad_norm": 0.1416015625, "learning_rate": 2.6785398001737404e-05, "loss": 1.5628021955490112, "step": 6133 }, { "epoch": 0.5178392410539979, "grad_norm": 0.142578125, "learning_rate": 2.6778904839368708e-05, "loss": 1.4280924797058105, "step": 6134 }, { "epoch": 0.517923662188829, "grad_norm": 0.1396484375, "learning_rate": 2.6772411556385966e-05, "loss": 1.4949456453323364, "step": 6135 }, { "epoch": 0.5180080833236601, "grad_norm": 0.134765625, "learning_rate": 2.676591815322948e-05, "loss": 1.56898033618927, "step": 6136 }, { "epoch": 0.5180925044584912, "grad_norm": 0.13671875, "learning_rate": 2.6759424630339485e-05, "loss": 1.4875476360321045, "step": 6137 }, { "epoch": 0.5181769255933223, "grad_norm": 0.1455078125, "learning_rate": 2.6752930988156278e-05, "loss": 1.554540753364563, "step": 6138 }, { "epoch": 0.5182613467281534, "grad_norm": 0.1357421875, "learning_rate": 2.674643722712014e-05, "loss": 1.4834403991699219, "step": 6139 }, { "epoch": 0.5183457678629845, "grad_norm": 0.1357421875, "learning_rate": 2.6739943347671347e-05, "loss": 1.4733400344848633, "step": 6140 }, { "epoch": 0.5184301889978156, "grad_norm": 0.146484375, "learning_rate": 2.673344935025023e-05, "loss": 1.5424246788024902, "step": 6141 }, { "epoch": 0.5185146101326467, "grad_norm": 0.1298828125, "learning_rate": 2.672695523529707e-05, "loss": 1.479303002357483, "step": 6142 }, { "epoch": 0.5185990312674779, "grad_norm": 0.138671875, "learning_rate": 2.672046100325219e-05, "loss": 1.4850646257400513, "step": 6143 }, { "epoch": 0.518683452402309, "grad_norm": 0.142578125, "learning_rate": 2.671396665455592e-05, "loss": 1.5839546918869019, "step": 6144 }, { "epoch": 0.51876787353714, "grad_norm": 0.1376953125, "learning_rate": 2.6707472189648598e-05, "loss": 1.5030461549758911, "step": 6145 }, { "epoch": 0.5188522946719711, "grad_norm": 0.134765625, "learning_rate": 2.6700977608970557e-05, "loss": 1.5155479907989502, "step": 6146 }, { "epoch": 0.5189367158068022, "grad_norm": 0.142578125, "learning_rate": 2.6694482912962144e-05, "loss": 1.5489065647125244, "step": 6147 }, { "epoch": 0.5190211369416333, "grad_norm": 0.138671875, "learning_rate": 2.668798810206371e-05, "loss": 1.5634585618972778, "step": 6148 }, { "epoch": 0.5191055580764644, "grad_norm": 0.1513671875, "learning_rate": 2.6681493176715633e-05, "loss": 1.5698223114013672, "step": 6149 }, { "epoch": 0.5191899792112955, "grad_norm": 0.1328125, "learning_rate": 2.667499813735827e-05, "loss": 1.472408652305603, "step": 6150 }, { "epoch": 0.5192744003461267, "grad_norm": 0.1494140625, "learning_rate": 2.6668502984432014e-05, "loss": 1.582095980644226, "step": 6151 }, { "epoch": 0.5193588214809578, "grad_norm": 0.14453125, "learning_rate": 2.666200771837724e-05, "loss": 1.634243369102478, "step": 6152 }, { "epoch": 0.5194432426157889, "grad_norm": 0.1337890625, "learning_rate": 2.6655512339634352e-05, "loss": 1.4917858839035034, "step": 6153 }, { "epoch": 0.51952766375062, "grad_norm": 0.13671875, "learning_rate": 2.6649016848643742e-05, "loss": 1.5834968090057373, "step": 6154 }, { "epoch": 0.5196120848854511, "grad_norm": 0.1318359375, "learning_rate": 2.664252124584583e-05, "loss": 1.4863126277923584, "step": 6155 }, { "epoch": 0.5196965060202822, "grad_norm": 0.140625, "learning_rate": 2.6636025531681035e-05, "loss": 1.5122729539871216, "step": 6156 }, { "epoch": 0.5197809271551133, "grad_norm": 0.1435546875, "learning_rate": 2.6629529706589774e-05, "loss": 1.5686376094818115, "step": 6157 }, { "epoch": 0.5198653482899444, "grad_norm": 0.130859375, "learning_rate": 2.6623033771012475e-05, "loss": 1.5092973709106445, "step": 6158 }, { "epoch": 0.5199497694247754, "grad_norm": 0.1484375, "learning_rate": 2.661653772538959e-05, "loss": 1.4758837223052979, "step": 6159 }, { "epoch": 0.5200341905596066, "grad_norm": 0.13671875, "learning_rate": 2.6610041570161563e-05, "loss": 1.6126477718353271, "step": 6160 }, { "epoch": 0.5201186116944377, "grad_norm": 0.1435546875, "learning_rate": 2.6603545305768845e-05, "loss": 1.4736679792404175, "step": 6161 }, { "epoch": 0.5202030328292688, "grad_norm": 0.14453125, "learning_rate": 2.6597048932651892e-05, "loss": 1.572677493095398, "step": 6162 }, { "epoch": 0.5202874539640999, "grad_norm": 0.13671875, "learning_rate": 2.65905524512512e-05, "loss": 1.5743465423583984, "step": 6163 }, { "epoch": 0.520371875098931, "grad_norm": 0.14453125, "learning_rate": 2.6584055862007218e-05, "loss": 1.5831738710403442, "step": 6164 }, { "epoch": 0.5204562962337621, "grad_norm": 0.146484375, "learning_rate": 2.657755916536045e-05, "loss": 1.5449106693267822, "step": 6165 }, { "epoch": 0.5205407173685932, "grad_norm": 0.1259765625, "learning_rate": 2.657106236175137e-05, "loss": 1.4779447317123413, "step": 6166 }, { "epoch": 0.5206251385034243, "grad_norm": 0.1435546875, "learning_rate": 2.6564565451620482e-05, "loss": 1.5825544595718384, "step": 6167 }, { "epoch": 0.5207095596382555, "grad_norm": 0.14453125, "learning_rate": 2.65580684354083e-05, "loss": 1.6236103773117065, "step": 6168 }, { "epoch": 0.5207939807730866, "grad_norm": 0.126953125, "learning_rate": 2.6551571313555333e-05, "loss": 1.3897802829742432, "step": 6169 }, { "epoch": 0.5208784019079177, "grad_norm": 0.1357421875, "learning_rate": 2.6545074086502108e-05, "loss": 1.4383289813995361, "step": 6170 }, { "epoch": 0.5209628230427488, "grad_norm": 0.1494140625, "learning_rate": 2.653857675468914e-05, "loss": 1.4484220743179321, "step": 6171 }, { "epoch": 0.5210472441775799, "grad_norm": 0.1328125, "learning_rate": 2.6532079318556968e-05, "loss": 1.5097968578338623, "step": 6172 }, { "epoch": 0.521131665312411, "grad_norm": 0.1357421875, "learning_rate": 2.652558177854614e-05, "loss": 1.5417183637619019, "step": 6173 }, { "epoch": 0.521216086447242, "grad_norm": 0.1416015625, "learning_rate": 2.6519084135097192e-05, "loss": 1.4825719594955444, "step": 6174 }, { "epoch": 0.5213005075820731, "grad_norm": 0.166015625, "learning_rate": 2.65125863886507e-05, "loss": 1.4985765218734741, "step": 6175 }, { "epoch": 0.5213849287169042, "grad_norm": 0.1416015625, "learning_rate": 2.6506088539647205e-05, "loss": 1.5147514343261719, "step": 6176 }, { "epoch": 0.5214693498517354, "grad_norm": 0.1337890625, "learning_rate": 2.6499590588527296e-05, "loss": 1.5688854455947876, "step": 6177 }, { "epoch": 0.5215537709865665, "grad_norm": 0.1416015625, "learning_rate": 2.6493092535731534e-05, "loss": 1.509448528289795, "step": 6178 }, { "epoch": 0.5216381921213976, "grad_norm": 0.142578125, "learning_rate": 2.6486594381700512e-05, "loss": 1.5121312141418457, "step": 6179 }, { "epoch": 0.5217226132562287, "grad_norm": 0.142578125, "learning_rate": 2.6480096126874815e-05, "loss": 1.5582275390625, "step": 6180 }, { "epoch": 0.5218070343910598, "grad_norm": 0.1435546875, "learning_rate": 2.6473597771695047e-05, "loss": 1.5068063735961914, "step": 6181 }, { "epoch": 0.5218914555258909, "grad_norm": 0.1396484375, "learning_rate": 2.6467099316601807e-05, "loss": 1.512855887413025, "step": 6182 }, { "epoch": 0.521975876660722, "grad_norm": 0.1376953125, "learning_rate": 2.6460600762035704e-05, "loss": 1.542912483215332, "step": 6183 }, { "epoch": 0.5220602977955531, "grad_norm": 0.1328125, "learning_rate": 2.645410210843736e-05, "loss": 1.531064510345459, "step": 6184 }, { "epoch": 0.5221447189303842, "grad_norm": 0.1357421875, "learning_rate": 2.6447603356247396e-05, "loss": 1.498856782913208, "step": 6185 }, { "epoch": 0.5222291400652154, "grad_norm": 0.1494140625, "learning_rate": 2.6441104505906444e-05, "loss": 1.501878023147583, "step": 6186 }, { "epoch": 0.5223135612000465, "grad_norm": 0.13671875, "learning_rate": 2.6434605557855153e-05, "loss": 1.4670244455337524, "step": 6187 }, { "epoch": 0.5223979823348776, "grad_norm": 0.142578125, "learning_rate": 2.6428106512534146e-05, "loss": 1.500710368156433, "step": 6188 }, { "epoch": 0.5224824034697086, "grad_norm": 0.134765625, "learning_rate": 2.642160737038409e-05, "loss": 1.4665108919143677, "step": 6189 }, { "epoch": 0.5225668246045397, "grad_norm": 0.134765625, "learning_rate": 2.6415108131845634e-05, "loss": 1.5186940431594849, "step": 6190 }, { "epoch": 0.5226512457393708, "grad_norm": 0.1396484375, "learning_rate": 2.640860879735944e-05, "loss": 1.5820204019546509, "step": 6191 }, { "epoch": 0.5227356668742019, "grad_norm": 0.1376953125, "learning_rate": 2.6402109367366196e-05, "loss": 1.5257831811904907, "step": 6192 }, { "epoch": 0.522820088009033, "grad_norm": 0.142578125, "learning_rate": 2.6395609842306557e-05, "loss": 1.5538547039031982, "step": 6193 }, { "epoch": 0.5229045091438642, "grad_norm": 0.1396484375, "learning_rate": 2.6389110222621223e-05, "loss": 1.5973423719406128, "step": 6194 }, { "epoch": 0.5229889302786953, "grad_norm": 0.1435546875, "learning_rate": 2.6382610508750873e-05, "loss": 1.5083712339401245, "step": 6195 }, { "epoch": 0.5230733514135264, "grad_norm": 0.13671875, "learning_rate": 2.637611070113621e-05, "loss": 1.5292845964431763, "step": 6196 }, { "epoch": 0.5231577725483575, "grad_norm": 0.13671875, "learning_rate": 2.636961080021793e-05, "loss": 1.5256904363632202, "step": 6197 }, { "epoch": 0.5232421936831886, "grad_norm": 0.1640625, "learning_rate": 2.636311080643674e-05, "loss": 1.5044043064117432, "step": 6198 }, { "epoch": 0.5233266148180197, "grad_norm": 0.1484375, "learning_rate": 2.6356610720233377e-05, "loss": 1.4555047750473022, "step": 6199 }, { "epoch": 0.5234110359528508, "grad_norm": 0.14453125, "learning_rate": 2.6350110542048534e-05, "loss": 1.5986799001693726, "step": 6200 }, { "epoch": 0.5234954570876819, "grad_norm": 0.1318359375, "learning_rate": 2.634361027232296e-05, "loss": 1.544377088546753, "step": 6201 }, { "epoch": 0.523579878222513, "grad_norm": 0.1494140625, "learning_rate": 2.6337109911497366e-05, "loss": 1.5668666362762451, "step": 6202 }, { "epoch": 0.5236642993573442, "grad_norm": 0.15234375, "learning_rate": 2.6330609460012517e-05, "loss": 1.4945510625839233, "step": 6203 }, { "epoch": 0.5237487204921752, "grad_norm": 0.1396484375, "learning_rate": 2.632410891830915e-05, "loss": 1.4695347547531128, "step": 6204 }, { "epoch": 0.5238331416270063, "grad_norm": 0.1318359375, "learning_rate": 2.631760828682801e-05, "loss": 1.5010582208633423, "step": 6205 }, { "epoch": 0.5239175627618374, "grad_norm": 0.1396484375, "learning_rate": 2.6311107566009864e-05, "loss": 1.6018391847610474, "step": 6206 }, { "epoch": 0.5240019838966685, "grad_norm": 0.134765625, "learning_rate": 2.6304606756295463e-05, "loss": 1.556215524673462, "step": 6207 }, { "epoch": 0.5240864050314996, "grad_norm": 0.140625, "learning_rate": 2.6298105858125605e-05, "loss": 1.6120555400848389, "step": 6208 }, { "epoch": 0.5241708261663307, "grad_norm": 0.134765625, "learning_rate": 2.629160487194104e-05, "loss": 1.5629212856292725, "step": 6209 }, { "epoch": 0.5242552473011618, "grad_norm": 0.1572265625, "learning_rate": 2.628510379818256e-05, "loss": 1.544041633605957, "step": 6210 }, { "epoch": 0.524339668435993, "grad_norm": 0.1357421875, "learning_rate": 2.6278602637290955e-05, "loss": 1.4765998125076294, "step": 6211 }, { "epoch": 0.5244240895708241, "grad_norm": 0.15625, "learning_rate": 2.6272101389707016e-05, "loss": 1.4867033958435059, "step": 6212 }, { "epoch": 0.5245085107056552, "grad_norm": 0.146484375, "learning_rate": 2.626560005587155e-05, "loss": 1.562036395072937, "step": 6213 }, { "epoch": 0.5245929318404863, "grad_norm": 0.1328125, "learning_rate": 2.6259098636225354e-05, "loss": 1.48829984664917, "step": 6214 }, { "epoch": 0.5246773529753174, "grad_norm": 0.1396484375, "learning_rate": 2.6252597131209244e-05, "loss": 1.5447334051132202, "step": 6215 }, { "epoch": 0.5247617741101485, "grad_norm": 0.1328125, "learning_rate": 2.6246095541264037e-05, "loss": 1.5007020235061646, "step": 6216 }, { "epoch": 0.5248461952449796, "grad_norm": 0.1376953125, "learning_rate": 2.623959386683056e-05, "loss": 1.5526517629623413, "step": 6217 }, { "epoch": 0.5249306163798106, "grad_norm": 0.1376953125, "learning_rate": 2.623309210834964e-05, "loss": 1.5000293254852295, "step": 6218 }, { "epoch": 0.5250150375146417, "grad_norm": 0.140625, "learning_rate": 2.6226590266262107e-05, "loss": 1.4651658535003662, "step": 6219 }, { "epoch": 0.5250994586494729, "grad_norm": 0.1376953125, "learning_rate": 2.6220088341008807e-05, "loss": 1.5435504913330078, "step": 6220 }, { "epoch": 0.525183879784304, "grad_norm": 0.1337890625, "learning_rate": 2.6213586333030588e-05, "loss": 1.5117157697677612, "step": 6221 }, { "epoch": 0.5252683009191351, "grad_norm": 0.134765625, "learning_rate": 2.6207084242768294e-05, "loss": 1.5035349130630493, "step": 6222 }, { "epoch": 0.5253527220539662, "grad_norm": 0.1630859375, "learning_rate": 2.6200582070662794e-05, "loss": 1.548896074295044, "step": 6223 }, { "epoch": 0.5254371431887973, "grad_norm": 0.146484375, "learning_rate": 2.6194079817154937e-05, "loss": 1.6008539199829102, "step": 6224 }, { "epoch": 0.5255215643236284, "grad_norm": 0.1376953125, "learning_rate": 2.6187577482685598e-05, "loss": 1.534541368484497, "step": 6225 }, { "epoch": 0.5256059854584595, "grad_norm": 0.14453125, "learning_rate": 2.618107506769565e-05, "loss": 1.5342090129852295, "step": 6226 }, { "epoch": 0.5256904065932906, "grad_norm": 0.134765625, "learning_rate": 2.6174572572625977e-05, "loss": 1.5015969276428223, "step": 6227 }, { "epoch": 0.5257748277281218, "grad_norm": 0.140625, "learning_rate": 2.616806999791746e-05, "loss": 1.5294734239578247, "step": 6228 }, { "epoch": 0.5258592488629529, "grad_norm": 0.1455078125, "learning_rate": 2.6161567344010983e-05, "loss": 1.4669268131256104, "step": 6229 }, { "epoch": 0.525943669997784, "grad_norm": 0.1396484375, "learning_rate": 2.6155064611347464e-05, "loss": 1.5159912109375, "step": 6230 }, { "epoch": 0.5260280911326151, "grad_norm": 0.1455078125, "learning_rate": 2.6148561800367777e-05, "loss": 1.5322636365890503, "step": 6231 }, { "epoch": 0.5261125122674462, "grad_norm": 0.140625, "learning_rate": 2.6142058911512836e-05, "loss": 1.443222999572754, "step": 6232 }, { "epoch": 0.5261969334022772, "grad_norm": 0.12890625, "learning_rate": 2.6135555945223566e-05, "loss": 1.503501296043396, "step": 6233 }, { "epoch": 0.5262813545371083, "grad_norm": 0.142578125, "learning_rate": 2.612905290194086e-05, "loss": 1.5068227052688599, "step": 6234 }, { "epoch": 0.5263657756719394, "grad_norm": 0.1416015625, "learning_rate": 2.6122549782105666e-05, "loss": 1.5222766399383545, "step": 6235 }, { "epoch": 0.5264501968067705, "grad_norm": 0.140625, "learning_rate": 2.6116046586158893e-05, "loss": 1.5866549015045166, "step": 6236 }, { "epoch": 0.5265346179416017, "grad_norm": 0.138671875, "learning_rate": 2.6109543314541472e-05, "loss": 1.4464105367660522, "step": 6237 }, { "epoch": 0.5266190390764328, "grad_norm": 0.142578125, "learning_rate": 2.610303996769436e-05, "loss": 1.5425207614898682, "step": 6238 }, { "epoch": 0.5267034602112639, "grad_norm": 0.142578125, "learning_rate": 2.6096536546058477e-05, "loss": 1.5279182195663452, "step": 6239 }, { "epoch": 0.526787881346095, "grad_norm": 0.1337890625, "learning_rate": 2.609003305007479e-05, "loss": 1.559056282043457, "step": 6240 }, { "epoch": 0.5268723024809261, "grad_norm": 0.138671875, "learning_rate": 2.6083529480184233e-05, "loss": 1.4861185550689697, "step": 6241 }, { "epoch": 0.5269567236157572, "grad_norm": 0.1376953125, "learning_rate": 2.6077025836827785e-05, "loss": 1.5296727418899536, "step": 6242 }, { "epoch": 0.5270411447505883, "grad_norm": 0.146484375, "learning_rate": 2.6070522120446378e-05, "loss": 1.4956562519073486, "step": 6243 }, { "epoch": 0.5271255658854194, "grad_norm": 0.1376953125, "learning_rate": 2.6064018331481017e-05, "loss": 1.5034631490707397, "step": 6244 }, { "epoch": 0.5272099870202506, "grad_norm": 0.1435546875, "learning_rate": 2.605751447037264e-05, "loss": 1.5437899827957153, "step": 6245 }, { "epoch": 0.5272944081550817, "grad_norm": 0.1533203125, "learning_rate": 2.605101053756225e-05, "loss": 1.6185026168823242, "step": 6246 }, { "epoch": 0.5273788292899128, "grad_norm": 0.1435546875, "learning_rate": 2.6044506533490814e-05, "loss": 1.60055673122406, "step": 6247 }, { "epoch": 0.5274632504247438, "grad_norm": 0.1357421875, "learning_rate": 2.6038002458599324e-05, "loss": 1.5111727714538574, "step": 6248 }, { "epoch": 0.5275476715595749, "grad_norm": 0.142578125, "learning_rate": 2.6031498313328777e-05, "loss": 1.5409297943115234, "step": 6249 }, { "epoch": 0.527632092694406, "grad_norm": 0.138671875, "learning_rate": 2.6024994098120164e-05, "loss": 1.5190705060958862, "step": 6250 }, { "epoch": 0.5277165138292371, "grad_norm": 0.1591796875, "learning_rate": 2.6018489813414482e-05, "loss": 1.5884579420089722, "step": 6251 }, { "epoch": 0.5278009349640682, "grad_norm": 0.14453125, "learning_rate": 2.601198545965275e-05, "loss": 1.5738598108291626, "step": 6252 }, { "epoch": 0.5278853560988993, "grad_norm": 0.1337890625, "learning_rate": 2.6005481037275963e-05, "loss": 1.5413259267807007, "step": 6253 }, { "epoch": 0.5279697772337305, "grad_norm": 0.140625, "learning_rate": 2.599897654672515e-05, "loss": 1.5178536176681519, "step": 6254 }, { "epoch": 0.5280541983685616, "grad_norm": 0.142578125, "learning_rate": 2.599247198844133e-05, "loss": 1.5420352220535278, "step": 6255 }, { "epoch": 0.5281386195033927, "grad_norm": 0.134765625, "learning_rate": 2.5985967362865514e-05, "loss": 1.5098295211791992, "step": 6256 }, { "epoch": 0.5282230406382238, "grad_norm": 0.13671875, "learning_rate": 2.5979462670438748e-05, "loss": 1.5534775257110596, "step": 6257 }, { "epoch": 0.5283074617730549, "grad_norm": 0.1455078125, "learning_rate": 2.597295791160205e-05, "loss": 1.5336910486221313, "step": 6258 }, { "epoch": 0.528391882907886, "grad_norm": 0.138671875, "learning_rate": 2.5966453086796483e-05, "loss": 1.4916353225708008, "step": 6259 }, { "epoch": 0.5284763040427171, "grad_norm": 0.1416015625, "learning_rate": 2.5959948196463058e-05, "loss": 1.5003883838653564, "step": 6260 }, { "epoch": 0.5285607251775482, "grad_norm": 0.13671875, "learning_rate": 2.5953443241042845e-05, "loss": 1.509516954421997, "step": 6261 }, { "epoch": 0.5286451463123794, "grad_norm": 0.1484375, "learning_rate": 2.5946938220976884e-05, "loss": 1.5292855501174927, "step": 6262 }, { "epoch": 0.5287295674472104, "grad_norm": 0.1328125, "learning_rate": 2.5940433136706242e-05, "loss": 1.4917614459991455, "step": 6263 }, { "epoch": 0.5288139885820415, "grad_norm": 0.1513671875, "learning_rate": 2.5933927988671974e-05, "loss": 1.5591933727264404, "step": 6264 }, { "epoch": 0.5288984097168726, "grad_norm": 0.138671875, "learning_rate": 2.592742277731513e-05, "loss": 1.541408658027649, "step": 6265 }, { "epoch": 0.5289828308517037, "grad_norm": 0.140625, "learning_rate": 2.592091750307681e-05, "loss": 1.4677205085754395, "step": 6266 }, { "epoch": 0.5290672519865348, "grad_norm": 0.14453125, "learning_rate": 2.591441216639806e-05, "loss": 1.5351307392120361, "step": 6267 }, { "epoch": 0.5291516731213659, "grad_norm": 0.142578125, "learning_rate": 2.5907906767719963e-05, "loss": 1.459291696548462, "step": 6268 }, { "epoch": 0.529236094256197, "grad_norm": 0.1474609375, "learning_rate": 2.5901401307483614e-05, "loss": 1.4947541952133179, "step": 6269 }, { "epoch": 0.5293205153910281, "grad_norm": 0.140625, "learning_rate": 2.5894895786130087e-05, "loss": 1.5735310316085815, "step": 6270 }, { "epoch": 0.5294049365258593, "grad_norm": 0.1455078125, "learning_rate": 2.5888390204100477e-05, "loss": 1.600075125694275, "step": 6271 }, { "epoch": 0.5294893576606904, "grad_norm": 0.138671875, "learning_rate": 2.5881884561835866e-05, "loss": 1.5500578880310059, "step": 6272 }, { "epoch": 0.5295737787955215, "grad_norm": 0.1416015625, "learning_rate": 2.587537885977737e-05, "loss": 1.5057148933410645, "step": 6273 }, { "epoch": 0.5296581999303526, "grad_norm": 0.158203125, "learning_rate": 2.586887309836608e-05, "loss": 1.5078929662704468, "step": 6274 }, { "epoch": 0.5297426210651837, "grad_norm": 0.1396484375, "learning_rate": 2.5862367278043103e-05, "loss": 1.528587818145752, "step": 6275 }, { "epoch": 0.5298270422000148, "grad_norm": 0.154296875, "learning_rate": 2.5855861399249563e-05, "loss": 1.5342751741409302, "step": 6276 }, { "epoch": 0.5299114633348458, "grad_norm": 0.1376953125, "learning_rate": 2.5849355462426555e-05, "loss": 1.4677242040634155, "step": 6277 }, { "epoch": 0.5299958844696769, "grad_norm": 0.1337890625, "learning_rate": 2.5842849468015207e-05, "loss": 1.5755181312561035, "step": 6278 }, { "epoch": 0.5300803056045081, "grad_norm": 0.1396484375, "learning_rate": 2.5836343416456633e-05, "loss": 1.6062204837799072, "step": 6279 }, { "epoch": 0.5301647267393392, "grad_norm": 0.1396484375, "learning_rate": 2.5829837308191968e-05, "loss": 1.5962727069854736, "step": 6280 }, { "epoch": 0.5302491478741703, "grad_norm": 0.146484375, "learning_rate": 2.5823331143662343e-05, "loss": 1.5074598789215088, "step": 6281 }, { "epoch": 0.5303335690090014, "grad_norm": 0.1474609375, "learning_rate": 2.5816824923308886e-05, "loss": 1.5352251529693604, "step": 6282 }, { "epoch": 0.5304179901438325, "grad_norm": 0.1328125, "learning_rate": 2.5810318647572733e-05, "loss": 1.5061661005020142, "step": 6283 }, { "epoch": 0.5305024112786636, "grad_norm": 0.1328125, "learning_rate": 2.580381231689503e-05, "loss": 1.5460827350616455, "step": 6284 }, { "epoch": 0.5305868324134947, "grad_norm": 0.1298828125, "learning_rate": 2.5797305931716924e-05, "loss": 1.529005765914917, "step": 6285 }, { "epoch": 0.5306712535483258, "grad_norm": 0.1357421875, "learning_rate": 2.5790799492479556e-05, "loss": 1.5861237049102783, "step": 6286 }, { "epoch": 0.5307556746831569, "grad_norm": 0.146484375, "learning_rate": 2.578429299962407e-05, "loss": 1.4909968376159668, "step": 6287 }, { "epoch": 0.5308400958179881, "grad_norm": 0.12890625, "learning_rate": 2.577778645359165e-05, "loss": 1.5223069190979004, "step": 6288 }, { "epoch": 0.5309245169528192, "grad_norm": 0.140625, "learning_rate": 2.5771279854823432e-05, "loss": 1.512303113937378, "step": 6289 }, { "epoch": 0.5310089380876503, "grad_norm": 0.1376953125, "learning_rate": 2.5764773203760596e-05, "loss": 1.5733250379562378, "step": 6290 }, { "epoch": 0.5310933592224814, "grad_norm": 0.1357421875, "learning_rate": 2.5758266500844287e-05, "loss": 1.4967701435089111, "step": 6291 }, { "epoch": 0.5311777803573124, "grad_norm": 0.13671875, "learning_rate": 2.5751759746515687e-05, "loss": 1.5420864820480347, "step": 6292 }, { "epoch": 0.5312622014921435, "grad_norm": 0.13671875, "learning_rate": 2.5745252941215968e-05, "loss": 1.574913501739502, "step": 6293 }, { "epoch": 0.5313466226269746, "grad_norm": 0.1455078125, "learning_rate": 2.5738746085386312e-05, "loss": 1.568799376487732, "step": 6294 }, { "epoch": 0.5314310437618057, "grad_norm": 0.1298828125, "learning_rate": 2.5732239179467898e-05, "loss": 1.4527971744537354, "step": 6295 }, { "epoch": 0.5315154648966369, "grad_norm": 0.146484375, "learning_rate": 2.57257322239019e-05, "loss": 1.4903689622879028, "step": 6296 }, { "epoch": 0.531599886031468, "grad_norm": 0.140625, "learning_rate": 2.5719225219129522e-05, "loss": 1.5497560501098633, "step": 6297 }, { "epoch": 0.5316843071662991, "grad_norm": 0.142578125, "learning_rate": 2.5712718165591937e-05, "loss": 1.527289628982544, "step": 6298 }, { "epoch": 0.5317687283011302, "grad_norm": 0.1318359375, "learning_rate": 2.570621106373035e-05, "loss": 1.4521828889846802, "step": 6299 }, { "epoch": 0.5318531494359613, "grad_norm": 0.1435546875, "learning_rate": 2.569970391398596e-05, "loss": 1.5560816526412964, "step": 6300 }, { "epoch": 0.5319375705707924, "grad_norm": 0.1376953125, "learning_rate": 2.5693196716799957e-05, "loss": 1.5870347023010254, "step": 6301 }, { "epoch": 0.5320219917056235, "grad_norm": 0.1357421875, "learning_rate": 2.5686689472613555e-05, "loss": 1.5027042627334595, "step": 6302 }, { "epoch": 0.5321064128404546, "grad_norm": 0.1357421875, "learning_rate": 2.568018218186795e-05, "loss": 1.5530011653900146, "step": 6303 }, { "epoch": 0.5321908339752857, "grad_norm": 0.140625, "learning_rate": 2.5673674845004364e-05, "loss": 1.564389944076538, "step": 6304 }, { "epoch": 0.5322752551101169, "grad_norm": 0.140625, "learning_rate": 2.5667167462463997e-05, "loss": 1.5263583660125732, "step": 6305 }, { "epoch": 0.532359676244948, "grad_norm": 0.1337890625, "learning_rate": 2.5660660034688077e-05, "loss": 1.4837279319763184, "step": 6306 }, { "epoch": 0.532444097379779, "grad_norm": 0.193359375, "learning_rate": 2.565415256211782e-05, "loss": 1.457201600074768, "step": 6307 }, { "epoch": 0.5325285185146101, "grad_norm": 0.1376953125, "learning_rate": 2.564764504519445e-05, "loss": 1.5679751634597778, "step": 6308 }, { "epoch": 0.5326129396494412, "grad_norm": 0.1337890625, "learning_rate": 2.5641137484359184e-05, "loss": 1.489781141281128, "step": 6309 }, { "epoch": 0.5326973607842723, "grad_norm": 0.142578125, "learning_rate": 2.5634629880053256e-05, "loss": 1.5584220886230469, "step": 6310 }, { "epoch": 0.5327817819191034, "grad_norm": 0.1416015625, "learning_rate": 2.5628122232717894e-05, "loss": 1.4865858554840088, "step": 6311 }, { "epoch": 0.5328662030539345, "grad_norm": 0.1328125, "learning_rate": 2.5621614542794342e-05, "loss": 1.516252040863037, "step": 6312 }, { "epoch": 0.5329506241887657, "grad_norm": 0.1396484375, "learning_rate": 2.5615106810723827e-05, "loss": 1.582737684249878, "step": 6313 }, { "epoch": 0.5330350453235968, "grad_norm": 0.140625, "learning_rate": 2.560859903694759e-05, "loss": 1.5619451999664307, "step": 6314 }, { "epoch": 0.5331194664584279, "grad_norm": 0.150390625, "learning_rate": 2.5602091221906876e-05, "loss": 1.4633781909942627, "step": 6315 }, { "epoch": 0.533203887593259, "grad_norm": 0.1396484375, "learning_rate": 2.559558336604293e-05, "loss": 1.534868836402893, "step": 6316 }, { "epoch": 0.5332883087280901, "grad_norm": 0.1396484375, "learning_rate": 2.5589075469797002e-05, "loss": 1.5077846050262451, "step": 6317 }, { "epoch": 0.5333727298629212, "grad_norm": 0.138671875, "learning_rate": 2.558256753361034e-05, "loss": 1.5467469692230225, "step": 6318 }, { "epoch": 0.5334571509977523, "grad_norm": 0.138671875, "learning_rate": 2.55760595579242e-05, "loss": 1.481715202331543, "step": 6319 }, { "epoch": 0.5335415721325834, "grad_norm": 0.1767578125, "learning_rate": 2.5569551543179833e-05, "loss": 1.5255719423294067, "step": 6320 }, { "epoch": 0.5336259932674144, "grad_norm": 0.1416015625, "learning_rate": 2.55630434898185e-05, "loss": 1.5264315605163574, "step": 6321 }, { "epoch": 0.5337104144022456, "grad_norm": 0.1337890625, "learning_rate": 2.5556535398281472e-05, "loss": 1.551700234413147, "step": 6322 }, { "epoch": 0.5337948355370767, "grad_norm": 0.1396484375, "learning_rate": 2.555002726901e-05, "loss": 1.523393988609314, "step": 6323 }, { "epoch": 0.5338792566719078, "grad_norm": 0.1357421875, "learning_rate": 2.5543519102445368e-05, "loss": 1.4990997314453125, "step": 6324 }, { "epoch": 0.5339636778067389, "grad_norm": 0.1416015625, "learning_rate": 2.5537010899028824e-05, "loss": 1.524398684501648, "step": 6325 }, { "epoch": 0.53404809894157, "grad_norm": 0.1416015625, "learning_rate": 2.553050265920166e-05, "loss": 1.5854130983352661, "step": 6326 }, { "epoch": 0.5341325200764011, "grad_norm": 0.142578125, "learning_rate": 2.5523994383405132e-05, "loss": 1.5091551542282104, "step": 6327 }, { "epoch": 0.5342169412112322, "grad_norm": 0.1455078125, "learning_rate": 2.551748607208052e-05, "loss": 1.6109806299209595, "step": 6328 }, { "epoch": 0.5343013623460633, "grad_norm": 0.1416015625, "learning_rate": 2.5510977725669122e-05, "loss": 1.494272232055664, "step": 6329 }, { "epoch": 0.5343857834808945, "grad_norm": 0.1435546875, "learning_rate": 2.5504469344612198e-05, "loss": 1.5206046104431152, "step": 6330 }, { "epoch": 0.5344702046157256, "grad_norm": 0.15625, "learning_rate": 2.549796092935105e-05, "loss": 1.5324684381484985, "step": 6331 }, { "epoch": 0.5345546257505567, "grad_norm": 0.134765625, "learning_rate": 2.549145248032694e-05, "loss": 1.5527164936065674, "step": 6332 }, { "epoch": 0.5346390468853878, "grad_norm": 0.1396484375, "learning_rate": 2.5484943997981183e-05, "loss": 1.5266104936599731, "step": 6333 }, { "epoch": 0.5347234680202189, "grad_norm": 0.1328125, "learning_rate": 2.5478435482755046e-05, "loss": 1.4971001148223877, "step": 6334 }, { "epoch": 0.53480788915505, "grad_norm": 0.1494140625, "learning_rate": 2.5471926935089835e-05, "loss": 1.5780413150787354, "step": 6335 }, { "epoch": 0.534892310289881, "grad_norm": 0.13671875, "learning_rate": 2.5465418355426847e-05, "loss": 1.4869556427001953, "step": 6336 }, { "epoch": 0.5349767314247121, "grad_norm": 0.140625, "learning_rate": 2.5458909744207375e-05, "loss": 1.5812559127807617, "step": 6337 }, { "epoch": 0.5350611525595432, "grad_norm": 0.1337890625, "learning_rate": 2.5452401101872724e-05, "loss": 1.5909581184387207, "step": 6338 }, { "epoch": 0.5351455736943744, "grad_norm": 0.1435546875, "learning_rate": 2.5445892428864187e-05, "loss": 1.5714521408081055, "step": 6339 }, { "epoch": 0.5352299948292055, "grad_norm": 0.134765625, "learning_rate": 2.5439383725623066e-05, "loss": 1.4733271598815918, "step": 6340 }, { "epoch": 0.5353144159640366, "grad_norm": 0.1416015625, "learning_rate": 2.5432874992590678e-05, "loss": 1.5671303272247314, "step": 6341 }, { "epoch": 0.5353988370988677, "grad_norm": 0.1328125, "learning_rate": 2.5426366230208327e-05, "loss": 1.4202905893325806, "step": 6342 }, { "epoch": 0.5354832582336988, "grad_norm": 0.1455078125, "learning_rate": 2.541985743891732e-05, "loss": 1.52191960811615, "step": 6343 }, { "epoch": 0.5355676793685299, "grad_norm": 0.142578125, "learning_rate": 2.5413348619158967e-05, "loss": 1.5113937854766846, "step": 6344 }, { "epoch": 0.535652100503361, "grad_norm": 0.146484375, "learning_rate": 2.540683977137458e-05, "loss": 1.5493059158325195, "step": 6345 }, { "epoch": 0.5357365216381921, "grad_norm": 0.142578125, "learning_rate": 2.5400330896005485e-05, "loss": 1.440904974937439, "step": 6346 }, { "epoch": 0.5358209427730233, "grad_norm": 0.1357421875, "learning_rate": 2.539382199349299e-05, "loss": 1.466042399406433, "step": 6347 }, { "epoch": 0.5359053639078544, "grad_norm": 0.1435546875, "learning_rate": 2.5387313064278422e-05, "loss": 1.482100248336792, "step": 6348 }, { "epoch": 0.5359897850426855, "grad_norm": 0.14453125, "learning_rate": 2.538080410880309e-05, "loss": 1.5694688558578491, "step": 6349 }, { "epoch": 0.5360742061775166, "grad_norm": 0.146484375, "learning_rate": 2.537429512750833e-05, "loss": 1.5252599716186523, "step": 6350 }, { "epoch": 0.5361586273123476, "grad_norm": 0.134765625, "learning_rate": 2.5367786120835457e-05, "loss": 1.5409685373306274, "step": 6351 }, { "epoch": 0.5362430484471787, "grad_norm": 0.140625, "learning_rate": 2.5361277089225798e-05, "loss": 1.5137178897857666, "step": 6352 }, { "epoch": 0.5363274695820098, "grad_norm": 0.1318359375, "learning_rate": 2.5354768033120695e-05, "loss": 1.469653844833374, "step": 6353 }, { "epoch": 0.5364118907168409, "grad_norm": 0.134765625, "learning_rate": 2.5348258952961452e-05, "loss": 1.5434651374816895, "step": 6354 }, { "epoch": 0.536496311851672, "grad_norm": 0.140625, "learning_rate": 2.5341749849189428e-05, "loss": 1.5325251817703247, "step": 6355 }, { "epoch": 0.5365807329865032, "grad_norm": 0.140625, "learning_rate": 2.533524072224594e-05, "loss": 1.5524051189422607, "step": 6356 }, { "epoch": 0.5366651541213343, "grad_norm": 0.1484375, "learning_rate": 2.532873157257232e-05, "loss": 1.5950062274932861, "step": 6357 }, { "epoch": 0.5367495752561654, "grad_norm": 0.146484375, "learning_rate": 2.5322222400609914e-05, "loss": 1.578754186630249, "step": 6358 }, { "epoch": 0.5368339963909965, "grad_norm": 0.140625, "learning_rate": 2.5315713206800046e-05, "loss": 1.526193618774414, "step": 6359 }, { "epoch": 0.5369184175258276, "grad_norm": 0.13671875, "learning_rate": 2.5309203991584073e-05, "loss": 1.5039916038513184, "step": 6360 }, { "epoch": 0.5370028386606587, "grad_norm": 0.146484375, "learning_rate": 2.5302694755403326e-05, "loss": 1.5613327026367188, "step": 6361 }, { "epoch": 0.5370872597954898, "grad_norm": 0.134765625, "learning_rate": 2.5296185498699148e-05, "loss": 1.4959111213684082, "step": 6362 }, { "epoch": 0.5371716809303209, "grad_norm": 0.1318359375, "learning_rate": 2.528967622191287e-05, "loss": 1.5176489353179932, "step": 6363 }, { "epoch": 0.5372561020651521, "grad_norm": 0.1328125, "learning_rate": 2.5283166925485856e-05, "loss": 1.5327427387237549, "step": 6364 }, { "epoch": 0.5373405231999832, "grad_norm": 0.13671875, "learning_rate": 2.527665760985945e-05, "loss": 1.5541690587997437, "step": 6365 }, { "epoch": 0.5374249443348142, "grad_norm": 0.1328125, "learning_rate": 2.5270148275474988e-05, "loss": 1.4882827997207642, "step": 6366 }, { "epoch": 0.5375093654696453, "grad_norm": 0.1376953125, "learning_rate": 2.5263638922773824e-05, "loss": 1.4237395524978638, "step": 6367 }, { "epoch": 0.5375937866044764, "grad_norm": 0.130859375, "learning_rate": 2.5257129552197294e-05, "loss": 1.483190655708313, "step": 6368 }, { "epoch": 0.5376782077393075, "grad_norm": 0.134765625, "learning_rate": 2.5250620164186783e-05, "loss": 1.5247255563735962, "step": 6369 }, { "epoch": 0.5377626288741386, "grad_norm": 0.138671875, "learning_rate": 2.5244110759183608e-05, "loss": 1.5144600868225098, "step": 6370 }, { "epoch": 0.5378470500089697, "grad_norm": 0.158203125, "learning_rate": 2.5237601337629142e-05, "loss": 1.6241731643676758, "step": 6371 }, { "epoch": 0.5379314711438008, "grad_norm": 0.1494140625, "learning_rate": 2.5231091899964736e-05, "loss": 1.5513734817504883, "step": 6372 }, { "epoch": 0.538015892278632, "grad_norm": 0.13671875, "learning_rate": 2.5224582446631738e-05, "loss": 1.5456817150115967, "step": 6373 }, { "epoch": 0.5381003134134631, "grad_norm": 0.1318359375, "learning_rate": 2.521807297807152e-05, "loss": 1.506013035774231, "step": 6374 }, { "epoch": 0.5381847345482942, "grad_norm": 0.146484375, "learning_rate": 2.5211563494725422e-05, "loss": 1.4916174411773682, "step": 6375 }, { "epoch": 0.5382691556831253, "grad_norm": 0.140625, "learning_rate": 2.520505399703481e-05, "loss": 1.5789278745651245, "step": 6376 }, { "epoch": 0.5383535768179564, "grad_norm": 0.1318359375, "learning_rate": 2.519854448544105e-05, "loss": 1.5493764877319336, "step": 6377 }, { "epoch": 0.5384379979527875, "grad_norm": 0.12890625, "learning_rate": 2.519203496038549e-05, "loss": 1.5352896451950073, "step": 6378 }, { "epoch": 0.5385224190876186, "grad_norm": 0.16796875, "learning_rate": 2.518552542230951e-05, "loss": 1.553908109664917, "step": 6379 }, { "epoch": 0.5386068402224496, "grad_norm": 0.134765625, "learning_rate": 2.517901587165445e-05, "loss": 1.578876256942749, "step": 6380 }, { "epoch": 0.5386912613572808, "grad_norm": 0.1416015625, "learning_rate": 2.517250630886168e-05, "loss": 1.5370734930038452, "step": 6381 }, { "epoch": 0.5387756824921119, "grad_norm": 0.1357421875, "learning_rate": 2.516599673437257e-05, "loss": 1.539906620979309, "step": 6382 }, { "epoch": 0.538860103626943, "grad_norm": 0.140625, "learning_rate": 2.5159487148628485e-05, "loss": 1.581976294517517, "step": 6383 }, { "epoch": 0.5389445247617741, "grad_norm": 0.138671875, "learning_rate": 2.5152977552070794e-05, "loss": 1.542264461517334, "step": 6384 }, { "epoch": 0.5390289458966052, "grad_norm": 0.138671875, "learning_rate": 2.514646794514085e-05, "loss": 1.5175721645355225, "step": 6385 }, { "epoch": 0.5391133670314363, "grad_norm": 0.1318359375, "learning_rate": 2.5139958328280028e-05, "loss": 1.4642183780670166, "step": 6386 }, { "epoch": 0.5391977881662674, "grad_norm": 0.142578125, "learning_rate": 2.5133448701929695e-05, "loss": 1.5330556631088257, "step": 6387 }, { "epoch": 0.5392822093010985, "grad_norm": 0.130859375, "learning_rate": 2.5126939066531218e-05, "loss": 1.484971284866333, "step": 6388 }, { "epoch": 0.5393666304359296, "grad_norm": 0.142578125, "learning_rate": 2.5120429422525977e-05, "loss": 1.566344976425171, "step": 6389 }, { "epoch": 0.5394510515707608, "grad_norm": 0.1396484375, "learning_rate": 2.5113919770355316e-05, "loss": 1.5132590532302856, "step": 6390 }, { "epoch": 0.5395354727055919, "grad_norm": 0.140625, "learning_rate": 2.5107410110460632e-05, "loss": 1.5241988897323608, "step": 6391 }, { "epoch": 0.539619893840423, "grad_norm": 0.1328125, "learning_rate": 2.510090044328328e-05, "loss": 1.4983422756195068, "step": 6392 }, { "epoch": 0.5397043149752541, "grad_norm": 0.1435546875, "learning_rate": 2.5094390769264637e-05, "loss": 1.5000181198120117, "step": 6393 }, { "epoch": 0.5397887361100852, "grad_norm": 0.1455078125, "learning_rate": 2.5087881088846077e-05, "loss": 1.438820242881775, "step": 6394 }, { "epoch": 0.5398731572449162, "grad_norm": 0.1337890625, "learning_rate": 2.5081371402468956e-05, "loss": 1.462909460067749, "step": 6395 }, { "epoch": 0.5399575783797473, "grad_norm": 0.1484375, "learning_rate": 2.507486171057467e-05, "loss": 1.4970163106918335, "step": 6396 }, { "epoch": 0.5400419995145784, "grad_norm": 0.1474609375, "learning_rate": 2.5068352013604573e-05, "loss": 1.6044740676879883, "step": 6397 }, { "epoch": 0.5401264206494096, "grad_norm": 0.140625, "learning_rate": 2.506184231200005e-05, "loss": 1.548268437385559, "step": 6398 }, { "epoch": 0.5402108417842407, "grad_norm": 0.1533203125, "learning_rate": 2.5055332606202464e-05, "loss": 1.5953683853149414, "step": 6399 }, { "epoch": 0.5402952629190718, "grad_norm": 0.1376953125, "learning_rate": 2.50488228966532e-05, "loss": 1.525863528251648, "step": 6400 }, { "epoch": 0.5403796840539029, "grad_norm": 0.134765625, "learning_rate": 2.5042313183793625e-05, "loss": 1.4926674365997314, "step": 6401 }, { "epoch": 0.540464105188734, "grad_norm": 0.1337890625, "learning_rate": 2.5035803468065118e-05, "loss": 1.4739959239959717, "step": 6402 }, { "epoch": 0.5405485263235651, "grad_norm": 0.1435546875, "learning_rate": 2.5029293749909045e-05, "loss": 1.5501512289047241, "step": 6403 }, { "epoch": 0.5406329474583962, "grad_norm": 0.1376953125, "learning_rate": 2.5022784029766784e-05, "loss": 1.600808024406433, "step": 6404 }, { "epoch": 0.5407173685932273, "grad_norm": 0.1455078125, "learning_rate": 2.501627430807971e-05, "loss": 1.4833768606185913, "step": 6405 }, { "epoch": 0.5408017897280584, "grad_norm": 0.1357421875, "learning_rate": 2.5009764585289203e-05, "loss": 1.4305505752563477, "step": 6406 }, { "epoch": 0.5408862108628896, "grad_norm": 0.1396484375, "learning_rate": 2.5003254861836633e-05, "loss": 1.526084542274475, "step": 6407 }, { "epoch": 0.5409706319977207, "grad_norm": 0.138671875, "learning_rate": 2.499674513816338e-05, "loss": 1.4640343189239502, "step": 6408 }, { "epoch": 0.5410550531325518, "grad_norm": 0.146484375, "learning_rate": 2.49902354147108e-05, "loss": 1.5013940334320068, "step": 6409 }, { "epoch": 0.5411394742673828, "grad_norm": 0.134765625, "learning_rate": 2.4983725691920294e-05, "loss": 1.504707932472229, "step": 6410 }, { "epoch": 0.5412238954022139, "grad_norm": 0.1416015625, "learning_rate": 2.4977215970233225e-05, "loss": 1.4582675695419312, "step": 6411 }, { "epoch": 0.541308316537045, "grad_norm": 0.142578125, "learning_rate": 2.4970706250090958e-05, "loss": 1.4607030153274536, "step": 6412 }, { "epoch": 0.5413927376718761, "grad_norm": 0.134765625, "learning_rate": 2.4964196531934898e-05, "loss": 1.45745849609375, "step": 6413 }, { "epoch": 0.5414771588067072, "grad_norm": 0.1416015625, "learning_rate": 2.4957686816206377e-05, "loss": 1.5977636575698853, "step": 6414 }, { "epoch": 0.5415615799415384, "grad_norm": 0.13671875, "learning_rate": 2.49511771033468e-05, "loss": 1.5346440076828003, "step": 6415 }, { "epoch": 0.5416460010763695, "grad_norm": 0.1279296875, "learning_rate": 2.4944667393797538e-05, "loss": 1.4826509952545166, "step": 6416 }, { "epoch": 0.5417304222112006, "grad_norm": 0.1455078125, "learning_rate": 2.4938157687999954e-05, "loss": 1.5204968452453613, "step": 6417 }, { "epoch": 0.5418148433460317, "grad_norm": 0.154296875, "learning_rate": 2.4931647986395433e-05, "loss": 1.5580617189407349, "step": 6418 }, { "epoch": 0.5418992644808628, "grad_norm": 0.1572265625, "learning_rate": 2.4925138289425334e-05, "loss": 1.5729260444641113, "step": 6419 }, { "epoch": 0.5419836856156939, "grad_norm": 0.1416015625, "learning_rate": 2.4918628597531043e-05, "loss": 1.531097173690796, "step": 6420 }, { "epoch": 0.542068106750525, "grad_norm": 0.14453125, "learning_rate": 2.4912118911153935e-05, "loss": 1.5666987895965576, "step": 6421 }, { "epoch": 0.5421525278853561, "grad_norm": 0.1435546875, "learning_rate": 2.490560923073537e-05, "loss": 1.5116710662841797, "step": 6422 }, { "epoch": 0.5422369490201872, "grad_norm": 0.14453125, "learning_rate": 2.489909955671673e-05, "loss": 1.5554378032684326, "step": 6423 }, { "epoch": 0.5423213701550184, "grad_norm": 0.1435546875, "learning_rate": 2.489258988953937e-05, "loss": 1.614504098892212, "step": 6424 }, { "epoch": 0.5424057912898494, "grad_norm": 0.13671875, "learning_rate": 2.488608022964468e-05, "loss": 1.489672064781189, "step": 6425 }, { "epoch": 0.5424902124246805, "grad_norm": 0.1533203125, "learning_rate": 2.4879570577474035e-05, "loss": 1.5590863227844238, "step": 6426 }, { "epoch": 0.5425746335595116, "grad_norm": 0.1494140625, "learning_rate": 2.4873060933468785e-05, "loss": 1.5870487689971924, "step": 6427 }, { "epoch": 0.5426590546943427, "grad_norm": 0.142578125, "learning_rate": 2.4866551298070304e-05, "loss": 1.5392016172409058, "step": 6428 }, { "epoch": 0.5427434758291738, "grad_norm": 0.134765625, "learning_rate": 2.4860041671719975e-05, "loss": 1.5920131206512451, "step": 6429 }, { "epoch": 0.5428278969640049, "grad_norm": 0.1357421875, "learning_rate": 2.4853532054859152e-05, "loss": 1.546474575996399, "step": 6430 }, { "epoch": 0.542912318098836, "grad_norm": 0.1337890625, "learning_rate": 2.4847022447929215e-05, "loss": 1.4985049962997437, "step": 6431 }, { "epoch": 0.5429967392336672, "grad_norm": 0.1396484375, "learning_rate": 2.4840512851371518e-05, "loss": 1.513995885848999, "step": 6432 }, { "epoch": 0.5430811603684983, "grad_norm": 0.1416015625, "learning_rate": 2.4834003265627426e-05, "loss": 1.5574685335159302, "step": 6433 }, { "epoch": 0.5431655815033294, "grad_norm": 0.1484375, "learning_rate": 2.4827493691138322e-05, "loss": 1.5540392398834229, "step": 6434 }, { "epoch": 0.5432500026381605, "grad_norm": 0.1484375, "learning_rate": 2.482098412834556e-05, "loss": 1.5328779220581055, "step": 6435 }, { "epoch": 0.5433344237729916, "grad_norm": 0.15625, "learning_rate": 2.4814474577690504e-05, "loss": 1.578859567642212, "step": 6436 }, { "epoch": 0.5434188449078227, "grad_norm": 0.1474609375, "learning_rate": 2.4807965039614512e-05, "loss": 1.6001313924789429, "step": 6437 }, { "epoch": 0.5435032660426538, "grad_norm": 0.1396484375, "learning_rate": 2.4801455514558953e-05, "loss": 1.4895548820495605, "step": 6438 }, { "epoch": 0.5435876871774848, "grad_norm": 0.154296875, "learning_rate": 2.4794946002965193e-05, "loss": 1.5635528564453125, "step": 6439 }, { "epoch": 0.5436721083123159, "grad_norm": 0.14453125, "learning_rate": 2.478843650527458e-05, "loss": 1.6092214584350586, "step": 6440 }, { "epoch": 0.5437565294471471, "grad_norm": 0.13671875, "learning_rate": 2.478192702192849e-05, "loss": 1.362985372543335, "step": 6441 }, { "epoch": 0.5438409505819782, "grad_norm": 0.154296875, "learning_rate": 2.4775417553368268e-05, "loss": 1.5137008428573608, "step": 6442 }, { "epoch": 0.5439253717168093, "grad_norm": 0.1396484375, "learning_rate": 2.4768908100035267e-05, "loss": 1.5429518222808838, "step": 6443 }, { "epoch": 0.5440097928516404, "grad_norm": 0.1396484375, "learning_rate": 2.4762398662370867e-05, "loss": 1.5837534666061401, "step": 6444 }, { "epoch": 0.5440942139864715, "grad_norm": 0.1396484375, "learning_rate": 2.4755889240816398e-05, "loss": 1.424726128578186, "step": 6445 }, { "epoch": 0.5441786351213026, "grad_norm": 0.146484375, "learning_rate": 2.4749379835813223e-05, "loss": 1.5250531435012817, "step": 6446 }, { "epoch": 0.5442630562561337, "grad_norm": 0.140625, "learning_rate": 2.474287044780271e-05, "loss": 1.5752662420272827, "step": 6447 }, { "epoch": 0.5443474773909648, "grad_norm": 0.14453125, "learning_rate": 2.4736361077226182e-05, "loss": 1.5438491106033325, "step": 6448 }, { "epoch": 0.544431898525796, "grad_norm": 0.1474609375, "learning_rate": 2.4729851724525028e-05, "loss": 1.4344327449798584, "step": 6449 }, { "epoch": 0.5445163196606271, "grad_norm": 0.146484375, "learning_rate": 2.472334239014056e-05, "loss": 1.563511610031128, "step": 6450 }, { "epoch": 0.5446007407954582, "grad_norm": 0.1328125, "learning_rate": 2.4716833074514143e-05, "loss": 1.4924006462097168, "step": 6451 }, { "epoch": 0.5446851619302893, "grad_norm": 0.1416015625, "learning_rate": 2.4710323778087134e-05, "loss": 1.4463708400726318, "step": 6452 }, { "epoch": 0.5447695830651204, "grad_norm": 0.1318359375, "learning_rate": 2.4703814501300858e-05, "loss": 1.4902263879776, "step": 6453 }, { "epoch": 0.5448540041999514, "grad_norm": 0.1455078125, "learning_rate": 2.4697305244596686e-05, "loss": 1.553887963294983, "step": 6454 }, { "epoch": 0.5449384253347825, "grad_norm": 0.1435546875, "learning_rate": 2.469079600841593e-05, "loss": 1.5569783449172974, "step": 6455 }, { "epoch": 0.5450228464696136, "grad_norm": 0.1474609375, "learning_rate": 2.468428679319995e-05, "loss": 1.5073668956756592, "step": 6456 }, { "epoch": 0.5451072676044447, "grad_norm": 0.146484375, "learning_rate": 2.4677777599390095e-05, "loss": 1.436696171760559, "step": 6457 }, { "epoch": 0.5451916887392759, "grad_norm": 0.138671875, "learning_rate": 2.4671268427427687e-05, "loss": 1.5312453508377075, "step": 6458 }, { "epoch": 0.545276109874107, "grad_norm": 0.154296875, "learning_rate": 2.4664759277754063e-05, "loss": 1.5970969200134277, "step": 6459 }, { "epoch": 0.5453605310089381, "grad_norm": 0.142578125, "learning_rate": 2.4658250150810578e-05, "loss": 1.567935824394226, "step": 6460 }, { "epoch": 0.5454449521437692, "grad_norm": 0.154296875, "learning_rate": 2.4651741047038547e-05, "loss": 1.5079995393753052, "step": 6461 }, { "epoch": 0.5455293732786003, "grad_norm": 0.1484375, "learning_rate": 2.4645231966879314e-05, "loss": 1.5431404113769531, "step": 6462 }, { "epoch": 0.5456137944134314, "grad_norm": 0.138671875, "learning_rate": 2.4638722910774205e-05, "loss": 1.4620269536972046, "step": 6463 }, { "epoch": 0.5456982155482625, "grad_norm": 0.1259765625, "learning_rate": 2.4632213879164542e-05, "loss": 1.5227054357528687, "step": 6464 }, { "epoch": 0.5457826366830936, "grad_norm": 0.126953125, "learning_rate": 2.4625704872491676e-05, "loss": 1.5677120685577393, "step": 6465 }, { "epoch": 0.5458670578179248, "grad_norm": 0.140625, "learning_rate": 2.4619195891196912e-05, "loss": 1.4528056383132935, "step": 6466 }, { "epoch": 0.5459514789527559, "grad_norm": 0.142578125, "learning_rate": 2.461268693572159e-05, "loss": 1.4648693799972534, "step": 6467 }, { "epoch": 0.546035900087587, "grad_norm": 0.1337890625, "learning_rate": 2.4606178006507017e-05, "loss": 1.4972175359725952, "step": 6468 }, { "epoch": 0.546120321222418, "grad_norm": 0.150390625, "learning_rate": 2.4599669103994517e-05, "loss": 1.532205581665039, "step": 6469 }, { "epoch": 0.5462047423572491, "grad_norm": 0.1474609375, "learning_rate": 2.459316022862542e-05, "loss": 1.548776388168335, "step": 6470 }, { "epoch": 0.5462891634920802, "grad_norm": 0.1474609375, "learning_rate": 2.458665138084104e-05, "loss": 1.5830022096633911, "step": 6471 }, { "epoch": 0.5463735846269113, "grad_norm": 0.1455078125, "learning_rate": 2.458014256108269e-05, "loss": 1.5047366619110107, "step": 6472 }, { "epoch": 0.5464580057617424, "grad_norm": 0.140625, "learning_rate": 2.4573633769791682e-05, "loss": 1.5385441780090332, "step": 6473 }, { "epoch": 0.5465424268965735, "grad_norm": 0.1474609375, "learning_rate": 2.456712500740932e-05, "loss": 1.5027512311935425, "step": 6474 }, { "epoch": 0.5466268480314047, "grad_norm": 0.138671875, "learning_rate": 2.4560616274376937e-05, "loss": 1.5424011945724487, "step": 6475 }, { "epoch": 0.5467112691662358, "grad_norm": 0.13671875, "learning_rate": 2.455410757113582e-05, "loss": 1.5044312477111816, "step": 6476 }, { "epoch": 0.5467956903010669, "grad_norm": 0.1376953125, "learning_rate": 2.4547598898127282e-05, "loss": 1.5030723810195923, "step": 6477 }, { "epoch": 0.546880111435898, "grad_norm": 0.1357421875, "learning_rate": 2.454109025579263e-05, "loss": 1.5099573135375977, "step": 6478 }, { "epoch": 0.5469645325707291, "grad_norm": 0.1435546875, "learning_rate": 2.4534581644573152e-05, "loss": 1.5335441827774048, "step": 6479 }, { "epoch": 0.5470489537055602, "grad_norm": 0.1298828125, "learning_rate": 2.4528073064910174e-05, "loss": 1.474519968032837, "step": 6480 }, { "epoch": 0.5471333748403913, "grad_norm": 0.1416015625, "learning_rate": 2.452156451724496e-05, "loss": 1.5205693244934082, "step": 6481 }, { "epoch": 0.5472177959752224, "grad_norm": 0.146484375, "learning_rate": 2.4515056002018827e-05, "loss": 1.5465480089187622, "step": 6482 }, { "epoch": 0.5473022171100536, "grad_norm": 0.13671875, "learning_rate": 2.4508547519673066e-05, "loss": 1.5193952322006226, "step": 6483 }, { "epoch": 0.5473866382448846, "grad_norm": 0.1435546875, "learning_rate": 2.450203907064896e-05, "loss": 1.5389695167541504, "step": 6484 }, { "epoch": 0.5474710593797157, "grad_norm": 0.15234375, "learning_rate": 2.449553065538781e-05, "loss": 1.553946852684021, "step": 6485 }, { "epoch": 0.5475554805145468, "grad_norm": 0.1455078125, "learning_rate": 2.4489022274330884e-05, "loss": 1.397512435913086, "step": 6486 }, { "epoch": 0.5476399016493779, "grad_norm": 0.1630859375, "learning_rate": 2.4482513927919478e-05, "loss": 1.6622658967971802, "step": 6487 }, { "epoch": 0.547724322784209, "grad_norm": 0.138671875, "learning_rate": 2.4476005616594877e-05, "loss": 1.5565181970596313, "step": 6488 }, { "epoch": 0.5478087439190401, "grad_norm": 0.1376953125, "learning_rate": 2.4469497340798345e-05, "loss": 1.5264440774917603, "step": 6489 }, { "epoch": 0.5478931650538712, "grad_norm": 0.140625, "learning_rate": 2.446298910097119e-05, "loss": 1.494728922843933, "step": 6490 }, { "epoch": 0.5479775861887023, "grad_norm": 0.140625, "learning_rate": 2.445648089755464e-05, "loss": 1.492112398147583, "step": 6491 }, { "epoch": 0.5480620073235335, "grad_norm": 0.142578125, "learning_rate": 2.4449972730989997e-05, "loss": 1.5669655799865723, "step": 6492 }, { "epoch": 0.5481464284583646, "grad_norm": 0.1435546875, "learning_rate": 2.4443464601718537e-05, "loss": 1.5490849018096924, "step": 6493 }, { "epoch": 0.5482308495931957, "grad_norm": 0.134765625, "learning_rate": 2.4436956510181506e-05, "loss": 1.5252076387405396, "step": 6494 }, { "epoch": 0.5483152707280268, "grad_norm": 0.1474609375, "learning_rate": 2.443044845682017e-05, "loss": 1.4685418605804443, "step": 6495 }, { "epoch": 0.5483996918628579, "grad_norm": 0.1416015625, "learning_rate": 2.442394044207581e-05, "loss": 1.418795108795166, "step": 6496 }, { "epoch": 0.548484112997689, "grad_norm": 0.1396484375, "learning_rate": 2.4417432466389668e-05, "loss": 1.529132604598999, "step": 6497 }, { "epoch": 0.54856853413252, "grad_norm": 0.1357421875, "learning_rate": 2.4410924530203007e-05, "loss": 1.5254777669906616, "step": 6498 }, { "epoch": 0.5486529552673511, "grad_norm": 0.169921875, "learning_rate": 2.4404416633957076e-05, "loss": 1.639824628829956, "step": 6499 }, { "epoch": 0.5487373764021822, "grad_norm": 0.130859375, "learning_rate": 2.4397908778093126e-05, "loss": 1.4790351390838623, "step": 6500 }, { "epoch": 0.5488217975370134, "grad_norm": 0.14453125, "learning_rate": 2.4391400963052417e-05, "loss": 1.583620309829712, "step": 6501 }, { "epoch": 0.5489062186718445, "grad_norm": 0.1396484375, "learning_rate": 2.438489318927618e-05, "loss": 1.5704925060272217, "step": 6502 }, { "epoch": 0.5489906398066756, "grad_norm": 0.13671875, "learning_rate": 2.4378385457205667e-05, "loss": 1.518730878829956, "step": 6503 }, { "epoch": 0.5490750609415067, "grad_norm": 0.130859375, "learning_rate": 2.437187776728211e-05, "loss": 1.5077805519104004, "step": 6504 }, { "epoch": 0.5491594820763378, "grad_norm": 0.138671875, "learning_rate": 2.4365370119946747e-05, "loss": 1.526872992515564, "step": 6505 }, { "epoch": 0.5492439032111689, "grad_norm": 0.140625, "learning_rate": 2.435886251564082e-05, "loss": 1.4952789545059204, "step": 6506 }, { "epoch": 0.549328324346, "grad_norm": 0.146484375, "learning_rate": 2.4352354954805555e-05, "loss": 1.4919415712356567, "step": 6507 }, { "epoch": 0.5494127454808311, "grad_norm": 0.158203125, "learning_rate": 2.4345847437882185e-05, "loss": 1.5637177228927612, "step": 6508 }, { "epoch": 0.5494971666156623, "grad_norm": 0.142578125, "learning_rate": 2.4339339965311926e-05, "loss": 1.575257658958435, "step": 6509 }, { "epoch": 0.5495815877504934, "grad_norm": 0.142578125, "learning_rate": 2.4332832537536e-05, "loss": 1.4938642978668213, "step": 6510 }, { "epoch": 0.5496660088853245, "grad_norm": 0.134765625, "learning_rate": 2.4326325154995645e-05, "loss": 1.5694879293441772, "step": 6511 }, { "epoch": 0.5497504300201556, "grad_norm": 0.15234375, "learning_rate": 2.4319817818132055e-05, "loss": 1.495237946510315, "step": 6512 }, { "epoch": 0.5498348511549866, "grad_norm": 0.1484375, "learning_rate": 2.431331052738645e-05, "loss": 1.5609999895095825, "step": 6513 }, { "epoch": 0.5499192722898177, "grad_norm": 0.1494140625, "learning_rate": 2.4306803283200052e-05, "loss": 1.4590051174163818, "step": 6514 }, { "epoch": 0.5500036934246488, "grad_norm": 0.15234375, "learning_rate": 2.4300296086014042e-05, "loss": 1.5577900409698486, "step": 6515 }, { "epoch": 0.5500881145594799, "grad_norm": 0.1396484375, "learning_rate": 2.4293788936269655e-05, "loss": 1.531140923500061, "step": 6516 }, { "epoch": 0.550172535694311, "grad_norm": 0.16015625, "learning_rate": 2.428728183440807e-05, "loss": 1.5247721672058105, "step": 6517 }, { "epoch": 0.5502569568291422, "grad_norm": 0.130859375, "learning_rate": 2.4280774780870484e-05, "loss": 1.504956841468811, "step": 6518 }, { "epoch": 0.5503413779639733, "grad_norm": 0.1337890625, "learning_rate": 2.4274267776098107e-05, "loss": 1.4439527988433838, "step": 6519 }, { "epoch": 0.5504257990988044, "grad_norm": 0.140625, "learning_rate": 2.4267760820532108e-05, "loss": 1.5350085496902466, "step": 6520 }, { "epoch": 0.5505102202336355, "grad_norm": 0.134765625, "learning_rate": 2.42612539146137e-05, "loss": 1.514662504196167, "step": 6521 }, { "epoch": 0.5505946413684666, "grad_norm": 0.15234375, "learning_rate": 2.4254747058784034e-05, "loss": 1.6262117624282837, "step": 6522 }, { "epoch": 0.5506790625032977, "grad_norm": 0.1455078125, "learning_rate": 2.424824025348432e-05, "loss": 1.5067036151885986, "step": 6523 }, { "epoch": 0.5507634836381288, "grad_norm": 0.1416015625, "learning_rate": 2.424173349915573e-05, "loss": 1.5376375913619995, "step": 6524 }, { "epoch": 0.5508479047729599, "grad_norm": 0.138671875, "learning_rate": 2.4235226796239413e-05, "loss": 1.5361193418502808, "step": 6525 }, { "epoch": 0.5509323259077911, "grad_norm": 0.1396484375, "learning_rate": 2.4228720145176567e-05, "loss": 1.498002529144287, "step": 6526 }, { "epoch": 0.5510167470426222, "grad_norm": 0.14453125, "learning_rate": 2.4222213546408353e-05, "loss": 1.442471981048584, "step": 6527 }, { "epoch": 0.5511011681774532, "grad_norm": 0.1376953125, "learning_rate": 2.421570700037593e-05, "loss": 1.488374948501587, "step": 6528 }, { "epoch": 0.5511855893122843, "grad_norm": 0.1630859375, "learning_rate": 2.4209200507520456e-05, "loss": 1.5016119480133057, "step": 6529 }, { "epoch": 0.5512700104471154, "grad_norm": 0.1376953125, "learning_rate": 2.420269406828308e-05, "loss": 1.4900141954421997, "step": 6530 }, { "epoch": 0.5513544315819465, "grad_norm": 0.1416015625, "learning_rate": 2.419618768310497e-05, "loss": 1.5038598775863647, "step": 6531 }, { "epoch": 0.5514388527167776, "grad_norm": 0.13671875, "learning_rate": 2.418968135242727e-05, "loss": 1.508094310760498, "step": 6532 }, { "epoch": 0.5515232738516087, "grad_norm": 0.142578125, "learning_rate": 2.4183175076691116e-05, "loss": 1.5672500133514404, "step": 6533 }, { "epoch": 0.5516076949864398, "grad_norm": 0.1337890625, "learning_rate": 2.4176668856337663e-05, "loss": 1.5067964792251587, "step": 6534 }, { "epoch": 0.551692116121271, "grad_norm": 0.1845703125, "learning_rate": 2.4170162691808034e-05, "loss": 1.5294601917266846, "step": 6535 }, { "epoch": 0.5517765372561021, "grad_norm": 0.1416015625, "learning_rate": 2.4163656583543366e-05, "loss": 1.4899216890335083, "step": 6536 }, { "epoch": 0.5518609583909332, "grad_norm": 0.134765625, "learning_rate": 2.4157150531984802e-05, "loss": 1.5437910556793213, "step": 6537 }, { "epoch": 0.5519453795257643, "grad_norm": 0.138671875, "learning_rate": 2.415064453757345e-05, "loss": 1.5628880262374878, "step": 6538 }, { "epoch": 0.5520298006605954, "grad_norm": 0.1640625, "learning_rate": 2.414413860075045e-05, "loss": 1.4794073104858398, "step": 6539 }, { "epoch": 0.5521142217954265, "grad_norm": 0.14453125, "learning_rate": 2.41376327219569e-05, "loss": 1.602303385734558, "step": 6540 }, { "epoch": 0.5521986429302576, "grad_norm": 0.158203125, "learning_rate": 2.413112690163392e-05, "loss": 1.5641285181045532, "step": 6541 }, { "epoch": 0.5522830640650886, "grad_norm": 0.1474609375, "learning_rate": 2.4124621140222635e-05, "loss": 1.6289957761764526, "step": 6542 }, { "epoch": 0.5523674851999198, "grad_norm": 0.1357421875, "learning_rate": 2.4118115438164136e-05, "loss": 1.5353471040725708, "step": 6543 }, { "epoch": 0.5524519063347509, "grad_norm": 0.138671875, "learning_rate": 2.4111609795899526e-05, "loss": 1.563204288482666, "step": 6544 }, { "epoch": 0.552536327469582, "grad_norm": 0.1396484375, "learning_rate": 2.4105104213869922e-05, "loss": 1.5593212842941284, "step": 6545 }, { "epoch": 0.5526207486044131, "grad_norm": 0.13671875, "learning_rate": 2.409859869251639e-05, "loss": 1.443429708480835, "step": 6546 }, { "epoch": 0.5527051697392442, "grad_norm": 0.1484375, "learning_rate": 2.409209323228004e-05, "loss": 1.5330305099487305, "step": 6547 }, { "epoch": 0.5527895908740753, "grad_norm": 0.13671875, "learning_rate": 2.4085587833601945e-05, "loss": 1.57905113697052, "step": 6548 }, { "epoch": 0.5528740120089064, "grad_norm": 0.146484375, "learning_rate": 2.4079082496923197e-05, "loss": 1.5086729526519775, "step": 6549 }, { "epoch": 0.5529584331437375, "grad_norm": 0.1455078125, "learning_rate": 2.407257722268487e-05, "loss": 1.6609247922897339, "step": 6550 }, { "epoch": 0.5530428542785686, "grad_norm": 0.1474609375, "learning_rate": 2.4066072011328032e-05, "loss": 1.4910917282104492, "step": 6551 }, { "epoch": 0.5531272754133998, "grad_norm": 0.1396484375, "learning_rate": 2.4059566863293763e-05, "loss": 1.5214542150497437, "step": 6552 }, { "epoch": 0.5532116965482309, "grad_norm": 0.1396484375, "learning_rate": 2.405306177902312e-05, "loss": 1.5315684080123901, "step": 6553 }, { "epoch": 0.553296117683062, "grad_norm": 0.12890625, "learning_rate": 2.4046556758957158e-05, "loss": 1.4715156555175781, "step": 6554 }, { "epoch": 0.5533805388178931, "grad_norm": 0.1474609375, "learning_rate": 2.404005180353695e-05, "loss": 1.5394197702407837, "step": 6555 }, { "epoch": 0.5534649599527242, "grad_norm": 0.1396484375, "learning_rate": 2.4033546913203522e-05, "loss": 1.4618113040924072, "step": 6556 }, { "epoch": 0.5535493810875552, "grad_norm": 0.1376953125, "learning_rate": 2.402704208839795e-05, "loss": 1.622420072555542, "step": 6557 }, { "epoch": 0.5536338022223863, "grad_norm": 0.1396484375, "learning_rate": 2.402053732956126e-05, "loss": 1.5404276847839355, "step": 6558 }, { "epoch": 0.5537182233572174, "grad_norm": 0.138671875, "learning_rate": 2.4014032637134488e-05, "loss": 1.4373472929000854, "step": 6559 }, { "epoch": 0.5538026444920486, "grad_norm": 0.1435546875, "learning_rate": 2.4007528011558683e-05, "loss": 1.5168201923370361, "step": 6560 }, { "epoch": 0.5538870656268797, "grad_norm": 0.1494140625, "learning_rate": 2.400102345327485e-05, "loss": 1.5804097652435303, "step": 6561 }, { "epoch": 0.5539714867617108, "grad_norm": 0.154296875, "learning_rate": 2.3994518962724036e-05, "loss": 1.4960427284240723, "step": 6562 }, { "epoch": 0.5540559078965419, "grad_norm": 0.138671875, "learning_rate": 2.398801454034726e-05, "loss": 1.5905613899230957, "step": 6563 }, { "epoch": 0.554140329031373, "grad_norm": 0.142578125, "learning_rate": 2.3981510186585524e-05, "loss": 1.5127767324447632, "step": 6564 }, { "epoch": 0.5542247501662041, "grad_norm": 0.1376953125, "learning_rate": 2.397500590187985e-05, "loss": 1.5573890209197998, "step": 6565 }, { "epoch": 0.5543091713010352, "grad_norm": 0.1474609375, "learning_rate": 2.396850168667123e-05, "loss": 1.5739439725875854, "step": 6566 }, { "epoch": 0.5543935924358663, "grad_norm": 0.142578125, "learning_rate": 2.396199754140068e-05, "loss": 1.57050621509552, "step": 6567 }, { "epoch": 0.5544780135706974, "grad_norm": 0.1396484375, "learning_rate": 2.3955493466509195e-05, "loss": 1.5733380317687988, "step": 6568 }, { "epoch": 0.5545624347055286, "grad_norm": 0.146484375, "learning_rate": 2.3948989462437757e-05, "loss": 1.5609431266784668, "step": 6569 }, { "epoch": 0.5546468558403597, "grad_norm": 0.138671875, "learning_rate": 2.3942485529627366e-05, "loss": 1.4866286516189575, "step": 6570 }, { "epoch": 0.5547312769751908, "grad_norm": 0.1396484375, "learning_rate": 2.3935981668518992e-05, "loss": 1.5518250465393066, "step": 6571 }, { "epoch": 0.5548156981100218, "grad_norm": 0.1416015625, "learning_rate": 2.392947787955362e-05, "loss": 1.5711147785186768, "step": 6572 }, { "epoch": 0.5549001192448529, "grad_norm": 0.134765625, "learning_rate": 2.392297416317223e-05, "loss": 1.5909525156021118, "step": 6573 }, { "epoch": 0.554984540379684, "grad_norm": 0.130859375, "learning_rate": 2.391647051981577e-05, "loss": 1.503958821296692, "step": 6574 }, { "epoch": 0.5550689615145151, "grad_norm": 0.140625, "learning_rate": 2.390996694992522e-05, "loss": 1.4380712509155273, "step": 6575 }, { "epoch": 0.5551533826493462, "grad_norm": 0.1455078125, "learning_rate": 2.3903463453941526e-05, "loss": 1.478562593460083, "step": 6576 }, { "epoch": 0.5552378037841774, "grad_norm": 0.146484375, "learning_rate": 2.3896960032305642e-05, "loss": 1.4976438283920288, "step": 6577 }, { "epoch": 0.5553222249190085, "grad_norm": 0.1376953125, "learning_rate": 2.389045668545853e-05, "loss": 1.5066639184951782, "step": 6578 }, { "epoch": 0.5554066460538396, "grad_norm": 0.1494140625, "learning_rate": 2.3883953413841116e-05, "loss": 1.5716546773910522, "step": 6579 }, { "epoch": 0.5554910671886707, "grad_norm": 0.142578125, "learning_rate": 2.3877450217894333e-05, "loss": 1.4902104139328003, "step": 6580 }, { "epoch": 0.5555754883235018, "grad_norm": 0.13671875, "learning_rate": 2.3870947098059145e-05, "loss": 1.5167635679244995, "step": 6581 }, { "epoch": 0.5556599094583329, "grad_norm": 0.13671875, "learning_rate": 2.386444405477644e-05, "loss": 1.5014681816101074, "step": 6582 }, { "epoch": 0.555744330593164, "grad_norm": 0.1376953125, "learning_rate": 2.3857941088487167e-05, "loss": 1.4770137071609497, "step": 6583 }, { "epoch": 0.5558287517279951, "grad_norm": 0.1328125, "learning_rate": 2.3851438199632232e-05, "loss": 1.5119585990905762, "step": 6584 }, { "epoch": 0.5559131728628262, "grad_norm": 0.150390625, "learning_rate": 2.3844935388652545e-05, "loss": 1.5931295156478882, "step": 6585 }, { "epoch": 0.5559975939976574, "grad_norm": 0.142578125, "learning_rate": 2.383843265598902e-05, "loss": 1.53200364112854, "step": 6586 }, { "epoch": 0.5560820151324884, "grad_norm": 0.142578125, "learning_rate": 2.3831930002082542e-05, "loss": 1.5382224321365356, "step": 6587 }, { "epoch": 0.5561664362673195, "grad_norm": 0.1455078125, "learning_rate": 2.3825427427374032e-05, "loss": 1.5476583242416382, "step": 6588 }, { "epoch": 0.5562508574021506, "grad_norm": 0.138671875, "learning_rate": 2.3818924932304353e-05, "loss": 1.5348293781280518, "step": 6589 }, { "epoch": 0.5563352785369817, "grad_norm": 0.1455078125, "learning_rate": 2.3812422517314408e-05, "loss": 1.5561703443527222, "step": 6590 }, { "epoch": 0.5564196996718128, "grad_norm": 0.1337890625, "learning_rate": 2.3805920182845075e-05, "loss": 1.4623651504516602, "step": 6591 }, { "epoch": 0.5565041208066439, "grad_norm": 0.1376953125, "learning_rate": 2.3799417929337215e-05, "loss": 1.5948407649993896, "step": 6592 }, { "epoch": 0.556588541941475, "grad_norm": 0.1337890625, "learning_rate": 2.3792915757231712e-05, "loss": 1.514407753944397, "step": 6593 }, { "epoch": 0.5566729630763062, "grad_norm": 0.1494140625, "learning_rate": 2.378641366696942e-05, "loss": 1.5093117952346802, "step": 6594 }, { "epoch": 0.5567573842111373, "grad_norm": 0.134765625, "learning_rate": 2.37799116589912e-05, "loss": 1.441554069519043, "step": 6595 }, { "epoch": 0.5568418053459684, "grad_norm": 0.142578125, "learning_rate": 2.3773409733737903e-05, "loss": 1.546703815460205, "step": 6596 }, { "epoch": 0.5569262264807995, "grad_norm": 0.138671875, "learning_rate": 2.3766907891650364e-05, "loss": 1.4882621765136719, "step": 6597 }, { "epoch": 0.5570106476156306, "grad_norm": 0.1533203125, "learning_rate": 2.3760406133169443e-05, "loss": 1.6005767583847046, "step": 6598 }, { "epoch": 0.5570950687504617, "grad_norm": 0.15234375, "learning_rate": 2.375390445873597e-05, "loss": 1.5159313678741455, "step": 6599 }, { "epoch": 0.5571794898852928, "grad_norm": 0.1318359375, "learning_rate": 2.374740286879076e-05, "loss": 1.550066590309143, "step": 6600 }, { "epoch": 0.5572639110201238, "grad_norm": 0.146484375, "learning_rate": 2.3740901363774655e-05, "loss": 1.5752619504928589, "step": 6601 }, { "epoch": 0.5573483321549549, "grad_norm": 0.1376953125, "learning_rate": 2.3734399944128454e-05, "loss": 1.5521976947784424, "step": 6602 }, { "epoch": 0.5574327532897861, "grad_norm": 0.1376953125, "learning_rate": 2.3727898610292983e-05, "loss": 1.5131136178970337, "step": 6603 }, { "epoch": 0.5575171744246172, "grad_norm": 0.140625, "learning_rate": 2.3721397362709054e-05, "loss": 1.5326426029205322, "step": 6604 }, { "epoch": 0.5576015955594483, "grad_norm": 0.142578125, "learning_rate": 2.3714896201817446e-05, "loss": 1.5452966690063477, "step": 6605 }, { "epoch": 0.5576860166942794, "grad_norm": 0.1748046875, "learning_rate": 2.3708395128058972e-05, "loss": 1.45321786403656, "step": 6606 }, { "epoch": 0.5577704378291105, "grad_norm": 0.1376953125, "learning_rate": 2.37018941418744e-05, "loss": 1.5365701913833618, "step": 6607 }, { "epoch": 0.5578548589639416, "grad_norm": 0.1455078125, "learning_rate": 2.3695393243704533e-05, "loss": 1.5092387199401855, "step": 6608 }, { "epoch": 0.5579392800987727, "grad_norm": 0.1435546875, "learning_rate": 2.3688892433990145e-05, "loss": 1.542725682258606, "step": 6609 }, { "epoch": 0.5580237012336038, "grad_norm": 0.1318359375, "learning_rate": 2.3682391713171998e-05, "loss": 1.517991542816162, "step": 6610 }, { "epoch": 0.558108122368435, "grad_norm": 0.1298828125, "learning_rate": 2.3675891081690853e-05, "loss": 1.5030447244644165, "step": 6611 }, { "epoch": 0.5581925435032661, "grad_norm": 0.1416015625, "learning_rate": 2.3669390539987492e-05, "loss": 1.5700589418411255, "step": 6612 }, { "epoch": 0.5582769646380972, "grad_norm": 0.14453125, "learning_rate": 2.3662890088502633e-05, "loss": 1.5905946493148804, "step": 6613 }, { "epoch": 0.5583613857729283, "grad_norm": 0.1416015625, "learning_rate": 2.365638972767705e-05, "loss": 1.5335371494293213, "step": 6614 }, { "epoch": 0.5584458069077594, "grad_norm": 0.146484375, "learning_rate": 2.3649889457951472e-05, "loss": 1.5522562265396118, "step": 6615 }, { "epoch": 0.5585302280425904, "grad_norm": 0.1494140625, "learning_rate": 2.3643389279766622e-05, "loss": 1.6090656518936157, "step": 6616 }, { "epoch": 0.5586146491774215, "grad_norm": 0.138671875, "learning_rate": 2.363688919356326e-05, "loss": 1.5253833532333374, "step": 6617 }, { "epoch": 0.5586990703122526, "grad_norm": 0.138671875, "learning_rate": 2.3630389199782072e-05, "loss": 1.5844788551330566, "step": 6618 }, { "epoch": 0.5587834914470837, "grad_norm": 0.1484375, "learning_rate": 2.36238892988638e-05, "loss": 1.582287311553955, "step": 6619 }, { "epoch": 0.5588679125819149, "grad_norm": 0.1328125, "learning_rate": 2.361738949124913e-05, "loss": 1.4444999694824219, "step": 6620 }, { "epoch": 0.558952333716746, "grad_norm": 0.138671875, "learning_rate": 2.3610889777378776e-05, "loss": 1.5085694789886475, "step": 6621 }, { "epoch": 0.5590367548515771, "grad_norm": 0.134765625, "learning_rate": 2.360439015769345e-05, "loss": 1.497869610786438, "step": 6622 }, { "epoch": 0.5591211759864082, "grad_norm": 0.1513671875, "learning_rate": 2.3597890632633807e-05, "loss": 1.5937491655349731, "step": 6623 }, { "epoch": 0.5592055971212393, "grad_norm": 0.1337890625, "learning_rate": 2.3591391202640562e-05, "loss": 1.5216054916381836, "step": 6624 }, { "epoch": 0.5592900182560704, "grad_norm": 0.1396484375, "learning_rate": 2.3584891868154375e-05, "loss": 1.4876664876937866, "step": 6625 }, { "epoch": 0.5593744393909015, "grad_norm": 0.13671875, "learning_rate": 2.3578392629615916e-05, "loss": 1.5504990816116333, "step": 6626 }, { "epoch": 0.5594588605257326, "grad_norm": 0.142578125, "learning_rate": 2.3571893487465863e-05, "loss": 1.5811970233917236, "step": 6627 }, { "epoch": 0.5595432816605638, "grad_norm": 0.1474609375, "learning_rate": 2.3565394442144852e-05, "loss": 1.5292755365371704, "step": 6628 }, { "epoch": 0.5596277027953949, "grad_norm": 0.1435546875, "learning_rate": 2.355889549409355e-05, "loss": 1.5123353004455566, "step": 6629 }, { "epoch": 0.559712123930226, "grad_norm": 0.1337890625, "learning_rate": 2.355239664375261e-05, "loss": 1.5702060461044312, "step": 6630 }, { "epoch": 0.559796545065057, "grad_norm": 0.1318359375, "learning_rate": 2.3545897891562644e-05, "loss": 1.5173468589782715, "step": 6631 }, { "epoch": 0.5598809661998881, "grad_norm": 0.1435546875, "learning_rate": 2.353939923796431e-05, "loss": 1.5521297454833984, "step": 6632 }, { "epoch": 0.5599653873347192, "grad_norm": 0.140625, "learning_rate": 2.35329006833982e-05, "loss": 1.5534272193908691, "step": 6633 }, { "epoch": 0.5600498084695503, "grad_norm": 0.138671875, "learning_rate": 2.3526402228304955e-05, "loss": 1.5533612966537476, "step": 6634 }, { "epoch": 0.5601342296043814, "grad_norm": 0.14453125, "learning_rate": 2.351990387312519e-05, "loss": 1.5442137718200684, "step": 6635 }, { "epoch": 0.5602186507392125, "grad_norm": 0.15625, "learning_rate": 2.3513405618299494e-05, "loss": 1.5677390098571777, "step": 6636 }, { "epoch": 0.5603030718740437, "grad_norm": 0.12451171875, "learning_rate": 2.3506907464268478e-05, "loss": 1.4570430517196655, "step": 6637 }, { "epoch": 0.5603874930088748, "grad_norm": 0.1337890625, "learning_rate": 2.350040941147271e-05, "loss": 1.4930680990219116, "step": 6638 }, { "epoch": 0.5604719141437059, "grad_norm": 0.1435546875, "learning_rate": 2.3493911460352794e-05, "loss": 1.5272918939590454, "step": 6639 }, { "epoch": 0.560556335278537, "grad_norm": 0.1416015625, "learning_rate": 2.3487413611349306e-05, "loss": 1.5743950605392456, "step": 6640 }, { "epoch": 0.5606407564133681, "grad_norm": 0.130859375, "learning_rate": 2.348091586490281e-05, "loss": 1.5011835098266602, "step": 6641 }, { "epoch": 0.5607251775481992, "grad_norm": 0.140625, "learning_rate": 2.3474418221453873e-05, "loss": 1.5900459289550781, "step": 6642 }, { "epoch": 0.5608095986830303, "grad_norm": 0.14453125, "learning_rate": 2.3467920681443038e-05, "loss": 1.5583410263061523, "step": 6643 }, { "epoch": 0.5608940198178614, "grad_norm": 0.142578125, "learning_rate": 2.3461423245310864e-05, "loss": 1.5157408714294434, "step": 6644 }, { "epoch": 0.5609784409526926, "grad_norm": 0.1484375, "learning_rate": 2.34549259134979e-05, "loss": 1.563393473625183, "step": 6645 }, { "epoch": 0.5610628620875237, "grad_norm": 0.1328125, "learning_rate": 2.344842868644467e-05, "loss": 1.4525806903839111, "step": 6646 }, { "epoch": 0.5611472832223547, "grad_norm": 0.15625, "learning_rate": 2.34419315645917e-05, "loss": 1.6008836030960083, "step": 6647 }, { "epoch": 0.5612317043571858, "grad_norm": 0.140625, "learning_rate": 2.343543454837952e-05, "loss": 1.510560154914856, "step": 6648 }, { "epoch": 0.5613161254920169, "grad_norm": 0.1484375, "learning_rate": 2.342893763824864e-05, "loss": 1.4848498106002808, "step": 6649 }, { "epoch": 0.561400546626848, "grad_norm": 0.150390625, "learning_rate": 2.3422440834639565e-05, "loss": 1.5527846813201904, "step": 6650 }, { "epoch": 0.5614849677616791, "grad_norm": 0.1435546875, "learning_rate": 2.3415944137992788e-05, "loss": 1.5660144090652466, "step": 6651 }, { "epoch": 0.5615693888965102, "grad_norm": 0.1396484375, "learning_rate": 2.3409447548748803e-05, "loss": 1.5432208776474, "step": 6652 }, { "epoch": 0.5616538100313413, "grad_norm": 0.1416015625, "learning_rate": 2.340295106734811e-05, "loss": 1.4996392726898193, "step": 6653 }, { "epoch": 0.5617382311661725, "grad_norm": 0.142578125, "learning_rate": 2.339645469423116e-05, "loss": 1.6521718502044678, "step": 6654 }, { "epoch": 0.5618226523010036, "grad_norm": 0.13671875, "learning_rate": 2.338995842983845e-05, "loss": 1.5192811489105225, "step": 6655 }, { "epoch": 0.5619070734358347, "grad_norm": 0.142578125, "learning_rate": 2.338346227461042e-05, "loss": 1.455217957496643, "step": 6656 }, { "epoch": 0.5619914945706658, "grad_norm": 0.14453125, "learning_rate": 2.3376966228987524e-05, "loss": 1.5874135494232178, "step": 6657 }, { "epoch": 0.5620759157054969, "grad_norm": 0.142578125, "learning_rate": 2.337047029341024e-05, "loss": 1.5110667943954468, "step": 6658 }, { "epoch": 0.562160336840328, "grad_norm": 0.1484375, "learning_rate": 2.336397446831897e-05, "loss": 1.5171458721160889, "step": 6659 }, { "epoch": 0.562244757975159, "grad_norm": 0.142578125, "learning_rate": 2.3357478754154173e-05, "loss": 1.4954652786254883, "step": 6660 }, { "epoch": 0.5623291791099901, "grad_norm": 0.140625, "learning_rate": 2.335098315135626e-05, "loss": 1.4835829734802246, "step": 6661 }, { "epoch": 0.5624136002448213, "grad_norm": 0.1376953125, "learning_rate": 2.3344487660365647e-05, "loss": 1.4583234786987305, "step": 6662 }, { "epoch": 0.5624980213796524, "grad_norm": 0.130859375, "learning_rate": 2.333799228162277e-05, "loss": 1.4943082332611084, "step": 6663 }, { "epoch": 0.5625824425144835, "grad_norm": 0.1328125, "learning_rate": 2.3331497015567988e-05, "loss": 1.5162925720214844, "step": 6664 }, { "epoch": 0.5626668636493146, "grad_norm": 0.1494140625, "learning_rate": 2.332500186264173e-05, "loss": 1.5281317234039307, "step": 6665 }, { "epoch": 0.5627512847841457, "grad_norm": 0.1298828125, "learning_rate": 2.3318506823284376e-05, "loss": 1.4913922548294067, "step": 6666 }, { "epoch": 0.5628357059189768, "grad_norm": 0.142578125, "learning_rate": 2.3312011897936297e-05, "loss": 1.5290348529815674, "step": 6667 }, { "epoch": 0.5629201270538079, "grad_norm": 0.1328125, "learning_rate": 2.330551708703787e-05, "loss": 1.525438666343689, "step": 6668 }, { "epoch": 0.563004548188639, "grad_norm": 0.1396484375, "learning_rate": 2.329902239102945e-05, "loss": 1.5215483903884888, "step": 6669 }, { "epoch": 0.5630889693234701, "grad_norm": 0.146484375, "learning_rate": 2.3292527810351404e-05, "loss": 1.5131312608718872, "step": 6670 }, { "epoch": 0.5631733904583013, "grad_norm": 0.134765625, "learning_rate": 2.3286033345444082e-05, "loss": 1.472608208656311, "step": 6671 }, { "epoch": 0.5632578115931324, "grad_norm": 0.162109375, "learning_rate": 2.3279538996747817e-05, "loss": 1.57112717628479, "step": 6672 }, { "epoch": 0.5633422327279635, "grad_norm": 0.1357421875, "learning_rate": 2.3273044764702943e-05, "loss": 1.4748237133026123, "step": 6673 }, { "epoch": 0.5634266538627946, "grad_norm": 0.134765625, "learning_rate": 2.326655064974978e-05, "loss": 1.4934475421905518, "step": 6674 }, { "epoch": 0.5635110749976256, "grad_norm": 0.1396484375, "learning_rate": 2.3260056652328652e-05, "loss": 1.439807653427124, "step": 6675 }, { "epoch": 0.5635954961324567, "grad_norm": 0.140625, "learning_rate": 2.325356277287987e-05, "loss": 1.5321264266967773, "step": 6676 }, { "epoch": 0.5636799172672878, "grad_norm": 0.1357421875, "learning_rate": 2.3247069011843728e-05, "loss": 1.5219272375106812, "step": 6677 }, { "epoch": 0.5637643384021189, "grad_norm": 0.1337890625, "learning_rate": 2.324057536966051e-05, "loss": 1.5198614597320557, "step": 6678 }, { "epoch": 0.5638487595369501, "grad_norm": 0.1708984375, "learning_rate": 2.323408184677053e-05, "loss": 1.6113982200622559, "step": 6679 }, { "epoch": 0.5639331806717812, "grad_norm": 0.146484375, "learning_rate": 2.3227588443614033e-05, "loss": 1.605634331703186, "step": 6680 }, { "epoch": 0.5640176018066123, "grad_norm": 0.1376953125, "learning_rate": 2.3221095160631308e-05, "loss": 1.5685936212539673, "step": 6681 }, { "epoch": 0.5641020229414434, "grad_norm": 0.1435546875, "learning_rate": 2.3214601998262602e-05, "loss": 1.5368108749389648, "step": 6682 }, { "epoch": 0.5641864440762745, "grad_norm": 0.1416015625, "learning_rate": 2.320810895694816e-05, "loss": 1.55655038356781, "step": 6683 }, { "epoch": 0.5642708652111056, "grad_norm": 0.1318359375, "learning_rate": 2.3201616037128258e-05, "loss": 1.5037375688552856, "step": 6684 }, { "epoch": 0.5643552863459367, "grad_norm": 0.150390625, "learning_rate": 2.3195123239243098e-05, "loss": 1.46750807762146, "step": 6685 }, { "epoch": 0.5644397074807678, "grad_norm": 0.138671875, "learning_rate": 2.318863056373293e-05, "loss": 1.5266939401626587, "step": 6686 }, { "epoch": 0.5645241286155989, "grad_norm": 0.1357421875, "learning_rate": 2.3182138011037964e-05, "loss": 1.525556206703186, "step": 6687 }, { "epoch": 0.5646085497504301, "grad_norm": 0.15625, "learning_rate": 2.3175645581598397e-05, "loss": 1.5677604675292969, "step": 6688 }, { "epoch": 0.5646929708852612, "grad_norm": 0.1416015625, "learning_rate": 2.3169153275854463e-05, "loss": 1.5111202001571655, "step": 6689 }, { "epoch": 0.5647773920200923, "grad_norm": 0.154296875, "learning_rate": 2.3162661094246325e-05, "loss": 1.5547617673873901, "step": 6690 }, { "epoch": 0.5648618131549233, "grad_norm": 0.13671875, "learning_rate": 2.3156169037214188e-05, "loss": 1.4988938570022583, "step": 6691 }, { "epoch": 0.5649462342897544, "grad_norm": 0.134765625, "learning_rate": 2.3149677105198216e-05, "loss": 1.5081589221954346, "step": 6692 }, { "epoch": 0.5650306554245855, "grad_norm": 0.1396484375, "learning_rate": 2.314318529863858e-05, "loss": 1.5718564987182617, "step": 6693 }, { "epoch": 0.5651150765594166, "grad_norm": 0.162109375, "learning_rate": 2.313669361797546e-05, "loss": 1.554452896118164, "step": 6694 }, { "epoch": 0.5651994976942477, "grad_norm": 0.1435546875, "learning_rate": 2.3130202063648976e-05, "loss": 1.5107840299606323, "step": 6695 }, { "epoch": 0.5652839188290789, "grad_norm": 0.1357421875, "learning_rate": 2.3123710636099295e-05, "loss": 1.5598679780960083, "step": 6696 }, { "epoch": 0.56536833996391, "grad_norm": 0.140625, "learning_rate": 2.3117219335766542e-05, "loss": 1.5201222896575928, "step": 6697 }, { "epoch": 0.5654527610987411, "grad_norm": 0.134765625, "learning_rate": 2.3110728163090836e-05, "loss": 1.52445387840271, "step": 6698 }, { "epoch": 0.5655371822335722, "grad_norm": 0.140625, "learning_rate": 2.3104237118512316e-05, "loss": 1.5794790983200073, "step": 6699 }, { "epoch": 0.5656216033684033, "grad_norm": 0.1484375, "learning_rate": 2.3097746202471063e-05, "loss": 1.5480549335479736, "step": 6700 }, { "epoch": 0.5657060245032344, "grad_norm": 0.1357421875, "learning_rate": 2.3091255415407194e-05, "loss": 1.503610372543335, "step": 6701 }, { "epoch": 0.5657904456380655, "grad_norm": 0.1376953125, "learning_rate": 2.3084764757760802e-05, "loss": 1.5656553506851196, "step": 6702 }, { "epoch": 0.5658748667728966, "grad_norm": 0.1513671875, "learning_rate": 2.3078274229971957e-05, "loss": 1.4722727537155151, "step": 6703 }, { "epoch": 0.5659592879077276, "grad_norm": 0.1328125, "learning_rate": 2.3071783832480743e-05, "loss": 1.449195146560669, "step": 6704 }, { "epoch": 0.5660437090425589, "grad_norm": 0.1376953125, "learning_rate": 2.3065293565727212e-05, "loss": 1.4709798097610474, "step": 6705 }, { "epoch": 0.5661281301773899, "grad_norm": 0.1337890625, "learning_rate": 2.305880343015143e-05, "loss": 1.501918077468872, "step": 6706 }, { "epoch": 0.566212551312221, "grad_norm": 0.1435546875, "learning_rate": 2.305231342619345e-05, "loss": 1.5574134588241577, "step": 6707 }, { "epoch": 0.5662969724470521, "grad_norm": 0.1474609375, "learning_rate": 2.304582355429329e-05, "loss": 1.5297279357910156, "step": 6708 }, { "epoch": 0.5663813935818832, "grad_norm": 0.1396484375, "learning_rate": 2.3039333814891e-05, "loss": 1.5082111358642578, "step": 6709 }, { "epoch": 0.5664658147167143, "grad_norm": 0.1396484375, "learning_rate": 2.303284420842658e-05, "loss": 1.5354300737380981, "step": 6710 }, { "epoch": 0.5665502358515454, "grad_norm": 0.1396484375, "learning_rate": 2.3026354735340057e-05, "loss": 1.6027193069458008, "step": 6711 }, { "epoch": 0.5666346569863765, "grad_norm": 0.138671875, "learning_rate": 2.3019865396071428e-05, "loss": 1.5335209369659424, "step": 6712 }, { "epoch": 0.5667190781212077, "grad_norm": 0.134765625, "learning_rate": 2.3013376191060682e-05, "loss": 1.530334234237671, "step": 6713 }, { "epoch": 0.5668034992560388, "grad_norm": 0.150390625, "learning_rate": 2.30068871207478e-05, "loss": 1.5281219482421875, "step": 6714 }, { "epoch": 0.5668879203908699, "grad_norm": 0.1396484375, "learning_rate": 2.300039818557277e-05, "loss": 1.5645992755889893, "step": 6715 }, { "epoch": 0.566972341525701, "grad_norm": 0.1337890625, "learning_rate": 2.2993909385975548e-05, "loss": 1.581368327140808, "step": 6716 }, { "epoch": 0.5670567626605321, "grad_norm": 0.1357421875, "learning_rate": 2.2987420722396095e-05, "loss": 1.5434194803237915, "step": 6717 }, { "epoch": 0.5671411837953632, "grad_norm": 0.140625, "learning_rate": 2.2980932195274352e-05, "loss": 1.519860863685608, "step": 6718 }, { "epoch": 0.5672256049301942, "grad_norm": 0.130859375, "learning_rate": 2.2974443805050253e-05, "loss": 1.5651988983154297, "step": 6719 }, { "epoch": 0.5673100260650253, "grad_norm": 0.138671875, "learning_rate": 2.296795555216374e-05, "loss": 1.5383243560791016, "step": 6720 }, { "epoch": 0.5673944471998564, "grad_norm": 0.138671875, "learning_rate": 2.2961467437054727e-05, "loss": 1.5452468395233154, "step": 6721 }, { "epoch": 0.5674788683346876, "grad_norm": 0.15625, "learning_rate": 2.295497946016312e-05, "loss": 1.448390245437622, "step": 6722 }, { "epoch": 0.5675632894695187, "grad_norm": 0.1357421875, "learning_rate": 2.294849162192882e-05, "loss": 1.3892252445220947, "step": 6723 }, { "epoch": 0.5676477106043498, "grad_norm": 0.1298828125, "learning_rate": 2.294200392279171e-05, "loss": 1.465672492980957, "step": 6724 }, { "epoch": 0.5677321317391809, "grad_norm": 0.130859375, "learning_rate": 2.2935516363191693e-05, "loss": 1.499752402305603, "step": 6725 }, { "epoch": 0.567816552874012, "grad_norm": 0.140625, "learning_rate": 2.2929028943568625e-05, "loss": 1.5978662967681885, "step": 6726 }, { "epoch": 0.5679009740088431, "grad_norm": 0.142578125, "learning_rate": 2.292254166436238e-05, "loss": 1.5546581745147705, "step": 6727 }, { "epoch": 0.5679853951436742, "grad_norm": 0.1376953125, "learning_rate": 2.2916054526012793e-05, "loss": 1.5077638626098633, "step": 6728 }, { "epoch": 0.5680698162785053, "grad_norm": 0.1396484375, "learning_rate": 2.2909567528959717e-05, "loss": 1.5241106748580933, "step": 6729 }, { "epoch": 0.5681542374133365, "grad_norm": 0.15625, "learning_rate": 2.2903080673643002e-05, "loss": 1.5682425498962402, "step": 6730 }, { "epoch": 0.5682386585481676, "grad_norm": 0.138671875, "learning_rate": 2.2896593960502437e-05, "loss": 1.4324922561645508, "step": 6731 }, { "epoch": 0.5683230796829987, "grad_norm": 0.1328125, "learning_rate": 2.2890107389977867e-05, "loss": 1.5152080059051514, "step": 6732 }, { "epoch": 0.5684075008178298, "grad_norm": 0.1513671875, "learning_rate": 2.2883620962509095e-05, "loss": 1.4899473190307617, "step": 6733 }, { "epoch": 0.5684919219526609, "grad_norm": 0.1376953125, "learning_rate": 2.2877134678535896e-05, "loss": 1.56219482421875, "step": 6734 }, { "epoch": 0.5685763430874919, "grad_norm": 0.140625, "learning_rate": 2.2870648538498085e-05, "loss": 1.4947090148925781, "step": 6735 }, { "epoch": 0.568660764222323, "grad_norm": 0.140625, "learning_rate": 2.2864162542835406e-05, "loss": 1.5304896831512451, "step": 6736 }, { "epoch": 0.5687451853571541, "grad_norm": 0.1455078125, "learning_rate": 2.2857676691987646e-05, "loss": 1.5241929292678833, "step": 6737 }, { "epoch": 0.5688296064919852, "grad_norm": 0.1416015625, "learning_rate": 2.2851190986394558e-05, "loss": 1.5912425518035889, "step": 6738 }, { "epoch": 0.5689140276268164, "grad_norm": 0.1416015625, "learning_rate": 2.2844705426495877e-05, "loss": 1.5282092094421387, "step": 6739 }, { "epoch": 0.5689984487616475, "grad_norm": 0.134765625, "learning_rate": 2.2838220012731365e-05, "loss": 1.4450387954711914, "step": 6740 }, { "epoch": 0.5690828698964786, "grad_norm": 0.1396484375, "learning_rate": 2.2831734745540717e-05, "loss": 1.5352343320846558, "step": 6741 }, { "epoch": 0.5691672910313097, "grad_norm": 0.1474609375, "learning_rate": 2.282524962536367e-05, "loss": 1.5199174880981445, "step": 6742 }, { "epoch": 0.5692517121661408, "grad_norm": 0.1474609375, "learning_rate": 2.281876465263993e-05, "loss": 1.5830422639846802, "step": 6743 }, { "epoch": 0.5693361333009719, "grad_norm": 0.1376953125, "learning_rate": 2.2812279827809187e-05, "loss": 1.4715611934661865, "step": 6744 }, { "epoch": 0.569420554435803, "grad_norm": 0.138671875, "learning_rate": 2.280579515131112e-05, "loss": 1.5084047317504883, "step": 6745 }, { "epoch": 0.5695049755706341, "grad_norm": 0.1396484375, "learning_rate": 2.2799310623585433e-05, "loss": 1.3989996910095215, "step": 6746 }, { "epoch": 0.5695893967054653, "grad_norm": 0.130859375, "learning_rate": 2.2792826245071766e-05, "loss": 1.4720675945281982, "step": 6747 }, { "epoch": 0.5696738178402964, "grad_norm": 0.1357421875, "learning_rate": 2.2786342016209792e-05, "loss": 1.5729384422302246, "step": 6748 }, { "epoch": 0.5697582389751275, "grad_norm": 0.1416015625, "learning_rate": 2.2779857937439143e-05, "loss": 1.584799885749817, "step": 6749 }, { "epoch": 0.5698426601099585, "grad_norm": 0.138671875, "learning_rate": 2.277337400919946e-05, "loss": 1.5368726253509521, "step": 6750 }, { "epoch": 0.5699270812447896, "grad_norm": 0.1474609375, "learning_rate": 2.2766890231930377e-05, "loss": 1.496105670928955, "step": 6751 }, { "epoch": 0.5700115023796207, "grad_norm": 0.1494140625, "learning_rate": 2.27604066060715e-05, "loss": 1.504561424255371, "step": 6752 }, { "epoch": 0.5700959235144518, "grad_norm": 0.150390625, "learning_rate": 2.275392313206245e-05, "loss": 1.4946987628936768, "step": 6753 }, { "epoch": 0.5701803446492829, "grad_norm": 0.1396484375, "learning_rate": 2.27474398103428e-05, "loss": 1.5230014324188232, "step": 6754 }, { "epoch": 0.570264765784114, "grad_norm": 0.1494140625, "learning_rate": 2.274095664135214e-05, "loss": 1.5976378917694092, "step": 6755 }, { "epoch": 0.5703491869189452, "grad_norm": 0.138671875, "learning_rate": 2.2734473625530057e-05, "loss": 1.5997633934020996, "step": 6756 }, { "epoch": 0.5704336080537763, "grad_norm": 0.1396484375, "learning_rate": 2.272799076331611e-05, "loss": 1.5017939805984497, "step": 6757 }, { "epoch": 0.5705180291886074, "grad_norm": 0.1376953125, "learning_rate": 2.2721508055149852e-05, "loss": 1.5242574214935303, "step": 6758 }, { "epoch": 0.5706024503234385, "grad_norm": 0.140625, "learning_rate": 2.271502550147082e-05, "loss": 1.5460832118988037, "step": 6759 }, { "epoch": 0.5706868714582696, "grad_norm": 0.1337890625, "learning_rate": 2.2708543102718542e-05, "loss": 1.4479140043258667, "step": 6760 }, { "epoch": 0.5707712925931007, "grad_norm": 0.1435546875, "learning_rate": 2.2702060859332565e-05, "loss": 1.4926522970199585, "step": 6761 }, { "epoch": 0.5708557137279318, "grad_norm": 0.12890625, "learning_rate": 2.269557877175238e-05, "loss": 1.4569091796875, "step": 6762 }, { "epoch": 0.5709401348627628, "grad_norm": 0.146484375, "learning_rate": 2.2689096840417493e-05, "loss": 1.5312925577163696, "step": 6763 }, { "epoch": 0.571024555997594, "grad_norm": 0.138671875, "learning_rate": 2.26826150657674e-05, "loss": 1.5420136451721191, "step": 6764 }, { "epoch": 0.5711089771324251, "grad_norm": 0.1484375, "learning_rate": 2.2676133448241563e-05, "loss": 1.6010558605194092, "step": 6765 }, { "epoch": 0.5711933982672562, "grad_norm": 0.154296875, "learning_rate": 2.2669651988279476e-05, "loss": 1.5816742181777954, "step": 6766 }, { "epoch": 0.5712778194020873, "grad_norm": 0.1455078125, "learning_rate": 2.266317068632058e-05, "loss": 1.5227150917053223, "step": 6767 }, { "epoch": 0.5713622405369184, "grad_norm": 0.1357421875, "learning_rate": 2.2656689542804326e-05, "loss": 1.5103734731674194, "step": 6768 }, { "epoch": 0.5714466616717495, "grad_norm": 0.1318359375, "learning_rate": 2.2650208558170162e-05, "loss": 1.441286563873291, "step": 6769 }, { "epoch": 0.5715310828065806, "grad_norm": 0.1455078125, "learning_rate": 2.26437277328575e-05, "loss": 1.5412191152572632, "step": 6770 }, { "epoch": 0.5716155039414117, "grad_norm": 0.1376953125, "learning_rate": 2.263724706730577e-05, "loss": 1.5051294565200806, "step": 6771 }, { "epoch": 0.5716999250762428, "grad_norm": 0.1357421875, "learning_rate": 2.2630766561954353e-05, "loss": 1.4913852214813232, "step": 6772 }, { "epoch": 0.571784346211074, "grad_norm": 0.1357421875, "learning_rate": 2.2624286217242665e-05, "loss": 1.550589680671692, "step": 6773 }, { "epoch": 0.5718687673459051, "grad_norm": 0.1416015625, "learning_rate": 2.261780603361009e-05, "loss": 1.5620620250701904, "step": 6774 }, { "epoch": 0.5719531884807362, "grad_norm": 0.1376953125, "learning_rate": 2.2611326011495974e-05, "loss": 1.5263277292251587, "step": 6775 }, { "epoch": 0.5720376096155673, "grad_norm": 0.1357421875, "learning_rate": 2.260484615133972e-05, "loss": 1.483681559562683, "step": 6776 }, { "epoch": 0.5721220307503984, "grad_norm": 0.134765625, "learning_rate": 2.259836645358063e-05, "loss": 1.4962828159332275, "step": 6777 }, { "epoch": 0.5722064518852295, "grad_norm": 0.146484375, "learning_rate": 2.2591886918658082e-05, "loss": 1.5354430675506592, "step": 6778 }, { "epoch": 0.5722908730200605, "grad_norm": 0.14453125, "learning_rate": 2.258540754701139e-05, "loss": 1.5521031618118286, "step": 6779 }, { "epoch": 0.5723752941548916, "grad_norm": 0.1357421875, "learning_rate": 2.2578928339079857e-05, "loss": 1.4890658855438232, "step": 6780 }, { "epoch": 0.5724597152897228, "grad_norm": 0.1572265625, "learning_rate": 2.2572449295302812e-05, "loss": 1.599316120147705, "step": 6781 }, { "epoch": 0.5725441364245539, "grad_norm": 0.130859375, "learning_rate": 2.2565970416119543e-05, "loss": 1.515693187713623, "step": 6782 }, { "epoch": 0.572628557559385, "grad_norm": 0.1357421875, "learning_rate": 2.2559491701969324e-05, "loss": 1.5064960718154907, "step": 6783 }, { "epoch": 0.5727129786942161, "grad_norm": 0.142578125, "learning_rate": 2.255301315329144e-05, "loss": 1.5379575490951538, "step": 6784 }, { "epoch": 0.5727973998290472, "grad_norm": 0.1494140625, "learning_rate": 2.254653477052514e-05, "loss": 1.5391061305999756, "step": 6785 }, { "epoch": 0.5728818209638783, "grad_norm": 0.140625, "learning_rate": 2.2540056554109677e-05, "loss": 1.475682258605957, "step": 6786 }, { "epoch": 0.5729662420987094, "grad_norm": 0.142578125, "learning_rate": 2.2533578504484303e-05, "loss": 1.5019335746765137, "step": 6787 }, { "epoch": 0.5730506632335405, "grad_norm": 0.1357421875, "learning_rate": 2.2527100622088227e-05, "loss": 1.5705140829086304, "step": 6788 }, { "epoch": 0.5731350843683716, "grad_norm": 0.1357421875, "learning_rate": 2.2520622907360676e-05, "loss": 1.5099685192108154, "step": 6789 }, { "epoch": 0.5732195055032028, "grad_norm": 0.1513671875, "learning_rate": 2.251414536074085e-05, "loss": 1.569680094718933, "step": 6790 }, { "epoch": 0.5733039266380339, "grad_norm": 0.1435546875, "learning_rate": 2.250766798266794e-05, "loss": 1.5173819065093994, "step": 6791 }, { "epoch": 0.573388347772865, "grad_norm": 0.138671875, "learning_rate": 2.250119077358114e-05, "loss": 1.5652796030044556, "step": 6792 }, { "epoch": 0.573472768907696, "grad_norm": 0.1337890625, "learning_rate": 2.2494713733919607e-05, "loss": 1.4598480463027954, "step": 6793 }, { "epoch": 0.5735571900425271, "grad_norm": 0.146484375, "learning_rate": 2.2488236864122512e-05, "loss": 1.5287631750106812, "step": 6794 }, { "epoch": 0.5736416111773582, "grad_norm": 0.140625, "learning_rate": 2.2481760164628984e-05, "loss": 1.5052379369735718, "step": 6795 }, { "epoch": 0.5737260323121893, "grad_norm": 0.1416015625, "learning_rate": 2.247528363587817e-05, "loss": 1.6279724836349487, "step": 6796 }, { "epoch": 0.5738104534470204, "grad_norm": 0.1416015625, "learning_rate": 2.2468807278309202e-05, "loss": 1.4801920652389526, "step": 6797 }, { "epoch": 0.5738948745818516, "grad_norm": 0.1416015625, "learning_rate": 2.246233109236118e-05, "loss": 1.580423355102539, "step": 6798 }, { "epoch": 0.5739792957166827, "grad_norm": 0.1435546875, "learning_rate": 2.245585507847321e-05, "loss": 1.481316089630127, "step": 6799 }, { "epoch": 0.5740637168515138, "grad_norm": 0.1396484375, "learning_rate": 2.2449379237084388e-05, "loss": 1.531354546546936, "step": 6800 }, { "epoch": 0.5741481379863449, "grad_norm": 0.142578125, "learning_rate": 2.2442903568633773e-05, "loss": 1.5095049142837524, "step": 6801 }, { "epoch": 0.574232559121176, "grad_norm": 0.1669921875, "learning_rate": 2.2436428073560452e-05, "loss": 1.466845154762268, "step": 6802 }, { "epoch": 0.5743169802560071, "grad_norm": 0.130859375, "learning_rate": 2.2429952752303465e-05, "loss": 1.4133588075637817, "step": 6803 }, { "epoch": 0.5744014013908382, "grad_norm": 0.13671875, "learning_rate": 2.2423477605301857e-05, "loss": 1.4563640356063843, "step": 6804 }, { "epoch": 0.5744858225256693, "grad_norm": 0.140625, "learning_rate": 2.241700263299467e-05, "loss": 1.5113214254379272, "step": 6805 }, { "epoch": 0.5745702436605004, "grad_norm": 0.142578125, "learning_rate": 2.24105278358209e-05, "loss": 1.4949047565460205, "step": 6806 }, { "epoch": 0.5746546647953316, "grad_norm": 0.1376953125, "learning_rate": 2.240405321421958e-05, "loss": 1.4970718622207642, "step": 6807 }, { "epoch": 0.5747390859301627, "grad_norm": 0.1435546875, "learning_rate": 2.239757876862968e-05, "loss": 1.5540199279785156, "step": 6808 }, { "epoch": 0.5748235070649937, "grad_norm": 0.13671875, "learning_rate": 2.23911044994902e-05, "loss": 1.5804985761642456, "step": 6809 }, { "epoch": 0.5749079281998248, "grad_norm": 0.1416015625, "learning_rate": 2.238463040724011e-05, "loss": 1.566820740699768, "step": 6810 }, { "epoch": 0.5749923493346559, "grad_norm": 0.13671875, "learning_rate": 2.2378156492318356e-05, "loss": 1.5381643772125244, "step": 6811 }, { "epoch": 0.575076770469487, "grad_norm": 0.134765625, "learning_rate": 2.237168275516391e-05, "loss": 1.4933799505233765, "step": 6812 }, { "epoch": 0.5751611916043181, "grad_norm": 0.1435546875, "learning_rate": 2.2365209196215672e-05, "loss": 1.5673799514770508, "step": 6813 }, { "epoch": 0.5752456127391492, "grad_norm": 0.1513671875, "learning_rate": 2.235873581591259e-05, "loss": 1.5765724182128906, "step": 6814 }, { "epoch": 0.5753300338739803, "grad_norm": 0.13671875, "learning_rate": 2.2352262614693574e-05, "loss": 1.4717895984649658, "step": 6815 }, { "epoch": 0.5754144550088115, "grad_norm": 0.1513671875, "learning_rate": 2.2345789592997506e-05, "loss": 1.5788847208023071, "step": 6816 }, { "epoch": 0.5754988761436426, "grad_norm": 0.138671875, "learning_rate": 2.233931675126329e-05, "loss": 1.6226484775543213, "step": 6817 }, { "epoch": 0.5755832972784737, "grad_norm": 0.1396484375, "learning_rate": 2.23328440899298e-05, "loss": 1.4981650114059448, "step": 6818 }, { "epoch": 0.5756677184133048, "grad_norm": 0.1416015625, "learning_rate": 2.2326371609435883e-05, "loss": 1.508745551109314, "step": 6819 }, { "epoch": 0.5757521395481359, "grad_norm": 0.1376953125, "learning_rate": 2.2319899310220406e-05, "loss": 1.5260950326919556, "step": 6820 }, { "epoch": 0.575836560682967, "grad_norm": 0.15234375, "learning_rate": 2.231342719272219e-05, "loss": 1.644171953201294, "step": 6821 }, { "epoch": 0.575920981817798, "grad_norm": 0.1474609375, "learning_rate": 2.2306955257380064e-05, "loss": 1.6449240446090698, "step": 6822 }, { "epoch": 0.5760054029526291, "grad_norm": 0.1416015625, "learning_rate": 2.2300483504632856e-05, "loss": 1.592907428741455, "step": 6823 }, { "epoch": 0.5760898240874603, "grad_norm": 0.146484375, "learning_rate": 2.2294011934919348e-05, "loss": 1.5795899629592896, "step": 6824 }, { "epoch": 0.5761742452222914, "grad_norm": 0.1552734375, "learning_rate": 2.2287540548678344e-05, "loss": 1.6310781240463257, "step": 6825 }, { "epoch": 0.5762586663571225, "grad_norm": 0.1376953125, "learning_rate": 2.2281069346348602e-05, "loss": 1.4859440326690674, "step": 6826 }, { "epoch": 0.5763430874919536, "grad_norm": 0.13671875, "learning_rate": 2.227459832836889e-05, "loss": 1.4727767705917358, "step": 6827 }, { "epoch": 0.5764275086267847, "grad_norm": 0.1396484375, "learning_rate": 2.226812749517797e-05, "loss": 1.4901515245437622, "step": 6828 }, { "epoch": 0.5765119297616158, "grad_norm": 0.1357421875, "learning_rate": 2.2261656847214572e-05, "loss": 1.4282218217849731, "step": 6829 }, { "epoch": 0.5765963508964469, "grad_norm": 0.1416015625, "learning_rate": 2.225518638491741e-05, "loss": 1.5286251306533813, "step": 6830 }, { "epoch": 0.576680772031278, "grad_norm": 0.1337890625, "learning_rate": 2.224871610872523e-05, "loss": 1.560643196105957, "step": 6831 }, { "epoch": 0.5767651931661091, "grad_norm": 0.1376953125, "learning_rate": 2.2242246019076694e-05, "loss": 1.5421099662780762, "step": 6832 }, { "epoch": 0.5768496143009403, "grad_norm": 0.12890625, "learning_rate": 2.223577611641052e-05, "loss": 1.5165951251983643, "step": 6833 }, { "epoch": 0.5769340354357714, "grad_norm": 0.1318359375, "learning_rate": 2.222930640116536e-05, "loss": 1.5237147808074951, "step": 6834 }, { "epoch": 0.5770184565706025, "grad_norm": 0.1513671875, "learning_rate": 2.2222836873779888e-05, "loss": 1.56056547164917, "step": 6835 }, { "epoch": 0.5771028777054336, "grad_norm": 0.1416015625, "learning_rate": 2.2216367534692756e-05, "loss": 1.5936037302017212, "step": 6836 }, { "epoch": 0.5771872988402647, "grad_norm": 0.1435546875, "learning_rate": 2.2209898384342582e-05, "loss": 1.6113967895507812, "step": 6837 }, { "epoch": 0.5772717199750957, "grad_norm": 0.142578125, "learning_rate": 2.2203429423168022e-05, "loss": 1.5895828008651733, "step": 6838 }, { "epoch": 0.5773561411099268, "grad_norm": 0.14453125, "learning_rate": 2.219696065160766e-05, "loss": 1.505820870399475, "step": 6839 }, { "epoch": 0.5774405622447579, "grad_norm": 0.1357421875, "learning_rate": 2.2190492070100103e-05, "loss": 1.4571691751480103, "step": 6840 }, { "epoch": 0.5775249833795891, "grad_norm": 0.1416015625, "learning_rate": 2.218402367908394e-05, "loss": 1.4534820318222046, "step": 6841 }, { "epoch": 0.5776094045144202, "grad_norm": 0.1474609375, "learning_rate": 2.2177555478997734e-05, "loss": 1.6622127294540405, "step": 6842 }, { "epoch": 0.5776938256492513, "grad_norm": 0.13671875, "learning_rate": 2.217108747028006e-05, "loss": 1.53859281539917, "step": 6843 }, { "epoch": 0.5777782467840824, "grad_norm": 0.1396484375, "learning_rate": 2.216461965336945e-05, "loss": 1.4870033264160156, "step": 6844 }, { "epoch": 0.5778626679189135, "grad_norm": 0.140625, "learning_rate": 2.215815202870444e-05, "loss": 1.4670952558517456, "step": 6845 }, { "epoch": 0.5779470890537446, "grad_norm": 0.1318359375, "learning_rate": 2.2151684596723564e-05, "loss": 1.5255413055419922, "step": 6846 }, { "epoch": 0.5780315101885757, "grad_norm": 0.134765625, "learning_rate": 2.2145217357865307e-05, "loss": 1.5143191814422607, "step": 6847 }, { "epoch": 0.5781159313234068, "grad_norm": 0.1484375, "learning_rate": 2.2138750312568177e-05, "loss": 1.588911533355713, "step": 6848 }, { "epoch": 0.5782003524582379, "grad_norm": 0.142578125, "learning_rate": 2.213228346127066e-05, "loss": 1.5378938913345337, "step": 6849 }, { "epoch": 0.5782847735930691, "grad_norm": 0.140625, "learning_rate": 2.2125816804411216e-05, "loss": 1.6018106937408447, "step": 6850 }, { "epoch": 0.5783691947279002, "grad_norm": 0.142578125, "learning_rate": 2.2119350342428302e-05, "loss": 1.5365593433380127, "step": 6851 }, { "epoch": 0.5784536158627313, "grad_norm": 0.14453125, "learning_rate": 2.2112884075760347e-05, "loss": 1.5739121437072754, "step": 6852 }, { "epoch": 0.5785380369975623, "grad_norm": 0.1455078125, "learning_rate": 2.21064180048458e-05, "loss": 1.534256935119629, "step": 6853 }, { "epoch": 0.5786224581323934, "grad_norm": 0.1337890625, "learning_rate": 2.2099952130123072e-05, "loss": 1.47127366065979, "step": 6854 }, { "epoch": 0.5787068792672245, "grad_norm": 0.1357421875, "learning_rate": 2.2093486452030553e-05, "loss": 1.5623201131820679, "step": 6855 }, { "epoch": 0.5787913004020556, "grad_norm": 0.1337890625, "learning_rate": 2.208702097100665e-05, "loss": 1.4702732563018799, "step": 6856 }, { "epoch": 0.5788757215368867, "grad_norm": 0.138671875, "learning_rate": 2.208055568748971e-05, "loss": 1.5074721574783325, "step": 6857 }, { "epoch": 0.5789601426717179, "grad_norm": 0.1455078125, "learning_rate": 2.207409060191812e-05, "loss": 1.5552687644958496, "step": 6858 }, { "epoch": 0.579044563806549, "grad_norm": 0.1337890625, "learning_rate": 2.2067625714730226e-05, "loss": 1.5491750240325928, "step": 6859 }, { "epoch": 0.5791289849413801, "grad_norm": 0.1396484375, "learning_rate": 2.2061161026364353e-05, "loss": 1.4746023416519165, "step": 6860 }, { "epoch": 0.5792134060762112, "grad_norm": 0.1357421875, "learning_rate": 2.205469653725883e-05, "loss": 1.4715622663497925, "step": 6861 }, { "epoch": 0.5792978272110423, "grad_norm": 0.1357421875, "learning_rate": 2.2048232247851955e-05, "loss": 1.4992694854736328, "step": 6862 }, { "epoch": 0.5793822483458734, "grad_norm": 0.150390625, "learning_rate": 2.2041768158582025e-05, "loss": 1.5363224744796753, "step": 6863 }, { "epoch": 0.5794666694807045, "grad_norm": 0.138671875, "learning_rate": 2.2035304269887333e-05, "loss": 1.548933744430542, "step": 6864 }, { "epoch": 0.5795510906155356, "grad_norm": 0.1318359375, "learning_rate": 2.2028840582206136e-05, "loss": 1.473546028137207, "step": 6865 }, { "epoch": 0.5796355117503666, "grad_norm": 0.142578125, "learning_rate": 2.2022377095976678e-05, "loss": 1.5121062994003296, "step": 6866 }, { "epoch": 0.5797199328851979, "grad_norm": 0.1474609375, "learning_rate": 2.2015913811637232e-05, "loss": 1.5911535024642944, "step": 6867 }, { "epoch": 0.579804354020029, "grad_norm": 0.1376953125, "learning_rate": 2.200945072962598e-05, "loss": 1.4641456604003906, "step": 6868 }, { "epoch": 0.57988877515486, "grad_norm": 0.13671875, "learning_rate": 2.2002987850381177e-05, "loss": 1.580901861190796, "step": 6869 }, { "epoch": 0.5799731962896911, "grad_norm": 0.150390625, "learning_rate": 2.199652517434099e-05, "loss": 1.5669382810592651, "step": 6870 }, { "epoch": 0.5800576174245222, "grad_norm": 0.13671875, "learning_rate": 2.199006270194361e-05, "loss": 1.5452498197555542, "step": 6871 }, { "epoch": 0.5801420385593533, "grad_norm": 0.1376953125, "learning_rate": 2.1983600433627232e-05, "loss": 1.4894781112670898, "step": 6872 }, { "epoch": 0.5802264596941844, "grad_norm": 0.15234375, "learning_rate": 2.1977138369829978e-05, "loss": 1.6042248010635376, "step": 6873 }, { "epoch": 0.5803108808290155, "grad_norm": 0.142578125, "learning_rate": 2.1970676510990017e-05, "loss": 1.5178921222686768, "step": 6874 }, { "epoch": 0.5803953019638467, "grad_norm": 0.138671875, "learning_rate": 2.196421485754547e-05, "loss": 1.542917013168335, "step": 6875 }, { "epoch": 0.5804797230986778, "grad_norm": 0.1396484375, "learning_rate": 2.195775340993445e-05, "loss": 1.5366992950439453, "step": 6876 }, { "epoch": 0.5805641442335089, "grad_norm": 0.140625, "learning_rate": 2.1951292168595067e-05, "loss": 1.4458997249603271, "step": 6877 }, { "epoch": 0.58064856536834, "grad_norm": 0.130859375, "learning_rate": 2.194483113396539e-05, "loss": 1.4795465469360352, "step": 6878 }, { "epoch": 0.5807329865031711, "grad_norm": 0.1357421875, "learning_rate": 2.1938370306483518e-05, "loss": 1.5117065906524658, "step": 6879 }, { "epoch": 0.5808174076380022, "grad_norm": 0.146484375, "learning_rate": 2.1931909686587493e-05, "loss": 1.540164589881897, "step": 6880 }, { "epoch": 0.5809018287728333, "grad_norm": 0.1279296875, "learning_rate": 2.192544927471537e-05, "loss": 1.5330479145050049, "step": 6881 }, { "epoch": 0.5809862499076643, "grad_norm": 0.1484375, "learning_rate": 2.1918989071305176e-05, "loss": 1.596901297569275, "step": 6882 }, { "epoch": 0.5810706710424954, "grad_norm": 0.1337890625, "learning_rate": 2.1912529076794917e-05, "loss": 1.5248074531555176, "step": 6883 }, { "epoch": 0.5811550921773266, "grad_norm": 0.1474609375, "learning_rate": 2.1906069291622617e-05, "loss": 1.6278572082519531, "step": 6884 }, { "epoch": 0.5812395133121577, "grad_norm": 0.138671875, "learning_rate": 2.1899609716226263e-05, "loss": 1.5052908658981323, "step": 6885 }, { "epoch": 0.5813239344469888, "grad_norm": 0.1396484375, "learning_rate": 2.1893150351043815e-05, "loss": 1.5349383354187012, "step": 6886 }, { "epoch": 0.5814083555818199, "grad_norm": 0.1416015625, "learning_rate": 2.1886691196513247e-05, "loss": 1.5058913230895996, "step": 6887 }, { "epoch": 0.581492776716651, "grad_norm": 0.138671875, "learning_rate": 2.1880232253072488e-05, "loss": 1.5422554016113281, "step": 6888 }, { "epoch": 0.5815771978514821, "grad_norm": 0.138671875, "learning_rate": 2.1873773521159484e-05, "loss": 1.5035017728805542, "step": 6889 }, { "epoch": 0.5816616189863132, "grad_norm": 0.1357421875, "learning_rate": 2.186731500121216e-05, "loss": 1.5964916944503784, "step": 6890 }, { "epoch": 0.5817460401211443, "grad_norm": 0.134765625, "learning_rate": 2.1860856693668402e-05, "loss": 1.5503332614898682, "step": 6891 }, { "epoch": 0.5818304612559755, "grad_norm": 0.1298828125, "learning_rate": 2.1854398598966108e-05, "loss": 1.520788311958313, "step": 6892 }, { "epoch": 0.5819148823908066, "grad_norm": 0.154296875, "learning_rate": 2.1847940717543142e-05, "loss": 1.5725029706954956, "step": 6893 }, { "epoch": 0.5819993035256377, "grad_norm": 0.138671875, "learning_rate": 2.1841483049837377e-05, "loss": 1.543238878250122, "step": 6894 }, { "epoch": 0.5820837246604688, "grad_norm": 0.1357421875, "learning_rate": 2.1835025596286657e-05, "loss": 1.4885923862457275, "step": 6895 }, { "epoch": 0.5821681457952999, "grad_norm": 0.1357421875, "learning_rate": 2.1828568357328806e-05, "loss": 1.5931661128997803, "step": 6896 }, { "epoch": 0.5822525669301309, "grad_norm": 0.130859375, "learning_rate": 2.1822111333401637e-05, "loss": 1.4929866790771484, "step": 6897 }, { "epoch": 0.582336988064962, "grad_norm": 0.142578125, "learning_rate": 2.181565452494297e-05, "loss": 1.537421464920044, "step": 6898 }, { "epoch": 0.5824214091997931, "grad_norm": 0.1435546875, "learning_rate": 2.1809197932390575e-05, "loss": 1.5684943199157715, "step": 6899 }, { "epoch": 0.5825058303346242, "grad_norm": 0.140625, "learning_rate": 2.1802741556182232e-05, "loss": 1.513788104057312, "step": 6900 }, { "epoch": 0.5825902514694554, "grad_norm": 0.138671875, "learning_rate": 2.1796285396755693e-05, "loss": 1.5297696590423584, "step": 6901 }, { "epoch": 0.5826746726042865, "grad_norm": 0.150390625, "learning_rate": 2.1789829454548703e-05, "loss": 1.5031198263168335, "step": 6902 }, { "epoch": 0.5827590937391176, "grad_norm": 0.1416015625, "learning_rate": 2.1783373729999006e-05, "loss": 1.4940727949142456, "step": 6903 }, { "epoch": 0.5828435148739487, "grad_norm": 0.1650390625, "learning_rate": 2.1776918223544284e-05, "loss": 1.5923776626586914, "step": 6904 }, { "epoch": 0.5829279360087798, "grad_norm": 0.13671875, "learning_rate": 2.1770462935622267e-05, "loss": 1.4756239652633667, "step": 6905 }, { "epoch": 0.5830123571436109, "grad_norm": 0.1396484375, "learning_rate": 2.176400786667062e-05, "loss": 1.5133938789367676, "step": 6906 }, { "epoch": 0.583096778278442, "grad_norm": 0.14453125, "learning_rate": 2.175755301712701e-05, "loss": 1.5956361293792725, "step": 6907 }, { "epoch": 0.5831811994132731, "grad_norm": 0.146484375, "learning_rate": 2.1751098387429116e-05, "loss": 1.6097347736358643, "step": 6908 }, { "epoch": 0.5832656205481043, "grad_norm": 0.1396484375, "learning_rate": 2.1744643978014547e-05, "loss": 1.5565696954727173, "step": 6909 }, { "epoch": 0.5833500416829354, "grad_norm": 0.14453125, "learning_rate": 2.173818978932095e-05, "loss": 1.514896035194397, "step": 6910 }, { "epoch": 0.5834344628177665, "grad_norm": 0.140625, "learning_rate": 2.173173582178592e-05, "loss": 1.515235424041748, "step": 6911 }, { "epoch": 0.5835188839525975, "grad_norm": 0.1396484375, "learning_rate": 2.1725282075847058e-05, "loss": 1.53853440284729, "step": 6912 }, { "epoch": 0.5836033050874286, "grad_norm": 0.1435546875, "learning_rate": 2.171882855194195e-05, "loss": 1.508946418762207, "step": 6913 }, { "epoch": 0.5836877262222597, "grad_norm": 0.1376953125, "learning_rate": 2.1712375250508138e-05, "loss": 1.5287233591079712, "step": 6914 }, { "epoch": 0.5837721473570908, "grad_norm": 0.140625, "learning_rate": 2.1705922171983194e-05, "loss": 1.54202401638031, "step": 6915 }, { "epoch": 0.5838565684919219, "grad_norm": 0.14453125, "learning_rate": 2.169946931680465e-05, "loss": 1.5894700288772583, "step": 6916 }, { "epoch": 0.583940989626753, "grad_norm": 0.1455078125, "learning_rate": 2.1693016685410016e-05, "loss": 1.516810655593872, "step": 6917 }, { "epoch": 0.5840254107615842, "grad_norm": 0.154296875, "learning_rate": 2.1686564278236803e-05, "loss": 1.5355724096298218, "step": 6918 }, { "epoch": 0.5841098318964153, "grad_norm": 0.1396484375, "learning_rate": 2.1680112095722487e-05, "loss": 1.567524790763855, "step": 6919 }, { "epoch": 0.5841942530312464, "grad_norm": 0.138671875, "learning_rate": 2.1673660138304555e-05, "loss": 1.5666491985321045, "step": 6920 }, { "epoch": 0.5842786741660775, "grad_norm": 0.138671875, "learning_rate": 2.1667208406420466e-05, "loss": 1.5012394189834595, "step": 6921 }, { "epoch": 0.5843630953009086, "grad_norm": 0.1416015625, "learning_rate": 2.1660756900507656e-05, "loss": 1.5033364295959473, "step": 6922 }, { "epoch": 0.5844475164357397, "grad_norm": 0.1376953125, "learning_rate": 2.1654305621003558e-05, "loss": 1.5577844381332397, "step": 6923 }, { "epoch": 0.5845319375705708, "grad_norm": 0.13671875, "learning_rate": 2.164785456834557e-05, "loss": 1.574541687965393, "step": 6924 }, { "epoch": 0.5846163587054019, "grad_norm": 0.1494140625, "learning_rate": 2.16414037429711e-05, "loss": 1.5770292282104492, "step": 6925 }, { "epoch": 0.584700779840233, "grad_norm": 0.1376953125, "learning_rate": 2.1634953145317545e-05, "loss": 1.5449475049972534, "step": 6926 }, { "epoch": 0.5847852009750641, "grad_norm": 0.1416015625, "learning_rate": 2.162850277582224e-05, "loss": 1.564906358718872, "step": 6927 }, { "epoch": 0.5848696221098952, "grad_norm": 0.1416015625, "learning_rate": 2.162205263492256e-05, "loss": 1.4219236373901367, "step": 6928 }, { "epoch": 0.5849540432447263, "grad_norm": 0.1357421875, "learning_rate": 2.1615602723055824e-05, "loss": 1.553195834159851, "step": 6929 }, { "epoch": 0.5850384643795574, "grad_norm": 0.1484375, "learning_rate": 2.1609153040659358e-05, "loss": 1.4823801517486572, "step": 6930 }, { "epoch": 0.5851228855143885, "grad_norm": 0.14453125, "learning_rate": 2.1602703588170477e-05, "loss": 1.4774912595748901, "step": 6931 }, { "epoch": 0.5852073066492196, "grad_norm": 0.140625, "learning_rate": 2.1596254366026446e-05, "loss": 1.485119342803955, "step": 6932 }, { "epoch": 0.5852917277840507, "grad_norm": 0.14453125, "learning_rate": 2.158980537466455e-05, "loss": 1.5135198831558228, "step": 6933 }, { "epoch": 0.5853761489188818, "grad_norm": 0.138671875, "learning_rate": 2.158335661452206e-05, "loss": 1.4317777156829834, "step": 6934 }, { "epoch": 0.585460570053713, "grad_norm": 0.1328125, "learning_rate": 2.1576908086036195e-05, "loss": 1.5669180154800415, "step": 6935 }, { "epoch": 0.5855449911885441, "grad_norm": 0.1396484375, "learning_rate": 2.1570459789644196e-05, "loss": 1.4754043817520142, "step": 6936 }, { "epoch": 0.5856294123233752, "grad_norm": 0.138671875, "learning_rate": 2.1564011725783263e-05, "loss": 1.404151201248169, "step": 6937 }, { "epoch": 0.5857138334582063, "grad_norm": 0.134765625, "learning_rate": 2.1557563894890587e-05, "loss": 1.5239861011505127, "step": 6938 }, { "epoch": 0.5857982545930374, "grad_norm": 0.1474609375, "learning_rate": 2.1551116297403366e-05, "loss": 1.6030744314193726, "step": 6939 }, { "epoch": 0.5858826757278685, "grad_norm": 0.1435546875, "learning_rate": 2.154466893375874e-05, "loss": 1.4999698400497437, "step": 6940 }, { "epoch": 0.5859670968626995, "grad_norm": 0.142578125, "learning_rate": 2.1538221804393875e-05, "loss": 1.5063799619674683, "step": 6941 }, { "epoch": 0.5860515179975306, "grad_norm": 0.140625, "learning_rate": 2.1531774909745883e-05, "loss": 1.508119821548462, "step": 6942 }, { "epoch": 0.5861359391323618, "grad_norm": 0.1337890625, "learning_rate": 2.1525328250251888e-05, "loss": 1.4797028303146362, "step": 6943 }, { "epoch": 0.5862203602671929, "grad_norm": 0.12890625, "learning_rate": 2.1518881826349005e-05, "loss": 1.48270845413208, "step": 6944 }, { "epoch": 0.586304781402024, "grad_norm": 0.142578125, "learning_rate": 2.1512435638474286e-05, "loss": 1.4961520433425903, "step": 6945 }, { "epoch": 0.5863892025368551, "grad_norm": 0.1376953125, "learning_rate": 2.150598968706482e-05, "loss": 1.4991545677185059, "step": 6946 }, { "epoch": 0.5864736236716862, "grad_norm": 0.1474609375, "learning_rate": 2.149954397255765e-05, "loss": 1.482361078262329, "step": 6947 }, { "epoch": 0.5865580448065173, "grad_norm": 0.1357421875, "learning_rate": 2.1493098495389808e-05, "loss": 1.5129896402359009, "step": 6948 }, { "epoch": 0.5866424659413484, "grad_norm": 0.1455078125, "learning_rate": 2.148665325599833e-05, "loss": 1.4757437705993652, "step": 6949 }, { "epoch": 0.5867268870761795, "grad_norm": 0.1357421875, "learning_rate": 2.1480208254820196e-05, "loss": 1.5338927507400513, "step": 6950 }, { "epoch": 0.5868113082110106, "grad_norm": 0.140625, "learning_rate": 2.1473763492292405e-05, "loss": 1.4798578023910522, "step": 6951 }, { "epoch": 0.5868957293458418, "grad_norm": 0.138671875, "learning_rate": 2.146731896885193e-05, "loss": 1.579545259475708, "step": 6952 }, { "epoch": 0.5869801504806729, "grad_norm": 0.140625, "learning_rate": 2.1460874684935715e-05, "loss": 1.5895229578018188, "step": 6953 }, { "epoch": 0.587064571615504, "grad_norm": 0.140625, "learning_rate": 2.1454430640980712e-05, "loss": 1.5108914375305176, "step": 6954 }, { "epoch": 0.587148992750335, "grad_norm": 0.140625, "learning_rate": 2.1447986837423816e-05, "loss": 1.5322673320770264, "step": 6955 }, { "epoch": 0.5872334138851661, "grad_norm": 0.138671875, "learning_rate": 2.1441543274701962e-05, "loss": 1.6085169315338135, "step": 6956 }, { "epoch": 0.5873178350199972, "grad_norm": 0.1357421875, "learning_rate": 2.143509995325203e-05, "loss": 1.4956921339035034, "step": 6957 }, { "epoch": 0.5874022561548283, "grad_norm": 0.1435546875, "learning_rate": 2.1428656873510885e-05, "loss": 1.5429766178131104, "step": 6958 }, { "epoch": 0.5874866772896594, "grad_norm": 0.158203125, "learning_rate": 2.1422214035915394e-05, "loss": 1.6231164932250977, "step": 6959 }, { "epoch": 0.5875710984244906, "grad_norm": 0.1376953125, "learning_rate": 2.1415771440902384e-05, "loss": 1.4955198764801025, "step": 6960 }, { "epoch": 0.5876555195593217, "grad_norm": 0.14453125, "learning_rate": 2.1409329088908686e-05, "loss": 1.6047941446304321, "step": 6961 }, { "epoch": 0.5877399406941528, "grad_norm": 0.1435546875, "learning_rate": 2.140288698037111e-05, "loss": 1.5429798364639282, "step": 6962 }, { "epoch": 0.5878243618289839, "grad_norm": 0.1435546875, "learning_rate": 2.1396445115726443e-05, "loss": 1.552295446395874, "step": 6963 }, { "epoch": 0.587908782963815, "grad_norm": 0.1357421875, "learning_rate": 2.1390003495411466e-05, "loss": 1.4888745546340942, "step": 6964 }, { "epoch": 0.5879932040986461, "grad_norm": 0.1376953125, "learning_rate": 2.1383562119862913e-05, "loss": 1.5256582498550415, "step": 6965 }, { "epoch": 0.5880776252334772, "grad_norm": 0.1357421875, "learning_rate": 2.137712098951755e-05, "loss": 1.5032156705856323, "step": 6966 }, { "epoch": 0.5881620463683083, "grad_norm": 0.1328125, "learning_rate": 2.1370680104812098e-05, "loss": 1.479636549949646, "step": 6967 }, { "epoch": 0.5882464675031394, "grad_norm": 0.140625, "learning_rate": 2.136423946618325e-05, "loss": 1.4926451444625854, "step": 6968 }, { "epoch": 0.5883308886379706, "grad_norm": 0.142578125, "learning_rate": 2.13577990740677e-05, "loss": 1.4648038148880005, "step": 6969 }, { "epoch": 0.5884153097728017, "grad_norm": 0.1396484375, "learning_rate": 2.1351358928902136e-05, "loss": 1.524501085281372, "step": 6970 }, { "epoch": 0.5884997309076327, "grad_norm": 0.1494140625, "learning_rate": 2.1344919031123207e-05, "loss": 1.5810860395431519, "step": 6971 }, { "epoch": 0.5885841520424638, "grad_norm": 0.13671875, "learning_rate": 2.133847938116756e-05, "loss": 1.4841910600662231, "step": 6972 }, { "epoch": 0.5886685731772949, "grad_norm": 0.126953125, "learning_rate": 2.1332039979471802e-05, "loss": 1.417410135269165, "step": 6973 }, { "epoch": 0.588752994312126, "grad_norm": 0.146484375, "learning_rate": 2.132560082647255e-05, "loss": 1.506545066833496, "step": 6974 }, { "epoch": 0.5888374154469571, "grad_norm": 0.1328125, "learning_rate": 2.1319161922606396e-05, "loss": 1.536377191543579, "step": 6975 }, { "epoch": 0.5889218365817882, "grad_norm": 0.154296875, "learning_rate": 2.131272326830991e-05, "loss": 1.487434983253479, "step": 6976 }, { "epoch": 0.5890062577166194, "grad_norm": 0.1376953125, "learning_rate": 2.1306284864019657e-05, "loss": 1.5908340215682983, "step": 6977 }, { "epoch": 0.5890906788514505, "grad_norm": 0.13671875, "learning_rate": 2.129984671017216e-05, "loss": 1.5844321250915527, "step": 6978 }, { "epoch": 0.5891750999862816, "grad_norm": 0.1376953125, "learning_rate": 2.1293408807203947e-05, "loss": 1.4819713830947876, "step": 6979 }, { "epoch": 0.5892595211211127, "grad_norm": 0.1298828125, "learning_rate": 2.1286971155551545e-05, "loss": 1.426051139831543, "step": 6980 }, { "epoch": 0.5893439422559438, "grad_norm": 0.1435546875, "learning_rate": 2.1280533755651405e-05, "loss": 1.5430617332458496, "step": 6981 }, { "epoch": 0.5894283633907749, "grad_norm": 0.1357421875, "learning_rate": 2.1274096607940018e-05, "loss": 1.4770357608795166, "step": 6982 }, { "epoch": 0.589512784525606, "grad_norm": 0.1376953125, "learning_rate": 2.126765971285385e-05, "loss": 1.4696396589279175, "step": 6983 }, { "epoch": 0.589597205660437, "grad_norm": 0.140625, "learning_rate": 2.1261223070829307e-05, "loss": 1.5486778020858765, "step": 6984 }, { "epoch": 0.5896816267952681, "grad_norm": 0.1484375, "learning_rate": 2.1254786682302847e-05, "loss": 1.6389645338058472, "step": 6985 }, { "epoch": 0.5897660479300993, "grad_norm": 0.15625, "learning_rate": 2.1248350547710834e-05, "loss": 1.5658917427062988, "step": 6986 }, { "epoch": 0.5898504690649304, "grad_norm": 0.1318359375, "learning_rate": 2.124191466748968e-05, "loss": 1.4443285465240479, "step": 6987 }, { "epoch": 0.5899348901997615, "grad_norm": 0.13671875, "learning_rate": 2.1235479042075748e-05, "loss": 1.4560834169387817, "step": 6988 }, { "epoch": 0.5900193113345926, "grad_norm": 0.140625, "learning_rate": 2.1229043671905376e-05, "loss": 1.5070923566818237, "step": 6989 }, { "epoch": 0.5901037324694237, "grad_norm": 0.142578125, "learning_rate": 2.122260855741492e-05, "loss": 1.5129024982452393, "step": 6990 }, { "epoch": 0.5901881536042548, "grad_norm": 0.1416015625, "learning_rate": 2.121617369904067e-05, "loss": 1.5966582298278809, "step": 6991 }, { "epoch": 0.5902725747390859, "grad_norm": 0.1435546875, "learning_rate": 2.1209739097218943e-05, "loss": 1.4645003080368042, "step": 6992 }, { "epoch": 0.590356995873917, "grad_norm": 0.1416015625, "learning_rate": 2.1203304752386026e-05, "loss": 1.548431634902954, "step": 6993 }, { "epoch": 0.5904414170087482, "grad_norm": 0.1337890625, "learning_rate": 2.1196870664978162e-05, "loss": 1.5380651950836182, "step": 6994 }, { "epoch": 0.5905258381435793, "grad_norm": 0.1416015625, "learning_rate": 2.1190436835431616e-05, "loss": 1.5071468353271484, "step": 6995 }, { "epoch": 0.5906102592784104, "grad_norm": 0.138671875, "learning_rate": 2.1184003264182594e-05, "loss": 1.5546526908874512, "step": 6996 }, { "epoch": 0.5906946804132415, "grad_norm": 0.1396484375, "learning_rate": 2.1177569951667334e-05, "loss": 1.557421326637268, "step": 6997 }, { "epoch": 0.5907791015480726, "grad_norm": 0.140625, "learning_rate": 2.1171136898322022e-05, "loss": 1.5016701221466064, "step": 6998 }, { "epoch": 0.5908635226829037, "grad_norm": 0.1376953125, "learning_rate": 2.1164704104582828e-05, "loss": 1.5018587112426758, "step": 6999 }, { "epoch": 0.5909479438177347, "grad_norm": 0.1328125, "learning_rate": 2.1158271570885906e-05, "loss": 1.5045620203018188, "step": 7000 }, { "epoch": 0.5910323649525658, "grad_norm": 0.1328125, "learning_rate": 2.1151839297667418e-05, "loss": 1.552308440208435, "step": 7001 }, { "epoch": 0.5911167860873969, "grad_norm": 0.134765625, "learning_rate": 2.1145407285363474e-05, "loss": 1.5186976194381714, "step": 7002 }, { "epoch": 0.5912012072222281, "grad_norm": 0.1455078125, "learning_rate": 2.1138975534410183e-05, "loss": 1.5048772096633911, "step": 7003 }, { "epoch": 0.5912856283570592, "grad_norm": 0.140625, "learning_rate": 2.1132544045243626e-05, "loss": 1.5025432109832764, "step": 7004 }, { "epoch": 0.5913700494918903, "grad_norm": 0.15234375, "learning_rate": 2.1126112818299876e-05, "loss": 1.5156770944595337, "step": 7005 }, { "epoch": 0.5914544706267214, "grad_norm": 0.1455078125, "learning_rate": 2.1119681854014998e-05, "loss": 1.6099050045013428, "step": 7006 }, { "epoch": 0.5915388917615525, "grad_norm": 0.1298828125, "learning_rate": 2.1113251152825007e-05, "loss": 1.5280520915985107, "step": 7007 }, { "epoch": 0.5916233128963836, "grad_norm": 0.1328125, "learning_rate": 2.1106820715165944e-05, "loss": 1.511886477470398, "step": 7008 }, { "epoch": 0.5917077340312147, "grad_norm": 0.138671875, "learning_rate": 2.1100390541473782e-05, "loss": 1.5400428771972656, "step": 7009 }, { "epoch": 0.5917921551660458, "grad_norm": 0.154296875, "learning_rate": 2.1093960632184513e-05, "loss": 1.482604742050171, "step": 7010 }, { "epoch": 0.591876576300877, "grad_norm": 0.134765625, "learning_rate": 2.1087530987734115e-05, "loss": 1.5047862529754639, "step": 7011 }, { "epoch": 0.5919609974357081, "grad_norm": 0.13671875, "learning_rate": 2.1081101608558512e-05, "loss": 1.5023787021636963, "step": 7012 }, { "epoch": 0.5920454185705392, "grad_norm": 0.1455078125, "learning_rate": 2.1074672495093644e-05, "loss": 1.5084128379821777, "step": 7013 }, { "epoch": 0.5921298397053703, "grad_norm": 0.1484375, "learning_rate": 2.1068243647775413e-05, "loss": 1.5423762798309326, "step": 7014 }, { "epoch": 0.5922142608402013, "grad_norm": 0.1396484375, "learning_rate": 2.1061815067039707e-05, "loss": 1.510399580001831, "step": 7015 }, { "epoch": 0.5922986819750324, "grad_norm": 0.14453125, "learning_rate": 2.1055386753322416e-05, "loss": 1.5849701166152954, "step": 7016 }, { "epoch": 0.5923831031098635, "grad_norm": 0.1328125, "learning_rate": 2.104895870705938e-05, "loss": 1.528548002243042, "step": 7017 }, { "epoch": 0.5924675242446946, "grad_norm": 0.1513671875, "learning_rate": 2.1042530928686438e-05, "loss": 1.5162330865859985, "step": 7018 }, { "epoch": 0.5925519453795257, "grad_norm": 0.1494140625, "learning_rate": 2.1036103418639422e-05, "loss": 1.5966310501098633, "step": 7019 }, { "epoch": 0.5926363665143569, "grad_norm": 0.1376953125, "learning_rate": 2.1029676177354107e-05, "loss": 1.5540770292282104, "step": 7020 }, { "epoch": 0.592720787649188, "grad_norm": 0.14453125, "learning_rate": 2.1023249205266308e-05, "loss": 1.5202229022979736, "step": 7021 }, { "epoch": 0.5928052087840191, "grad_norm": 0.146484375, "learning_rate": 2.1016822502811756e-05, "loss": 1.6091413497924805, "step": 7022 }, { "epoch": 0.5928896299188502, "grad_norm": 0.1416015625, "learning_rate": 2.101039607042622e-05, "loss": 1.5216007232666016, "step": 7023 }, { "epoch": 0.5929740510536813, "grad_norm": 0.1357421875, "learning_rate": 2.1003969908545425e-05, "loss": 1.4465974569320679, "step": 7024 }, { "epoch": 0.5930584721885124, "grad_norm": 0.1357421875, "learning_rate": 2.0997544017605062e-05, "loss": 1.4570837020874023, "step": 7025 }, { "epoch": 0.5931428933233435, "grad_norm": 0.1318359375, "learning_rate": 2.0991118398040852e-05, "loss": 1.4592982530593872, "step": 7026 }, { "epoch": 0.5932273144581746, "grad_norm": 0.13671875, "learning_rate": 2.0984693050288434e-05, "loss": 1.4969464540481567, "step": 7027 }, { "epoch": 0.5933117355930058, "grad_norm": 0.1357421875, "learning_rate": 2.0978267974783485e-05, "loss": 1.450088381767273, "step": 7028 }, { "epoch": 0.5933961567278369, "grad_norm": 0.13671875, "learning_rate": 2.0971843171961643e-05, "loss": 1.4558923244476318, "step": 7029 }, { "epoch": 0.593480577862668, "grad_norm": 0.1357421875, "learning_rate": 2.0965418642258504e-05, "loss": 1.5195469856262207, "step": 7030 }, { "epoch": 0.593564998997499, "grad_norm": 0.142578125, "learning_rate": 2.0958994386109693e-05, "loss": 1.5173134803771973, "step": 7031 }, { "epoch": 0.5936494201323301, "grad_norm": 0.142578125, "learning_rate": 2.095257040395076e-05, "loss": 1.4971275329589844, "step": 7032 }, { "epoch": 0.5937338412671612, "grad_norm": 0.1357421875, "learning_rate": 2.0946146696217286e-05, "loss": 1.5267884731292725, "step": 7033 }, { "epoch": 0.5938182624019923, "grad_norm": 0.1376953125, "learning_rate": 2.093972326334482e-05, "loss": 1.5776593685150146, "step": 7034 }, { "epoch": 0.5939026835368234, "grad_norm": 0.1484375, "learning_rate": 2.0933300105768867e-05, "loss": 1.6080776453018188, "step": 7035 }, { "epoch": 0.5939871046716545, "grad_norm": 0.1435546875, "learning_rate": 2.092687722392494e-05, "loss": 1.4971790313720703, "step": 7036 }, { "epoch": 0.5940715258064857, "grad_norm": 0.1376953125, "learning_rate": 2.0920454618248537e-05, "loss": 1.486080288887024, "step": 7037 }, { "epoch": 0.5941559469413168, "grad_norm": 0.1533203125, "learning_rate": 2.0914032289175108e-05, "loss": 1.647865891456604, "step": 7038 }, { "epoch": 0.5942403680761479, "grad_norm": 0.1318359375, "learning_rate": 2.090761023714012e-05, "loss": 1.472216248512268, "step": 7039 }, { "epoch": 0.594324789210979, "grad_norm": 0.134765625, "learning_rate": 2.090118846257899e-05, "loss": 1.5186915397644043, "step": 7040 }, { "epoch": 0.5944092103458101, "grad_norm": 0.13671875, "learning_rate": 2.0894766965927126e-05, "loss": 1.5665888786315918, "step": 7041 }, { "epoch": 0.5944936314806412, "grad_norm": 0.146484375, "learning_rate": 2.0888345747619944e-05, "loss": 1.5761959552764893, "step": 7042 }, { "epoch": 0.5945780526154723, "grad_norm": 0.140625, "learning_rate": 2.0881924808092796e-05, "loss": 1.575677514076233, "step": 7043 }, { "epoch": 0.5946624737503033, "grad_norm": 0.134765625, "learning_rate": 2.087550414778105e-05, "loss": 1.414209246635437, "step": 7044 }, { "epoch": 0.5947468948851345, "grad_norm": 0.1416015625, "learning_rate": 2.086908376712003e-05, "loss": 1.5543849468231201, "step": 7045 }, { "epoch": 0.5948313160199656, "grad_norm": 0.1318359375, "learning_rate": 2.0862663666545058e-05, "loss": 1.4784234762191772, "step": 7046 }, { "epoch": 0.5949157371547967, "grad_norm": 0.1318359375, "learning_rate": 2.0856243846491445e-05, "loss": 1.4747494459152222, "step": 7047 }, { "epoch": 0.5950001582896278, "grad_norm": 0.142578125, "learning_rate": 2.084982430739445e-05, "loss": 1.6320197582244873, "step": 7048 }, { "epoch": 0.5950845794244589, "grad_norm": 0.138671875, "learning_rate": 2.0843405049689346e-05, "loss": 1.489828109741211, "step": 7049 }, { "epoch": 0.59516900055929, "grad_norm": 0.1552734375, "learning_rate": 2.0836986073811375e-05, "loss": 1.6203224658966064, "step": 7050 }, { "epoch": 0.5952534216941211, "grad_norm": 0.1376953125, "learning_rate": 2.0830567380195746e-05, "loss": 1.5515190362930298, "step": 7051 }, { "epoch": 0.5953378428289522, "grad_norm": 0.150390625, "learning_rate": 2.0824148969277678e-05, "loss": 1.4441124200820923, "step": 7052 }, { "epoch": 0.5954222639637833, "grad_norm": 0.1396484375, "learning_rate": 2.0817730841492343e-05, "loss": 1.5640779733657837, "step": 7053 }, { "epoch": 0.5955066850986145, "grad_norm": 0.140625, "learning_rate": 2.0811312997274913e-05, "loss": 1.5069421529769897, "step": 7054 }, { "epoch": 0.5955911062334456, "grad_norm": 0.1337890625, "learning_rate": 2.080489543706053e-05, "loss": 1.56014084815979, "step": 7055 }, { "epoch": 0.5956755273682767, "grad_norm": 0.14453125, "learning_rate": 2.0798478161284313e-05, "loss": 1.5423533916473389, "step": 7056 }, { "epoch": 0.5957599485031078, "grad_norm": 0.138671875, "learning_rate": 2.0792061170381393e-05, "loss": 1.4554858207702637, "step": 7057 }, { "epoch": 0.5958443696379389, "grad_norm": 0.1435546875, "learning_rate": 2.078564446478682e-05, "loss": 1.5649633407592773, "step": 7058 }, { "epoch": 0.59592879077277, "grad_norm": 0.140625, "learning_rate": 2.077922804493569e-05, "loss": 1.5085207223892212, "step": 7059 }, { "epoch": 0.596013211907601, "grad_norm": 0.13671875, "learning_rate": 2.0772811911263048e-05, "loss": 1.569990873336792, "step": 7060 }, { "epoch": 0.5960976330424321, "grad_norm": 0.1416015625, "learning_rate": 2.0766396064203912e-05, "loss": 1.4798486232757568, "step": 7061 }, { "epoch": 0.5961820541772633, "grad_norm": 0.134765625, "learning_rate": 2.075998050419331e-05, "loss": 1.5188438892364502, "step": 7062 }, { "epoch": 0.5962664753120944, "grad_norm": 0.140625, "learning_rate": 2.075356523166621e-05, "loss": 1.49697744846344, "step": 7063 }, { "epoch": 0.5963508964469255, "grad_norm": 0.1435546875, "learning_rate": 2.0747150247057596e-05, "loss": 1.4738948345184326, "step": 7064 }, { "epoch": 0.5964353175817566, "grad_norm": 0.1455078125, "learning_rate": 2.0740735550802427e-05, "loss": 1.5204473733901978, "step": 7065 }, { "epoch": 0.5965197387165877, "grad_norm": 0.1435546875, "learning_rate": 2.073432114333561e-05, "loss": 1.4892117977142334, "step": 7066 }, { "epoch": 0.5966041598514188, "grad_norm": 0.1435546875, "learning_rate": 2.072790702509208e-05, "loss": 1.5258688926696777, "step": 7067 }, { "epoch": 0.5966885809862499, "grad_norm": 0.134765625, "learning_rate": 2.072149319650673e-05, "loss": 1.4911918640136719, "step": 7068 }, { "epoch": 0.596773002121081, "grad_norm": 0.16015625, "learning_rate": 2.0715079658014418e-05, "loss": 1.607593059539795, "step": 7069 }, { "epoch": 0.5968574232559121, "grad_norm": 0.1474609375, "learning_rate": 2.0708666410050013e-05, "loss": 1.5668060779571533, "step": 7070 }, { "epoch": 0.5969418443907433, "grad_norm": 0.13671875, "learning_rate": 2.0702253453048333e-05, "loss": 1.466736912727356, "step": 7071 }, { "epoch": 0.5970262655255744, "grad_norm": 0.1318359375, "learning_rate": 2.069584078744419e-05, "loss": 1.5021240711212158, "step": 7072 }, { "epoch": 0.5971106866604055, "grad_norm": 0.13671875, "learning_rate": 2.0689428413672408e-05, "loss": 1.535115361213684, "step": 7073 }, { "epoch": 0.5971951077952365, "grad_norm": 0.1337890625, "learning_rate": 2.0683016332167726e-05, "loss": 1.5325863361358643, "step": 7074 }, { "epoch": 0.5972795289300676, "grad_norm": 0.1533203125, "learning_rate": 2.0676604543364926e-05, "loss": 1.5934298038482666, "step": 7075 }, { "epoch": 0.5973639500648987, "grad_norm": 0.13671875, "learning_rate": 2.0670193047698717e-05, "loss": 1.4994598627090454, "step": 7076 }, { "epoch": 0.5974483711997298, "grad_norm": 0.150390625, "learning_rate": 2.0663781845603828e-05, "loss": 1.5939826965332031, "step": 7077 }, { "epoch": 0.5975327923345609, "grad_norm": 0.1416015625, "learning_rate": 2.065737093751496e-05, "loss": 1.5027488470077515, "step": 7078 }, { "epoch": 0.5976172134693921, "grad_norm": 0.1396484375, "learning_rate": 2.0650960323866778e-05, "loss": 1.5146756172180176, "step": 7079 }, { "epoch": 0.5977016346042232, "grad_norm": 0.142578125, "learning_rate": 2.0644550005093943e-05, "loss": 1.5082558393478394, "step": 7080 }, { "epoch": 0.5977860557390543, "grad_norm": 0.140625, "learning_rate": 2.0638139981631082e-05, "loss": 1.4664299488067627, "step": 7081 }, { "epoch": 0.5978704768738854, "grad_norm": 0.1396484375, "learning_rate": 2.063173025391281e-05, "loss": 1.553031325340271, "step": 7082 }, { "epoch": 0.5979548980087165, "grad_norm": 0.1396484375, "learning_rate": 2.0625320822373736e-05, "loss": 1.5813581943511963, "step": 7083 }, { "epoch": 0.5980393191435476, "grad_norm": 0.1435546875, "learning_rate": 2.0618911687448423e-05, "loss": 1.5367753505706787, "step": 7084 }, { "epoch": 0.5981237402783787, "grad_norm": 0.1298828125, "learning_rate": 2.0612502849571425e-05, "loss": 1.4449933767318726, "step": 7085 }, { "epoch": 0.5982081614132098, "grad_norm": 0.1435546875, "learning_rate": 2.0606094309177288e-05, "loss": 1.5780446529388428, "step": 7086 }, { "epoch": 0.5982925825480409, "grad_norm": 0.138671875, "learning_rate": 2.0599686066700504e-05, "loss": 1.467635989189148, "step": 7087 }, { "epoch": 0.598377003682872, "grad_norm": 0.1376953125, "learning_rate": 2.0593278122575593e-05, "loss": 1.4849367141723633, "step": 7088 }, { "epoch": 0.5984614248177031, "grad_norm": 0.1474609375, "learning_rate": 2.0586870477237016e-05, "loss": 1.5493512153625488, "step": 7089 }, { "epoch": 0.5985458459525342, "grad_norm": 0.1328125, "learning_rate": 2.0580463131119226e-05, "loss": 1.495597004890442, "step": 7090 }, { "epoch": 0.5986302670873653, "grad_norm": 0.142578125, "learning_rate": 2.0574056084656664e-05, "loss": 1.5632447004318237, "step": 7091 }, { "epoch": 0.5987146882221964, "grad_norm": 0.14453125, "learning_rate": 2.056764933828373e-05, "loss": 1.5304867029190063, "step": 7092 }, { "epoch": 0.5987991093570275, "grad_norm": 0.130859375, "learning_rate": 2.0561242892434832e-05, "loss": 1.4706577062606812, "step": 7093 }, { "epoch": 0.5988835304918586, "grad_norm": 0.1494140625, "learning_rate": 2.055483674754433e-05, "loss": 1.5289562940597534, "step": 7094 }, { "epoch": 0.5989679516266897, "grad_norm": 0.1357421875, "learning_rate": 2.0548430904046583e-05, "loss": 1.5003163814544678, "step": 7095 }, { "epoch": 0.5990523727615209, "grad_norm": 0.162109375, "learning_rate": 2.0542025362375927e-05, "loss": 1.546415090560913, "step": 7096 }, { "epoch": 0.599136793896352, "grad_norm": 0.142578125, "learning_rate": 2.0535620122966655e-05, "loss": 1.5120635032653809, "step": 7097 }, { "epoch": 0.5992212150311831, "grad_norm": 0.1328125, "learning_rate": 2.0529215186253086e-05, "loss": 1.4464527368545532, "step": 7098 }, { "epoch": 0.5993056361660142, "grad_norm": 0.140625, "learning_rate": 2.052281055266946e-05, "loss": 1.540027379989624, "step": 7099 }, { "epoch": 0.5993900573008453, "grad_norm": 0.138671875, "learning_rate": 2.0516406222650042e-05, "loss": 1.5686066150665283, "step": 7100 }, { "epoch": 0.5994744784356764, "grad_norm": 0.140625, "learning_rate": 2.0510002196629063e-05, "loss": 1.5290898084640503, "step": 7101 }, { "epoch": 0.5995588995705075, "grad_norm": 0.134765625, "learning_rate": 2.0503598475040718e-05, "loss": 1.5358765125274658, "step": 7102 }, { "epoch": 0.5996433207053385, "grad_norm": 0.138671875, "learning_rate": 2.049719505831921e-05, "loss": 1.5493743419647217, "step": 7103 }, { "epoch": 0.5997277418401696, "grad_norm": 0.130859375, "learning_rate": 2.0490791946898714e-05, "loss": 1.4203895330429077, "step": 7104 }, { "epoch": 0.5998121629750008, "grad_norm": 0.1328125, "learning_rate": 2.048438914121335e-05, "loss": 1.5001676082611084, "step": 7105 }, { "epoch": 0.5998965841098319, "grad_norm": 0.13671875, "learning_rate": 2.047798664169726e-05, "loss": 1.5497701168060303, "step": 7106 }, { "epoch": 0.599981005244663, "grad_norm": 0.1396484375, "learning_rate": 2.0471584448784536e-05, "loss": 1.502245306968689, "step": 7107 }, { "epoch": 0.6000654263794941, "grad_norm": 0.1376953125, "learning_rate": 2.0465182562909277e-05, "loss": 1.5338214635849, "step": 7108 }, { "epoch": 0.6001498475143252, "grad_norm": 0.1396484375, "learning_rate": 2.0458780984505548e-05, "loss": 1.600345253944397, "step": 7109 }, { "epoch": 0.6002342686491563, "grad_norm": 0.1591796875, "learning_rate": 2.0452379714007375e-05, "loss": 1.4856934547424316, "step": 7110 }, { "epoch": 0.6003186897839874, "grad_norm": 0.1376953125, "learning_rate": 2.0445978751848796e-05, "loss": 1.4104630947113037, "step": 7111 }, { "epoch": 0.6004031109188185, "grad_norm": 0.138671875, "learning_rate": 2.0439578098463795e-05, "loss": 1.5270566940307617, "step": 7112 }, { "epoch": 0.6004875320536497, "grad_norm": 0.1298828125, "learning_rate": 2.0433177754286363e-05, "loss": 1.4184482097625732, "step": 7113 }, { "epoch": 0.6005719531884808, "grad_norm": 0.14453125, "learning_rate": 2.042677771975046e-05, "loss": 1.5438424348831177, "step": 7114 }, { "epoch": 0.6006563743233119, "grad_norm": 0.1328125, "learning_rate": 2.0420377995290017e-05, "loss": 1.5055252313613892, "step": 7115 }, { "epoch": 0.600740795458143, "grad_norm": 0.1337890625, "learning_rate": 2.041397858133896e-05, "loss": 1.4801980257034302, "step": 7116 }, { "epoch": 0.600825216592974, "grad_norm": 0.140625, "learning_rate": 2.0407579478331174e-05, "loss": 1.6092195510864258, "step": 7117 }, { "epoch": 0.6009096377278051, "grad_norm": 0.1474609375, "learning_rate": 2.040118068670053e-05, "loss": 1.5209548473358154, "step": 7118 }, { "epoch": 0.6009940588626362, "grad_norm": 0.142578125, "learning_rate": 2.0394782206880903e-05, "loss": 1.5243239402770996, "step": 7119 }, { "epoch": 0.6010784799974673, "grad_norm": 0.142578125, "learning_rate": 2.0388384039306106e-05, "loss": 1.520937204360962, "step": 7120 }, { "epoch": 0.6011629011322984, "grad_norm": 0.1513671875, "learning_rate": 2.0381986184409953e-05, "loss": 1.51717209815979, "step": 7121 }, { "epoch": 0.6012473222671296, "grad_norm": 0.158203125, "learning_rate": 2.0375588642626247e-05, "loss": 1.5226390361785889, "step": 7122 }, { "epoch": 0.6013317434019607, "grad_norm": 0.1396484375, "learning_rate": 2.036919141438873e-05, "loss": 1.4885752201080322, "step": 7123 }, { "epoch": 0.6014161645367918, "grad_norm": 0.140625, "learning_rate": 2.0362794500131184e-05, "loss": 1.482771635055542, "step": 7124 }, { "epoch": 0.6015005856716229, "grad_norm": 0.140625, "learning_rate": 2.0356397900287307e-05, "loss": 1.5020638704299927, "step": 7125 }, { "epoch": 0.601585006806454, "grad_norm": 0.13671875, "learning_rate": 2.0350001615290814e-05, "loss": 1.433548092842102, "step": 7126 }, { "epoch": 0.6016694279412851, "grad_norm": 0.1396484375, "learning_rate": 2.0343605645575397e-05, "loss": 1.430599570274353, "step": 7127 }, { "epoch": 0.6017538490761162, "grad_norm": 0.1484375, "learning_rate": 2.0337209991574695e-05, "loss": 1.5534465312957764, "step": 7128 }, { "epoch": 0.6018382702109473, "grad_norm": 0.146484375, "learning_rate": 2.033081465372238e-05, "loss": 1.503881573677063, "step": 7129 }, { "epoch": 0.6019226913457785, "grad_norm": 0.1337890625, "learning_rate": 2.0324419632452048e-05, "loss": 1.532867193222046, "step": 7130 }, { "epoch": 0.6020071124806096, "grad_norm": 0.1474609375, "learning_rate": 2.0318024928197298e-05, "loss": 1.4447739124298096, "step": 7131 }, { "epoch": 0.6020915336154407, "grad_norm": 0.146484375, "learning_rate": 2.0311630541391722e-05, "loss": 1.427281141281128, "step": 7132 }, { "epoch": 0.6021759547502717, "grad_norm": 0.138671875, "learning_rate": 2.0305236472468854e-05, "loss": 1.5473248958587646, "step": 7133 }, { "epoch": 0.6022603758851028, "grad_norm": 0.1328125, "learning_rate": 2.0298842721862238e-05, "loss": 1.5080715417861938, "step": 7134 }, { "epoch": 0.6023447970199339, "grad_norm": 0.1513671875, "learning_rate": 2.0292449290005395e-05, "loss": 1.5401331186294556, "step": 7135 }, { "epoch": 0.602429218154765, "grad_norm": 0.14453125, "learning_rate": 2.0286056177331804e-05, "loss": 1.544345498085022, "step": 7136 }, { "epoch": 0.6025136392895961, "grad_norm": 0.1318359375, "learning_rate": 2.0279663384274932e-05, "loss": 1.5047203302383423, "step": 7137 }, { "epoch": 0.6025980604244272, "grad_norm": 0.1328125, "learning_rate": 2.0273270911268222e-05, "loss": 1.4878427982330322, "step": 7138 }, { "epoch": 0.6026824815592584, "grad_norm": 0.1357421875, "learning_rate": 2.026687875874511e-05, "loss": 1.4524340629577637, "step": 7139 }, { "epoch": 0.6027669026940895, "grad_norm": 0.1435546875, "learning_rate": 2.0260486927139007e-05, "loss": 1.4920824766159058, "step": 7140 }, { "epoch": 0.6028513238289206, "grad_norm": 0.154296875, "learning_rate": 2.025409541688327e-05, "loss": 1.5325331687927246, "step": 7141 }, { "epoch": 0.6029357449637517, "grad_norm": 0.1376953125, "learning_rate": 2.024770422841128e-05, "loss": 1.4938210248947144, "step": 7142 }, { "epoch": 0.6030201660985828, "grad_norm": 0.1416015625, "learning_rate": 2.0241313362156354e-05, "loss": 1.4835269451141357, "step": 7143 }, { "epoch": 0.6031045872334139, "grad_norm": 0.1337890625, "learning_rate": 2.0234922818551825e-05, "loss": 1.405920147895813, "step": 7144 }, { "epoch": 0.603189008368245, "grad_norm": 0.1494140625, "learning_rate": 2.0228532598030992e-05, "loss": 1.5783545970916748, "step": 7145 }, { "epoch": 0.603273429503076, "grad_norm": 0.1435546875, "learning_rate": 2.022214270102711e-05, "loss": 1.5340842008590698, "step": 7146 }, { "epoch": 0.6033578506379071, "grad_norm": 0.1455078125, "learning_rate": 2.0215753127973443e-05, "loss": 1.5132567882537842, "step": 7147 }, { "epoch": 0.6034422717727383, "grad_norm": 0.1474609375, "learning_rate": 2.0209363879303207e-05, "loss": 1.5278853178024292, "step": 7148 }, { "epoch": 0.6035266929075694, "grad_norm": 0.14453125, "learning_rate": 2.0202974955449612e-05, "loss": 1.5620882511138916, "step": 7149 }, { "epoch": 0.6036111140424005, "grad_norm": 0.1328125, "learning_rate": 2.0196586356845854e-05, "loss": 1.5547399520874023, "step": 7150 }, { "epoch": 0.6036955351772316, "grad_norm": 0.1455078125, "learning_rate": 2.019019808392508e-05, "loss": 1.504356026649475, "step": 7151 }, { "epoch": 0.6037799563120627, "grad_norm": 0.1396484375, "learning_rate": 2.0183810137120433e-05, "loss": 1.5063953399658203, "step": 7152 }, { "epoch": 0.6038643774468938, "grad_norm": 0.1357421875, "learning_rate": 2.0177422516865055e-05, "loss": 1.4715559482574463, "step": 7153 }, { "epoch": 0.6039487985817249, "grad_norm": 0.1376953125, "learning_rate": 2.0171035223592005e-05, "loss": 1.555473804473877, "step": 7154 }, { "epoch": 0.604033219716556, "grad_norm": 0.138671875, "learning_rate": 2.0164648257734384e-05, "loss": 1.5693020820617676, "step": 7155 }, { "epoch": 0.6041176408513872, "grad_norm": 0.1357421875, "learning_rate": 2.015826161972523e-05, "loss": 1.486803412437439, "step": 7156 }, { "epoch": 0.6042020619862183, "grad_norm": 0.1435546875, "learning_rate": 2.0151875309997566e-05, "loss": 1.5366806983947754, "step": 7157 }, { "epoch": 0.6042864831210494, "grad_norm": 0.1376953125, "learning_rate": 2.014548932898443e-05, "loss": 1.5078457593917847, "step": 7158 }, { "epoch": 0.6043709042558805, "grad_norm": 0.1376953125, "learning_rate": 2.0139103677118768e-05, "loss": 1.5168880224227905, "step": 7159 }, { "epoch": 0.6044553253907116, "grad_norm": 0.1357421875, "learning_rate": 2.013271835483357e-05, "loss": 1.446636438369751, "step": 7160 }, { "epoch": 0.6045397465255427, "grad_norm": 0.140625, "learning_rate": 2.0126333362561768e-05, "loss": 1.5045368671417236, "step": 7161 }, { "epoch": 0.6046241676603737, "grad_norm": 0.1376953125, "learning_rate": 2.011994870073627e-05, "loss": 1.515583872795105, "step": 7162 }, { "epoch": 0.6047085887952048, "grad_norm": 0.1640625, "learning_rate": 2.0113564369789992e-05, "loss": 1.4889390468597412, "step": 7163 }, { "epoch": 0.6047930099300359, "grad_norm": 0.130859375, "learning_rate": 2.010718037015578e-05, "loss": 1.4696637392044067, "step": 7164 }, { "epoch": 0.6048774310648671, "grad_norm": 0.134765625, "learning_rate": 2.0100796702266517e-05, "loss": 1.4935433864593506, "step": 7165 }, { "epoch": 0.6049618521996982, "grad_norm": 0.1474609375, "learning_rate": 2.0094413366555003e-05, "loss": 1.5308382511138916, "step": 7166 }, { "epoch": 0.6050462733345293, "grad_norm": 0.1455078125, "learning_rate": 2.0088030363454055e-05, "loss": 1.5347683429718018, "step": 7167 }, { "epoch": 0.6051306944693604, "grad_norm": 0.1435546875, "learning_rate": 2.008164769339646e-05, "loss": 1.5907583236694336, "step": 7168 }, { "epoch": 0.6052151156041915, "grad_norm": 0.1337890625, "learning_rate": 2.0075265356814965e-05, "loss": 1.5004351139068604, "step": 7169 }, { "epoch": 0.6052995367390226, "grad_norm": 0.1611328125, "learning_rate": 2.006888335414232e-05, "loss": 1.4971377849578857, "step": 7170 }, { "epoch": 0.6053839578738537, "grad_norm": 0.1474609375, "learning_rate": 2.006250168581124e-05, "loss": 1.5806584358215332, "step": 7171 }, { "epoch": 0.6054683790086848, "grad_norm": 0.1396484375, "learning_rate": 2.0056120352254413e-05, "loss": 1.4740965366363525, "step": 7172 }, { "epoch": 0.605552800143516, "grad_norm": 0.1455078125, "learning_rate": 2.0049739353904513e-05, "loss": 1.565710186958313, "step": 7173 }, { "epoch": 0.6056372212783471, "grad_norm": 0.1455078125, "learning_rate": 2.0043358691194173e-05, "loss": 1.527367353439331, "step": 7174 }, { "epoch": 0.6057216424131782, "grad_norm": 0.1474609375, "learning_rate": 2.0036978364556033e-05, "loss": 1.509887933731079, "step": 7175 }, { "epoch": 0.6058060635480093, "grad_norm": 0.1474609375, "learning_rate": 2.0030598374422697e-05, "loss": 1.6584218740463257, "step": 7176 }, { "epoch": 0.6058904846828403, "grad_norm": 0.140625, "learning_rate": 2.0024218721226728e-05, "loss": 1.5878760814666748, "step": 7177 }, { "epoch": 0.6059749058176714, "grad_norm": 0.1396484375, "learning_rate": 2.0017839405400695e-05, "loss": 1.451689600944519, "step": 7178 }, { "epoch": 0.6060593269525025, "grad_norm": 0.146484375, "learning_rate": 2.0011460427377115e-05, "loss": 1.540102481842041, "step": 7179 }, { "epoch": 0.6061437480873336, "grad_norm": 0.1318359375, "learning_rate": 2.0005081787588514e-05, "loss": 1.4983807802200317, "step": 7180 }, { "epoch": 0.6062281692221647, "grad_norm": 0.1455078125, "learning_rate": 1.9998703486467383e-05, "loss": 1.520894169807434, "step": 7181 }, { "epoch": 0.6063125903569959, "grad_norm": 0.1376953125, "learning_rate": 1.9992325524446172e-05, "loss": 1.4627137184143066, "step": 7182 }, { "epoch": 0.606397011491827, "grad_norm": 0.142578125, "learning_rate": 1.9985947901957328e-05, "loss": 1.5411263704299927, "step": 7183 }, { "epoch": 0.6064814326266581, "grad_norm": 0.1318359375, "learning_rate": 1.997957061943326e-05, "loss": 1.53860342502594, "step": 7184 }, { "epoch": 0.6065658537614892, "grad_norm": 0.1376953125, "learning_rate": 1.9973193677306377e-05, "loss": 1.5554914474487305, "step": 7185 }, { "epoch": 0.6066502748963203, "grad_norm": 0.142578125, "learning_rate": 1.9966817076009047e-05, "loss": 1.5956159830093384, "step": 7186 }, { "epoch": 0.6067346960311514, "grad_norm": 0.1484375, "learning_rate": 1.996044081597362e-05, "loss": 1.5327599048614502, "step": 7187 }, { "epoch": 0.6068191171659825, "grad_norm": 0.142578125, "learning_rate": 1.9954064897632406e-05, "loss": 1.5629030466079712, "step": 7188 }, { "epoch": 0.6069035383008136, "grad_norm": 0.1357421875, "learning_rate": 1.994768932141774e-05, "loss": 1.4399758577346802, "step": 7189 }, { "epoch": 0.6069879594356448, "grad_norm": 0.1435546875, "learning_rate": 1.9941314087761866e-05, "loss": 1.5934834480285645, "step": 7190 }, { "epoch": 0.6070723805704759, "grad_norm": 0.1416015625, "learning_rate": 1.993493919709707e-05, "loss": 1.5332581996917725, "step": 7191 }, { "epoch": 0.607156801705307, "grad_norm": 0.1455078125, "learning_rate": 1.9928564649855562e-05, "loss": 1.4267197847366333, "step": 7192 }, { "epoch": 0.607241222840138, "grad_norm": 0.1357421875, "learning_rate": 1.992219044646956e-05, "loss": 1.5137839317321777, "step": 7193 }, { "epoch": 0.6073256439749691, "grad_norm": 0.13671875, "learning_rate": 1.991581658737126e-05, "loss": 1.5992194414138794, "step": 7194 }, { "epoch": 0.6074100651098002, "grad_norm": 0.142578125, "learning_rate": 1.9909443072992807e-05, "loss": 1.566354751586914, "step": 7195 }, { "epoch": 0.6074944862446313, "grad_norm": 0.140625, "learning_rate": 1.9903069903766355e-05, "loss": 1.5095354318618774, "step": 7196 }, { "epoch": 0.6075789073794624, "grad_norm": 0.1318359375, "learning_rate": 1.989669708012401e-05, "loss": 1.4451137781143188, "step": 7197 }, { "epoch": 0.6076633285142935, "grad_norm": 0.14453125, "learning_rate": 1.989032460249787e-05, "loss": 1.6158668994903564, "step": 7198 }, { "epoch": 0.6077477496491247, "grad_norm": 0.1328125, "learning_rate": 1.9883952471320018e-05, "loss": 1.5323030948638916, "step": 7199 }, { "epoch": 0.6078321707839558, "grad_norm": 0.1357421875, "learning_rate": 1.9877580687022467e-05, "loss": 1.5517659187316895, "step": 7200 }, { "epoch": 0.6079165919187869, "grad_norm": 0.1328125, "learning_rate": 1.9871209250037263e-05, "loss": 1.5464882850646973, "step": 7201 }, { "epoch": 0.608001013053618, "grad_norm": 0.138671875, "learning_rate": 1.9864838160796405e-05, "loss": 1.5702096223831177, "step": 7202 }, { "epoch": 0.6080854341884491, "grad_norm": 0.1357421875, "learning_rate": 1.9858467419731862e-05, "loss": 1.5165680646896362, "step": 7203 }, { "epoch": 0.6081698553232802, "grad_norm": 0.14453125, "learning_rate": 1.985209702727559e-05, "loss": 1.5424658060073853, "step": 7204 }, { "epoch": 0.6082542764581113, "grad_norm": 0.1416015625, "learning_rate": 1.9845726983859502e-05, "loss": 1.4840368032455444, "step": 7205 }, { "epoch": 0.6083386975929423, "grad_norm": 0.14453125, "learning_rate": 1.983935728991552e-05, "loss": 1.5500843524932861, "step": 7206 }, { "epoch": 0.6084231187277735, "grad_norm": 0.1416015625, "learning_rate": 1.983298794587552e-05, "loss": 1.4764834642410278, "step": 7207 }, { "epoch": 0.6085075398626046, "grad_norm": 0.1474609375, "learning_rate": 1.982661895217136e-05, "loss": 1.5943572521209717, "step": 7208 }, { "epoch": 0.6085919609974357, "grad_norm": 0.1328125, "learning_rate": 1.9820250309234867e-05, "loss": 1.4702324867248535, "step": 7209 }, { "epoch": 0.6086763821322668, "grad_norm": 0.1376953125, "learning_rate": 1.9813882017497848e-05, "loss": 1.5702400207519531, "step": 7210 }, { "epoch": 0.6087608032670979, "grad_norm": 0.1494140625, "learning_rate": 1.9807514077392097e-05, "loss": 1.5970300436019897, "step": 7211 }, { "epoch": 0.608845224401929, "grad_norm": 0.146484375, "learning_rate": 1.9801146489349377e-05, "loss": 1.5897701978683472, "step": 7212 }, { "epoch": 0.6089296455367601, "grad_norm": 0.1455078125, "learning_rate": 1.9794779253801417e-05, "loss": 1.6303600072860718, "step": 7213 }, { "epoch": 0.6090140666715912, "grad_norm": 0.154296875, "learning_rate": 1.9788412371179942e-05, "loss": 1.555274486541748, "step": 7214 }, { "epoch": 0.6090984878064223, "grad_norm": 0.1513671875, "learning_rate": 1.9782045841916625e-05, "loss": 1.579489827156067, "step": 7215 }, { "epoch": 0.6091829089412535, "grad_norm": 0.1298828125, "learning_rate": 1.9775679666443145e-05, "loss": 1.5147963762283325, "step": 7216 }, { "epoch": 0.6092673300760846, "grad_norm": 0.1376953125, "learning_rate": 1.9769313845191148e-05, "loss": 1.565248966217041, "step": 7217 }, { "epoch": 0.6093517512109157, "grad_norm": 0.1396484375, "learning_rate": 1.976294837859224e-05, "loss": 1.5578851699829102, "step": 7218 }, { "epoch": 0.6094361723457468, "grad_norm": 0.142578125, "learning_rate": 1.9756583267078016e-05, "loss": 1.4553278684616089, "step": 7219 }, { "epoch": 0.6095205934805779, "grad_norm": 0.1416015625, "learning_rate": 1.975021851108006e-05, "loss": 1.5033900737762451, "step": 7220 }, { "epoch": 0.609605014615409, "grad_norm": 0.1396484375, "learning_rate": 1.97438541110299e-05, "loss": 1.5587735176086426, "step": 7221 }, { "epoch": 0.60968943575024, "grad_norm": 0.1416015625, "learning_rate": 1.973749006735907e-05, "loss": 1.6127525568008423, "step": 7222 }, { "epoch": 0.6097738568850711, "grad_norm": 0.142578125, "learning_rate": 1.973112638049906e-05, "loss": 1.4267665147781372, "step": 7223 }, { "epoch": 0.6098582780199023, "grad_norm": 0.1435546875, "learning_rate": 1.9724763050881344e-05, "loss": 1.5675690174102783, "step": 7224 }, { "epoch": 0.6099426991547334, "grad_norm": 0.1474609375, "learning_rate": 1.971840007893738e-05, "loss": 1.557833194732666, "step": 7225 }, { "epoch": 0.6100271202895645, "grad_norm": 0.134765625, "learning_rate": 1.9712037465098583e-05, "loss": 1.5541540384292603, "step": 7226 }, { "epoch": 0.6101115414243956, "grad_norm": 0.138671875, "learning_rate": 1.9705675209796358e-05, "loss": 1.52138090133667, "step": 7227 }, { "epoch": 0.6101959625592267, "grad_norm": 0.140625, "learning_rate": 1.9699313313462074e-05, "loss": 1.5646108388900757, "step": 7228 }, { "epoch": 0.6102803836940578, "grad_norm": 0.134765625, "learning_rate": 1.9692951776527085e-05, "loss": 1.5730034112930298, "step": 7229 }, { "epoch": 0.6103648048288889, "grad_norm": 0.1318359375, "learning_rate": 1.9686590599422738e-05, "loss": 1.4842020273208618, "step": 7230 }, { "epoch": 0.61044922596372, "grad_norm": 0.15234375, "learning_rate": 1.9680229782580307e-05, "loss": 1.6399648189544678, "step": 7231 }, { "epoch": 0.6105336470985511, "grad_norm": 0.142578125, "learning_rate": 1.9673869326431092e-05, "loss": 1.5283970832824707, "step": 7232 }, { "epoch": 0.6106180682333823, "grad_norm": 0.138671875, "learning_rate": 1.9667509231406334e-05, "loss": 1.57840895652771, "step": 7233 }, { "epoch": 0.6107024893682134, "grad_norm": 0.140625, "learning_rate": 1.966114949793726e-05, "loss": 1.4916108846664429, "step": 7234 }, { "epoch": 0.6107869105030445, "grad_norm": 0.146484375, "learning_rate": 1.9654790126455103e-05, "loss": 1.5047051906585693, "step": 7235 }, { "epoch": 0.6108713316378755, "grad_norm": 0.1435546875, "learning_rate": 1.9648431117391006e-05, "loss": 1.5735533237457275, "step": 7236 }, { "epoch": 0.6109557527727066, "grad_norm": 0.138671875, "learning_rate": 1.9642072471176144e-05, "loss": 1.498610496520996, "step": 7237 }, { "epoch": 0.6110401739075377, "grad_norm": 0.1474609375, "learning_rate": 1.963571418824166e-05, "loss": 1.5966424942016602, "step": 7238 }, { "epoch": 0.6111245950423688, "grad_norm": 0.1337890625, "learning_rate": 1.9629356269018638e-05, "loss": 1.4716086387634277, "step": 7239 }, { "epoch": 0.6112090161771999, "grad_norm": 0.150390625, "learning_rate": 1.9622998713938175e-05, "loss": 1.544145107269287, "step": 7240 }, { "epoch": 0.6112934373120311, "grad_norm": 0.142578125, "learning_rate": 1.9616641523431318e-05, "loss": 1.542877197265625, "step": 7241 }, { "epoch": 0.6113778584468622, "grad_norm": 0.1357421875, "learning_rate": 1.9610284697929104e-05, "loss": 1.5542447566986084, "step": 7242 }, { "epoch": 0.6114622795816933, "grad_norm": 0.1396484375, "learning_rate": 1.9603928237862553e-05, "loss": 1.4679560661315918, "step": 7243 }, { "epoch": 0.6115467007165244, "grad_norm": 0.1328125, "learning_rate": 1.9597572143662633e-05, "loss": 1.479941725730896, "step": 7244 }, { "epoch": 0.6116311218513555, "grad_norm": 0.1474609375, "learning_rate": 1.959121641576031e-05, "loss": 1.4933797121047974, "step": 7245 }, { "epoch": 0.6117155429861866, "grad_norm": 0.13671875, "learning_rate": 1.9584861054586506e-05, "loss": 1.5381646156311035, "step": 7246 }, { "epoch": 0.6117999641210177, "grad_norm": 0.1357421875, "learning_rate": 1.9578506060572145e-05, "loss": 1.5184402465820312, "step": 7247 }, { "epoch": 0.6118843852558488, "grad_norm": 0.1376953125, "learning_rate": 1.9572151434148107e-05, "loss": 1.545759677886963, "step": 7248 }, { "epoch": 0.6119688063906799, "grad_norm": 0.138671875, "learning_rate": 1.9565797175745242e-05, "loss": 1.5357704162597656, "step": 7249 }, { "epoch": 0.6120532275255111, "grad_norm": 0.146484375, "learning_rate": 1.9559443285794397e-05, "loss": 1.540578007698059, "step": 7250 }, { "epoch": 0.6121376486603421, "grad_norm": 0.140625, "learning_rate": 1.9553089764726367e-05, "loss": 1.538644790649414, "step": 7251 }, { "epoch": 0.6122220697951732, "grad_norm": 0.1328125, "learning_rate": 1.954673661297195e-05, "loss": 1.5018349885940552, "step": 7252 }, { "epoch": 0.6123064909300043, "grad_norm": 0.142578125, "learning_rate": 1.95403838309619e-05, "loss": 1.518977165222168, "step": 7253 }, { "epoch": 0.6123909120648354, "grad_norm": 0.1435546875, "learning_rate": 1.9534031419126947e-05, "loss": 1.5570032596588135, "step": 7254 }, { "epoch": 0.6124753331996665, "grad_norm": 0.138671875, "learning_rate": 1.9527679377897795e-05, "loss": 1.5544428825378418, "step": 7255 }, { "epoch": 0.6125597543344976, "grad_norm": 0.1357421875, "learning_rate": 1.9521327707705144e-05, "loss": 1.5855317115783691, "step": 7256 }, { "epoch": 0.6126441754693287, "grad_norm": 0.1435546875, "learning_rate": 1.951497640897964e-05, "loss": 1.4527462720870972, "step": 7257 }, { "epoch": 0.6127285966041599, "grad_norm": 0.1337890625, "learning_rate": 1.9508625482151926e-05, "loss": 1.471235990524292, "step": 7258 }, { "epoch": 0.612813017738991, "grad_norm": 0.134765625, "learning_rate": 1.9502274927652598e-05, "loss": 1.5516325235366821, "step": 7259 }, { "epoch": 0.6128974388738221, "grad_norm": 0.1474609375, "learning_rate": 1.949592474591224e-05, "loss": 1.5345147848129272, "step": 7260 }, { "epoch": 0.6129818600086532, "grad_norm": 0.1318359375, "learning_rate": 1.948957493736142e-05, "loss": 1.5521705150604248, "step": 7261 }, { "epoch": 0.6130662811434843, "grad_norm": 0.13671875, "learning_rate": 1.9483225502430666e-05, "loss": 1.5113999843597412, "step": 7262 }, { "epoch": 0.6131507022783154, "grad_norm": 0.150390625, "learning_rate": 1.9476876441550484e-05, "loss": 1.5443520545959473, "step": 7263 }, { "epoch": 0.6132351234131465, "grad_norm": 0.1318359375, "learning_rate": 1.9470527755151353e-05, "loss": 1.5575655698776245, "step": 7264 }, { "epoch": 0.6133195445479775, "grad_norm": 0.14453125, "learning_rate": 1.9464179443663723e-05, "loss": 1.545440673828125, "step": 7265 }, { "epoch": 0.6134039656828086, "grad_norm": 0.1669921875, "learning_rate": 1.9457831507518052e-05, "loss": 1.5314702987670898, "step": 7266 }, { "epoch": 0.6134883868176398, "grad_norm": 0.1455078125, "learning_rate": 1.945148394714471e-05, "loss": 1.543103575706482, "step": 7267 }, { "epoch": 0.6135728079524709, "grad_norm": 0.1591796875, "learning_rate": 1.9445136762974102e-05, "loss": 1.6205112934112549, "step": 7268 }, { "epoch": 0.613657229087302, "grad_norm": 0.134765625, "learning_rate": 1.943878995543657e-05, "loss": 1.466407060623169, "step": 7269 }, { "epoch": 0.6137416502221331, "grad_norm": 0.1474609375, "learning_rate": 1.943244352496244e-05, "loss": 1.4690181016921997, "step": 7270 }, { "epoch": 0.6138260713569642, "grad_norm": 0.130859375, "learning_rate": 1.9426097471982037e-05, "loss": 1.4606971740722656, "step": 7271 }, { "epoch": 0.6139104924917953, "grad_norm": 0.1396484375, "learning_rate": 1.941975179692561e-05, "loss": 1.5520718097686768, "step": 7272 }, { "epoch": 0.6139949136266264, "grad_norm": 0.14453125, "learning_rate": 1.941340650022343e-05, "loss": 1.6531943082809448, "step": 7273 }, { "epoch": 0.6140793347614575, "grad_norm": 0.1396484375, "learning_rate": 1.9407061582305718e-05, "loss": 1.554274082183838, "step": 7274 }, { "epoch": 0.6141637558962887, "grad_norm": 0.138671875, "learning_rate": 1.9400717043602666e-05, "loss": 1.5011465549468994, "step": 7275 }, { "epoch": 0.6142481770311198, "grad_norm": 0.1474609375, "learning_rate": 1.9394372884544478e-05, "loss": 1.4816133975982666, "step": 7276 }, { "epoch": 0.6143325981659509, "grad_norm": 0.1474609375, "learning_rate": 1.938802910556126e-05, "loss": 1.500902533531189, "step": 7277 }, { "epoch": 0.614417019300782, "grad_norm": 0.1474609375, "learning_rate": 1.9381685707083165e-05, "loss": 1.6064594984054565, "step": 7278 }, { "epoch": 0.6145014404356131, "grad_norm": 0.1298828125, "learning_rate": 1.9375342689540292e-05, "loss": 1.4944016933441162, "step": 7279 }, { "epoch": 0.6145858615704441, "grad_norm": 0.1376953125, "learning_rate": 1.93690000533627e-05, "loss": 1.55669105052948, "step": 7280 }, { "epoch": 0.6146702827052752, "grad_norm": 0.1591796875, "learning_rate": 1.9362657798980442e-05, "loss": 1.4860507249832153, "step": 7281 }, { "epoch": 0.6147547038401063, "grad_norm": 0.1376953125, "learning_rate": 1.9356315926823523e-05, "loss": 1.4964889287948608, "step": 7282 }, { "epoch": 0.6148391249749374, "grad_norm": 0.1337890625, "learning_rate": 1.9349974437321957e-05, "loss": 1.5236486196517944, "step": 7283 }, { "epoch": 0.6149235461097686, "grad_norm": 0.1435546875, "learning_rate": 1.9343633330905712e-05, "loss": 1.5241519212722778, "step": 7284 }, { "epoch": 0.6150079672445997, "grad_norm": 0.12890625, "learning_rate": 1.9337292608004715e-05, "loss": 1.5201225280761719, "step": 7285 }, { "epoch": 0.6150923883794308, "grad_norm": 0.146484375, "learning_rate": 1.933095226904889e-05, "loss": 1.489680290222168, "step": 7286 }, { "epoch": 0.6151768095142619, "grad_norm": 0.134765625, "learning_rate": 1.932461231446813e-05, "loss": 1.4731297492980957, "step": 7287 }, { "epoch": 0.615261230649093, "grad_norm": 0.1513671875, "learning_rate": 1.93182727446923e-05, "loss": 1.5818616151809692, "step": 7288 }, { "epoch": 0.6153456517839241, "grad_norm": 0.142578125, "learning_rate": 1.9311933560151234e-05, "loss": 1.5825581550598145, "step": 7289 }, { "epoch": 0.6154300729187552, "grad_norm": 0.140625, "learning_rate": 1.9305594761274745e-05, "loss": 1.425336480140686, "step": 7290 }, { "epoch": 0.6155144940535863, "grad_norm": 0.1357421875, "learning_rate": 1.929925634849261e-05, "loss": 1.5442283153533936, "step": 7291 }, { "epoch": 0.6155989151884175, "grad_norm": 0.1298828125, "learning_rate": 1.929291832223461e-05, "loss": 1.4782018661499023, "step": 7292 }, { "epoch": 0.6156833363232486, "grad_norm": 0.1494140625, "learning_rate": 1.928658068293046e-05, "loss": 1.5887025594711304, "step": 7293 }, { "epoch": 0.6157677574580797, "grad_norm": 0.150390625, "learning_rate": 1.928024343100988e-05, "loss": 1.5462909936904907, "step": 7294 }, { "epoch": 0.6158521785929107, "grad_norm": 0.1494140625, "learning_rate": 1.9273906566902534e-05, "loss": 1.6783252954483032, "step": 7295 }, { "epoch": 0.6159365997277418, "grad_norm": 0.140625, "learning_rate": 1.9267570091038084e-05, "loss": 1.519517421722412, "step": 7296 }, { "epoch": 0.6160210208625729, "grad_norm": 0.1376953125, "learning_rate": 1.926123400384617e-05, "loss": 1.5213755369186401, "step": 7297 }, { "epoch": 0.616105441997404, "grad_norm": 0.15234375, "learning_rate": 1.9254898305756382e-05, "loss": 1.5183483362197876, "step": 7298 }, { "epoch": 0.6161898631322351, "grad_norm": 0.138671875, "learning_rate": 1.92485629971983e-05, "loss": 1.500775694847107, "step": 7299 }, { "epoch": 0.6162742842670662, "grad_norm": 0.1474609375, "learning_rate": 1.924222807860147e-05, "loss": 1.532400369644165, "step": 7300 }, { "epoch": 0.6163587054018974, "grad_norm": 0.13671875, "learning_rate": 1.9235893550395406e-05, "loss": 1.4580203294754028, "step": 7301 }, { "epoch": 0.6164431265367285, "grad_norm": 0.1494140625, "learning_rate": 1.922955941300963e-05, "loss": 1.5077087879180908, "step": 7302 }, { "epoch": 0.6165275476715596, "grad_norm": 0.138671875, "learning_rate": 1.922322566687359e-05, "loss": 1.5291029214859009, "step": 7303 }, { "epoch": 0.6166119688063907, "grad_norm": 0.1416015625, "learning_rate": 1.9216892312416732e-05, "loss": 1.551145076751709, "step": 7304 }, { "epoch": 0.6166963899412218, "grad_norm": 0.1376953125, "learning_rate": 1.9210559350068485e-05, "loss": 1.486208200454712, "step": 7305 }, { "epoch": 0.6167808110760529, "grad_norm": 0.1455078125, "learning_rate": 1.9204226780258215e-05, "loss": 1.5064644813537598, "step": 7306 }, { "epoch": 0.616865232210884, "grad_norm": 0.1357421875, "learning_rate": 1.919789460341532e-05, "loss": 1.4496350288391113, "step": 7307 }, { "epoch": 0.616949653345715, "grad_norm": 0.1357421875, "learning_rate": 1.91915628199691e-05, "loss": 1.4377492666244507, "step": 7308 }, { "epoch": 0.6170340744805463, "grad_norm": 0.158203125, "learning_rate": 1.9185231430348887e-05, "loss": 1.5245335102081299, "step": 7309 }, { "epoch": 0.6171184956153773, "grad_norm": 0.1533203125, "learning_rate": 1.917890043498397e-05, "loss": 1.6672062873840332, "step": 7310 }, { "epoch": 0.6172029167502084, "grad_norm": 0.1357421875, "learning_rate": 1.917256983430358e-05, "loss": 1.463863492012024, "step": 7311 }, { "epoch": 0.6172873378850395, "grad_norm": 0.1376953125, "learning_rate": 1.916623962873698e-05, "loss": 1.5651935338974, "step": 7312 }, { "epoch": 0.6173717590198706, "grad_norm": 0.134765625, "learning_rate": 1.915990981871334e-05, "loss": 1.4993247985839844, "step": 7313 }, { "epoch": 0.6174561801547017, "grad_norm": 0.126953125, "learning_rate": 1.9153580404661857e-05, "loss": 1.477495789527893, "step": 7314 }, { "epoch": 0.6175406012895328, "grad_norm": 0.1494140625, "learning_rate": 1.914725138701168e-05, "loss": 1.5351810455322266, "step": 7315 }, { "epoch": 0.6176250224243639, "grad_norm": 0.134765625, "learning_rate": 1.9140922766191918e-05, "loss": 1.534197211265564, "step": 7316 }, { "epoch": 0.617709443559195, "grad_norm": 0.1376953125, "learning_rate": 1.913459454263169e-05, "loss": 1.545862078666687, "step": 7317 }, { "epoch": 0.6177938646940262, "grad_norm": 0.142578125, "learning_rate": 1.9128266716760037e-05, "loss": 1.5363013744354248, "step": 7318 }, { "epoch": 0.6178782858288573, "grad_norm": 0.140625, "learning_rate": 1.912193928900602e-05, "loss": 1.508461594581604, "step": 7319 }, { "epoch": 0.6179627069636884, "grad_norm": 0.1474609375, "learning_rate": 1.911561225979865e-05, "loss": 1.5050009489059448, "step": 7320 }, { "epoch": 0.6180471280985195, "grad_norm": 0.1630859375, "learning_rate": 1.910928562956691e-05, "loss": 1.628390908241272, "step": 7321 }, { "epoch": 0.6181315492333506, "grad_norm": 0.1474609375, "learning_rate": 1.9102959398739758e-05, "loss": 1.5862871408462524, "step": 7322 }, { "epoch": 0.6182159703681817, "grad_norm": 0.1474609375, "learning_rate": 1.9096633567746143e-05, "loss": 1.4656143188476562, "step": 7323 }, { "epoch": 0.6183003915030127, "grad_norm": 0.12890625, "learning_rate": 1.909030813701496e-05, "loss": 1.4707832336425781, "step": 7324 }, { "epoch": 0.6183848126378438, "grad_norm": 0.154296875, "learning_rate": 1.9083983106975093e-05, "loss": 1.5623767375946045, "step": 7325 }, { "epoch": 0.618469233772675, "grad_norm": 0.1591796875, "learning_rate": 1.9077658478055384e-05, "loss": 1.597103476524353, "step": 7326 }, { "epoch": 0.6185536549075061, "grad_norm": 0.14453125, "learning_rate": 1.9071334250684664e-05, "loss": 1.5215916633605957, "step": 7327 }, { "epoch": 0.6186380760423372, "grad_norm": 0.1474609375, "learning_rate": 1.906501042529174e-05, "loss": 1.532488465309143, "step": 7328 }, { "epoch": 0.6187224971771683, "grad_norm": 0.1396484375, "learning_rate": 1.9058687002305375e-05, "loss": 1.567121982574463, "step": 7329 }, { "epoch": 0.6188069183119994, "grad_norm": 0.1318359375, "learning_rate": 1.9052363982154316e-05, "loss": 1.5237895250320435, "step": 7330 }, { "epoch": 0.6188913394468305, "grad_norm": 0.1435546875, "learning_rate": 1.9046041365267264e-05, "loss": 1.5535093545913696, "step": 7331 }, { "epoch": 0.6189757605816616, "grad_norm": 0.142578125, "learning_rate": 1.903971915207292e-05, "loss": 1.532159447669983, "step": 7332 }, { "epoch": 0.6190601817164927, "grad_norm": 0.140625, "learning_rate": 1.903339734299995e-05, "loss": 1.5516252517700195, "step": 7333 }, { "epoch": 0.6191446028513238, "grad_norm": 0.140625, "learning_rate": 1.902707593847698e-05, "loss": 1.5823554992675781, "step": 7334 }, { "epoch": 0.619229023986155, "grad_norm": 0.138671875, "learning_rate": 1.9020754938932624e-05, "loss": 1.5638175010681152, "step": 7335 }, { "epoch": 0.6193134451209861, "grad_norm": 0.1376953125, "learning_rate": 1.901443434479545e-05, "loss": 1.4791646003723145, "step": 7336 }, { "epoch": 0.6193978662558172, "grad_norm": 0.1328125, "learning_rate": 1.9008114156494006e-05, "loss": 1.530404806137085, "step": 7337 }, { "epoch": 0.6194822873906483, "grad_norm": 0.14453125, "learning_rate": 1.900179437445684e-05, "loss": 1.5551954507827759, "step": 7338 }, { "epoch": 0.6195667085254793, "grad_norm": 0.1513671875, "learning_rate": 1.899547499911242e-05, "loss": 1.4914181232452393, "step": 7339 }, { "epoch": 0.6196511296603104, "grad_norm": 0.1484375, "learning_rate": 1.898915603088924e-05, "loss": 1.4787821769714355, "step": 7340 }, { "epoch": 0.6197355507951415, "grad_norm": 0.1337890625, "learning_rate": 1.8982837470215726e-05, "loss": 1.577422022819519, "step": 7341 }, { "epoch": 0.6198199719299726, "grad_norm": 0.146484375, "learning_rate": 1.8976519317520287e-05, "loss": 1.533935785293579, "step": 7342 }, { "epoch": 0.6199043930648038, "grad_norm": 0.1357421875, "learning_rate": 1.897020157323133e-05, "loss": 1.520772099494934, "step": 7343 }, { "epoch": 0.6199888141996349, "grad_norm": 0.1376953125, "learning_rate": 1.8963884237777188e-05, "loss": 1.5459156036376953, "step": 7344 }, { "epoch": 0.620073235334466, "grad_norm": 0.1455078125, "learning_rate": 1.895756731158621e-05, "loss": 1.5636152029037476, "step": 7345 }, { "epoch": 0.6201576564692971, "grad_norm": 0.1337890625, "learning_rate": 1.8951250795086693e-05, "loss": 1.5718274116516113, "step": 7346 }, { "epoch": 0.6202420776041282, "grad_norm": 0.138671875, "learning_rate": 1.8944934688706902e-05, "loss": 1.5536919832229614, "step": 7347 }, { "epoch": 0.6203264987389593, "grad_norm": 0.126953125, "learning_rate": 1.8938618992875112e-05, "loss": 1.4733638763427734, "step": 7348 }, { "epoch": 0.6204109198737904, "grad_norm": 0.13671875, "learning_rate": 1.8932303708019506e-05, "loss": 1.496578335762024, "step": 7349 }, { "epoch": 0.6204953410086215, "grad_norm": 0.1484375, "learning_rate": 1.8925988834568297e-05, "loss": 1.4883369207382202, "step": 7350 }, { "epoch": 0.6205797621434526, "grad_norm": 0.140625, "learning_rate": 1.8919674372949654e-05, "loss": 1.5126036405563354, "step": 7351 }, { "epoch": 0.6206641832782838, "grad_norm": 0.138671875, "learning_rate": 1.891336032359169e-05, "loss": 1.433480978012085, "step": 7352 }, { "epoch": 0.6207486044131149, "grad_norm": 0.1435546875, "learning_rate": 1.8907046686922534e-05, "loss": 1.4709059000015259, "step": 7353 }, { "epoch": 0.620833025547946, "grad_norm": 0.13671875, "learning_rate": 1.8900733463370262e-05, "loss": 1.5202609300613403, "step": 7354 }, { "epoch": 0.620917446682777, "grad_norm": 0.1328125, "learning_rate": 1.8894420653362917e-05, "loss": 1.5123614072799683, "step": 7355 }, { "epoch": 0.6210018678176081, "grad_norm": 0.154296875, "learning_rate": 1.8888108257328536e-05, "loss": 1.5549302101135254, "step": 7356 }, { "epoch": 0.6210862889524392, "grad_norm": 0.1435546875, "learning_rate": 1.8881796275695098e-05, "loss": 1.4932600259780884, "step": 7357 }, { "epoch": 0.6211707100872703, "grad_norm": 0.138671875, "learning_rate": 1.887548470889057e-05, "loss": 1.4493467807769775, "step": 7358 }, { "epoch": 0.6212551312221014, "grad_norm": 0.14453125, "learning_rate": 1.8869173557342914e-05, "loss": 1.5100444555282593, "step": 7359 }, { "epoch": 0.6213395523569326, "grad_norm": 0.14453125, "learning_rate": 1.8862862821480025e-05, "loss": 1.4779839515686035, "step": 7360 }, { "epoch": 0.6214239734917637, "grad_norm": 0.1298828125, "learning_rate": 1.8856552501729792e-05, "loss": 1.4714577198028564, "step": 7361 }, { "epoch": 0.6215083946265948, "grad_norm": 0.1396484375, "learning_rate": 1.8850242598520056e-05, "loss": 1.5394396781921387, "step": 7362 }, { "epoch": 0.6215928157614259, "grad_norm": 0.1435546875, "learning_rate": 1.8843933112278653e-05, "loss": 1.5072193145751953, "step": 7363 }, { "epoch": 0.621677236896257, "grad_norm": 0.13671875, "learning_rate": 1.8837624043433393e-05, "loss": 1.4984174966812134, "step": 7364 }, { "epoch": 0.6217616580310881, "grad_norm": 0.13671875, "learning_rate": 1.883131539241203e-05, "loss": 1.6045961380004883, "step": 7365 }, { "epoch": 0.6218460791659192, "grad_norm": 0.1396484375, "learning_rate": 1.8825007159642315e-05, "loss": 1.549293875694275, "step": 7366 }, { "epoch": 0.6219305003007503, "grad_norm": 0.1376953125, "learning_rate": 1.8818699345551953e-05, "loss": 1.5729769468307495, "step": 7367 }, { "epoch": 0.6220149214355813, "grad_norm": 0.150390625, "learning_rate": 1.8812391950568625e-05, "loss": 1.546658992767334, "step": 7368 }, { "epoch": 0.6220993425704126, "grad_norm": 0.15234375, "learning_rate": 1.880608497512001e-05, "loss": 1.50814950466156, "step": 7369 }, { "epoch": 0.6221837637052436, "grad_norm": 0.146484375, "learning_rate": 1.8799778419633714e-05, "loss": 1.5489063262939453, "step": 7370 }, { "epoch": 0.6222681848400747, "grad_norm": 0.1328125, "learning_rate": 1.8793472284537346e-05, "loss": 1.4774223566055298, "step": 7371 }, { "epoch": 0.6223526059749058, "grad_norm": 0.14453125, "learning_rate": 1.8787166570258483e-05, "loss": 1.6390413045883179, "step": 7372 }, { "epoch": 0.6224370271097369, "grad_norm": 0.1533203125, "learning_rate": 1.878086127722465e-05, "loss": 1.6420321464538574, "step": 7373 }, { "epoch": 0.622521448244568, "grad_norm": 0.1357421875, "learning_rate": 1.8774556405863376e-05, "loss": 1.4813311100006104, "step": 7374 }, { "epoch": 0.6226058693793991, "grad_norm": 0.142578125, "learning_rate": 1.8768251956602138e-05, "loss": 1.5864415168762207, "step": 7375 }, { "epoch": 0.6226902905142302, "grad_norm": 0.1376953125, "learning_rate": 1.87619479298684e-05, "loss": 1.5169233083724976, "step": 7376 }, { "epoch": 0.6227747116490614, "grad_norm": 0.1416015625, "learning_rate": 1.8755644326089593e-05, "loss": 1.5114312171936035, "step": 7377 }, { "epoch": 0.6228591327838925, "grad_norm": 0.140625, "learning_rate": 1.8749341145693095e-05, "loss": 1.4934321641921997, "step": 7378 }, { "epoch": 0.6229435539187236, "grad_norm": 0.1357421875, "learning_rate": 1.8743038389106303e-05, "loss": 1.4747447967529297, "step": 7379 }, { "epoch": 0.6230279750535547, "grad_norm": 0.1455078125, "learning_rate": 1.8736736056756545e-05, "loss": 1.531180739402771, "step": 7380 }, { "epoch": 0.6231123961883858, "grad_norm": 0.1416015625, "learning_rate": 1.8730434149071137e-05, "loss": 1.496848702430725, "step": 7381 }, { "epoch": 0.6231968173232169, "grad_norm": 0.1357421875, "learning_rate": 1.8724132666477368e-05, "loss": 1.4695866107940674, "step": 7382 }, { "epoch": 0.623281238458048, "grad_norm": 0.1455078125, "learning_rate": 1.8717831609402482e-05, "loss": 1.5154364109039307, "step": 7383 }, { "epoch": 0.623365659592879, "grad_norm": 0.138671875, "learning_rate": 1.8711530978273724e-05, "loss": 1.5784261226654053, "step": 7384 }, { "epoch": 0.6234500807277101, "grad_norm": 0.1337890625, "learning_rate": 1.8705230773518267e-05, "loss": 1.4601433277130127, "step": 7385 }, { "epoch": 0.6235345018625413, "grad_norm": 0.1328125, "learning_rate": 1.8698930995563302e-05, "loss": 1.4854388236999512, "step": 7386 }, { "epoch": 0.6236189229973724, "grad_norm": 0.1435546875, "learning_rate": 1.869263164483596e-05, "loss": 1.539962887763977, "step": 7387 }, { "epoch": 0.6237033441322035, "grad_norm": 0.1416015625, "learning_rate": 1.868633272176335e-05, "loss": 1.4637690782546997, "step": 7388 }, { "epoch": 0.6237877652670346, "grad_norm": 0.1494140625, "learning_rate": 1.8680034226772557e-05, "loss": 1.5355130434036255, "step": 7389 }, { "epoch": 0.6238721864018657, "grad_norm": 0.1376953125, "learning_rate": 1.8673736160290644e-05, "loss": 1.6547948122024536, "step": 7390 }, { "epoch": 0.6239566075366968, "grad_norm": 0.14453125, "learning_rate": 1.8667438522744622e-05, "loss": 1.530167579650879, "step": 7391 }, { "epoch": 0.6240410286715279, "grad_norm": 0.1396484375, "learning_rate": 1.8661141314561493e-05, "loss": 1.4578100442886353, "step": 7392 }, { "epoch": 0.624125449806359, "grad_norm": 0.1396484375, "learning_rate": 1.865484453616821e-05, "loss": 1.4736433029174805, "step": 7393 }, { "epoch": 0.6242098709411902, "grad_norm": 0.15234375, "learning_rate": 1.864854818799172e-05, "loss": 1.5436028242111206, "step": 7394 }, { "epoch": 0.6242942920760213, "grad_norm": 0.1513671875, "learning_rate": 1.8642252270458936e-05, "loss": 1.5527231693267822, "step": 7395 }, { "epoch": 0.6243787132108524, "grad_norm": 0.138671875, "learning_rate": 1.8635956783996727e-05, "loss": 1.563420057296753, "step": 7396 }, { "epoch": 0.6244631343456835, "grad_norm": 0.150390625, "learning_rate": 1.862966172903195e-05, "loss": 1.5018737316131592, "step": 7397 }, { "epoch": 0.6245475554805145, "grad_norm": 0.140625, "learning_rate": 1.862336710599142e-05, "loss": 1.508135437965393, "step": 7398 }, { "epoch": 0.6246319766153456, "grad_norm": 0.130859375, "learning_rate": 1.8617072915301914e-05, "loss": 1.522359848022461, "step": 7399 }, { "epoch": 0.6247163977501767, "grad_norm": 0.142578125, "learning_rate": 1.861077915739022e-05, "loss": 1.5309853553771973, "step": 7400 }, { "epoch": 0.6248008188850078, "grad_norm": 0.14453125, "learning_rate": 1.8604485832683054e-05, "loss": 1.5027453899383545, "step": 7401 }, { "epoch": 0.6248852400198389, "grad_norm": 0.146484375, "learning_rate": 1.8598192941607123e-05, "loss": 1.5396853685379028, "step": 7402 }, { "epoch": 0.6249696611546701, "grad_norm": 0.142578125, "learning_rate": 1.8591900484589095e-05, "loss": 1.5169763565063477, "step": 7403 }, { "epoch": 0.6250540822895012, "grad_norm": 0.1376953125, "learning_rate": 1.858560846205561e-05, "loss": 1.5107208490371704, "step": 7404 }, { "epoch": 0.6251385034243323, "grad_norm": 0.13671875, "learning_rate": 1.8579316874433305e-05, "loss": 1.473009467124939, "step": 7405 }, { "epoch": 0.6252229245591634, "grad_norm": 0.134765625, "learning_rate": 1.857302572214874e-05, "loss": 1.5621464252471924, "step": 7406 }, { "epoch": 0.6253073456939945, "grad_norm": 0.1455078125, "learning_rate": 1.8566735005628475e-05, "loss": 1.5653560161590576, "step": 7407 }, { "epoch": 0.6253917668288256, "grad_norm": 0.1435546875, "learning_rate": 1.8560444725299056e-05, "loss": 1.519783854484558, "step": 7408 }, { "epoch": 0.6254761879636567, "grad_norm": 0.14453125, "learning_rate": 1.8554154881586945e-05, "loss": 1.5018141269683838, "step": 7409 }, { "epoch": 0.6255606090984878, "grad_norm": 0.1416015625, "learning_rate": 1.854786547491864e-05, "loss": 1.5235859155654907, "step": 7410 }, { "epoch": 0.625645030233319, "grad_norm": 0.1435546875, "learning_rate": 1.854157650572056e-05, "loss": 1.6072654724121094, "step": 7411 }, { "epoch": 0.6257294513681501, "grad_norm": 0.1513671875, "learning_rate": 1.853528797441912e-05, "loss": 1.480780005455017, "step": 7412 }, { "epoch": 0.6258138725029811, "grad_norm": 0.1328125, "learning_rate": 1.852899988144069e-05, "loss": 1.5362422466278076, "step": 7413 }, { "epoch": 0.6258982936378122, "grad_norm": 0.146484375, "learning_rate": 1.852271222721162e-05, "loss": 1.5653204917907715, "step": 7414 }, { "epoch": 0.6259827147726433, "grad_norm": 0.142578125, "learning_rate": 1.851642501215824e-05, "loss": 1.4609203338623047, "step": 7415 }, { "epoch": 0.6260671359074744, "grad_norm": 0.1376953125, "learning_rate": 1.851013823670682e-05, "loss": 1.5466399192810059, "step": 7416 }, { "epoch": 0.6261515570423055, "grad_norm": 0.1357421875, "learning_rate": 1.8503851901283632e-05, "loss": 1.4919395446777344, "step": 7417 }, { "epoch": 0.6262359781771366, "grad_norm": 0.1396484375, "learning_rate": 1.84975660063149e-05, "loss": 1.4567537307739258, "step": 7418 }, { "epoch": 0.6263203993119677, "grad_norm": 0.1494140625, "learning_rate": 1.8491280552226815e-05, "loss": 1.4938504695892334, "step": 7419 }, { "epoch": 0.6264048204467989, "grad_norm": 0.1416015625, "learning_rate": 1.8484995539445553e-05, "loss": 1.550073504447937, "step": 7420 }, { "epoch": 0.62648924158163, "grad_norm": 0.14453125, "learning_rate": 1.847871096839727e-05, "loss": 1.5493791103363037, "step": 7421 }, { "epoch": 0.6265736627164611, "grad_norm": 0.1435546875, "learning_rate": 1.8472426839508046e-05, "loss": 1.519145131111145, "step": 7422 }, { "epoch": 0.6266580838512922, "grad_norm": 0.130859375, "learning_rate": 1.8466143153203974e-05, "loss": 1.5096838474273682, "step": 7423 }, { "epoch": 0.6267425049861233, "grad_norm": 0.138671875, "learning_rate": 1.8459859909911097e-05, "loss": 1.5746374130249023, "step": 7424 }, { "epoch": 0.6268269261209544, "grad_norm": 0.1376953125, "learning_rate": 1.845357711005544e-05, "loss": 1.4781124591827393, "step": 7425 }, { "epoch": 0.6269113472557855, "grad_norm": 0.138671875, "learning_rate": 1.8447294754063e-05, "loss": 1.4933425188064575, "step": 7426 }, { "epoch": 0.6269957683906165, "grad_norm": 0.1328125, "learning_rate": 1.844101284235972e-05, "loss": 1.474226951599121, "step": 7427 }, { "epoch": 0.6270801895254478, "grad_norm": 0.1396484375, "learning_rate": 1.8434731375371537e-05, "loss": 1.4873995780944824, "step": 7428 }, { "epoch": 0.6271646106602788, "grad_norm": 0.14453125, "learning_rate": 1.842845035352434e-05, "loss": 1.5454615354537964, "step": 7429 }, { "epoch": 0.6272490317951099, "grad_norm": 0.15234375, "learning_rate": 1.842216977724401e-05, "loss": 1.5944584608078003, "step": 7430 }, { "epoch": 0.627333452929941, "grad_norm": 0.1328125, "learning_rate": 1.8415889646956387e-05, "loss": 1.4754712581634521, "step": 7431 }, { "epoch": 0.6274178740647721, "grad_norm": 0.150390625, "learning_rate": 1.840960996308726e-05, "loss": 1.5412133932113647, "step": 7432 }, { "epoch": 0.6275022951996032, "grad_norm": 0.1318359375, "learning_rate": 1.840333072606243e-05, "loss": 1.491044044494629, "step": 7433 }, { "epoch": 0.6275867163344343, "grad_norm": 0.13671875, "learning_rate": 1.839705193630762e-05, "loss": 1.459276556968689, "step": 7434 }, { "epoch": 0.6276711374692654, "grad_norm": 0.1396484375, "learning_rate": 1.8390773594248568e-05, "loss": 1.565279245376587, "step": 7435 }, { "epoch": 0.6277555586040965, "grad_norm": 0.1337890625, "learning_rate": 1.8384495700310957e-05, "loss": 1.5076040029525757, "step": 7436 }, { "epoch": 0.6278399797389277, "grad_norm": 0.142578125, "learning_rate": 1.8378218254920433e-05, "loss": 1.5601327419281006, "step": 7437 }, { "epoch": 0.6279244008737588, "grad_norm": 0.140625, "learning_rate": 1.8371941258502622e-05, "loss": 1.4193300008773804, "step": 7438 }, { "epoch": 0.6280088220085899, "grad_norm": 0.1357421875, "learning_rate": 1.8365664711483143e-05, "loss": 1.54460871219635, "step": 7439 }, { "epoch": 0.628093243143421, "grad_norm": 0.1416015625, "learning_rate": 1.8359388614287527e-05, "loss": 1.5641310214996338, "step": 7440 }, { "epoch": 0.6281776642782521, "grad_norm": 0.1318359375, "learning_rate": 1.8353112967341335e-05, "loss": 1.4902760982513428, "step": 7441 }, { "epoch": 0.6282620854130831, "grad_norm": 0.138671875, "learning_rate": 1.8346837771070057e-05, "loss": 1.5732594728469849, "step": 7442 }, { "epoch": 0.6283465065479142, "grad_norm": 0.1328125, "learning_rate": 1.8340563025899165e-05, "loss": 1.5289807319641113, "step": 7443 }, { "epoch": 0.6284309276827453, "grad_norm": 0.1513671875, "learning_rate": 1.8334288732254124e-05, "loss": 1.5726183652877808, "step": 7444 }, { "epoch": 0.6285153488175765, "grad_norm": 0.1533203125, "learning_rate": 1.8328014890560306e-05, "loss": 1.5865421295166016, "step": 7445 }, { "epoch": 0.6285997699524076, "grad_norm": 0.13671875, "learning_rate": 1.8321741501243134e-05, "loss": 1.584130048751831, "step": 7446 }, { "epoch": 0.6286841910872387, "grad_norm": 0.13671875, "learning_rate": 1.8315468564727932e-05, "loss": 1.6327433586120605, "step": 7447 }, { "epoch": 0.6287686122220698, "grad_norm": 0.1474609375, "learning_rate": 1.830919608144003e-05, "loss": 1.6134833097457886, "step": 7448 }, { "epoch": 0.6288530333569009, "grad_norm": 0.154296875, "learning_rate": 1.830292405180472e-05, "loss": 1.4731553792953491, "step": 7449 }, { "epoch": 0.628937454491732, "grad_norm": 0.1640625, "learning_rate": 1.829665247624725e-05, "loss": 1.5020618438720703, "step": 7450 }, { "epoch": 0.6290218756265631, "grad_norm": 0.138671875, "learning_rate": 1.8290381355192863e-05, "loss": 1.4743216037750244, "step": 7451 }, { "epoch": 0.6291062967613942, "grad_norm": 0.1474609375, "learning_rate": 1.828411068906674e-05, "loss": 1.5830724239349365, "step": 7452 }, { "epoch": 0.6291907178962253, "grad_norm": 0.1435546875, "learning_rate": 1.8277840478294063e-05, "loss": 1.515989065170288, "step": 7453 }, { "epoch": 0.6292751390310565, "grad_norm": 0.13671875, "learning_rate": 1.8271570723299958e-05, "loss": 1.5688499212265015, "step": 7454 }, { "epoch": 0.6293595601658876, "grad_norm": 0.15625, "learning_rate": 1.826530142450952e-05, "loss": 1.6975446939468384, "step": 7455 }, { "epoch": 0.6294439813007187, "grad_norm": 0.14453125, "learning_rate": 1.825903258234784e-05, "loss": 1.6294944286346436, "step": 7456 }, { "epoch": 0.6295284024355497, "grad_norm": 0.1435546875, "learning_rate": 1.825276419723996e-05, "loss": 1.5280879735946655, "step": 7457 }, { "epoch": 0.6296128235703808, "grad_norm": 0.146484375, "learning_rate": 1.824649626961088e-05, "loss": 1.482893466949463, "step": 7458 }, { "epoch": 0.6296972447052119, "grad_norm": 0.1435546875, "learning_rate": 1.8240228799885594e-05, "loss": 1.4502971172332764, "step": 7459 }, { "epoch": 0.629781665840043, "grad_norm": 0.146484375, "learning_rate": 1.823396178848903e-05, "loss": 1.646730661392212, "step": 7460 }, { "epoch": 0.6298660869748741, "grad_norm": 0.1484375, "learning_rate": 1.8227695235846127e-05, "loss": 1.5607919692993164, "step": 7461 }, { "epoch": 0.6299505081097052, "grad_norm": 0.138671875, "learning_rate": 1.8221429142381767e-05, "loss": 1.4550751447677612, "step": 7462 }, { "epoch": 0.6300349292445364, "grad_norm": 0.1435546875, "learning_rate": 1.8215163508520804e-05, "loss": 1.5980085134506226, "step": 7463 }, { "epoch": 0.6301193503793675, "grad_norm": 0.1328125, "learning_rate": 1.820889833468807e-05, "loss": 1.5146573781967163, "step": 7464 }, { "epoch": 0.6302037715141986, "grad_norm": 0.138671875, "learning_rate": 1.820263362130834e-05, "loss": 1.4917566776275635, "step": 7465 }, { "epoch": 0.6302881926490297, "grad_norm": 0.1484375, "learning_rate": 1.8196369368806395e-05, "loss": 1.5106103420257568, "step": 7466 }, { "epoch": 0.6303726137838608, "grad_norm": 0.1376953125, "learning_rate": 1.8190105577606963e-05, "loss": 1.5517122745513916, "step": 7467 }, { "epoch": 0.6304570349186919, "grad_norm": 0.134765625, "learning_rate": 1.818384224813474e-05, "loss": 1.4760856628417969, "step": 7468 }, { "epoch": 0.630541456053523, "grad_norm": 0.1328125, "learning_rate": 1.8177579380814398e-05, "loss": 1.438362956047058, "step": 7469 }, { "epoch": 0.6306258771883541, "grad_norm": 0.14453125, "learning_rate": 1.8171316976070567e-05, "loss": 1.5632994174957275, "step": 7470 }, { "epoch": 0.6307102983231853, "grad_norm": 0.13671875, "learning_rate": 1.816505503432786e-05, "loss": 1.5107245445251465, "step": 7471 }, { "epoch": 0.6307947194580164, "grad_norm": 0.1416015625, "learning_rate": 1.815879355601086e-05, "loss": 1.454547643661499, "step": 7472 }, { "epoch": 0.6308791405928474, "grad_norm": 0.12890625, "learning_rate": 1.815253254154409e-05, "loss": 1.4993501901626587, "step": 7473 }, { "epoch": 0.6309635617276785, "grad_norm": 0.138671875, "learning_rate": 1.8146271991352074e-05, "loss": 1.5505672693252563, "step": 7474 }, { "epoch": 0.6310479828625096, "grad_norm": 0.140625, "learning_rate": 1.8140011905859307e-05, "loss": 1.51985502243042, "step": 7475 }, { "epoch": 0.6311324039973407, "grad_norm": 0.138671875, "learning_rate": 1.81337522854902e-05, "loss": 1.5938520431518555, "step": 7476 }, { "epoch": 0.6312168251321718, "grad_norm": 0.1416015625, "learning_rate": 1.8127493130669204e-05, "loss": 1.5178205966949463, "step": 7477 }, { "epoch": 0.6313012462670029, "grad_norm": 0.138671875, "learning_rate": 1.812123444182069e-05, "loss": 1.5509045124053955, "step": 7478 }, { "epoch": 0.631385667401834, "grad_norm": 0.1513671875, "learning_rate": 1.811497621936901e-05, "loss": 1.532671332359314, "step": 7479 }, { "epoch": 0.6314700885366652, "grad_norm": 0.1396484375, "learning_rate": 1.810871846373851e-05, "loss": 1.5879372358322144, "step": 7480 }, { "epoch": 0.6315545096714963, "grad_norm": 0.1376953125, "learning_rate": 1.8102461175353443e-05, "loss": 1.5214016437530518, "step": 7481 }, { "epoch": 0.6316389308063274, "grad_norm": 0.1435546875, "learning_rate": 1.80962043546381e-05, "loss": 1.591956377029419, "step": 7482 }, { "epoch": 0.6317233519411585, "grad_norm": 0.142578125, "learning_rate": 1.808994800201669e-05, "loss": 1.5182082653045654, "step": 7483 }, { "epoch": 0.6318077730759896, "grad_norm": 0.140625, "learning_rate": 1.8083692117913413e-05, "loss": 1.5521849393844604, "step": 7484 }, { "epoch": 0.6318921942108207, "grad_norm": 0.1396484375, "learning_rate": 1.8077436702752448e-05, "loss": 1.5048444271087646, "step": 7485 }, { "epoch": 0.6319766153456517, "grad_norm": 0.1376953125, "learning_rate": 1.8071181756957897e-05, "loss": 1.5918141603469849, "step": 7486 }, { "epoch": 0.6320610364804828, "grad_norm": 0.138671875, "learning_rate": 1.806492728095389e-05, "loss": 1.5378998517990112, "step": 7487 }, { "epoch": 0.632145457615314, "grad_norm": 0.1533203125, "learning_rate": 1.8058673275164477e-05, "loss": 1.4556461572647095, "step": 7488 }, { "epoch": 0.6322298787501451, "grad_norm": 0.1435546875, "learning_rate": 1.80524197400137e-05, "loss": 1.4878311157226562, "step": 7489 }, { "epoch": 0.6323142998849762, "grad_norm": 0.1318359375, "learning_rate": 1.8046166675925574e-05, "loss": 1.4587976932525635, "step": 7490 }, { "epoch": 0.6323987210198073, "grad_norm": 0.1396484375, "learning_rate": 1.803991408332405e-05, "loss": 1.5242726802825928, "step": 7491 }, { "epoch": 0.6324831421546384, "grad_norm": 0.1337890625, "learning_rate": 1.803366196263308e-05, "loss": 1.4466900825500488, "step": 7492 }, { "epoch": 0.6325675632894695, "grad_norm": 0.134765625, "learning_rate": 1.8027410314276586e-05, "loss": 1.5210903882980347, "step": 7493 }, { "epoch": 0.6326519844243006, "grad_norm": 0.134765625, "learning_rate": 1.8021159138678427e-05, "loss": 1.4922664165496826, "step": 7494 }, { "epoch": 0.6327364055591317, "grad_norm": 0.140625, "learning_rate": 1.8014908436262457e-05, "loss": 1.5427056550979614, "step": 7495 }, { "epoch": 0.6328208266939628, "grad_norm": 0.1396484375, "learning_rate": 1.800865820745247e-05, "loss": 1.5456165075302124, "step": 7496 }, { "epoch": 0.632905247828794, "grad_norm": 0.15625, "learning_rate": 1.8002408452672273e-05, "loss": 1.5921392440795898, "step": 7497 }, { "epoch": 0.6329896689636251, "grad_norm": 0.1376953125, "learning_rate": 1.7996159172345604e-05, "loss": 1.5124781131744385, "step": 7498 }, { "epoch": 0.6330740900984562, "grad_norm": 0.138671875, "learning_rate": 1.798991036689618e-05, "loss": 1.5470536947250366, "step": 7499 }, { "epoch": 0.6331585112332873, "grad_norm": 0.142578125, "learning_rate": 1.7983662036747682e-05, "loss": 1.5488418340682983, "step": 7500 }, { "epoch": 0.6332429323681183, "grad_norm": 0.1357421875, "learning_rate": 1.7977414182323754e-05, "loss": 1.5166771411895752, "step": 7501 }, { "epoch": 0.6333273535029494, "grad_norm": 0.1279296875, "learning_rate": 1.797116680404803e-05, "loss": 1.4847463369369507, "step": 7502 }, { "epoch": 0.6334117746377805, "grad_norm": 0.1328125, "learning_rate": 1.7964919902344097e-05, "loss": 1.4954131841659546, "step": 7503 }, { "epoch": 0.6334961957726116, "grad_norm": 0.142578125, "learning_rate": 1.79586734776355e-05, "loss": 1.5547523498535156, "step": 7504 }, { "epoch": 0.6335806169074428, "grad_norm": 0.138671875, "learning_rate": 1.7952427530345758e-05, "loss": 1.4964793920516968, "step": 7505 }, { "epoch": 0.6336650380422739, "grad_norm": 0.138671875, "learning_rate": 1.794618206089838e-05, "loss": 1.5484527349472046, "step": 7506 }, { "epoch": 0.633749459177105, "grad_norm": 0.140625, "learning_rate": 1.793993706971681e-05, "loss": 1.5809117555618286, "step": 7507 }, { "epoch": 0.6338338803119361, "grad_norm": 0.1494140625, "learning_rate": 1.7933692557224486e-05, "loss": 1.5276602506637573, "step": 7508 }, { "epoch": 0.6339183014467672, "grad_norm": 0.1435546875, "learning_rate": 1.7927448523844784e-05, "loss": 1.463384985923767, "step": 7509 }, { "epoch": 0.6340027225815983, "grad_norm": 0.1396484375, "learning_rate": 1.7921204970001065e-05, "loss": 1.5843266248703003, "step": 7510 }, { "epoch": 0.6340871437164294, "grad_norm": 0.1484375, "learning_rate": 1.7914961896116677e-05, "loss": 1.5399256944656372, "step": 7511 }, { "epoch": 0.6341715648512605, "grad_norm": 0.15234375, "learning_rate": 1.7908719302614896e-05, "loss": 1.5352543592453003, "step": 7512 }, { "epoch": 0.6342559859860916, "grad_norm": 0.1416015625, "learning_rate": 1.7902477189918997e-05, "loss": 1.4956982135772705, "step": 7513 }, { "epoch": 0.6343404071209228, "grad_norm": 0.1533203125, "learning_rate": 1.78962355584522e-05, "loss": 1.542783498764038, "step": 7514 }, { "epoch": 0.6344248282557539, "grad_norm": 0.1474609375, "learning_rate": 1.78899944086377e-05, "loss": 1.5655980110168457, "step": 7515 }, { "epoch": 0.634509249390585, "grad_norm": 0.1484375, "learning_rate": 1.7883753740898687e-05, "loss": 1.4977097511291504, "step": 7516 }, { "epoch": 0.634593670525416, "grad_norm": 0.130859375, "learning_rate": 1.787751355565826e-05, "loss": 1.5092418193817139, "step": 7517 }, { "epoch": 0.6346780916602471, "grad_norm": 0.16015625, "learning_rate": 1.7871273853339544e-05, "loss": 1.521079421043396, "step": 7518 }, { "epoch": 0.6347625127950782, "grad_norm": 0.140625, "learning_rate": 1.7865034634365592e-05, "loss": 1.5415233373641968, "step": 7519 }, { "epoch": 0.6348469339299093, "grad_norm": 0.1337890625, "learning_rate": 1.7858795899159435e-05, "loss": 1.4917281866073608, "step": 7520 }, { "epoch": 0.6349313550647404, "grad_norm": 0.13671875, "learning_rate": 1.7852557648144097e-05, "loss": 1.5090795755386353, "step": 7521 }, { "epoch": 0.6350157761995716, "grad_norm": 0.1396484375, "learning_rate": 1.7846319881742515e-05, "loss": 1.516488790512085, "step": 7522 }, { "epoch": 0.6351001973344027, "grad_norm": 0.142578125, "learning_rate": 1.7840082600377644e-05, "loss": 1.5341484546661377, "step": 7523 }, { "epoch": 0.6351846184692338, "grad_norm": 0.1357421875, "learning_rate": 1.7833845804472393e-05, "loss": 1.515733003616333, "step": 7524 }, { "epoch": 0.6352690396040649, "grad_norm": 0.1455078125, "learning_rate": 1.7827609494449608e-05, "loss": 1.5785391330718994, "step": 7525 }, { "epoch": 0.635353460738896, "grad_norm": 0.1328125, "learning_rate": 1.7821373670732155e-05, "loss": 1.5368200540542603, "step": 7526 }, { "epoch": 0.6354378818737271, "grad_norm": 0.1669921875, "learning_rate": 1.7815138333742805e-05, "loss": 1.5832968950271606, "step": 7527 }, { "epoch": 0.6355223030085582, "grad_norm": 0.13671875, "learning_rate": 1.7808903483904356e-05, "loss": 1.5825345516204834, "step": 7528 }, { "epoch": 0.6356067241433893, "grad_norm": 0.14453125, "learning_rate": 1.780266912163954e-05, "loss": 1.693873405456543, "step": 7529 }, { "epoch": 0.6356911452782203, "grad_norm": 0.15625, "learning_rate": 1.7796435247371046e-05, "loss": 1.494832158088684, "step": 7530 }, { "epoch": 0.6357755664130516, "grad_norm": 0.1416015625, "learning_rate": 1.779020186152157e-05, "loss": 1.51356840133667, "step": 7531 }, { "epoch": 0.6358599875478826, "grad_norm": 0.138671875, "learning_rate": 1.7783968964513724e-05, "loss": 1.5722410678863525, "step": 7532 }, { "epoch": 0.6359444086827137, "grad_norm": 0.1416015625, "learning_rate": 1.777773655677013e-05, "loss": 1.4227594137191772, "step": 7533 }, { "epoch": 0.6360288298175448, "grad_norm": 0.134765625, "learning_rate": 1.7771504638713368e-05, "loss": 1.48506498336792, "step": 7534 }, { "epoch": 0.6361132509523759, "grad_norm": 0.1396484375, "learning_rate": 1.776527321076596e-05, "loss": 1.5137771368026733, "step": 7535 }, { "epoch": 0.636197672087207, "grad_norm": 0.1416015625, "learning_rate": 1.7759042273350423e-05, "loss": 1.532317042350769, "step": 7536 }, { "epoch": 0.6362820932220381, "grad_norm": 0.14453125, "learning_rate": 1.7752811826889214e-05, "loss": 1.6008591651916504, "step": 7537 }, { "epoch": 0.6363665143568692, "grad_norm": 0.1376953125, "learning_rate": 1.7746581871804783e-05, "loss": 1.5672746896743774, "step": 7538 }, { "epoch": 0.6364509354917004, "grad_norm": 0.1484375, "learning_rate": 1.774035240851955e-05, "loss": 1.5286458730697632, "step": 7539 }, { "epoch": 0.6365353566265315, "grad_norm": 0.1357421875, "learning_rate": 1.7734123437455864e-05, "loss": 1.5134824514389038, "step": 7540 }, { "epoch": 0.6366197777613626, "grad_norm": 0.134765625, "learning_rate": 1.772789495903607e-05, "loss": 1.560030221939087, "step": 7541 }, { "epoch": 0.6367041988961937, "grad_norm": 0.1376953125, "learning_rate": 1.772166697368249e-05, "loss": 1.6555817127227783, "step": 7542 }, { "epoch": 0.6367886200310248, "grad_norm": 0.134765625, "learning_rate": 1.7715439481817375e-05, "loss": 1.5291446447372437, "step": 7543 }, { "epoch": 0.6368730411658559, "grad_norm": 0.134765625, "learning_rate": 1.770921248386298e-05, "loss": 1.4735556840896606, "step": 7544 }, { "epoch": 0.636957462300687, "grad_norm": 0.1337890625, "learning_rate": 1.7702985980241498e-05, "loss": 1.4534995555877686, "step": 7545 }, { "epoch": 0.637041883435518, "grad_norm": 0.13671875, "learning_rate": 1.7696759971375098e-05, "loss": 1.5330686569213867, "step": 7546 }, { "epoch": 0.6371263045703491, "grad_norm": 0.1396484375, "learning_rate": 1.769053445768594e-05, "loss": 1.5513486862182617, "step": 7547 }, { "epoch": 0.6372107257051803, "grad_norm": 0.1494140625, "learning_rate": 1.768430943959611e-05, "loss": 1.6024712324142456, "step": 7548 }, { "epoch": 0.6372951468400114, "grad_norm": 0.1416015625, "learning_rate": 1.7678084917527693e-05, "loss": 1.476156234741211, "step": 7549 }, { "epoch": 0.6373795679748425, "grad_norm": 0.1552734375, "learning_rate": 1.7671860891902708e-05, "loss": 1.4879894256591797, "step": 7550 }, { "epoch": 0.6374639891096736, "grad_norm": 0.150390625, "learning_rate": 1.7665637363143167e-05, "loss": 1.515289545059204, "step": 7551 }, { "epoch": 0.6375484102445047, "grad_norm": 0.14453125, "learning_rate": 1.765941433167105e-05, "loss": 1.5683848857879639, "step": 7552 }, { "epoch": 0.6376328313793358, "grad_norm": 0.1455078125, "learning_rate": 1.765319179790828e-05, "loss": 1.5038971900939941, "step": 7553 }, { "epoch": 0.6377172525141669, "grad_norm": 0.142578125, "learning_rate": 1.7646969762276775e-05, "loss": 1.4452931880950928, "step": 7554 }, { "epoch": 0.637801673648998, "grad_norm": 0.1318359375, "learning_rate": 1.7640748225198386e-05, "loss": 1.4850656986236572, "step": 7555 }, { "epoch": 0.6378860947838292, "grad_norm": 0.1357421875, "learning_rate": 1.763452718709495e-05, "loss": 1.4513152837753296, "step": 7556 }, { "epoch": 0.6379705159186603, "grad_norm": 0.150390625, "learning_rate": 1.7628306648388293e-05, "loss": 1.5741357803344727, "step": 7557 }, { "epoch": 0.6380549370534914, "grad_norm": 0.15234375, "learning_rate": 1.762208660950015e-05, "loss": 1.5639221668243408, "step": 7558 }, { "epoch": 0.6381393581883225, "grad_norm": 0.1416015625, "learning_rate": 1.7615867070852275e-05, "loss": 1.5401111841201782, "step": 7559 }, { "epoch": 0.6382237793231536, "grad_norm": 0.146484375, "learning_rate": 1.7609648032866362e-05, "loss": 1.5527781248092651, "step": 7560 }, { "epoch": 0.6383082004579846, "grad_norm": 0.134765625, "learning_rate": 1.760342949596407e-05, "loss": 1.4959867000579834, "step": 7561 }, { "epoch": 0.6383926215928157, "grad_norm": 0.130859375, "learning_rate": 1.7597211460567055e-05, "loss": 1.4947280883789062, "step": 7562 }, { "epoch": 0.6384770427276468, "grad_norm": 0.1376953125, "learning_rate": 1.7590993927096875e-05, "loss": 1.6051344871520996, "step": 7563 }, { "epoch": 0.6385614638624779, "grad_norm": 0.1533203125, "learning_rate": 1.7584776895975123e-05, "loss": 1.580979824066162, "step": 7564 }, { "epoch": 0.6386458849973091, "grad_norm": 0.140625, "learning_rate": 1.7578560367623326e-05, "loss": 1.475895643234253, "step": 7565 }, { "epoch": 0.6387303061321402, "grad_norm": 0.1474609375, "learning_rate": 1.757234434246297e-05, "loss": 1.619795322418213, "step": 7566 }, { "epoch": 0.6388147272669713, "grad_norm": 0.1396484375, "learning_rate": 1.7566128820915528e-05, "loss": 1.5771710872650146, "step": 7567 }, { "epoch": 0.6388991484018024, "grad_norm": 0.130859375, "learning_rate": 1.7559913803402412e-05, "loss": 1.4868606328964233, "step": 7568 }, { "epoch": 0.6389835695366335, "grad_norm": 0.142578125, "learning_rate": 1.7553699290345027e-05, "loss": 1.514605164527893, "step": 7569 }, { "epoch": 0.6390679906714646, "grad_norm": 0.1376953125, "learning_rate": 1.7547485282164733e-05, "loss": 1.525918960571289, "step": 7570 }, { "epoch": 0.6391524118062957, "grad_norm": 0.146484375, "learning_rate": 1.7541271779282846e-05, "loss": 1.496293306350708, "step": 7571 }, { "epoch": 0.6392368329411268, "grad_norm": 0.146484375, "learning_rate": 1.7535058782120655e-05, "loss": 1.5788452625274658, "step": 7572 }, { "epoch": 0.639321254075958, "grad_norm": 0.1484375, "learning_rate": 1.7528846291099433e-05, "loss": 1.5179725885391235, "step": 7573 }, { "epoch": 0.6394056752107891, "grad_norm": 0.1396484375, "learning_rate": 1.7522634306640384e-05, "loss": 1.536376953125, "step": 7574 }, { "epoch": 0.6394900963456202, "grad_norm": 0.1357421875, "learning_rate": 1.7516422829164707e-05, "loss": 1.5146238803863525, "step": 7575 }, { "epoch": 0.6395745174804512, "grad_norm": 0.1318359375, "learning_rate": 1.7510211859093552e-05, "loss": 1.491187334060669, "step": 7576 }, { "epoch": 0.6396589386152823, "grad_norm": 0.1474609375, "learning_rate": 1.750400139684802e-05, "loss": 1.5926740169525146, "step": 7577 }, { "epoch": 0.6397433597501134, "grad_norm": 0.1357421875, "learning_rate": 1.749779144284923e-05, "loss": 1.614290714263916, "step": 7578 }, { "epoch": 0.6398277808849445, "grad_norm": 0.15625, "learning_rate": 1.74915819975182e-05, "loss": 1.6143399477005005, "step": 7579 }, { "epoch": 0.6399122020197756, "grad_norm": 0.134765625, "learning_rate": 1.7485373061275973e-05, "loss": 1.4285659790039062, "step": 7580 }, { "epoch": 0.6399966231546067, "grad_norm": 0.142578125, "learning_rate": 1.7479164634543506e-05, "loss": 1.5588871240615845, "step": 7581 }, { "epoch": 0.6400810442894379, "grad_norm": 0.14453125, "learning_rate": 1.747295671774175e-05, "loss": 1.551590919494629, "step": 7582 }, { "epoch": 0.640165465424269, "grad_norm": 0.130859375, "learning_rate": 1.746674931129163e-05, "loss": 1.4917254447937012, "step": 7583 }, { "epoch": 0.6402498865591001, "grad_norm": 0.1328125, "learning_rate": 1.746054241561401e-05, "loss": 1.5436426401138306, "step": 7584 }, { "epoch": 0.6403343076939312, "grad_norm": 0.1318359375, "learning_rate": 1.7454336031129743e-05, "loss": 1.4797720909118652, "step": 7585 }, { "epoch": 0.6404187288287623, "grad_norm": 0.1416015625, "learning_rate": 1.7448130158259624e-05, "loss": 1.5144329071044922, "step": 7586 }, { "epoch": 0.6405031499635934, "grad_norm": 0.1376953125, "learning_rate": 1.7441924797424425e-05, "loss": 1.464094638824463, "step": 7587 }, { "epoch": 0.6405875710984245, "grad_norm": 0.130859375, "learning_rate": 1.7435719949044905e-05, "loss": 1.4393285512924194, "step": 7588 }, { "epoch": 0.6406719922332555, "grad_norm": 0.138671875, "learning_rate": 1.7429515613541747e-05, "loss": 1.5253403186798096, "step": 7589 }, { "epoch": 0.6407564133680868, "grad_norm": 0.1396484375, "learning_rate": 1.742331179133563e-05, "loss": 1.4975016117095947, "step": 7590 }, { "epoch": 0.6408408345029178, "grad_norm": 0.1376953125, "learning_rate": 1.7417108482847193e-05, "loss": 1.4831287860870361, "step": 7591 }, { "epoch": 0.6409252556377489, "grad_norm": 0.1376953125, "learning_rate": 1.7410905688497016e-05, "loss": 1.5600656270980835, "step": 7592 }, { "epoch": 0.64100967677258, "grad_norm": 0.1494140625, "learning_rate": 1.7404703408705687e-05, "loss": 1.5712292194366455, "step": 7593 }, { "epoch": 0.6410940979074111, "grad_norm": 0.1396484375, "learning_rate": 1.739850164389371e-05, "loss": 1.5010207891464233, "step": 7594 }, { "epoch": 0.6411785190422422, "grad_norm": 0.142578125, "learning_rate": 1.7392300394481597e-05, "loss": 1.552164077758789, "step": 7595 }, { "epoch": 0.6412629401770733, "grad_norm": 0.1357421875, "learning_rate": 1.738609966088981e-05, "loss": 1.4923338890075684, "step": 7596 }, { "epoch": 0.6413473613119044, "grad_norm": 0.146484375, "learning_rate": 1.7379899443538757e-05, "loss": 1.4968562126159668, "step": 7597 }, { "epoch": 0.6414317824467355, "grad_norm": 0.1484375, "learning_rate": 1.7373699742848857e-05, "loss": 1.529522180557251, "step": 7598 }, { "epoch": 0.6415162035815667, "grad_norm": 0.138671875, "learning_rate": 1.7367500559240425e-05, "loss": 1.4499906301498413, "step": 7599 }, { "epoch": 0.6416006247163978, "grad_norm": 0.134765625, "learning_rate": 1.736130189313381e-05, "loss": 1.4666545391082764, "step": 7600 }, { "epoch": 0.6416850458512289, "grad_norm": 0.134765625, "learning_rate": 1.7355103744949293e-05, "loss": 1.5199317932128906, "step": 7601 }, { "epoch": 0.64176946698606, "grad_norm": 0.142578125, "learning_rate": 1.7348906115107104e-05, "loss": 1.4867334365844727, "step": 7602 }, { "epoch": 0.6418538881208911, "grad_norm": 0.1396484375, "learning_rate": 1.734270900402749e-05, "loss": 1.5546458959579468, "step": 7603 }, { "epoch": 0.6419383092557222, "grad_norm": 0.14453125, "learning_rate": 1.7336512412130594e-05, "loss": 1.5185476541519165, "step": 7604 }, { "epoch": 0.6420227303905532, "grad_norm": 0.14453125, "learning_rate": 1.7330316339836584e-05, "loss": 1.508313536643982, "step": 7605 }, { "epoch": 0.6421071515253843, "grad_norm": 0.13671875, "learning_rate": 1.7324120787565563e-05, "loss": 1.5074951648712158, "step": 7606 }, { "epoch": 0.6421915726602155, "grad_norm": 0.138671875, "learning_rate": 1.7317925755737602e-05, "loss": 1.5352317094802856, "step": 7607 }, { "epoch": 0.6422759937950466, "grad_norm": 0.150390625, "learning_rate": 1.7311731244772732e-05, "loss": 1.5827112197875977, "step": 7608 }, { "epoch": 0.6423604149298777, "grad_norm": 0.146484375, "learning_rate": 1.7305537255090975e-05, "loss": 1.5679535865783691, "step": 7609 }, { "epoch": 0.6424448360647088, "grad_norm": 0.1357421875, "learning_rate": 1.729934378711228e-05, "loss": 1.4593449831008911, "step": 7610 }, { "epoch": 0.6425292571995399, "grad_norm": 0.1376953125, "learning_rate": 1.7293150841256595e-05, "loss": 1.491536259651184, "step": 7611 }, { "epoch": 0.642613678334371, "grad_norm": 0.1357421875, "learning_rate": 1.72869584179438e-05, "loss": 1.5201530456542969, "step": 7612 }, { "epoch": 0.6426980994692021, "grad_norm": 0.138671875, "learning_rate": 1.728076651759376e-05, "loss": 1.6024531126022339, "step": 7613 }, { "epoch": 0.6427825206040332, "grad_norm": 0.13671875, "learning_rate": 1.7274575140626318e-05, "loss": 1.516210913658142, "step": 7614 }, { "epoch": 0.6428669417388643, "grad_norm": 0.1435546875, "learning_rate": 1.7268384287461242e-05, "loss": 1.6136853694915771, "step": 7615 }, { "epoch": 0.6429513628736955, "grad_norm": 0.1416015625, "learning_rate": 1.7262193958518302e-05, "loss": 1.500690221786499, "step": 7616 }, { "epoch": 0.6430357840085266, "grad_norm": 0.13671875, "learning_rate": 1.7256004154217205e-05, "loss": 1.505547285079956, "step": 7617 }, { "epoch": 0.6431202051433577, "grad_norm": 0.1396484375, "learning_rate": 1.7249814874977635e-05, "loss": 1.5931717157363892, "step": 7618 }, { "epoch": 0.6432046262781888, "grad_norm": 0.130859375, "learning_rate": 1.7243626121219258e-05, "loss": 1.4852912425994873, "step": 7619 }, { "epoch": 0.6432890474130198, "grad_norm": 0.1328125, "learning_rate": 1.7237437893361665e-05, "loss": 1.5572834014892578, "step": 7620 }, { "epoch": 0.6433734685478509, "grad_norm": 0.1328125, "learning_rate": 1.723125019182445e-05, "loss": 1.5020661354064941, "step": 7621 }, { "epoch": 0.643457889682682, "grad_norm": 0.150390625, "learning_rate": 1.722506301702714e-05, "loss": 1.6057370901107788, "step": 7622 }, { "epoch": 0.6435423108175131, "grad_norm": 0.1328125, "learning_rate": 1.721887636938924e-05, "loss": 1.513455867767334, "step": 7623 }, { "epoch": 0.6436267319523443, "grad_norm": 0.134765625, "learning_rate": 1.7212690249330234e-05, "loss": 1.505097508430481, "step": 7624 }, { "epoch": 0.6437111530871754, "grad_norm": 0.1337890625, "learning_rate": 1.7206504657269547e-05, "loss": 1.466349482536316, "step": 7625 }, { "epoch": 0.6437955742220065, "grad_norm": 0.1474609375, "learning_rate": 1.7200319593626575e-05, "loss": 1.5571985244750977, "step": 7626 }, { "epoch": 0.6438799953568376, "grad_norm": 0.158203125, "learning_rate": 1.7194135058820686e-05, "loss": 1.5406657457351685, "step": 7627 }, { "epoch": 0.6439644164916687, "grad_norm": 0.1318359375, "learning_rate": 1.718795105327119e-05, "loss": 1.55411696434021, "step": 7628 }, { "epoch": 0.6440488376264998, "grad_norm": 0.1376953125, "learning_rate": 1.7181767577397405e-05, "loss": 1.5381582975387573, "step": 7629 }, { "epoch": 0.6441332587613309, "grad_norm": 0.138671875, "learning_rate": 1.717558463161857e-05, "loss": 1.5081439018249512, "step": 7630 }, { "epoch": 0.644217679896162, "grad_norm": 0.1376953125, "learning_rate": 1.7169402216353896e-05, "loss": 1.4746947288513184, "step": 7631 }, { "epoch": 0.6443021010309931, "grad_norm": 0.134765625, "learning_rate": 1.7163220332022583e-05, "loss": 1.5286868810653687, "step": 7632 }, { "epoch": 0.6443865221658243, "grad_norm": 0.138671875, "learning_rate": 1.7157038979043756e-05, "loss": 1.537412405014038, "step": 7633 }, { "epoch": 0.6444709433006554, "grad_norm": 0.1435546875, "learning_rate": 1.7150858157836557e-05, "loss": 1.4958761930465698, "step": 7634 }, { "epoch": 0.6445553644354864, "grad_norm": 0.1396484375, "learning_rate": 1.7144677868820026e-05, "loss": 1.4568411111831665, "step": 7635 }, { "epoch": 0.6446397855703175, "grad_norm": 0.1357421875, "learning_rate": 1.7138498112413222e-05, "loss": 1.5386250019073486, "step": 7636 }, { "epoch": 0.6447242067051486, "grad_norm": 0.1552734375, "learning_rate": 1.7132318889035144e-05, "loss": 1.5535132884979248, "step": 7637 }, { "epoch": 0.6448086278399797, "grad_norm": 0.1435546875, "learning_rate": 1.7126140199104752e-05, "loss": 1.5183576345443726, "step": 7638 }, { "epoch": 0.6448930489748108, "grad_norm": 0.1455078125, "learning_rate": 1.711996204304099e-05, "loss": 1.5510060787200928, "step": 7639 }, { "epoch": 0.6449774701096419, "grad_norm": 0.138671875, "learning_rate": 1.7113784421262734e-05, "loss": 1.4753451347351074, "step": 7640 }, { "epoch": 0.6450618912444731, "grad_norm": 0.134765625, "learning_rate": 1.7107607334188848e-05, "loss": 1.4642248153686523, "step": 7641 }, { "epoch": 0.6451463123793042, "grad_norm": 0.1376953125, "learning_rate": 1.7101430782238163e-05, "loss": 1.5765529870986938, "step": 7642 }, { "epoch": 0.6452307335141353, "grad_norm": 0.13671875, "learning_rate": 1.709525476582945e-05, "loss": 1.5234670639038086, "step": 7643 }, { "epoch": 0.6453151546489664, "grad_norm": 0.1298828125, "learning_rate": 1.708907928538147e-05, "loss": 1.5174230337142944, "step": 7644 }, { "epoch": 0.6453995757837975, "grad_norm": 0.1494140625, "learning_rate": 1.7082904341312932e-05, "loss": 1.4383591413497925, "step": 7645 }, { "epoch": 0.6454839969186286, "grad_norm": 0.1455078125, "learning_rate": 1.7076729934042504e-05, "loss": 1.459551453590393, "step": 7646 }, { "epoch": 0.6455684180534597, "grad_norm": 0.1328125, "learning_rate": 1.7070556063988838e-05, "loss": 1.4591528177261353, "step": 7647 }, { "epoch": 0.6456528391882908, "grad_norm": 0.13671875, "learning_rate": 1.7064382731570528e-05, "loss": 1.4904751777648926, "step": 7648 }, { "epoch": 0.6457372603231218, "grad_norm": 0.1357421875, "learning_rate": 1.7058209937206133e-05, "loss": 1.539045810699463, "step": 7649 }, { "epoch": 0.645821681457953, "grad_norm": 0.1435546875, "learning_rate": 1.705203768131421e-05, "loss": 1.5515040159225464, "step": 7650 }, { "epoch": 0.6459061025927841, "grad_norm": 0.13671875, "learning_rate": 1.7045865964313224e-05, "loss": 1.5833836793899536, "step": 7651 }, { "epoch": 0.6459905237276152, "grad_norm": 0.1357421875, "learning_rate": 1.703969478662166e-05, "loss": 1.4862741231918335, "step": 7652 }, { "epoch": 0.6460749448624463, "grad_norm": 0.1396484375, "learning_rate": 1.703352414865791e-05, "loss": 1.4796485900878906, "step": 7653 }, { "epoch": 0.6461593659972774, "grad_norm": 0.1396484375, "learning_rate": 1.7027354050840367e-05, "loss": 1.497806191444397, "step": 7654 }, { "epoch": 0.6462437871321085, "grad_norm": 0.138671875, "learning_rate": 1.7021184493587395e-05, "loss": 1.537733793258667, "step": 7655 }, { "epoch": 0.6463282082669396, "grad_norm": 0.13671875, "learning_rate": 1.701501547731729e-05, "loss": 1.5237150192260742, "step": 7656 }, { "epoch": 0.6464126294017707, "grad_norm": 0.1474609375, "learning_rate": 1.700884700244832e-05, "loss": 1.5033217668533325, "step": 7657 }, { "epoch": 0.6464970505366019, "grad_norm": 0.13671875, "learning_rate": 1.7002679069398753e-05, "loss": 1.5156813859939575, "step": 7658 }, { "epoch": 0.646581471671433, "grad_norm": 0.140625, "learning_rate": 1.6996511678586747e-05, "loss": 1.5076619386672974, "step": 7659 }, { "epoch": 0.6466658928062641, "grad_norm": 0.140625, "learning_rate": 1.6990344830430498e-05, "loss": 1.5486865043640137, "step": 7660 }, { "epoch": 0.6467503139410952, "grad_norm": 0.185546875, "learning_rate": 1.698417852534812e-05, "loss": 1.500553011894226, "step": 7661 }, { "epoch": 0.6468347350759263, "grad_norm": 0.1533203125, "learning_rate": 1.69780127637577e-05, "loss": 1.559467077255249, "step": 7662 }, { "epoch": 0.6469191562107574, "grad_norm": 0.1416015625, "learning_rate": 1.6971847546077307e-05, "loss": 1.519858717918396, "step": 7663 }, { "epoch": 0.6470035773455884, "grad_norm": 0.1484375, "learning_rate": 1.6965682872724937e-05, "loss": 1.5729773044586182, "step": 7664 }, { "epoch": 0.6470879984804195, "grad_norm": 0.13671875, "learning_rate": 1.6959518744118588e-05, "loss": 1.5712248086929321, "step": 7665 }, { "epoch": 0.6471724196152506, "grad_norm": 0.1328125, "learning_rate": 1.6953355160676193e-05, "loss": 1.4576570987701416, "step": 7666 }, { "epoch": 0.6472568407500818, "grad_norm": 0.1337890625, "learning_rate": 1.6947192122815655e-05, "loss": 1.467736005783081, "step": 7667 }, { "epoch": 0.6473412618849129, "grad_norm": 0.146484375, "learning_rate": 1.6941029630954858e-05, "loss": 1.6191192865371704, "step": 7668 }, { "epoch": 0.647425683019744, "grad_norm": 0.1328125, "learning_rate": 1.6934867685511607e-05, "loss": 1.5089924335479736, "step": 7669 }, { "epoch": 0.6475101041545751, "grad_norm": 0.1416015625, "learning_rate": 1.692870628690373e-05, "loss": 1.5409729480743408, "step": 7670 }, { "epoch": 0.6475945252894062, "grad_norm": 0.13671875, "learning_rate": 1.692254543554896e-05, "loss": 1.460979700088501, "step": 7671 }, { "epoch": 0.6476789464242373, "grad_norm": 0.1396484375, "learning_rate": 1.691638513186502e-05, "loss": 1.5773578882217407, "step": 7672 }, { "epoch": 0.6477633675590684, "grad_norm": 0.146484375, "learning_rate": 1.6910225376269607e-05, "loss": 1.5678688287734985, "step": 7673 }, { "epoch": 0.6478477886938995, "grad_norm": 0.1396484375, "learning_rate": 1.690406616918035e-05, "loss": 1.5637565851211548, "step": 7674 }, { "epoch": 0.6479322098287307, "grad_norm": 0.1435546875, "learning_rate": 1.689790751101487e-05, "loss": 1.5230193138122559, "step": 7675 }, { "epoch": 0.6480166309635618, "grad_norm": 0.14453125, "learning_rate": 1.6891749402190742e-05, "loss": 1.4450715780258179, "step": 7676 }, { "epoch": 0.6481010520983929, "grad_norm": 0.138671875, "learning_rate": 1.688559184312549e-05, "loss": 1.5633563995361328, "step": 7677 }, { "epoch": 0.648185473233224, "grad_norm": 0.154296875, "learning_rate": 1.687943483423662e-05, "loss": 1.5544452667236328, "step": 7678 }, { "epoch": 0.648269894368055, "grad_norm": 0.1318359375, "learning_rate": 1.6873278375941577e-05, "loss": 1.5063904523849487, "step": 7679 }, { "epoch": 0.6483543155028861, "grad_norm": 0.1484375, "learning_rate": 1.68671224686578e-05, "loss": 1.5375005006790161, "step": 7680 }, { "epoch": 0.6484387366377172, "grad_norm": 0.1357421875, "learning_rate": 1.6860967112802674e-05, "loss": 1.4870824813842773, "step": 7681 }, { "epoch": 0.6485231577725483, "grad_norm": 0.13671875, "learning_rate": 1.685481230879353e-05, "loss": 1.4681271314620972, "step": 7682 }, { "epoch": 0.6486075789073794, "grad_norm": 0.1328125, "learning_rate": 1.6848658057047705e-05, "loss": 1.492405652999878, "step": 7683 }, { "epoch": 0.6486920000422106, "grad_norm": 0.1552734375, "learning_rate": 1.6842504357982447e-05, "loss": 1.5618336200714111, "step": 7684 }, { "epoch": 0.6487764211770417, "grad_norm": 0.134765625, "learning_rate": 1.6836351212014996e-05, "loss": 1.5577329397201538, "step": 7685 }, { "epoch": 0.6488608423118728, "grad_norm": 0.1474609375, "learning_rate": 1.6830198619562566e-05, "loss": 1.5517189502716064, "step": 7686 }, { "epoch": 0.6489452634467039, "grad_norm": 0.12890625, "learning_rate": 1.68240465810423e-05, "loss": 1.5052052736282349, "step": 7687 }, { "epoch": 0.649029684581535, "grad_norm": 0.1337890625, "learning_rate": 1.681789509687134e-05, "loss": 1.5552597045898438, "step": 7688 }, { "epoch": 0.6491141057163661, "grad_norm": 0.1533203125, "learning_rate": 1.681174416746675e-05, "loss": 1.5800114870071411, "step": 7689 }, { "epoch": 0.6491985268511972, "grad_norm": 0.134765625, "learning_rate": 1.680559379324558e-05, "loss": 1.464720368385315, "step": 7690 }, { "epoch": 0.6492829479860283, "grad_norm": 0.1337890625, "learning_rate": 1.6799443974624862e-05, "loss": 1.4544154405593872, "step": 7691 }, { "epoch": 0.6493673691208595, "grad_norm": 0.15234375, "learning_rate": 1.6793294712021544e-05, "loss": 1.496217966079712, "step": 7692 }, { "epoch": 0.6494517902556906, "grad_norm": 0.13671875, "learning_rate": 1.678714600585257e-05, "loss": 1.50462806224823, "step": 7693 }, { "epoch": 0.6495362113905216, "grad_norm": 0.1416015625, "learning_rate": 1.6780997856534854e-05, "loss": 1.6065397262573242, "step": 7694 }, { "epoch": 0.6496206325253527, "grad_norm": 0.146484375, "learning_rate": 1.677485026448522e-05, "loss": 1.5619007349014282, "step": 7695 }, { "epoch": 0.6497050536601838, "grad_norm": 0.1455078125, "learning_rate": 1.676870323012052e-05, "loss": 1.5643908977508545, "step": 7696 }, { "epoch": 0.6497894747950149, "grad_norm": 0.13671875, "learning_rate": 1.6762556753857525e-05, "loss": 1.546271800994873, "step": 7697 }, { "epoch": 0.649873895929846, "grad_norm": 0.140625, "learning_rate": 1.675641083611298e-05, "loss": 1.5436049699783325, "step": 7698 }, { "epoch": 0.6499583170646771, "grad_norm": 0.138671875, "learning_rate": 1.67502654773036e-05, "loss": 1.5688865184783936, "step": 7699 }, { "epoch": 0.6500427381995082, "grad_norm": 0.1396484375, "learning_rate": 1.674412067784604e-05, "loss": 1.565739393234253, "step": 7700 }, { "epoch": 0.6501271593343394, "grad_norm": 0.154296875, "learning_rate": 1.6737976438156956e-05, "loss": 1.5427545309066772, "step": 7701 }, { "epoch": 0.6502115804691705, "grad_norm": 0.138671875, "learning_rate": 1.673183275865292e-05, "loss": 1.5358232259750366, "step": 7702 }, { "epoch": 0.6502960016040016, "grad_norm": 0.1591796875, "learning_rate": 1.67256896397505e-05, "loss": 1.514565110206604, "step": 7703 }, { "epoch": 0.6503804227388327, "grad_norm": 0.1376953125, "learning_rate": 1.671954708186621e-05, "loss": 1.5277154445648193, "step": 7704 }, { "epoch": 0.6504648438736638, "grad_norm": 0.134765625, "learning_rate": 1.6713405085416526e-05, "loss": 1.4726201295852661, "step": 7705 }, { "epoch": 0.6505492650084949, "grad_norm": 0.138671875, "learning_rate": 1.6707263650817905e-05, "loss": 1.5533125400543213, "step": 7706 }, { "epoch": 0.650633686143326, "grad_norm": 0.1376953125, "learning_rate": 1.6701122778486737e-05, "loss": 1.551015853881836, "step": 7707 }, { "epoch": 0.650718107278157, "grad_norm": 0.1318359375, "learning_rate": 1.669498246883939e-05, "loss": 1.5557113885879517, "step": 7708 }, { "epoch": 0.6508025284129882, "grad_norm": 0.1357421875, "learning_rate": 1.6688842722292204e-05, "loss": 1.4353132247924805, "step": 7709 }, { "epoch": 0.6508869495478193, "grad_norm": 0.1396484375, "learning_rate": 1.6682703539261442e-05, "loss": 1.5115422010421753, "step": 7710 }, { "epoch": 0.6509713706826504, "grad_norm": 0.142578125, "learning_rate": 1.6676564920163384e-05, "loss": 1.5414183139801025, "step": 7711 }, { "epoch": 0.6510557918174815, "grad_norm": 0.1435546875, "learning_rate": 1.6670426865414236e-05, "loss": 1.5056169033050537, "step": 7712 }, { "epoch": 0.6511402129523126, "grad_norm": 0.1494140625, "learning_rate": 1.6664289375430158e-05, "loss": 1.5329008102416992, "step": 7713 }, { "epoch": 0.6512246340871437, "grad_norm": 0.13671875, "learning_rate": 1.6658152450627303e-05, "loss": 1.5109457969665527, "step": 7714 }, { "epoch": 0.6513090552219748, "grad_norm": 0.1328125, "learning_rate": 1.6652016091421756e-05, "loss": 1.519421935081482, "step": 7715 }, { "epoch": 0.6513934763568059, "grad_norm": 0.13671875, "learning_rate": 1.664588029822959e-05, "loss": 1.545276165008545, "step": 7716 }, { "epoch": 0.651477897491637, "grad_norm": 0.134765625, "learning_rate": 1.663974507146682e-05, "loss": 1.4482420682907104, "step": 7717 }, { "epoch": 0.6515623186264682, "grad_norm": 0.134765625, "learning_rate": 1.6633610411549426e-05, "loss": 1.5354968309402466, "step": 7718 }, { "epoch": 0.6516467397612993, "grad_norm": 0.1474609375, "learning_rate": 1.6627476318893363e-05, "loss": 1.5670808553695679, "step": 7719 }, { "epoch": 0.6517311608961304, "grad_norm": 0.134765625, "learning_rate": 1.6621342793914523e-05, "loss": 1.547371506690979, "step": 7720 }, { "epoch": 0.6518155820309615, "grad_norm": 0.134765625, "learning_rate": 1.6615209837028784e-05, "loss": 1.5293951034545898, "step": 7721 }, { "epoch": 0.6519000031657926, "grad_norm": 0.1337890625, "learning_rate": 1.6609077448651977e-05, "loss": 1.5168856382369995, "step": 7722 }, { "epoch": 0.6519844243006236, "grad_norm": 0.140625, "learning_rate": 1.660294562919988e-05, "loss": 1.490988850593567, "step": 7723 }, { "epoch": 0.6520688454354547, "grad_norm": 0.1298828125, "learning_rate": 1.6596814379088252e-05, "loss": 1.5169919729232788, "step": 7724 }, { "epoch": 0.6521532665702858, "grad_norm": 0.1396484375, "learning_rate": 1.6590683698732823e-05, "loss": 1.5176043510437012, "step": 7725 }, { "epoch": 0.652237687705117, "grad_norm": 0.138671875, "learning_rate": 1.6584553588549234e-05, "loss": 1.595923900604248, "step": 7726 }, { "epoch": 0.6523221088399481, "grad_norm": 0.1396484375, "learning_rate": 1.6578424048953157e-05, "loss": 1.626219630241394, "step": 7727 }, { "epoch": 0.6524065299747792, "grad_norm": 0.1494140625, "learning_rate": 1.657229508036016e-05, "loss": 1.4910050630569458, "step": 7728 }, { "epoch": 0.6524909511096103, "grad_norm": 0.1494140625, "learning_rate": 1.656616668318581e-05, "loss": 1.4957407712936401, "step": 7729 }, { "epoch": 0.6525753722444414, "grad_norm": 0.1416015625, "learning_rate": 1.656003885784565e-05, "loss": 1.5553611516952515, "step": 7730 }, { "epoch": 0.6526597933792725, "grad_norm": 0.130859375, "learning_rate": 1.6553911604755125e-05, "loss": 1.4975420236587524, "step": 7731 }, { "epoch": 0.6527442145141036, "grad_norm": 0.1484375, "learning_rate": 1.6547784924329705e-05, "loss": 1.5790327787399292, "step": 7732 }, { "epoch": 0.6528286356489347, "grad_norm": 0.134765625, "learning_rate": 1.654165881698478e-05, "loss": 1.4748167991638184, "step": 7733 }, { "epoch": 0.6529130567837658, "grad_norm": 0.14453125, "learning_rate": 1.653553328313571e-05, "loss": 1.4884870052337646, "step": 7734 }, { "epoch": 0.652997477918597, "grad_norm": 0.138671875, "learning_rate": 1.652940832319785e-05, "loss": 1.504169225692749, "step": 7735 }, { "epoch": 0.6530818990534281, "grad_norm": 0.138671875, "learning_rate": 1.6523283937586443e-05, "loss": 1.4945262670516968, "step": 7736 }, { "epoch": 0.6531663201882592, "grad_norm": 0.1474609375, "learning_rate": 1.6517160126716775e-05, "loss": 1.5397670269012451, "step": 7737 }, { "epoch": 0.6532507413230902, "grad_norm": 0.1416015625, "learning_rate": 1.6511036891004037e-05, "loss": 1.508924126625061, "step": 7738 }, { "epoch": 0.6533351624579213, "grad_norm": 0.1396484375, "learning_rate": 1.65049142308634e-05, "loss": 1.4793896675109863, "step": 7739 }, { "epoch": 0.6534195835927524, "grad_norm": 0.14453125, "learning_rate": 1.6498792146710003e-05, "loss": 1.6194525957107544, "step": 7740 }, { "epoch": 0.6535040047275835, "grad_norm": 0.1376953125, "learning_rate": 1.6492670638958924e-05, "loss": 1.5338863134384155, "step": 7741 }, { "epoch": 0.6535884258624146, "grad_norm": 0.1484375, "learning_rate": 1.6486549708025228e-05, "loss": 1.556924819946289, "step": 7742 }, { "epoch": 0.6536728469972458, "grad_norm": 0.1376953125, "learning_rate": 1.6480429354323933e-05, "loss": 1.5548913478851318, "step": 7743 }, { "epoch": 0.6537572681320769, "grad_norm": 0.1552734375, "learning_rate": 1.647430957827e-05, "loss": 1.6041252613067627, "step": 7744 }, { "epoch": 0.653841689266908, "grad_norm": 0.140625, "learning_rate": 1.6468190380278374e-05, "loss": 1.5187835693359375, "step": 7745 }, { "epoch": 0.6539261104017391, "grad_norm": 0.130859375, "learning_rate": 1.6462071760763943e-05, "loss": 1.4637364149093628, "step": 7746 }, { "epoch": 0.6540105315365702, "grad_norm": 0.1611328125, "learning_rate": 1.645595372014157e-05, "loss": 1.562270164489746, "step": 7747 }, { "epoch": 0.6540949526714013, "grad_norm": 0.1396484375, "learning_rate": 1.6449836258826074e-05, "loss": 1.5598170757293701, "step": 7748 }, { "epoch": 0.6541793738062324, "grad_norm": 0.138671875, "learning_rate": 1.644371937723223e-05, "loss": 1.5853084325790405, "step": 7749 }, { "epoch": 0.6542637949410635, "grad_norm": 0.138671875, "learning_rate": 1.6437603075774783e-05, "loss": 1.5026775598526, "step": 7750 }, { "epoch": 0.6543482160758946, "grad_norm": 0.142578125, "learning_rate": 1.643148735486842e-05, "loss": 1.5306025743484497, "step": 7751 }, { "epoch": 0.6544326372107258, "grad_norm": 0.14453125, "learning_rate": 1.6425372214927814e-05, "loss": 1.5809863805770874, "step": 7752 }, { "epoch": 0.6545170583455568, "grad_norm": 0.134765625, "learning_rate": 1.641925765636759e-05, "loss": 1.548518180847168, "step": 7753 }, { "epoch": 0.6546014794803879, "grad_norm": 0.1435546875, "learning_rate": 1.6413143679602318e-05, "loss": 1.5481714010238647, "step": 7754 }, { "epoch": 0.654685900615219, "grad_norm": 0.1484375, "learning_rate": 1.6407030285046542e-05, "loss": 1.5009685754776, "step": 7755 }, { "epoch": 0.6547703217500501, "grad_norm": 0.142578125, "learning_rate": 1.6400917473114763e-05, "loss": 1.5600205659866333, "step": 7756 }, { "epoch": 0.6548547428848812, "grad_norm": 0.142578125, "learning_rate": 1.6394805244221457e-05, "loss": 1.5937480926513672, "step": 7757 }, { "epoch": 0.6549391640197123, "grad_norm": 0.13671875, "learning_rate": 1.6388693598781037e-05, "loss": 1.557663083076477, "step": 7758 }, { "epoch": 0.6550235851545434, "grad_norm": 0.1328125, "learning_rate": 1.638258253720789e-05, "loss": 1.498056411743164, "step": 7759 }, { "epoch": 0.6551080062893746, "grad_norm": 0.1396484375, "learning_rate": 1.6376472059916354e-05, "loss": 1.504156231880188, "step": 7760 }, { "epoch": 0.6551924274242057, "grad_norm": 0.1376953125, "learning_rate": 1.637036216732075e-05, "loss": 1.4727389812469482, "step": 7761 }, { "epoch": 0.6552768485590368, "grad_norm": 0.1328125, "learning_rate": 1.6364252859835332e-05, "loss": 1.440166711807251, "step": 7762 }, { "epoch": 0.6553612696938679, "grad_norm": 0.1396484375, "learning_rate": 1.6358144137874333e-05, "loss": 1.6219608783721924, "step": 7763 }, { "epoch": 0.655445690828699, "grad_norm": 0.1455078125, "learning_rate": 1.6352036001851923e-05, "loss": 1.5322487354278564, "step": 7764 }, { "epoch": 0.6555301119635301, "grad_norm": 0.13671875, "learning_rate": 1.6345928452182256e-05, "loss": 1.5524868965148926, "step": 7765 }, { "epoch": 0.6556145330983612, "grad_norm": 0.13671875, "learning_rate": 1.633982148927946e-05, "loss": 1.5943810939788818, "step": 7766 }, { "epoch": 0.6556989542331922, "grad_norm": 0.1455078125, "learning_rate": 1.6333715113557567e-05, "loss": 1.557685375213623, "step": 7767 }, { "epoch": 0.6557833753680233, "grad_norm": 0.1435546875, "learning_rate": 1.6327609325430628e-05, "loss": 1.554221272468567, "step": 7768 }, { "epoch": 0.6558677965028545, "grad_norm": 0.1435546875, "learning_rate": 1.632150412531262e-05, "loss": 1.568554162979126, "step": 7769 }, { "epoch": 0.6559522176376856, "grad_norm": 0.146484375, "learning_rate": 1.6315399513617486e-05, "loss": 1.6158641576766968, "step": 7770 }, { "epoch": 0.6560366387725167, "grad_norm": 0.134765625, "learning_rate": 1.630929549075916e-05, "loss": 1.5252045392990112, "step": 7771 }, { "epoch": 0.6561210599073478, "grad_norm": 0.142578125, "learning_rate": 1.6303192057151466e-05, "loss": 1.4244154691696167, "step": 7772 }, { "epoch": 0.6562054810421789, "grad_norm": 0.1484375, "learning_rate": 1.629708921320827e-05, "loss": 1.4901589155197144, "step": 7773 }, { "epoch": 0.65628990217701, "grad_norm": 0.13671875, "learning_rate": 1.6290986959343338e-05, "loss": 1.5230193138122559, "step": 7774 }, { "epoch": 0.6563743233118411, "grad_norm": 0.1474609375, "learning_rate": 1.6284885295970425e-05, "loss": 1.5078210830688477, "step": 7775 }, { "epoch": 0.6564587444466722, "grad_norm": 0.2060546875, "learning_rate": 1.627878422350324e-05, "loss": 1.5548028945922852, "step": 7776 }, { "epoch": 0.6565431655815033, "grad_norm": 0.1513671875, "learning_rate": 1.6272683742355438e-05, "loss": 1.5417232513427734, "step": 7777 }, { "epoch": 0.6566275867163345, "grad_norm": 0.1396484375, "learning_rate": 1.6266583852940665e-05, "loss": 1.5106476545333862, "step": 7778 }, { "epoch": 0.6567120078511656, "grad_norm": 0.1396484375, "learning_rate": 1.62604845556725e-05, "loss": 1.4628748893737793, "step": 7779 }, { "epoch": 0.6567964289859967, "grad_norm": 0.1416015625, "learning_rate": 1.625438585096449e-05, "loss": 1.5262691974639893, "step": 7780 }, { "epoch": 0.6568808501208278, "grad_norm": 0.15234375, "learning_rate": 1.624828773923014e-05, "loss": 1.5971744060516357, "step": 7781 }, { "epoch": 0.6569652712556588, "grad_norm": 0.1396484375, "learning_rate": 1.6242190220882907e-05, "loss": 1.6040302515029907, "step": 7782 }, { "epoch": 0.6570496923904899, "grad_norm": 0.1455078125, "learning_rate": 1.6236093296336234e-05, "loss": 1.4604661464691162, "step": 7783 }, { "epoch": 0.657134113525321, "grad_norm": 0.13671875, "learning_rate": 1.6229996966003507e-05, "loss": 1.5417215824127197, "step": 7784 }, { "epoch": 0.6572185346601521, "grad_norm": 0.162109375, "learning_rate": 1.6223901230298062e-05, "loss": 1.4853423833847046, "step": 7785 }, { "epoch": 0.6573029557949833, "grad_norm": 0.138671875, "learning_rate": 1.6217806089633215e-05, "loss": 1.5595210790634155, "step": 7786 }, { "epoch": 0.6573873769298144, "grad_norm": 0.14453125, "learning_rate": 1.6211711544422213e-05, "loss": 1.4819800853729248, "step": 7787 }, { "epoch": 0.6574717980646455, "grad_norm": 0.1279296875, "learning_rate": 1.6205617595078297e-05, "loss": 1.4599285125732422, "step": 7788 }, { "epoch": 0.6575562191994766, "grad_norm": 0.1337890625, "learning_rate": 1.6199524242014652e-05, "loss": 1.423171877861023, "step": 7789 }, { "epoch": 0.6576406403343077, "grad_norm": 0.1357421875, "learning_rate": 1.619343148564441e-05, "loss": 1.5108141899108887, "step": 7790 }, { "epoch": 0.6577250614691388, "grad_norm": 0.1376953125, "learning_rate": 1.618733932638069e-05, "loss": 1.5212737321853638, "step": 7791 }, { "epoch": 0.6578094826039699, "grad_norm": 0.138671875, "learning_rate": 1.6181247764636535e-05, "loss": 1.5601750612258911, "step": 7792 }, { "epoch": 0.657893903738801, "grad_norm": 0.14453125, "learning_rate": 1.6175156800824983e-05, "loss": 1.4971915483474731, "step": 7793 }, { "epoch": 0.6579783248736321, "grad_norm": 0.138671875, "learning_rate": 1.6169066435359022e-05, "loss": 1.5079320669174194, "step": 7794 }, { "epoch": 0.6580627460084633, "grad_norm": 0.1416015625, "learning_rate": 1.616297666865157e-05, "loss": 1.557439923286438, "step": 7795 }, { "epoch": 0.6581471671432944, "grad_norm": 0.140625, "learning_rate": 1.6156887501115543e-05, "loss": 1.480631709098816, "step": 7796 }, { "epoch": 0.6582315882781254, "grad_norm": 0.142578125, "learning_rate": 1.6150798933163807e-05, "loss": 1.500777006149292, "step": 7797 }, { "epoch": 0.6583160094129565, "grad_norm": 0.138671875, "learning_rate": 1.614471096520917e-05, "loss": 1.5171750783920288, "step": 7798 }, { "epoch": 0.6584004305477876, "grad_norm": 0.1416015625, "learning_rate": 1.613862359766442e-05, "loss": 1.5467603206634521, "step": 7799 }, { "epoch": 0.6584848516826187, "grad_norm": 0.14453125, "learning_rate": 1.6132536830942283e-05, "loss": 1.5509295463562012, "step": 7800 }, { "epoch": 0.6585692728174498, "grad_norm": 0.1376953125, "learning_rate": 1.6126450665455462e-05, "loss": 1.5688303709030151, "step": 7801 }, { "epoch": 0.6586536939522809, "grad_norm": 0.140625, "learning_rate": 1.6120365101616625e-05, "loss": 1.5147968530654907, "step": 7802 }, { "epoch": 0.6587381150871121, "grad_norm": 0.13671875, "learning_rate": 1.6114280139838368e-05, "loss": 1.546018362045288, "step": 7803 }, { "epoch": 0.6588225362219432, "grad_norm": 0.1474609375, "learning_rate": 1.610819578053328e-05, "loss": 1.4786057472229004, "step": 7804 }, { "epoch": 0.6589069573567743, "grad_norm": 0.1357421875, "learning_rate": 1.6102112024113892e-05, "loss": 1.5639530420303345, "step": 7805 }, { "epoch": 0.6589913784916054, "grad_norm": 0.1572265625, "learning_rate": 1.609602887099269e-05, "loss": 1.513426423072815, "step": 7806 }, { "epoch": 0.6590757996264365, "grad_norm": 0.1533203125, "learning_rate": 1.6089946321582146e-05, "loss": 1.4921815395355225, "step": 7807 }, { "epoch": 0.6591602207612676, "grad_norm": 0.13671875, "learning_rate": 1.6083864376294643e-05, "loss": 1.478329062461853, "step": 7808 }, { "epoch": 0.6592446418960987, "grad_norm": 0.1484375, "learning_rate": 1.6077783035542577e-05, "loss": 1.5692148208618164, "step": 7809 }, { "epoch": 0.6593290630309298, "grad_norm": 0.1474609375, "learning_rate": 1.6071702299738268e-05, "loss": 1.6057745218276978, "step": 7810 }, { "epoch": 0.6594134841657608, "grad_norm": 0.150390625, "learning_rate": 1.6065622169293993e-05, "loss": 1.5676454305648804, "step": 7811 }, { "epoch": 0.659497905300592, "grad_norm": 0.1357421875, "learning_rate": 1.6059542644622027e-05, "loss": 1.5183939933776855, "step": 7812 }, { "epoch": 0.6595823264354231, "grad_norm": 0.14453125, "learning_rate": 1.6053463726134546e-05, "loss": 1.5433552265167236, "step": 7813 }, { "epoch": 0.6596667475702542, "grad_norm": 0.14453125, "learning_rate": 1.6047385414243733e-05, "loss": 1.5845823287963867, "step": 7814 }, { "epoch": 0.6597511687050853, "grad_norm": 0.1435546875, "learning_rate": 1.6041307709361715e-05, "loss": 1.5376527309417725, "step": 7815 }, { "epoch": 0.6598355898399164, "grad_norm": 0.1416015625, "learning_rate": 1.603523061190056e-05, "loss": 1.5708109140396118, "step": 7816 }, { "epoch": 0.6599200109747475, "grad_norm": 0.1455078125, "learning_rate": 1.6029154122272323e-05, "loss": 1.5215370655059814, "step": 7817 }, { "epoch": 0.6600044321095786, "grad_norm": 0.140625, "learning_rate": 1.602307824088899e-05, "loss": 1.5323430299758911, "step": 7818 }, { "epoch": 0.6600888532444097, "grad_norm": 0.146484375, "learning_rate": 1.6017002968162536e-05, "loss": 1.6332759857177734, "step": 7819 }, { "epoch": 0.6601732743792409, "grad_norm": 0.1396484375, "learning_rate": 1.601092830450488e-05, "loss": 1.4258770942687988, "step": 7820 }, { "epoch": 0.660257695514072, "grad_norm": 0.1455078125, "learning_rate": 1.6004854250327883e-05, "loss": 1.552479863166809, "step": 7821 }, { "epoch": 0.6603421166489031, "grad_norm": 0.1376953125, "learning_rate": 1.5998780806043395e-05, "loss": 1.5272324085235596, "step": 7822 }, { "epoch": 0.6604265377837342, "grad_norm": 0.142578125, "learning_rate": 1.5992707972063195e-05, "loss": 1.6250848770141602, "step": 7823 }, { "epoch": 0.6605109589185653, "grad_norm": 0.1494140625, "learning_rate": 1.598663574879905e-05, "loss": 1.5476628541946411, "step": 7824 }, { "epoch": 0.6605953800533964, "grad_norm": 0.1328125, "learning_rate": 1.5980564136662673e-05, "loss": 1.4604600667953491, "step": 7825 }, { "epoch": 0.6606798011882274, "grad_norm": 0.15234375, "learning_rate": 1.597449313606572e-05, "loss": 1.5117747783660889, "step": 7826 }, { "epoch": 0.6607642223230585, "grad_norm": 0.125, "learning_rate": 1.5968422747419824e-05, "loss": 1.4466856718063354, "step": 7827 }, { "epoch": 0.6608486434578896, "grad_norm": 0.1416015625, "learning_rate": 1.5962352971136586e-05, "loss": 1.5208103656768799, "step": 7828 }, { "epoch": 0.6609330645927208, "grad_norm": 0.1494140625, "learning_rate": 1.595628380762753e-05, "loss": 1.496930480003357, "step": 7829 }, { "epoch": 0.6610174857275519, "grad_norm": 0.142578125, "learning_rate": 1.595021525730418e-05, "loss": 1.4724336862564087, "step": 7830 }, { "epoch": 0.661101906862383, "grad_norm": 0.134765625, "learning_rate": 1.5944147320577983e-05, "loss": 1.5496907234191895, "step": 7831 }, { "epoch": 0.6611863279972141, "grad_norm": 0.1494140625, "learning_rate": 1.5938079997860355e-05, "loss": 1.5168708562850952, "step": 7832 }, { "epoch": 0.6612707491320452, "grad_norm": 0.1376953125, "learning_rate": 1.5932013289562704e-05, "loss": 1.514054775238037, "step": 7833 }, { "epoch": 0.6613551702668763, "grad_norm": 0.1396484375, "learning_rate": 1.5925947196096335e-05, "loss": 1.4966487884521484, "step": 7834 }, { "epoch": 0.6614395914017074, "grad_norm": 0.138671875, "learning_rate": 1.5919881717872564e-05, "loss": 1.535801887512207, "step": 7835 }, { "epoch": 0.6615240125365385, "grad_norm": 0.1376953125, "learning_rate": 1.591381685530264e-05, "loss": 1.5582982301712036, "step": 7836 }, { "epoch": 0.6616084336713697, "grad_norm": 0.138671875, "learning_rate": 1.590775260879776e-05, "loss": 1.5169358253479004, "step": 7837 }, { "epoch": 0.6616928548062008, "grad_norm": 0.134765625, "learning_rate": 1.5901688978769123e-05, "loss": 1.4708586931228638, "step": 7838 }, { "epoch": 0.6617772759410319, "grad_norm": 0.130859375, "learning_rate": 1.5895625965627835e-05, "loss": 1.4744563102722168, "step": 7839 }, { "epoch": 0.661861697075863, "grad_norm": 0.1328125, "learning_rate": 1.5889563569784996e-05, "loss": 1.4351752996444702, "step": 7840 }, { "epoch": 0.661946118210694, "grad_norm": 0.134765625, "learning_rate": 1.5883501791651644e-05, "loss": 1.4822990894317627, "step": 7841 }, { "epoch": 0.6620305393455251, "grad_norm": 0.1591796875, "learning_rate": 1.5877440631638775e-05, "loss": 1.6065566539764404, "step": 7842 }, { "epoch": 0.6621149604803562, "grad_norm": 0.134765625, "learning_rate": 1.5871380090157374e-05, "loss": 1.5184108018875122, "step": 7843 }, { "epoch": 0.6621993816151873, "grad_norm": 0.15234375, "learning_rate": 1.586532016761833e-05, "loss": 1.5905977487564087, "step": 7844 }, { "epoch": 0.6622838027500184, "grad_norm": 0.162109375, "learning_rate": 1.5859260864432542e-05, "loss": 1.5936142206192017, "step": 7845 }, { "epoch": 0.6623682238848496, "grad_norm": 0.14453125, "learning_rate": 1.5853202181010844e-05, "loss": 1.484781265258789, "step": 7846 }, { "epoch": 0.6624526450196807, "grad_norm": 0.138671875, "learning_rate": 1.5847144117764014e-05, "loss": 1.4627331495285034, "step": 7847 }, { "epoch": 0.6625370661545118, "grad_norm": 0.1455078125, "learning_rate": 1.5841086675102828e-05, "loss": 1.4959278106689453, "step": 7848 }, { "epoch": 0.6626214872893429, "grad_norm": 0.134765625, "learning_rate": 1.5835029853437966e-05, "loss": 1.480555772781372, "step": 7849 }, { "epoch": 0.662705908424174, "grad_norm": 0.1455078125, "learning_rate": 1.5828973653180113e-05, "loss": 1.472778081893921, "step": 7850 }, { "epoch": 0.6627903295590051, "grad_norm": 0.1337890625, "learning_rate": 1.5822918074739897e-05, "loss": 1.508439064025879, "step": 7851 }, { "epoch": 0.6628747506938362, "grad_norm": 0.1494140625, "learning_rate": 1.581686311852788e-05, "loss": 1.6155846118927002, "step": 7852 }, { "epoch": 0.6629591718286673, "grad_norm": 0.1328125, "learning_rate": 1.581080878495464e-05, "loss": 1.4479528665542603, "step": 7853 }, { "epoch": 0.6630435929634985, "grad_norm": 0.1474609375, "learning_rate": 1.5804755074430633e-05, "loss": 1.4391261339187622, "step": 7854 }, { "epoch": 0.6631280140983296, "grad_norm": 0.138671875, "learning_rate": 1.5798701987366338e-05, "loss": 1.4879140853881836, "step": 7855 }, { "epoch": 0.6632124352331606, "grad_norm": 0.1435546875, "learning_rate": 1.579264952417217e-05, "loss": 1.5107712745666504, "step": 7856 }, { "epoch": 0.6632968563679917, "grad_norm": 0.16015625, "learning_rate": 1.5786597685258495e-05, "loss": 1.5467431545257568, "step": 7857 }, { "epoch": 0.6633812775028228, "grad_norm": 0.1455078125, "learning_rate": 1.5780546471035647e-05, "loss": 1.5771316289901733, "step": 7858 }, { "epoch": 0.6634656986376539, "grad_norm": 0.1416015625, "learning_rate": 1.57744958819139e-05, "loss": 1.5012235641479492, "step": 7859 }, { "epoch": 0.663550119772485, "grad_norm": 0.138671875, "learning_rate": 1.5768445918303505e-05, "loss": 1.5784443616867065, "step": 7860 }, { "epoch": 0.6636345409073161, "grad_norm": 0.130859375, "learning_rate": 1.5762396580614677e-05, "loss": 1.4859126806259155, "step": 7861 }, { "epoch": 0.6637189620421472, "grad_norm": 0.1396484375, "learning_rate": 1.575634786925756e-05, "loss": 1.5045932531356812, "step": 7862 }, { "epoch": 0.6638033831769784, "grad_norm": 0.138671875, "learning_rate": 1.575029978464227e-05, "loss": 1.5169389247894287, "step": 7863 }, { "epoch": 0.6638878043118095, "grad_norm": 0.140625, "learning_rate": 1.57442523271789e-05, "loss": 1.5510731935501099, "step": 7864 }, { "epoch": 0.6639722254466406, "grad_norm": 0.1376953125, "learning_rate": 1.5738205497277463e-05, "loss": 1.599621057510376, "step": 7865 }, { "epoch": 0.6640566465814717, "grad_norm": 0.1396484375, "learning_rate": 1.5732159295347964e-05, "loss": 1.550286054611206, "step": 7866 }, { "epoch": 0.6641410677163028, "grad_norm": 0.1376953125, "learning_rate": 1.5726113721800333e-05, "loss": 1.5423595905303955, "step": 7867 }, { "epoch": 0.6642254888511339, "grad_norm": 0.1357421875, "learning_rate": 1.5720068777044476e-05, "loss": 1.5056663751602173, "step": 7868 }, { "epoch": 0.664309909985965, "grad_norm": 0.142578125, "learning_rate": 1.571402446149028e-05, "loss": 1.4716126918792725, "step": 7869 }, { "epoch": 0.664394331120796, "grad_norm": 0.1416015625, "learning_rate": 1.570798077554754e-05, "loss": 1.5388489961624146, "step": 7870 }, { "epoch": 0.6644787522556272, "grad_norm": 0.1416015625, "learning_rate": 1.5701937719626037e-05, "loss": 1.5110747814178467, "step": 7871 }, { "epoch": 0.6645631733904583, "grad_norm": 0.14453125, "learning_rate": 1.5695895294135504e-05, "loss": 1.5176544189453125, "step": 7872 }, { "epoch": 0.6646475945252894, "grad_norm": 0.1328125, "learning_rate": 1.568985349948563e-05, "loss": 1.51015305519104, "step": 7873 }, { "epoch": 0.6647320156601205, "grad_norm": 0.1357421875, "learning_rate": 1.5683812336086075e-05, "loss": 1.4748363494873047, "step": 7874 }, { "epoch": 0.6648164367949516, "grad_norm": 0.1416015625, "learning_rate": 1.5677771804346432e-05, "loss": 1.527034044265747, "step": 7875 }, { "epoch": 0.6649008579297827, "grad_norm": 0.13671875, "learning_rate": 1.5671731904676273e-05, "loss": 1.5003913640975952, "step": 7876 }, { "epoch": 0.6649852790646138, "grad_norm": 0.1474609375, "learning_rate": 1.5665692637485114e-05, "loss": 1.6106462478637695, "step": 7877 }, { "epoch": 0.6650697001994449, "grad_norm": 0.16015625, "learning_rate": 1.565965400318242e-05, "loss": 1.5418734550476074, "step": 7878 }, { "epoch": 0.665154121334276, "grad_norm": 0.140625, "learning_rate": 1.565361600217765e-05, "loss": 1.5467232465744019, "step": 7879 }, { "epoch": 0.6652385424691072, "grad_norm": 0.130859375, "learning_rate": 1.564757863488017e-05, "loss": 1.4227162599563599, "step": 7880 }, { "epoch": 0.6653229636039383, "grad_norm": 0.13671875, "learning_rate": 1.5641541901699347e-05, "loss": 1.5121804475784302, "step": 7881 }, { "epoch": 0.6654073847387694, "grad_norm": 0.1474609375, "learning_rate": 1.5635505803044476e-05, "loss": 1.6633113622665405, "step": 7882 }, { "epoch": 0.6654918058736005, "grad_norm": 0.1376953125, "learning_rate": 1.5629470339324815e-05, "loss": 1.567435622215271, "step": 7883 }, { "epoch": 0.6655762270084316, "grad_norm": 0.1416015625, "learning_rate": 1.5623435510949602e-05, "loss": 1.5513834953308105, "step": 7884 }, { "epoch": 0.6656606481432626, "grad_norm": 0.140625, "learning_rate": 1.5617401318327985e-05, "loss": 1.569117784500122, "step": 7885 }, { "epoch": 0.6657450692780937, "grad_norm": 0.154296875, "learning_rate": 1.561136776186911e-05, "loss": 1.5615595579147339, "step": 7886 }, { "epoch": 0.6658294904129248, "grad_norm": 0.130859375, "learning_rate": 1.5605334841982084e-05, "loss": 1.498220682144165, "step": 7887 }, { "epoch": 0.665913911547756, "grad_norm": 0.1357421875, "learning_rate": 1.559930255907592e-05, "loss": 1.4802788496017456, "step": 7888 }, { "epoch": 0.6659983326825871, "grad_norm": 0.13671875, "learning_rate": 1.5593270913559657e-05, "loss": 1.5268657207489014, "step": 7889 }, { "epoch": 0.6660827538174182, "grad_norm": 0.1435546875, "learning_rate": 1.558723990584222e-05, "loss": 1.527440071105957, "step": 7890 }, { "epoch": 0.6661671749522493, "grad_norm": 0.142578125, "learning_rate": 1.558120953633255e-05, "loss": 1.5631978511810303, "step": 7891 }, { "epoch": 0.6662515960870804, "grad_norm": 0.142578125, "learning_rate": 1.5575179805439515e-05, "loss": 1.5315580368041992, "step": 7892 }, { "epoch": 0.6663360172219115, "grad_norm": 0.142578125, "learning_rate": 1.5569150713571942e-05, "loss": 1.541139006614685, "step": 7893 }, { "epoch": 0.6664204383567426, "grad_norm": 0.146484375, "learning_rate": 1.556312226113861e-05, "loss": 1.594529151916504, "step": 7894 }, { "epoch": 0.6665048594915737, "grad_norm": 0.150390625, "learning_rate": 1.5557094448548287e-05, "loss": 1.4746884107589722, "step": 7895 }, { "epoch": 0.6665892806264048, "grad_norm": 0.138671875, "learning_rate": 1.5551067276209652e-05, "loss": 1.5121877193450928, "step": 7896 }, { "epoch": 0.666673701761236, "grad_norm": 0.1552734375, "learning_rate": 1.554504074453137e-05, "loss": 1.5734388828277588, "step": 7897 }, { "epoch": 0.6667581228960671, "grad_norm": 0.1337890625, "learning_rate": 1.5539014853922052e-05, "loss": 1.5294777154922485, "step": 7898 }, { "epoch": 0.6668425440308982, "grad_norm": 0.134765625, "learning_rate": 1.553298960479026e-05, "loss": 1.4839437007904053, "step": 7899 }, { "epoch": 0.6669269651657292, "grad_norm": 0.1416015625, "learning_rate": 1.552696499754454e-05, "loss": 1.5213109254837036, "step": 7900 }, { "epoch": 0.6670113863005603, "grad_norm": 0.134765625, "learning_rate": 1.5520941032593355e-05, "loss": 1.4451684951782227, "step": 7901 }, { "epoch": 0.6670958074353914, "grad_norm": 0.1357421875, "learning_rate": 1.551491771034516e-05, "loss": 1.5238215923309326, "step": 7902 }, { "epoch": 0.6671802285702225, "grad_norm": 0.1279296875, "learning_rate": 1.5508895031208336e-05, "loss": 1.4967756271362305, "step": 7903 }, { "epoch": 0.6672646497050536, "grad_norm": 0.1455078125, "learning_rate": 1.5502872995591237e-05, "loss": 1.5125083923339844, "step": 7904 }, { "epoch": 0.6673490708398848, "grad_norm": 0.154296875, "learning_rate": 1.5496851603902192e-05, "loss": 1.5172839164733887, "step": 7905 }, { "epoch": 0.6674334919747159, "grad_norm": 0.1376953125, "learning_rate": 1.5490830856549443e-05, "loss": 1.506593108177185, "step": 7906 }, { "epoch": 0.667517913109547, "grad_norm": 0.142578125, "learning_rate": 1.5484810753941226e-05, "loss": 1.4965896606445312, "step": 7907 }, { "epoch": 0.6676023342443781, "grad_norm": 0.1474609375, "learning_rate": 1.5478791296485706e-05, "loss": 1.5080318450927734, "step": 7908 }, { "epoch": 0.6676867553792092, "grad_norm": 0.146484375, "learning_rate": 1.5472772484591014e-05, "loss": 1.5546330213546753, "step": 7909 }, { "epoch": 0.6677711765140403, "grad_norm": 0.1376953125, "learning_rate": 1.546675431866526e-05, "loss": 1.5441858768463135, "step": 7910 }, { "epoch": 0.6678555976488714, "grad_norm": 0.1357421875, "learning_rate": 1.5460736799116474e-05, "loss": 1.5743987560272217, "step": 7911 }, { "epoch": 0.6679400187837025, "grad_norm": 0.140625, "learning_rate": 1.545471992635266e-05, "loss": 1.4891549348831177, "step": 7912 }, { "epoch": 0.6680244399185336, "grad_norm": 0.13671875, "learning_rate": 1.5448703700781787e-05, "loss": 1.494246482849121, "step": 7913 }, { "epoch": 0.6681088610533648, "grad_norm": 0.142578125, "learning_rate": 1.544268812281175e-05, "loss": 1.4704060554504395, "step": 7914 }, { "epoch": 0.6681932821881958, "grad_norm": 0.1298828125, "learning_rate": 1.5436673192850436e-05, "loss": 1.473962664604187, "step": 7915 }, { "epoch": 0.6682777033230269, "grad_norm": 0.140625, "learning_rate": 1.5430658911305668e-05, "loss": 1.6032730340957642, "step": 7916 }, { "epoch": 0.668362124457858, "grad_norm": 0.1416015625, "learning_rate": 1.5424645278585224e-05, "loss": 1.5932520627975464, "step": 7917 }, { "epoch": 0.6684465455926891, "grad_norm": 0.1396484375, "learning_rate": 1.541863229509686e-05, "loss": 1.5756012201309204, "step": 7918 }, { "epoch": 0.6685309667275202, "grad_norm": 0.1435546875, "learning_rate": 1.5412619961248236e-05, "loss": 1.4608347415924072, "step": 7919 }, { "epoch": 0.6686153878623513, "grad_norm": 0.14453125, "learning_rate": 1.5406608277447042e-05, "loss": 1.567418098449707, "step": 7920 }, { "epoch": 0.6686998089971824, "grad_norm": 0.1376953125, "learning_rate": 1.540059724410085e-05, "loss": 1.5128114223480225, "step": 7921 }, { "epoch": 0.6687842301320136, "grad_norm": 0.150390625, "learning_rate": 1.539458686161725e-05, "loss": 1.6383503675460815, "step": 7922 }, { "epoch": 0.6688686512668447, "grad_norm": 0.146484375, "learning_rate": 1.538857713040375e-05, "loss": 1.5304450988769531, "step": 7923 }, { "epoch": 0.6689530724016758, "grad_norm": 0.1357421875, "learning_rate": 1.538256805086781e-05, "loss": 1.4911328554153442, "step": 7924 }, { "epoch": 0.6690374935365069, "grad_norm": 0.1376953125, "learning_rate": 1.5376559623416892e-05, "loss": 1.5021897554397583, "step": 7925 }, { "epoch": 0.669121914671338, "grad_norm": 0.1533203125, "learning_rate": 1.537055184845835e-05, "loss": 1.557399868965149, "step": 7926 }, { "epoch": 0.6692063358061691, "grad_norm": 0.1396484375, "learning_rate": 1.5364544726399537e-05, "loss": 1.5636541843414307, "step": 7927 }, { "epoch": 0.6692907569410002, "grad_norm": 0.1455078125, "learning_rate": 1.5358538257647764e-05, "loss": 1.5781402587890625, "step": 7928 }, { "epoch": 0.6693751780758312, "grad_norm": 0.140625, "learning_rate": 1.535253244261026e-05, "loss": 1.563003420829773, "step": 7929 }, { "epoch": 0.6694595992106623, "grad_norm": 0.1357421875, "learning_rate": 1.534652728169425e-05, "loss": 1.573636531829834, "step": 7930 }, { "epoch": 0.6695440203454935, "grad_norm": 0.154296875, "learning_rate": 1.5340522775306902e-05, "loss": 1.5298353433609009, "step": 7931 }, { "epoch": 0.6696284414803246, "grad_norm": 0.1376953125, "learning_rate": 1.533451892385532e-05, "loss": 1.4837191104888916, "step": 7932 }, { "epoch": 0.6697128626151557, "grad_norm": 0.13671875, "learning_rate": 1.5328515727746597e-05, "loss": 1.5092811584472656, "step": 7933 }, { "epoch": 0.6697972837499868, "grad_norm": 0.150390625, "learning_rate": 1.5322513187387744e-05, "loss": 1.4944924116134644, "step": 7934 }, { "epoch": 0.6698817048848179, "grad_norm": 0.1416015625, "learning_rate": 1.5316511303185755e-05, "loss": 1.53360915184021, "step": 7935 }, { "epoch": 0.669966126019649, "grad_norm": 0.1455078125, "learning_rate": 1.531051007554759e-05, "loss": 1.5312724113464355, "step": 7936 }, { "epoch": 0.6700505471544801, "grad_norm": 0.1474609375, "learning_rate": 1.530450950488012e-05, "loss": 1.6288847923278809, "step": 7937 }, { "epoch": 0.6701349682893112, "grad_norm": 0.138671875, "learning_rate": 1.529850959159022e-05, "loss": 1.5062857866287231, "step": 7938 }, { "epoch": 0.6702193894241424, "grad_norm": 0.1484375, "learning_rate": 1.5292510336084686e-05, "loss": 1.5334746837615967, "step": 7939 }, { "epoch": 0.6703038105589735, "grad_norm": 0.1416015625, "learning_rate": 1.5286511738770275e-05, "loss": 1.5003085136413574, "step": 7940 }, { "epoch": 0.6703882316938046, "grad_norm": 0.140625, "learning_rate": 1.528051380005373e-05, "loss": 1.520290493965149, "step": 7941 }, { "epoch": 0.6704726528286357, "grad_norm": 0.1416015625, "learning_rate": 1.527451652034171e-05, "loss": 1.5340344905853271, "step": 7942 }, { "epoch": 0.6705570739634668, "grad_norm": 0.146484375, "learning_rate": 1.5268519900040845e-05, "loss": 1.4936957359313965, "step": 7943 }, { "epoch": 0.6706414950982978, "grad_norm": 0.1376953125, "learning_rate": 1.5262523939557722e-05, "loss": 1.5489915609359741, "step": 7944 }, { "epoch": 0.6707259162331289, "grad_norm": 0.1455078125, "learning_rate": 1.5256528639298873e-05, "loss": 1.5426602363586426, "step": 7945 }, { "epoch": 0.67081033736796, "grad_norm": 0.1396484375, "learning_rate": 1.5250533999670813e-05, "loss": 1.5654829740524292, "step": 7946 }, { "epoch": 0.6708947585027911, "grad_norm": 0.1435546875, "learning_rate": 1.5244540021079979e-05, "loss": 1.5573360919952393, "step": 7947 }, { "epoch": 0.6709791796376223, "grad_norm": 0.130859375, "learning_rate": 1.523854670393278e-05, "loss": 1.5032880306243896, "step": 7948 }, { "epoch": 0.6710636007724534, "grad_norm": 0.146484375, "learning_rate": 1.5232554048635583e-05, "loss": 1.6726123094558716, "step": 7949 }, { "epoch": 0.6711480219072845, "grad_norm": 0.1435546875, "learning_rate": 1.522656205559469e-05, "loss": 1.4827109575271606, "step": 7950 }, { "epoch": 0.6712324430421156, "grad_norm": 0.134765625, "learning_rate": 1.522057072521639e-05, "loss": 1.5371029376983643, "step": 7951 }, { "epoch": 0.6713168641769467, "grad_norm": 0.138671875, "learning_rate": 1.5214580057906896e-05, "loss": 1.4419859647750854, "step": 7952 }, { "epoch": 0.6714012853117778, "grad_norm": 0.1484375, "learning_rate": 1.52085900540724e-05, "loss": 1.4943877458572388, "step": 7953 }, { "epoch": 0.6714857064466089, "grad_norm": 0.14453125, "learning_rate": 1.5202600714119037e-05, "loss": 1.6174750328063965, "step": 7954 }, { "epoch": 0.67157012758144, "grad_norm": 0.154296875, "learning_rate": 1.519661203845288e-05, "loss": 1.4926809072494507, "step": 7955 }, { "epoch": 0.6716545487162712, "grad_norm": 0.1396484375, "learning_rate": 1.5190624027480004e-05, "loss": 1.5091633796691895, "step": 7956 }, { "epoch": 0.6717389698511023, "grad_norm": 0.1396484375, "learning_rate": 1.5184636681606395e-05, "loss": 1.5383810997009277, "step": 7957 }, { "epoch": 0.6718233909859334, "grad_norm": 0.14453125, "learning_rate": 1.5178650001238012e-05, "loss": 1.5268009901046753, "step": 7958 }, { "epoch": 0.6719078121207644, "grad_norm": 0.14453125, "learning_rate": 1.5172663986780771e-05, "loss": 1.4618937969207764, "step": 7959 }, { "epoch": 0.6719922332555955, "grad_norm": 0.146484375, "learning_rate": 1.5166678638640521e-05, "loss": 1.5984175205230713, "step": 7960 }, { "epoch": 0.6720766543904266, "grad_norm": 0.1416015625, "learning_rate": 1.5160693957223104e-05, "loss": 1.4795241355895996, "step": 7961 }, { "epoch": 0.6721610755252577, "grad_norm": 0.13671875, "learning_rate": 1.5154709942934289e-05, "loss": 1.5340975522994995, "step": 7962 }, { "epoch": 0.6722454966600888, "grad_norm": 0.1328125, "learning_rate": 1.5148726596179802e-05, "loss": 1.5651394128799438, "step": 7963 }, { "epoch": 0.6723299177949199, "grad_norm": 0.1533203125, "learning_rate": 1.5142743917365334e-05, "loss": 1.5721466541290283, "step": 7964 }, { "epoch": 0.6724143389297511, "grad_norm": 0.134765625, "learning_rate": 1.5136761906896513e-05, "loss": 1.5033855438232422, "step": 7965 }, { "epoch": 0.6724987600645822, "grad_norm": 0.1328125, "learning_rate": 1.5130780565178947e-05, "loss": 1.451807975769043, "step": 7966 }, { "epoch": 0.6725831811994133, "grad_norm": 0.1591796875, "learning_rate": 1.512479989261819e-05, "loss": 1.5522727966308594, "step": 7967 }, { "epoch": 0.6726676023342444, "grad_norm": 0.134765625, "learning_rate": 1.5118819889619728e-05, "loss": 1.5078327655792236, "step": 7968 }, { "epoch": 0.6727520234690755, "grad_norm": 0.1533203125, "learning_rate": 1.5112840556589036e-05, "loss": 1.5289095640182495, "step": 7969 }, { "epoch": 0.6728364446039066, "grad_norm": 0.1484375, "learning_rate": 1.5106861893931509e-05, "loss": 1.513237476348877, "step": 7970 }, { "epoch": 0.6729208657387377, "grad_norm": 0.1328125, "learning_rate": 1.5100883902052531e-05, "loss": 1.5294407606124878, "step": 7971 }, { "epoch": 0.6730052868735688, "grad_norm": 0.146484375, "learning_rate": 1.5094906581357424e-05, "loss": 1.540025234222412, "step": 7972 }, { "epoch": 0.6730897080084, "grad_norm": 0.1474609375, "learning_rate": 1.5088929932251455e-05, "loss": 1.4958080053329468, "step": 7973 }, { "epoch": 0.673174129143231, "grad_norm": 0.1318359375, "learning_rate": 1.5082953955139861e-05, "loss": 1.499891757965088, "step": 7974 }, { "epoch": 0.6732585502780621, "grad_norm": 0.138671875, "learning_rate": 1.5076978650427826e-05, "loss": 1.518883466720581, "step": 7975 }, { "epoch": 0.6733429714128932, "grad_norm": 0.1435546875, "learning_rate": 1.5071004018520482e-05, "loss": 1.4917917251586914, "step": 7976 }, { "epoch": 0.6734273925477243, "grad_norm": 0.140625, "learning_rate": 1.5065030059822943e-05, "loss": 1.5615894794464111, "step": 7977 }, { "epoch": 0.6735118136825554, "grad_norm": 0.1328125, "learning_rate": 1.5059056774740243e-05, "loss": 1.4798610210418701, "step": 7978 }, { "epoch": 0.6735962348173865, "grad_norm": 0.1474609375, "learning_rate": 1.505308416367738e-05, "loss": 1.5394591093063354, "step": 7979 }, { "epoch": 0.6736806559522176, "grad_norm": 0.138671875, "learning_rate": 1.504711222703934e-05, "loss": 1.5770124197006226, "step": 7980 }, { "epoch": 0.6737650770870487, "grad_norm": 0.134765625, "learning_rate": 1.5041140965230993e-05, "loss": 1.5312095880508423, "step": 7981 }, { "epoch": 0.6738494982218799, "grad_norm": 0.14453125, "learning_rate": 1.5035170378657242e-05, "loss": 1.5425676107406616, "step": 7982 }, { "epoch": 0.673933919356711, "grad_norm": 0.1484375, "learning_rate": 1.5029200467722884e-05, "loss": 1.5339982509613037, "step": 7983 }, { "epoch": 0.6740183404915421, "grad_norm": 0.138671875, "learning_rate": 1.5023231232832696e-05, "loss": 1.5981262922286987, "step": 7984 }, { "epoch": 0.6741027616263732, "grad_norm": 0.134765625, "learning_rate": 1.5017262674391428e-05, "loss": 1.5187047719955444, "step": 7985 }, { "epoch": 0.6741871827612043, "grad_norm": 0.146484375, "learning_rate": 1.501129479280373e-05, "loss": 1.6070919036865234, "step": 7986 }, { "epoch": 0.6742716038960354, "grad_norm": 0.142578125, "learning_rate": 1.5005327588474264e-05, "loss": 1.4726272821426392, "step": 7987 }, { "epoch": 0.6743560250308664, "grad_norm": 0.134765625, "learning_rate": 1.4999361061807607e-05, "loss": 1.4490913152694702, "step": 7988 }, { "epoch": 0.6744404461656975, "grad_norm": 0.1376953125, "learning_rate": 1.4993395213208309e-05, "loss": 1.4887949228286743, "step": 7989 }, { "epoch": 0.6745248673005287, "grad_norm": 0.1376953125, "learning_rate": 1.4987430043080875e-05, "loss": 1.5581390857696533, "step": 7990 }, { "epoch": 0.6746092884353598, "grad_norm": 0.1396484375, "learning_rate": 1.4981465551829737e-05, "loss": 1.5179308652877808, "step": 7991 }, { "epoch": 0.6746937095701909, "grad_norm": 0.158203125, "learning_rate": 1.4975501739859327e-05, "loss": 1.5210679769515991, "step": 7992 }, { "epoch": 0.674778130705022, "grad_norm": 0.1357421875, "learning_rate": 1.496953860757399e-05, "loss": 1.5994945764541626, "step": 7993 }, { "epoch": 0.6748625518398531, "grad_norm": 0.369140625, "learning_rate": 1.4963576155378048e-05, "loss": 1.5197186470031738, "step": 7994 }, { "epoch": 0.6749469729746842, "grad_norm": 0.12890625, "learning_rate": 1.495761438367577e-05, "loss": 1.469122052192688, "step": 7995 }, { "epoch": 0.6750313941095153, "grad_norm": 0.1416015625, "learning_rate": 1.4951653292871365e-05, "loss": 1.4751933813095093, "step": 7996 }, { "epoch": 0.6751158152443464, "grad_norm": 0.1376953125, "learning_rate": 1.4945692883369027e-05, "loss": 1.5294865369796753, "step": 7997 }, { "epoch": 0.6752002363791775, "grad_norm": 0.12890625, "learning_rate": 1.4939733155572882e-05, "loss": 1.4731338024139404, "step": 7998 }, { "epoch": 0.6752846575140087, "grad_norm": 0.1376953125, "learning_rate": 1.4933774109887005e-05, "loss": 1.488788366317749, "step": 7999 }, { "epoch": 0.6753690786488398, "grad_norm": 0.1357421875, "learning_rate": 1.4927815746715446e-05, "loss": 1.5299900770187378, "step": 8000 }, { "epoch": 0.6754534997836709, "grad_norm": 0.140625, "learning_rate": 1.492185806646218e-05, "loss": 1.4326967000961304, "step": 8001 }, { "epoch": 0.675537920918502, "grad_norm": 0.150390625, "learning_rate": 1.4915901069531166e-05, "loss": 1.586167335510254, "step": 8002 }, { "epoch": 0.675622342053333, "grad_norm": 0.1435546875, "learning_rate": 1.4909944756326303e-05, "loss": 1.5074002742767334, "step": 8003 }, { "epoch": 0.6757067631881641, "grad_norm": 0.146484375, "learning_rate": 1.4903989127251433e-05, "loss": 1.5650238990783691, "step": 8004 }, { "epoch": 0.6757911843229952, "grad_norm": 0.134765625, "learning_rate": 1.4898034182710374e-05, "loss": 1.4426069259643555, "step": 8005 }, { "epoch": 0.6758756054578263, "grad_norm": 0.1337890625, "learning_rate": 1.4892079923106872e-05, "loss": 1.467668056488037, "step": 8006 }, { "epoch": 0.6759600265926575, "grad_norm": 0.134765625, "learning_rate": 1.4886126348844648e-05, "loss": 1.5609586238861084, "step": 8007 }, { "epoch": 0.6760444477274886, "grad_norm": 0.1513671875, "learning_rate": 1.4880173460327373e-05, "loss": 1.557689905166626, "step": 8008 }, { "epoch": 0.6761288688623197, "grad_norm": 0.1357421875, "learning_rate": 1.4874221257958663e-05, "loss": 1.4902416467666626, "step": 8009 }, { "epoch": 0.6762132899971508, "grad_norm": 0.154296875, "learning_rate": 1.486826974214209e-05, "loss": 1.5898265838623047, "step": 8010 }, { "epoch": 0.6762977111319819, "grad_norm": 0.13671875, "learning_rate": 1.486231891328118e-05, "loss": 1.495588779449463, "step": 8011 }, { "epoch": 0.676382132266813, "grad_norm": 0.1318359375, "learning_rate": 1.4856368771779411e-05, "loss": 1.4847873449325562, "step": 8012 }, { "epoch": 0.6764665534016441, "grad_norm": 0.1376953125, "learning_rate": 1.4850419318040226e-05, "loss": 1.5255022048950195, "step": 8013 }, { "epoch": 0.6765509745364752, "grad_norm": 0.13671875, "learning_rate": 1.484447055246701e-05, "loss": 1.5368506908416748, "step": 8014 }, { "epoch": 0.6766353956713063, "grad_norm": 0.1474609375, "learning_rate": 1.483852247546309e-05, "loss": 1.5360583066940308, "step": 8015 }, { "epoch": 0.6767198168061375, "grad_norm": 0.12890625, "learning_rate": 1.4832575087431789e-05, "loss": 1.4786217212677002, "step": 8016 }, { "epoch": 0.6768042379409686, "grad_norm": 0.1494140625, "learning_rate": 1.482662838877632e-05, "loss": 1.5768016576766968, "step": 8017 }, { "epoch": 0.6768886590757996, "grad_norm": 0.134765625, "learning_rate": 1.4820682379899914e-05, "loss": 1.5792986154556274, "step": 8018 }, { "epoch": 0.6769730802106307, "grad_norm": 0.138671875, "learning_rate": 1.4814737061205703e-05, "loss": 1.5521855354309082, "step": 8019 }, { "epoch": 0.6770575013454618, "grad_norm": 0.1455078125, "learning_rate": 1.4808792433096797e-05, "loss": 1.5721962451934814, "step": 8020 }, { "epoch": 0.6771419224802929, "grad_norm": 0.1376953125, "learning_rate": 1.4802848495976274e-05, "loss": 1.528660774230957, "step": 8021 }, { "epoch": 0.677226343615124, "grad_norm": 0.1396484375, "learning_rate": 1.4796905250247117e-05, "loss": 1.4685728549957275, "step": 8022 }, { "epoch": 0.6773107647499551, "grad_norm": 0.150390625, "learning_rate": 1.4790962696312322e-05, "loss": 1.563483715057373, "step": 8023 }, { "epoch": 0.6773951858847863, "grad_norm": 0.1337890625, "learning_rate": 1.478502083457479e-05, "loss": 1.5373116731643677, "step": 8024 }, { "epoch": 0.6774796070196174, "grad_norm": 0.177734375, "learning_rate": 1.4779079665437396e-05, "loss": 1.5382626056671143, "step": 8025 }, { "epoch": 0.6775640281544485, "grad_norm": 0.1318359375, "learning_rate": 1.4773139189302976e-05, "loss": 1.5088566541671753, "step": 8026 }, { "epoch": 0.6776484492892796, "grad_norm": 0.1533203125, "learning_rate": 1.4767199406574292e-05, "loss": 1.4821332693099976, "step": 8027 }, { "epoch": 0.6777328704241107, "grad_norm": 0.142578125, "learning_rate": 1.476126031765409e-05, "loss": 1.5632922649383545, "step": 8028 }, { "epoch": 0.6778172915589418, "grad_norm": 0.140625, "learning_rate": 1.4755321922945053e-05, "loss": 1.5456407070159912, "step": 8029 }, { "epoch": 0.6779017126937729, "grad_norm": 0.140625, "learning_rate": 1.474938422284981e-05, "loss": 1.5275967121124268, "step": 8030 }, { "epoch": 0.677986133828604, "grad_norm": 0.1416015625, "learning_rate": 1.4743447217770962e-05, "loss": 1.463427186012268, "step": 8031 }, { "epoch": 0.678070554963435, "grad_norm": 0.15234375, "learning_rate": 1.4737510908111033e-05, "loss": 1.5116435289382935, "step": 8032 }, { "epoch": 0.6781549760982662, "grad_norm": 0.1376953125, "learning_rate": 1.4731575294272537e-05, "loss": 1.6009477376937866, "step": 8033 }, { "epoch": 0.6782393972330973, "grad_norm": 0.1337890625, "learning_rate": 1.4725640376657926e-05, "loss": 1.4429086446762085, "step": 8034 }, { "epoch": 0.6783238183679284, "grad_norm": 0.1416015625, "learning_rate": 1.4719706155669587e-05, "loss": 1.522842526435852, "step": 8035 }, { "epoch": 0.6784082395027595, "grad_norm": 0.1318359375, "learning_rate": 1.4713772631709887e-05, "loss": 1.4676530361175537, "step": 8036 }, { "epoch": 0.6784926606375906, "grad_norm": 0.150390625, "learning_rate": 1.4707839805181117e-05, "loss": 1.5429688692092896, "step": 8037 }, { "epoch": 0.6785770817724217, "grad_norm": 0.158203125, "learning_rate": 1.4701907676485555e-05, "loss": 1.6218968629837036, "step": 8038 }, { "epoch": 0.6786615029072528, "grad_norm": 0.18359375, "learning_rate": 1.4695976246025406e-05, "loss": 1.6269383430480957, "step": 8039 }, { "epoch": 0.6787459240420839, "grad_norm": 0.1396484375, "learning_rate": 1.4690045514202833e-05, "loss": 1.5363664627075195, "step": 8040 }, { "epoch": 0.6788303451769151, "grad_norm": 0.146484375, "learning_rate": 1.4684115481419963e-05, "loss": 1.6103596687316895, "step": 8041 }, { "epoch": 0.6789147663117462, "grad_norm": 0.1376953125, "learning_rate": 1.4678186148078847e-05, "loss": 1.55413019657135, "step": 8042 }, { "epoch": 0.6789991874465773, "grad_norm": 0.1435546875, "learning_rate": 1.4672257514581525e-05, "loss": 1.601501226425171, "step": 8043 }, { "epoch": 0.6790836085814084, "grad_norm": 0.1455078125, "learning_rate": 1.4666329581329974e-05, "loss": 1.5186759233474731, "step": 8044 }, { "epoch": 0.6791680297162395, "grad_norm": 0.14453125, "learning_rate": 1.466040234872611e-05, "loss": 1.5420697927474976, "step": 8045 }, { "epoch": 0.6792524508510706, "grad_norm": 0.15234375, "learning_rate": 1.4654475817171814e-05, "loss": 1.54526948928833, "step": 8046 }, { "epoch": 0.6793368719859016, "grad_norm": 0.13671875, "learning_rate": 1.4648549987068938e-05, "loss": 1.5051600933074951, "step": 8047 }, { "epoch": 0.6794212931207327, "grad_norm": 0.1484375, "learning_rate": 1.4642624858819248e-05, "loss": 1.5814427137374878, "step": 8048 }, { "epoch": 0.6795057142555638, "grad_norm": 0.138671875, "learning_rate": 1.4636700432824497e-05, "loss": 1.583360195159912, "step": 8049 }, { "epoch": 0.679590135390395, "grad_norm": 0.1416015625, "learning_rate": 1.4630776709486357e-05, "loss": 1.4806748628616333, "step": 8050 }, { "epoch": 0.6796745565252261, "grad_norm": 0.142578125, "learning_rate": 1.4624853689206478e-05, "loss": 1.5465455055236816, "step": 8051 }, { "epoch": 0.6797589776600572, "grad_norm": 0.1865234375, "learning_rate": 1.4618931372386471e-05, "loss": 1.5351626873016357, "step": 8052 }, { "epoch": 0.6798433987948883, "grad_norm": 0.1435546875, "learning_rate": 1.4613009759427853e-05, "loss": 1.5616018772125244, "step": 8053 }, { "epoch": 0.6799278199297194, "grad_norm": 0.1484375, "learning_rate": 1.4607088850732154e-05, "loss": 1.5374902486801147, "step": 8054 }, { "epoch": 0.6800122410645505, "grad_norm": 0.1455078125, "learning_rate": 1.4601168646700808e-05, "loss": 1.5537241697311401, "step": 8055 }, { "epoch": 0.6800966621993816, "grad_norm": 0.1474609375, "learning_rate": 1.4595249147735212e-05, "loss": 1.5369290113449097, "step": 8056 }, { "epoch": 0.6801810833342127, "grad_norm": 0.142578125, "learning_rate": 1.4589330354236754e-05, "loss": 1.583044171333313, "step": 8057 }, { "epoch": 0.6802655044690439, "grad_norm": 0.142578125, "learning_rate": 1.4583412266606711e-05, "loss": 1.5344904661178589, "step": 8058 }, { "epoch": 0.680349925603875, "grad_norm": 0.1376953125, "learning_rate": 1.4577494885246353e-05, "loss": 1.516063928604126, "step": 8059 }, { "epoch": 0.6804343467387061, "grad_norm": 0.13671875, "learning_rate": 1.4571578210556896e-05, "loss": 1.5183897018432617, "step": 8060 }, { "epoch": 0.6805187678735372, "grad_norm": 0.13671875, "learning_rate": 1.4565662242939505e-05, "loss": 1.4706865549087524, "step": 8061 }, { "epoch": 0.6806031890083682, "grad_norm": 0.138671875, "learning_rate": 1.455974698279529e-05, "loss": 1.5360956192016602, "step": 8062 }, { "epoch": 0.6806876101431993, "grad_norm": 0.1416015625, "learning_rate": 1.4553832430525328e-05, "loss": 1.447850227355957, "step": 8063 }, { "epoch": 0.6807720312780304, "grad_norm": 0.13671875, "learning_rate": 1.4547918586530635e-05, "loss": 1.5508877038955688, "step": 8064 }, { "epoch": 0.6808564524128615, "grad_norm": 0.1376953125, "learning_rate": 1.4542005451212182e-05, "loss": 1.5508512258529663, "step": 8065 }, { "epoch": 0.6809408735476926, "grad_norm": 0.15234375, "learning_rate": 1.4536093024970901e-05, "loss": 1.5117344856262207, "step": 8066 }, { "epoch": 0.6810252946825238, "grad_norm": 0.138671875, "learning_rate": 1.4530181308207674e-05, "loss": 1.5960664749145508, "step": 8067 }, { "epoch": 0.6811097158173549, "grad_norm": 0.1318359375, "learning_rate": 1.4524270301323311e-05, "loss": 1.539820671081543, "step": 8068 }, { "epoch": 0.681194136952186, "grad_norm": 0.1396484375, "learning_rate": 1.4518360004718592e-05, "loss": 1.5317050218582153, "step": 8069 }, { "epoch": 0.6812785580870171, "grad_norm": 0.1376953125, "learning_rate": 1.4512450418794279e-05, "loss": 1.4909815788269043, "step": 8070 }, { "epoch": 0.6813629792218482, "grad_norm": 0.1376953125, "learning_rate": 1.4506541543951024e-05, "loss": 1.4726327657699585, "step": 8071 }, { "epoch": 0.6814474003566793, "grad_norm": 0.15234375, "learning_rate": 1.4500633380589479e-05, "loss": 1.4659539461135864, "step": 8072 }, { "epoch": 0.6815318214915104, "grad_norm": 0.1357421875, "learning_rate": 1.4494725929110225e-05, "loss": 1.5564345121383667, "step": 8073 }, { "epoch": 0.6816162426263415, "grad_norm": 0.14453125, "learning_rate": 1.4488819189913807e-05, "loss": 1.5290288925170898, "step": 8074 }, { "epoch": 0.6817006637611727, "grad_norm": 0.1455078125, "learning_rate": 1.4482913163400725e-05, "loss": 1.5274219512939453, "step": 8075 }, { "epoch": 0.6817850848960038, "grad_norm": 0.130859375, "learning_rate": 1.4477007849971385e-05, "loss": 1.4668036699295044, "step": 8076 }, { "epoch": 0.6818695060308348, "grad_norm": 0.14453125, "learning_rate": 1.447110325002623e-05, "loss": 1.5597409009933472, "step": 8077 }, { "epoch": 0.6819539271656659, "grad_norm": 0.142578125, "learning_rate": 1.446519936396557e-05, "loss": 1.5502139329910278, "step": 8078 }, { "epoch": 0.682038348300497, "grad_norm": 0.1396484375, "learning_rate": 1.4459296192189709e-05, "loss": 1.5665360689163208, "step": 8079 }, { "epoch": 0.6821227694353281, "grad_norm": 0.1484375, "learning_rate": 1.4453393735098921e-05, "loss": 1.5914106369018555, "step": 8080 }, { "epoch": 0.6822071905701592, "grad_norm": 0.150390625, "learning_rate": 1.444749199309338e-05, "loss": 1.5633254051208496, "step": 8081 }, { "epoch": 0.6822916117049903, "grad_norm": 0.14453125, "learning_rate": 1.4441590966573244e-05, "loss": 1.5548746585845947, "step": 8082 }, { "epoch": 0.6823760328398214, "grad_norm": 0.140625, "learning_rate": 1.4435690655938622e-05, "loss": 1.5233919620513916, "step": 8083 }, { "epoch": 0.6824604539746526, "grad_norm": 0.140625, "learning_rate": 1.4429791061589565e-05, "loss": 1.5511876344680786, "step": 8084 }, { "epoch": 0.6825448751094837, "grad_norm": 0.1376953125, "learning_rate": 1.4423892183926092e-05, "loss": 1.5761891603469849, "step": 8085 }, { "epoch": 0.6826292962443148, "grad_norm": 0.1396484375, "learning_rate": 1.441799402334813e-05, "loss": 1.5182647705078125, "step": 8086 }, { "epoch": 0.6827137173791459, "grad_norm": 0.140625, "learning_rate": 1.4412096580255619e-05, "loss": 1.5622879266738892, "step": 8087 }, { "epoch": 0.682798138513977, "grad_norm": 0.1416015625, "learning_rate": 1.4406199855048422e-05, "loss": 1.6126989126205444, "step": 8088 }, { "epoch": 0.6828825596488081, "grad_norm": 0.1435546875, "learning_rate": 1.440030384812633e-05, "loss": 1.5497853755950928, "step": 8089 }, { "epoch": 0.6829669807836392, "grad_norm": 0.146484375, "learning_rate": 1.4394408559889111e-05, "loss": 1.5388184785842896, "step": 8090 }, { "epoch": 0.6830514019184702, "grad_norm": 0.1455078125, "learning_rate": 1.4388513990736485e-05, "loss": 1.6130925416946411, "step": 8091 }, { "epoch": 0.6831358230533013, "grad_norm": 0.1513671875, "learning_rate": 1.4382620141068121e-05, "loss": 1.539616584777832, "step": 8092 }, { "epoch": 0.6832202441881325, "grad_norm": 0.1337890625, "learning_rate": 1.4376727011283625e-05, "loss": 1.5249910354614258, "step": 8093 }, { "epoch": 0.6833046653229636, "grad_norm": 0.14453125, "learning_rate": 1.437083460178258e-05, "loss": 1.4640755653381348, "step": 8094 }, { "epoch": 0.6833890864577947, "grad_norm": 0.1357421875, "learning_rate": 1.4364942912964493e-05, "loss": 1.5624568462371826, "step": 8095 }, { "epoch": 0.6834735075926258, "grad_norm": 0.15234375, "learning_rate": 1.4359051945228844e-05, "loss": 1.5819096565246582, "step": 8096 }, { "epoch": 0.6835579287274569, "grad_norm": 0.1357421875, "learning_rate": 1.4353161698975049e-05, "loss": 1.5196179151535034, "step": 8097 }, { "epoch": 0.683642349862288, "grad_norm": 0.13671875, "learning_rate": 1.4347272174602492e-05, "loss": 1.4848639965057373, "step": 8098 }, { "epoch": 0.6837267709971191, "grad_norm": 0.1513671875, "learning_rate": 1.4341383372510475e-05, "loss": 1.584694743156433, "step": 8099 }, { "epoch": 0.6838111921319502, "grad_norm": 0.1357421875, "learning_rate": 1.4335495293098277e-05, "loss": 1.5363786220550537, "step": 8100 }, { "epoch": 0.6838956132667814, "grad_norm": 0.13671875, "learning_rate": 1.4329607936765154e-05, "loss": 1.4928680658340454, "step": 8101 }, { "epoch": 0.6839800344016125, "grad_norm": 0.134765625, "learning_rate": 1.432372130391025e-05, "loss": 1.461669683456421, "step": 8102 }, { "epoch": 0.6840644555364436, "grad_norm": 0.1416015625, "learning_rate": 1.4317835394932704e-05, "loss": 1.5124270915985107, "step": 8103 }, { "epoch": 0.6841488766712747, "grad_norm": 0.1318359375, "learning_rate": 1.4311950210231595e-05, "loss": 1.566195011138916, "step": 8104 }, { "epoch": 0.6842332978061058, "grad_norm": 0.1435546875, "learning_rate": 1.4306065750205952e-05, "loss": 1.513215184211731, "step": 8105 }, { "epoch": 0.6843177189409368, "grad_norm": 0.1376953125, "learning_rate": 1.4300182015254757e-05, "loss": 1.5705066919326782, "step": 8106 }, { "epoch": 0.6844021400757679, "grad_norm": 0.138671875, "learning_rate": 1.429429900577694e-05, "loss": 1.4722533226013184, "step": 8107 }, { "epoch": 0.684486561210599, "grad_norm": 0.1337890625, "learning_rate": 1.4288416722171394e-05, "loss": 1.489668846130371, "step": 8108 }, { "epoch": 0.6845709823454301, "grad_norm": 0.1318359375, "learning_rate": 1.428253516483693e-05, "loss": 1.5320062637329102, "step": 8109 }, { "epoch": 0.6846554034802613, "grad_norm": 0.14453125, "learning_rate": 1.4276654334172332e-05, "loss": 1.5261579751968384, "step": 8110 }, { "epoch": 0.6847398246150924, "grad_norm": 0.1416015625, "learning_rate": 1.4270774230576368e-05, "loss": 1.5423530340194702, "step": 8111 }, { "epoch": 0.6848242457499235, "grad_norm": 0.134765625, "learning_rate": 1.426489485444769e-05, "loss": 1.4860904216766357, "step": 8112 }, { "epoch": 0.6849086668847546, "grad_norm": 0.1396484375, "learning_rate": 1.4259016206184944e-05, "loss": 1.5999878644943237, "step": 8113 }, { "epoch": 0.6849930880195857, "grad_norm": 0.1435546875, "learning_rate": 1.4253138286186718e-05, "loss": 1.559937596321106, "step": 8114 }, { "epoch": 0.6850775091544168, "grad_norm": 0.146484375, "learning_rate": 1.4247261094851549e-05, "loss": 1.523160696029663, "step": 8115 }, { "epoch": 0.6851619302892479, "grad_norm": 0.1484375, "learning_rate": 1.424138463257793e-05, "loss": 1.4814196825027466, "step": 8116 }, { "epoch": 0.685246351424079, "grad_norm": 0.1328125, "learning_rate": 1.423550889976428e-05, "loss": 1.4914484024047852, "step": 8117 }, { "epoch": 0.6853307725589102, "grad_norm": 0.138671875, "learning_rate": 1.4229633896809008e-05, "loss": 1.5067882537841797, "step": 8118 }, { "epoch": 0.6854151936937413, "grad_norm": 0.13671875, "learning_rate": 1.4223759624110456e-05, "loss": 1.4973902702331543, "step": 8119 }, { "epoch": 0.6854996148285724, "grad_norm": 0.1357421875, "learning_rate": 1.4217886082066884e-05, "loss": 1.5239174365997314, "step": 8120 }, { "epoch": 0.6855840359634034, "grad_norm": 0.1396484375, "learning_rate": 1.4212013271076572e-05, "loss": 1.5266436338424683, "step": 8121 }, { "epoch": 0.6856684570982345, "grad_norm": 0.1513671875, "learning_rate": 1.4206141191537682e-05, "loss": 1.6053868532180786, "step": 8122 }, { "epoch": 0.6857528782330656, "grad_norm": 0.1669921875, "learning_rate": 1.4200269843848363e-05, "loss": 1.598924994468689, "step": 8123 }, { "epoch": 0.6858372993678967, "grad_norm": 0.1357421875, "learning_rate": 1.4194399228406708e-05, "loss": 1.5493096113204956, "step": 8124 }, { "epoch": 0.6859217205027278, "grad_norm": 0.138671875, "learning_rate": 1.4188529345610756e-05, "loss": 1.5467023849487305, "step": 8125 }, { "epoch": 0.6860061416375589, "grad_norm": 0.13671875, "learning_rate": 1.4182660195858516e-05, "loss": 1.4861594438552856, "step": 8126 }, { "epoch": 0.6860905627723901, "grad_norm": 0.1474609375, "learning_rate": 1.4176791779547896e-05, "loss": 1.5339348316192627, "step": 8127 }, { "epoch": 0.6861749839072212, "grad_norm": 0.142578125, "learning_rate": 1.4170924097076819e-05, "loss": 1.5748097896575928, "step": 8128 }, { "epoch": 0.6862594050420523, "grad_norm": 0.140625, "learning_rate": 1.4165057148843125e-05, "loss": 1.5313796997070312, "step": 8129 }, { "epoch": 0.6863438261768834, "grad_norm": 0.1376953125, "learning_rate": 1.4159190935244592e-05, "loss": 1.5263924598693848, "step": 8130 }, { "epoch": 0.6864282473117145, "grad_norm": 0.140625, "learning_rate": 1.4153325456678963e-05, "loss": 1.4819916486740112, "step": 8131 }, { "epoch": 0.6865126684465456, "grad_norm": 0.1376953125, "learning_rate": 1.4147460713543958e-05, "loss": 1.5411322116851807, "step": 8132 }, { "epoch": 0.6865970895813767, "grad_norm": 0.1376953125, "learning_rate": 1.4141596706237192e-05, "loss": 1.508698582649231, "step": 8133 }, { "epoch": 0.6866815107162078, "grad_norm": 0.1474609375, "learning_rate": 1.4135733435156271e-05, "loss": 1.5385273694992065, "step": 8134 }, { "epoch": 0.686765931851039, "grad_norm": 0.1357421875, "learning_rate": 1.4129870900698739e-05, "loss": 1.4632750749588013, "step": 8135 }, { "epoch": 0.68685035298587, "grad_norm": 0.138671875, "learning_rate": 1.4124009103262083e-05, "loss": 1.5192335844039917, "step": 8136 }, { "epoch": 0.6869347741207011, "grad_norm": 0.1318359375, "learning_rate": 1.4118148043243757e-05, "loss": 1.539533257484436, "step": 8137 }, { "epoch": 0.6870191952555322, "grad_norm": 0.1396484375, "learning_rate": 1.4112287721041148e-05, "loss": 1.5449392795562744, "step": 8138 }, { "epoch": 0.6871036163903633, "grad_norm": 0.1376953125, "learning_rate": 1.4106428137051614e-05, "loss": 1.5603227615356445, "step": 8139 }, { "epoch": 0.6871880375251944, "grad_norm": 0.134765625, "learning_rate": 1.4100569291672425e-05, "loss": 1.4862807989120483, "step": 8140 }, { "epoch": 0.6872724586600255, "grad_norm": 0.13671875, "learning_rate": 1.4094711185300826e-05, "loss": 1.5668082237243652, "step": 8141 }, { "epoch": 0.6873568797948566, "grad_norm": 0.13671875, "learning_rate": 1.4088853818334044e-05, "loss": 1.544877052307129, "step": 8142 }, { "epoch": 0.6874413009296877, "grad_norm": 0.1435546875, "learning_rate": 1.4082997191169189e-05, "loss": 1.5712631940841675, "step": 8143 }, { "epoch": 0.6875257220645189, "grad_norm": 0.142578125, "learning_rate": 1.4077141304203365e-05, "loss": 1.5326181650161743, "step": 8144 }, { "epoch": 0.68761014319935, "grad_norm": 0.1455078125, "learning_rate": 1.4071286157833616e-05, "loss": 1.5141247510910034, "step": 8145 }, { "epoch": 0.6876945643341811, "grad_norm": 0.1357421875, "learning_rate": 1.4065431752456937e-05, "loss": 1.53974449634552, "step": 8146 }, { "epoch": 0.6877789854690122, "grad_norm": 0.1474609375, "learning_rate": 1.4059578088470265e-05, "loss": 1.5958091020584106, "step": 8147 }, { "epoch": 0.6878634066038433, "grad_norm": 0.14453125, "learning_rate": 1.4053725166270498e-05, "loss": 1.5768002271652222, "step": 8148 }, { "epoch": 0.6879478277386744, "grad_norm": 0.134765625, "learning_rate": 1.4047872986254474e-05, "loss": 1.5164417028427124, "step": 8149 }, { "epoch": 0.6880322488735054, "grad_norm": 0.1318359375, "learning_rate": 1.4042021548818999e-05, "loss": 1.5444488525390625, "step": 8150 }, { "epoch": 0.6881166700083365, "grad_norm": 0.134765625, "learning_rate": 1.4036170854360781e-05, "loss": 1.4904460906982422, "step": 8151 }, { "epoch": 0.6882010911431677, "grad_norm": 0.13671875, "learning_rate": 1.4030320903276553e-05, "loss": 1.5287684202194214, "step": 8152 }, { "epoch": 0.6882855122779988, "grad_norm": 0.1396484375, "learning_rate": 1.4024471695962927e-05, "loss": 1.4562681913375854, "step": 8153 }, { "epoch": 0.6883699334128299, "grad_norm": 0.130859375, "learning_rate": 1.40186232328165e-05, "loss": 1.5551762580871582, "step": 8154 }, { "epoch": 0.688454354547661, "grad_norm": 0.1416015625, "learning_rate": 1.4012775514233815e-05, "loss": 1.497353196144104, "step": 8155 }, { "epoch": 0.6885387756824921, "grad_norm": 0.1357421875, "learning_rate": 1.4006928540611358e-05, "loss": 1.481075644493103, "step": 8156 }, { "epoch": 0.6886231968173232, "grad_norm": 0.138671875, "learning_rate": 1.400108231234558e-05, "loss": 1.5812335014343262, "step": 8157 }, { "epoch": 0.6887076179521543, "grad_norm": 0.140625, "learning_rate": 1.3995236829832842e-05, "loss": 1.5945215225219727, "step": 8158 }, { "epoch": 0.6887920390869854, "grad_norm": 0.1337890625, "learning_rate": 1.3989392093469505e-05, "loss": 1.5092785358428955, "step": 8159 }, { "epoch": 0.6888764602218165, "grad_norm": 0.142578125, "learning_rate": 1.3983548103651861e-05, "loss": 1.526222825050354, "step": 8160 }, { "epoch": 0.6889608813566477, "grad_norm": 0.1376953125, "learning_rate": 1.3977704860776127e-05, "loss": 1.4448081254959106, "step": 8161 }, { "epoch": 0.6890453024914788, "grad_norm": 0.1337890625, "learning_rate": 1.3971862365238498e-05, "loss": 1.5200504064559937, "step": 8162 }, { "epoch": 0.6891297236263099, "grad_norm": 0.140625, "learning_rate": 1.3966020617435108e-05, "loss": 1.5104825496673584, "step": 8163 }, { "epoch": 0.689214144761141, "grad_norm": 0.1376953125, "learning_rate": 1.3960179617762043e-05, "loss": 1.5454567670822144, "step": 8164 }, { "epoch": 0.689298565895972, "grad_norm": 0.13671875, "learning_rate": 1.3954339366615334e-05, "loss": 1.5314757823944092, "step": 8165 }, { "epoch": 0.6893829870308031, "grad_norm": 0.1298828125, "learning_rate": 1.3948499864390967e-05, "loss": 1.4658170938491821, "step": 8166 }, { "epoch": 0.6894674081656342, "grad_norm": 0.1337890625, "learning_rate": 1.3942661111484875e-05, "loss": 1.4738118648529053, "step": 8167 }, { "epoch": 0.6895518293004653, "grad_norm": 0.1455078125, "learning_rate": 1.3936823108292937e-05, "loss": 1.5731921195983887, "step": 8168 }, { "epoch": 0.6896362504352965, "grad_norm": 0.1435546875, "learning_rate": 1.3930985855210984e-05, "loss": 1.593960165977478, "step": 8169 }, { "epoch": 0.6897206715701276, "grad_norm": 0.1396484375, "learning_rate": 1.3925149352634809e-05, "loss": 1.5954313278198242, "step": 8170 }, { "epoch": 0.6898050927049587, "grad_norm": 0.130859375, "learning_rate": 1.3919313600960116e-05, "loss": 1.4578137397766113, "step": 8171 }, { "epoch": 0.6898895138397898, "grad_norm": 0.1328125, "learning_rate": 1.3913478600582585e-05, "loss": 1.537861943244934, "step": 8172 }, { "epoch": 0.6899739349746209, "grad_norm": 0.1494140625, "learning_rate": 1.3907644351897875e-05, "loss": 1.471575140953064, "step": 8173 }, { "epoch": 0.690058356109452, "grad_norm": 0.14453125, "learning_rate": 1.3901810855301527e-05, "loss": 1.5991190671920776, "step": 8174 }, { "epoch": 0.6901427772442831, "grad_norm": 0.134765625, "learning_rate": 1.3895978111189084e-05, "loss": 1.475020408630371, "step": 8175 }, { "epoch": 0.6902271983791142, "grad_norm": 0.1396484375, "learning_rate": 1.3890146119956015e-05, "loss": 1.5272657871246338, "step": 8176 }, { "epoch": 0.6903116195139453, "grad_norm": 0.140625, "learning_rate": 1.3884314881997742e-05, "loss": 1.5317587852478027, "step": 8177 }, { "epoch": 0.6903960406487765, "grad_norm": 0.126953125, "learning_rate": 1.387848439770964e-05, "loss": 1.4893862009048462, "step": 8178 }, { "epoch": 0.6904804617836076, "grad_norm": 0.1357421875, "learning_rate": 1.3872654667487029e-05, "loss": 1.5063047409057617, "step": 8179 }, { "epoch": 0.6905648829184386, "grad_norm": 0.1337890625, "learning_rate": 1.3866825691725175e-05, "loss": 1.5423141717910767, "step": 8180 }, { "epoch": 0.6906493040532697, "grad_norm": 0.130859375, "learning_rate": 1.386099747081931e-05, "loss": 1.4933226108551025, "step": 8181 }, { "epoch": 0.6907337251881008, "grad_norm": 0.1611328125, "learning_rate": 1.3855170005164572e-05, "loss": 1.4835890531539917, "step": 8182 }, { "epoch": 0.6908181463229319, "grad_norm": 0.1435546875, "learning_rate": 1.3849343295156117e-05, "loss": 1.5286102294921875, "step": 8183 }, { "epoch": 0.690902567457763, "grad_norm": 0.1513671875, "learning_rate": 1.384351734118898e-05, "loss": 1.5299180746078491, "step": 8184 }, { "epoch": 0.6909869885925941, "grad_norm": 0.1552734375, "learning_rate": 1.3837692143658182e-05, "loss": 1.5340250730514526, "step": 8185 }, { "epoch": 0.6910714097274253, "grad_norm": 0.1357421875, "learning_rate": 1.383186770295869e-05, "loss": 1.4698922634124756, "step": 8186 }, { "epoch": 0.6911558308622564, "grad_norm": 0.1298828125, "learning_rate": 1.382604401948541e-05, "loss": 1.5537787675857544, "step": 8187 }, { "epoch": 0.6912402519970875, "grad_norm": 0.1337890625, "learning_rate": 1.3820221093633212e-05, "loss": 1.5797619819641113, "step": 8188 }, { "epoch": 0.6913246731319186, "grad_norm": 0.1357421875, "learning_rate": 1.3814398925796881e-05, "loss": 1.4474254846572876, "step": 8189 }, { "epoch": 0.6914090942667497, "grad_norm": 0.1455078125, "learning_rate": 1.3808577516371196e-05, "loss": 1.6633193492889404, "step": 8190 }, { "epoch": 0.6914935154015808, "grad_norm": 0.1640625, "learning_rate": 1.3802756865750872e-05, "loss": 1.5991957187652588, "step": 8191 }, { "epoch": 0.6915779365364119, "grad_norm": 0.142578125, "learning_rate": 1.379693697433052e-05, "loss": 1.5344915390014648, "step": 8192 }, { "epoch": 0.691662357671243, "grad_norm": 0.146484375, "learning_rate": 1.3791117842504791e-05, "loss": 1.5854830741882324, "step": 8193 }, { "epoch": 0.691746778806074, "grad_norm": 0.1328125, "learning_rate": 1.3785299470668208e-05, "loss": 1.5306321382522583, "step": 8194 }, { "epoch": 0.6918311999409053, "grad_norm": 0.15234375, "learning_rate": 1.3779481859215277e-05, "loss": 1.5160562992095947, "step": 8195 }, { "epoch": 0.6919156210757363, "grad_norm": 0.13671875, "learning_rate": 1.3773665008540446e-05, "loss": 1.5636417865753174, "step": 8196 }, { "epoch": 0.6920000422105674, "grad_norm": 0.1337890625, "learning_rate": 1.3767848919038112e-05, "loss": 1.4782133102416992, "step": 8197 }, { "epoch": 0.6920844633453985, "grad_norm": 0.1337890625, "learning_rate": 1.3762033591102618e-05, "loss": 1.517022967338562, "step": 8198 }, { "epoch": 0.6921688844802296, "grad_norm": 0.140625, "learning_rate": 1.3756219025128262e-05, "loss": 1.51491117477417, "step": 8199 }, { "epoch": 0.6922533056150607, "grad_norm": 0.1396484375, "learning_rate": 1.375040522150928e-05, "loss": 1.5508959293365479, "step": 8200 }, { "epoch": 0.6923377267498918, "grad_norm": 0.1376953125, "learning_rate": 1.3744592180639876e-05, "loss": 1.5939195156097412, "step": 8201 }, { "epoch": 0.6924221478847229, "grad_norm": 0.1357421875, "learning_rate": 1.3738779902914164e-05, "loss": 1.4740309715270996, "step": 8202 }, { "epoch": 0.6925065690195541, "grad_norm": 0.1328125, "learning_rate": 1.3732968388726236e-05, "loss": 1.4872058629989624, "step": 8203 }, { "epoch": 0.6925909901543852, "grad_norm": 0.1494140625, "learning_rate": 1.3727157638470153e-05, "loss": 1.5428006649017334, "step": 8204 }, { "epoch": 0.6926754112892163, "grad_norm": 0.14453125, "learning_rate": 1.3721347652539868e-05, "loss": 1.560658574104309, "step": 8205 }, { "epoch": 0.6927598324240474, "grad_norm": 0.1337890625, "learning_rate": 1.3715538431329323e-05, "loss": 1.5366039276123047, "step": 8206 }, { "epoch": 0.6928442535588785, "grad_norm": 0.140625, "learning_rate": 1.3709729975232393e-05, "loss": 1.5825289487838745, "step": 8207 }, { "epoch": 0.6929286746937096, "grad_norm": 0.1435546875, "learning_rate": 1.3703922284642914e-05, "loss": 1.5397748947143555, "step": 8208 }, { "epoch": 0.6930130958285406, "grad_norm": 0.1484375, "learning_rate": 1.3698115359954655e-05, "loss": 1.4748023748397827, "step": 8209 }, { "epoch": 0.6930975169633717, "grad_norm": 0.1474609375, "learning_rate": 1.369230920156134e-05, "loss": 1.5189135074615479, "step": 8210 }, { "epoch": 0.6931819380982028, "grad_norm": 0.14453125, "learning_rate": 1.3686503809856651e-05, "loss": 1.5072180032730103, "step": 8211 }, { "epoch": 0.693266359233034, "grad_norm": 0.142578125, "learning_rate": 1.368069918523419e-05, "loss": 1.5326783657073975, "step": 8212 }, { "epoch": 0.6933507803678651, "grad_norm": 0.1455078125, "learning_rate": 1.3674895328087519e-05, "loss": 1.5574333667755127, "step": 8213 }, { "epoch": 0.6934352015026962, "grad_norm": 0.1416015625, "learning_rate": 1.3669092238810188e-05, "loss": 1.5503990650177002, "step": 8214 }, { "epoch": 0.6935196226375273, "grad_norm": 0.1611328125, "learning_rate": 1.366328991779563e-05, "loss": 1.6443530321121216, "step": 8215 }, { "epoch": 0.6936040437723584, "grad_norm": 0.13671875, "learning_rate": 1.3657488365437266e-05, "loss": 1.4961366653442383, "step": 8216 }, { "epoch": 0.6936884649071895, "grad_norm": 0.140625, "learning_rate": 1.3651687582128453e-05, "loss": 1.5599300861358643, "step": 8217 }, { "epoch": 0.6937728860420206, "grad_norm": 0.1435546875, "learning_rate": 1.36458875682625e-05, "loss": 1.493046522140503, "step": 8218 }, { "epoch": 0.6938573071768517, "grad_norm": 0.134765625, "learning_rate": 1.3640088324232658e-05, "loss": 1.5418771505355835, "step": 8219 }, { "epoch": 0.6939417283116829, "grad_norm": 0.13671875, "learning_rate": 1.3634289850432139e-05, "loss": 1.4791717529296875, "step": 8220 }, { "epoch": 0.694026149446514, "grad_norm": 0.1416015625, "learning_rate": 1.3628492147254086e-05, "loss": 1.5003771781921387, "step": 8221 }, { "epoch": 0.6941105705813451, "grad_norm": 0.142578125, "learning_rate": 1.3622695215091608e-05, "loss": 1.4657096862792969, "step": 8222 }, { "epoch": 0.6941949917161762, "grad_norm": 0.1357421875, "learning_rate": 1.3616899054337723e-05, "loss": 1.5327705144882202, "step": 8223 }, { "epoch": 0.6942794128510072, "grad_norm": 0.138671875, "learning_rate": 1.361110366538546e-05, "loss": 1.5272551774978638, "step": 8224 }, { "epoch": 0.6943638339858383, "grad_norm": 0.1328125, "learning_rate": 1.3605309048627741e-05, "loss": 1.5382966995239258, "step": 8225 }, { "epoch": 0.6944482551206694, "grad_norm": 0.1455078125, "learning_rate": 1.3599515204457453e-05, "loss": 1.5189344882965088, "step": 8226 }, { "epoch": 0.6945326762555005, "grad_norm": 0.1376953125, "learning_rate": 1.3593722133267434e-05, "loss": 1.5511271953582764, "step": 8227 }, { "epoch": 0.6946170973903316, "grad_norm": 0.1533203125, "learning_rate": 1.3587929835450475e-05, "loss": 1.4764606952667236, "step": 8228 }, { "epoch": 0.6947015185251628, "grad_norm": 0.142578125, "learning_rate": 1.3582138311399317e-05, "loss": 1.622572422027588, "step": 8229 }, { "epoch": 0.6947859396599939, "grad_norm": 0.1376953125, "learning_rate": 1.3576347561506602e-05, "loss": 1.4911810159683228, "step": 8230 }, { "epoch": 0.694870360794825, "grad_norm": 0.154296875, "learning_rate": 1.3570557586164995e-05, "loss": 1.492313027381897, "step": 8231 }, { "epoch": 0.6949547819296561, "grad_norm": 0.1337890625, "learning_rate": 1.3564768385767063e-05, "loss": 1.523831844329834, "step": 8232 }, { "epoch": 0.6950392030644872, "grad_norm": 0.1298828125, "learning_rate": 1.35589799607053e-05, "loss": 1.5738959312438965, "step": 8233 }, { "epoch": 0.6951236241993183, "grad_norm": 0.1337890625, "learning_rate": 1.3553192311372209e-05, "loss": 1.5153477191925049, "step": 8234 }, { "epoch": 0.6952080453341494, "grad_norm": 0.1455078125, "learning_rate": 1.3547405438160205e-05, "loss": 1.5100429058074951, "step": 8235 }, { "epoch": 0.6952924664689805, "grad_norm": 0.1591796875, "learning_rate": 1.3541619341461629e-05, "loss": 1.5519851446151733, "step": 8236 }, { "epoch": 0.6953768876038117, "grad_norm": 0.1318359375, "learning_rate": 1.3535834021668803e-05, "loss": 1.4956849813461304, "step": 8237 }, { "epoch": 0.6954613087386428, "grad_norm": 0.1455078125, "learning_rate": 1.353004947917399e-05, "loss": 1.4490267038345337, "step": 8238 }, { "epoch": 0.6955457298734739, "grad_norm": 0.1416015625, "learning_rate": 1.3524265714369388e-05, "loss": 1.5860220193862915, "step": 8239 }, { "epoch": 0.6956301510083049, "grad_norm": 0.12890625, "learning_rate": 1.3518482727647159e-05, "loss": 1.5351438522338867, "step": 8240 }, { "epoch": 0.695714572143136, "grad_norm": 0.14453125, "learning_rate": 1.3512700519399396e-05, "loss": 1.6401796340942383, "step": 8241 }, { "epoch": 0.6957989932779671, "grad_norm": 0.140625, "learning_rate": 1.3506919090018158e-05, "loss": 1.4858514070510864, "step": 8242 }, { "epoch": 0.6958834144127982, "grad_norm": 0.142578125, "learning_rate": 1.3501138439895425e-05, "loss": 1.5344486236572266, "step": 8243 }, { "epoch": 0.6959678355476293, "grad_norm": 0.134765625, "learning_rate": 1.3495358569423133e-05, "loss": 1.4555336236953735, "step": 8244 }, { "epoch": 0.6960522566824604, "grad_norm": 0.1435546875, "learning_rate": 1.3489579478993206e-05, "loss": 1.6271002292633057, "step": 8245 }, { "epoch": 0.6961366778172916, "grad_norm": 0.1337890625, "learning_rate": 1.3483801168997446e-05, "loss": 1.520617961883545, "step": 8246 }, { "epoch": 0.6962210989521227, "grad_norm": 0.1357421875, "learning_rate": 1.3478023639827636e-05, "loss": 1.5728093385696411, "step": 8247 }, { "epoch": 0.6963055200869538, "grad_norm": 0.134765625, "learning_rate": 1.3472246891875543e-05, "loss": 1.507028579711914, "step": 8248 }, { "epoch": 0.6963899412217849, "grad_norm": 0.1435546875, "learning_rate": 1.346647092553281e-05, "loss": 1.5353394746780396, "step": 8249 }, { "epoch": 0.696474362356616, "grad_norm": 0.140625, "learning_rate": 1.3460695741191065e-05, "loss": 1.5053460597991943, "step": 8250 }, { "epoch": 0.6965587834914471, "grad_norm": 0.1318359375, "learning_rate": 1.3454921339241889e-05, "loss": 1.489551067352295, "step": 8251 }, { "epoch": 0.6966432046262782, "grad_norm": 0.1337890625, "learning_rate": 1.34491477200768e-05, "loss": 1.495011806488037, "step": 8252 }, { "epoch": 0.6967276257611092, "grad_norm": 0.13671875, "learning_rate": 1.3443374884087267e-05, "loss": 1.5703151226043701, "step": 8253 }, { "epoch": 0.6968120468959405, "grad_norm": 0.1416015625, "learning_rate": 1.3437602831664675e-05, "loss": 1.5305312871932983, "step": 8254 }, { "epoch": 0.6968964680307715, "grad_norm": 0.140625, "learning_rate": 1.3431831563200425e-05, "loss": 1.4873521327972412, "step": 8255 }, { "epoch": 0.6969808891656026, "grad_norm": 0.138671875, "learning_rate": 1.342606107908579e-05, "loss": 1.500228762626648, "step": 8256 }, { "epoch": 0.6970653103004337, "grad_norm": 0.140625, "learning_rate": 1.3420291379712036e-05, "loss": 1.5726946592330933, "step": 8257 }, { "epoch": 0.6971497314352648, "grad_norm": 0.1396484375, "learning_rate": 1.3414522465470358e-05, "loss": 1.5575897693634033, "step": 8258 }, { "epoch": 0.6972341525700959, "grad_norm": 0.1455078125, "learning_rate": 1.3408754336751906e-05, "loss": 1.5464692115783691, "step": 8259 }, { "epoch": 0.697318573704927, "grad_norm": 0.1357421875, "learning_rate": 1.340298699394777e-05, "loss": 1.489687204360962, "step": 8260 }, { "epoch": 0.6974029948397581, "grad_norm": 0.142578125, "learning_rate": 1.3397220437448992e-05, "loss": 1.590878963470459, "step": 8261 }, { "epoch": 0.6974874159745892, "grad_norm": 0.1318359375, "learning_rate": 1.3391454667646558e-05, "loss": 1.5011945962905884, "step": 8262 }, { "epoch": 0.6975718371094204, "grad_norm": 0.14453125, "learning_rate": 1.338568968493141e-05, "loss": 1.512548804283142, "step": 8263 }, { "epoch": 0.6976562582442515, "grad_norm": 0.1376953125, "learning_rate": 1.3379925489694401e-05, "loss": 1.5058271884918213, "step": 8264 }, { "epoch": 0.6977406793790826, "grad_norm": 0.130859375, "learning_rate": 1.337416208232638e-05, "loss": 1.5297842025756836, "step": 8265 }, { "epoch": 0.6978251005139137, "grad_norm": 0.13671875, "learning_rate": 1.3368399463218129e-05, "loss": 1.511439561843872, "step": 8266 }, { "epoch": 0.6979095216487448, "grad_norm": 0.1376953125, "learning_rate": 1.3362637632760345e-05, "loss": 1.5151419639587402, "step": 8267 }, { "epoch": 0.6979939427835758, "grad_norm": 0.1455078125, "learning_rate": 1.3356876591343697e-05, "loss": 1.5329281091690063, "step": 8268 }, { "epoch": 0.6980783639184069, "grad_norm": 0.1494140625, "learning_rate": 1.3351116339358804e-05, "loss": 1.487395167350769, "step": 8269 }, { "epoch": 0.698162785053238, "grad_norm": 0.1279296875, "learning_rate": 1.3345356877196225e-05, "loss": 1.5092663764953613, "step": 8270 }, { "epoch": 0.6982472061880692, "grad_norm": 0.1337890625, "learning_rate": 1.3339598205246462e-05, "loss": 1.4900115728378296, "step": 8271 }, { "epoch": 0.6983316273229003, "grad_norm": 0.1416015625, "learning_rate": 1.3333840323899968e-05, "loss": 1.5471163988113403, "step": 8272 }, { "epoch": 0.6984160484577314, "grad_norm": 0.13671875, "learning_rate": 1.3328083233547154e-05, "loss": 1.5109221935272217, "step": 8273 }, { "epoch": 0.6985004695925625, "grad_norm": 0.1533203125, "learning_rate": 1.3322326934578333e-05, "loss": 1.445583462715149, "step": 8274 }, { "epoch": 0.6985848907273936, "grad_norm": 0.1328125, "learning_rate": 1.3316571427383822e-05, "loss": 1.4997429847717285, "step": 8275 }, { "epoch": 0.6986693118622247, "grad_norm": 0.1376953125, "learning_rate": 1.3310816712353863e-05, "loss": 1.6214308738708496, "step": 8276 }, { "epoch": 0.6987537329970558, "grad_norm": 0.134765625, "learning_rate": 1.330506278987862e-05, "loss": 1.4248908758163452, "step": 8277 }, { "epoch": 0.6988381541318869, "grad_norm": 0.1357421875, "learning_rate": 1.3299309660348227e-05, "loss": 1.5065604448318481, "step": 8278 }, { "epoch": 0.698922575266718, "grad_norm": 0.130859375, "learning_rate": 1.3293557324152766e-05, "loss": 1.4672374725341797, "step": 8279 }, { "epoch": 0.6990069964015492, "grad_norm": 0.1474609375, "learning_rate": 1.3287805781682255e-05, "loss": 1.6399834156036377, "step": 8280 }, { "epoch": 0.6990914175363803, "grad_norm": 0.15234375, "learning_rate": 1.3282055033326669e-05, "loss": 1.5360490083694458, "step": 8281 }, { "epoch": 0.6991758386712114, "grad_norm": 0.1435546875, "learning_rate": 1.3276305079475915e-05, "loss": 1.5271326303482056, "step": 8282 }, { "epoch": 0.6992602598060425, "grad_norm": 0.1376953125, "learning_rate": 1.3270555920519855e-05, "loss": 1.6043379306793213, "step": 8283 }, { "epoch": 0.6993446809408735, "grad_norm": 0.1376953125, "learning_rate": 1.326480755684831e-05, "loss": 1.4548041820526123, "step": 8284 }, { "epoch": 0.6994291020757046, "grad_norm": 0.1484375, "learning_rate": 1.3259059988851e-05, "loss": 1.5241819620132446, "step": 8285 }, { "epoch": 0.6995135232105357, "grad_norm": 0.138671875, "learning_rate": 1.3253313216917661e-05, "loss": 1.5170868635177612, "step": 8286 }, { "epoch": 0.6995979443453668, "grad_norm": 0.1376953125, "learning_rate": 1.3247567241437917e-05, "loss": 1.5253872871398926, "step": 8287 }, { "epoch": 0.699682365480198, "grad_norm": 0.150390625, "learning_rate": 1.3241822062801351e-05, "loss": 1.5529825687408447, "step": 8288 }, { "epoch": 0.6997667866150291, "grad_norm": 0.1416015625, "learning_rate": 1.323607768139753e-05, "loss": 1.5090612173080444, "step": 8289 }, { "epoch": 0.6998512077498602, "grad_norm": 0.1318359375, "learning_rate": 1.323033409761591e-05, "loss": 1.5186599493026733, "step": 8290 }, { "epoch": 0.6999356288846913, "grad_norm": 0.140625, "learning_rate": 1.322459131184593e-05, "loss": 1.5625038146972656, "step": 8291 }, { "epoch": 0.7000200500195224, "grad_norm": 0.13671875, "learning_rate": 1.3218849324476962e-05, "loss": 1.499509572982788, "step": 8292 }, { "epoch": 0.7001044711543535, "grad_norm": 0.1318359375, "learning_rate": 1.3213108135898328e-05, "loss": 1.4588103294372559, "step": 8293 }, { "epoch": 0.7001888922891846, "grad_norm": 0.14453125, "learning_rate": 1.3207367746499304e-05, "loss": 1.527014970779419, "step": 8294 }, { "epoch": 0.7002733134240157, "grad_norm": 0.1455078125, "learning_rate": 1.3201628156669075e-05, "loss": 1.57137930393219, "step": 8295 }, { "epoch": 0.7003577345588468, "grad_norm": 0.1416015625, "learning_rate": 1.3195889366796832e-05, "loss": 1.500783920288086, "step": 8296 }, { "epoch": 0.700442155693678, "grad_norm": 0.1484375, "learning_rate": 1.3190151377271658e-05, "loss": 1.5564943552017212, "step": 8297 }, { "epoch": 0.700526576828509, "grad_norm": 0.1513671875, "learning_rate": 1.3184414188482605e-05, "loss": 1.4540828466415405, "step": 8298 }, { "epoch": 0.7006109979633401, "grad_norm": 0.1455078125, "learning_rate": 1.3178677800818672e-05, "loss": 1.6414557695388794, "step": 8299 }, { "epoch": 0.7006954190981712, "grad_norm": 0.1435546875, "learning_rate": 1.3172942214668798e-05, "loss": 1.5281140804290771, "step": 8300 }, { "epoch": 0.7007798402330023, "grad_norm": 0.150390625, "learning_rate": 1.3167207430421871e-05, "loss": 1.5157761573791504, "step": 8301 }, { "epoch": 0.7008642613678334, "grad_norm": 0.140625, "learning_rate": 1.316147344846672e-05, "loss": 1.537501335144043, "step": 8302 }, { "epoch": 0.7009486825026645, "grad_norm": 0.14453125, "learning_rate": 1.3155740269192129e-05, "loss": 1.5799009799957275, "step": 8303 }, { "epoch": 0.7010331036374956, "grad_norm": 0.146484375, "learning_rate": 1.3150007892986826e-05, "loss": 1.5339219570159912, "step": 8304 }, { "epoch": 0.7011175247723268, "grad_norm": 0.1416015625, "learning_rate": 1.3144276320239454e-05, "loss": 1.5798349380493164, "step": 8305 }, { "epoch": 0.7012019459071579, "grad_norm": 0.138671875, "learning_rate": 1.3138545551338652e-05, "loss": 1.5140873193740845, "step": 8306 }, { "epoch": 0.701286367041989, "grad_norm": 0.1689453125, "learning_rate": 1.3132815586672983e-05, "loss": 1.6428762674331665, "step": 8307 }, { "epoch": 0.7013707881768201, "grad_norm": 0.1376953125, "learning_rate": 1.3127086426630933e-05, "loss": 1.5320370197296143, "step": 8308 }, { "epoch": 0.7014552093116512, "grad_norm": 0.1337890625, "learning_rate": 1.3121358071600962e-05, "loss": 1.4923148155212402, "step": 8309 }, { "epoch": 0.7015396304464823, "grad_norm": 0.1435546875, "learning_rate": 1.3115630521971468e-05, "loss": 1.4713839292526245, "step": 8310 }, { "epoch": 0.7016240515813134, "grad_norm": 0.1337890625, "learning_rate": 1.3109903778130786e-05, "loss": 1.5226936340332031, "step": 8311 }, { "epoch": 0.7017084727161444, "grad_norm": 0.14453125, "learning_rate": 1.3104177840467213e-05, "loss": 1.5449613332748413, "step": 8312 }, { "epoch": 0.7017928938509755, "grad_norm": 0.1396484375, "learning_rate": 1.3098452709368972e-05, "loss": 1.5150096416473389, "step": 8313 }, { "epoch": 0.7018773149858067, "grad_norm": 0.1357421875, "learning_rate": 1.3092728385224256e-05, "loss": 1.4858911037445068, "step": 8314 }, { "epoch": 0.7019617361206378, "grad_norm": 0.1337890625, "learning_rate": 1.308700486842116e-05, "loss": 1.4617133140563965, "step": 8315 }, { "epoch": 0.7020461572554689, "grad_norm": 0.1396484375, "learning_rate": 1.3081282159347774e-05, "loss": 1.4888213872909546, "step": 8316 }, { "epoch": 0.7021305783903, "grad_norm": 0.1455078125, "learning_rate": 1.307556025839212e-05, "loss": 1.5304492712020874, "step": 8317 }, { "epoch": 0.7022149995251311, "grad_norm": 0.1533203125, "learning_rate": 1.3069839165942133e-05, "loss": 1.575510025024414, "step": 8318 }, { "epoch": 0.7022994206599622, "grad_norm": 0.1455078125, "learning_rate": 1.3064118882385714e-05, "loss": 1.5433255434036255, "step": 8319 }, { "epoch": 0.7023838417947933, "grad_norm": 0.1337890625, "learning_rate": 1.3058399408110748e-05, "loss": 1.446934700012207, "step": 8320 }, { "epoch": 0.7024682629296244, "grad_norm": 0.15234375, "learning_rate": 1.3052680743504994e-05, "loss": 1.4802411794662476, "step": 8321 }, { "epoch": 0.7025526840644556, "grad_norm": 0.1396484375, "learning_rate": 1.3046962888956204e-05, "loss": 1.5340418815612793, "step": 8322 }, { "epoch": 0.7026371051992867, "grad_norm": 0.146484375, "learning_rate": 1.3041245844852062e-05, "loss": 1.5099509954452515, "step": 8323 }, { "epoch": 0.7027215263341178, "grad_norm": 0.1396484375, "learning_rate": 1.3035529611580194e-05, "loss": 1.4427127838134766, "step": 8324 }, { "epoch": 0.7028059474689489, "grad_norm": 0.1552734375, "learning_rate": 1.302981418952819e-05, "loss": 1.4294037818908691, "step": 8325 }, { "epoch": 0.70289036860378, "grad_norm": 0.1396484375, "learning_rate": 1.3024099579083538e-05, "loss": 1.4779127836227417, "step": 8326 }, { "epoch": 0.702974789738611, "grad_norm": 0.134765625, "learning_rate": 1.3018385780633734e-05, "loss": 1.4896044731140137, "step": 8327 }, { "epoch": 0.7030592108734421, "grad_norm": 0.14453125, "learning_rate": 1.3012672794566171e-05, "loss": 1.5764379501342773, "step": 8328 }, { "epoch": 0.7031436320082732, "grad_norm": 0.138671875, "learning_rate": 1.3006960621268194e-05, "loss": 1.4102634191513062, "step": 8329 }, { "epoch": 0.7032280531431043, "grad_norm": 0.1953125, "learning_rate": 1.3001249261127135e-05, "loss": 1.5151640176773071, "step": 8330 }, { "epoch": 0.7033124742779355, "grad_norm": 0.15625, "learning_rate": 1.2995538714530203e-05, "loss": 1.5870544910430908, "step": 8331 }, { "epoch": 0.7033968954127666, "grad_norm": 0.1552734375, "learning_rate": 1.2989828981864608e-05, "loss": 1.5073152780532837, "step": 8332 }, { "epoch": 0.7034813165475977, "grad_norm": 0.1396484375, "learning_rate": 1.2984120063517472e-05, "loss": 1.4865156412124634, "step": 8333 }, { "epoch": 0.7035657376824288, "grad_norm": 0.1328125, "learning_rate": 1.297841195987588e-05, "loss": 1.4451183080673218, "step": 8334 }, { "epoch": 0.7036501588172599, "grad_norm": 0.1484375, "learning_rate": 1.2972704671326863e-05, "loss": 1.6186504364013672, "step": 8335 }, { "epoch": 0.703734579952091, "grad_norm": 0.146484375, "learning_rate": 1.2966998198257358e-05, "loss": 1.486598014831543, "step": 8336 }, { "epoch": 0.7038190010869221, "grad_norm": 0.14453125, "learning_rate": 1.296129254105431e-05, "loss": 1.4911701679229736, "step": 8337 }, { "epoch": 0.7039034222217532, "grad_norm": 0.1416015625, "learning_rate": 1.295558770010457e-05, "loss": 1.529323935508728, "step": 8338 }, { "epoch": 0.7039878433565844, "grad_norm": 0.142578125, "learning_rate": 1.2949883675794933e-05, "loss": 1.5072749853134155, "step": 8339 }, { "epoch": 0.7040722644914155, "grad_norm": 0.140625, "learning_rate": 1.2944180468512144e-05, "loss": 1.5110112428665161, "step": 8340 }, { "epoch": 0.7041566856262466, "grad_norm": 0.1689453125, "learning_rate": 1.2938478078642896e-05, "loss": 1.525011420249939, "step": 8341 }, { "epoch": 0.7042411067610777, "grad_norm": 0.1357421875, "learning_rate": 1.293277650657383e-05, "loss": 1.484086513519287, "step": 8342 }, { "epoch": 0.7043255278959087, "grad_norm": 0.140625, "learning_rate": 1.2927075752691517e-05, "loss": 1.5617878437042236, "step": 8343 }, { "epoch": 0.7044099490307398, "grad_norm": 0.1416015625, "learning_rate": 1.2921375817382492e-05, "loss": 1.6004235744476318, "step": 8344 }, { "epoch": 0.7044943701655709, "grad_norm": 0.14453125, "learning_rate": 1.2915676701033227e-05, "loss": 1.5890207290649414, "step": 8345 }, { "epoch": 0.704578791300402, "grad_norm": 0.14453125, "learning_rate": 1.290997840403011e-05, "loss": 1.4129618406295776, "step": 8346 }, { "epoch": 0.7046632124352331, "grad_norm": 0.150390625, "learning_rate": 1.2904280926759527e-05, "loss": 1.4991669654846191, "step": 8347 }, { "epoch": 0.7047476335700643, "grad_norm": 0.1376953125, "learning_rate": 1.2898584269607783e-05, "loss": 1.4886671304702759, "step": 8348 }, { "epoch": 0.7048320547048954, "grad_norm": 0.1376953125, "learning_rate": 1.2892888432961103e-05, "loss": 1.5526796579360962, "step": 8349 }, { "epoch": 0.7049164758397265, "grad_norm": 0.1318359375, "learning_rate": 1.2887193417205678e-05, "loss": 1.4633681774139404, "step": 8350 }, { "epoch": 0.7050008969745576, "grad_norm": 0.142578125, "learning_rate": 1.2881499222727677e-05, "loss": 1.5320791006088257, "step": 8351 }, { "epoch": 0.7050853181093887, "grad_norm": 0.14453125, "learning_rate": 1.2875805849913144e-05, "loss": 1.50361168384552, "step": 8352 }, { "epoch": 0.7051697392442198, "grad_norm": 0.140625, "learning_rate": 1.287011329914812e-05, "loss": 1.5398799180984497, "step": 8353 }, { "epoch": 0.7052541603790509, "grad_norm": 0.1416015625, "learning_rate": 1.2864421570818569e-05, "loss": 1.5541125535964966, "step": 8354 }, { "epoch": 0.705338581513882, "grad_norm": 0.140625, "learning_rate": 1.2858730665310409e-05, "loss": 1.5480231046676636, "step": 8355 }, { "epoch": 0.7054230026487132, "grad_norm": 0.1435546875, "learning_rate": 1.2853040583009491e-05, "loss": 1.5661845207214355, "step": 8356 }, { "epoch": 0.7055074237835443, "grad_norm": 0.142578125, "learning_rate": 1.2847351324301618e-05, "loss": 1.5727136135101318, "step": 8357 }, { "epoch": 0.7055918449183753, "grad_norm": 0.1416015625, "learning_rate": 1.2841662889572548e-05, "loss": 1.528531789779663, "step": 8358 }, { "epoch": 0.7056762660532064, "grad_norm": 0.142578125, "learning_rate": 1.2835975279207945e-05, "loss": 1.5105775594711304, "step": 8359 }, { "epoch": 0.7057606871880375, "grad_norm": 0.1357421875, "learning_rate": 1.2830288493593451e-05, "loss": 1.5080851316452026, "step": 8360 }, { "epoch": 0.7058451083228686, "grad_norm": 0.1279296875, "learning_rate": 1.2824602533114668e-05, "loss": 1.5003612041473389, "step": 8361 }, { "epoch": 0.7059295294576997, "grad_norm": 0.1376953125, "learning_rate": 1.281891739815709e-05, "loss": 1.5711907148361206, "step": 8362 }, { "epoch": 0.7060139505925308, "grad_norm": 0.1513671875, "learning_rate": 1.2813233089106192e-05, "loss": 1.547710657119751, "step": 8363 }, { "epoch": 0.7060983717273619, "grad_norm": 0.1318359375, "learning_rate": 1.280754960634738e-05, "loss": 1.5117806196212769, "step": 8364 }, { "epoch": 0.7061827928621931, "grad_norm": 0.1396484375, "learning_rate": 1.2801866950266017e-05, "loss": 1.4955614805221558, "step": 8365 }, { "epoch": 0.7062672139970242, "grad_norm": 0.138671875, "learning_rate": 1.27961851212474e-05, "loss": 1.5509538650512695, "step": 8366 }, { "epoch": 0.7063516351318553, "grad_norm": 0.1357421875, "learning_rate": 1.279050411967675e-05, "loss": 1.4899636507034302, "step": 8367 }, { "epoch": 0.7064360562666864, "grad_norm": 0.138671875, "learning_rate": 1.2784823945939275e-05, "loss": 1.5918605327606201, "step": 8368 }, { "epoch": 0.7065204774015175, "grad_norm": 0.140625, "learning_rate": 1.2779144600420112e-05, "loss": 1.5021260976791382, "step": 8369 }, { "epoch": 0.7066048985363486, "grad_norm": 0.1474609375, "learning_rate": 1.2773466083504295e-05, "loss": 1.5176444053649902, "step": 8370 }, { "epoch": 0.7066893196711796, "grad_norm": 0.1494140625, "learning_rate": 1.276778839557689e-05, "loss": 1.5613254308700562, "step": 8371 }, { "epoch": 0.7067737408060107, "grad_norm": 0.140625, "learning_rate": 1.2762111537022825e-05, "loss": 1.5049042701721191, "step": 8372 }, { "epoch": 0.706858161940842, "grad_norm": 0.1396484375, "learning_rate": 1.275643550822701e-05, "loss": 1.5081813335418701, "step": 8373 }, { "epoch": 0.706942583075673, "grad_norm": 0.1455078125, "learning_rate": 1.27507603095743e-05, "loss": 1.5561089515686035, "step": 8374 }, { "epoch": 0.7070270042105041, "grad_norm": 0.1455078125, "learning_rate": 1.2745085941449484e-05, "loss": 1.6213425397872925, "step": 8375 }, { "epoch": 0.7071114253453352, "grad_norm": 0.1416015625, "learning_rate": 1.2739412404237306e-05, "loss": 1.519821047782898, "step": 8376 }, { "epoch": 0.7071958464801663, "grad_norm": 0.1328125, "learning_rate": 1.273373969832242e-05, "loss": 1.4865479469299316, "step": 8377 }, { "epoch": 0.7072802676149974, "grad_norm": 0.1435546875, "learning_rate": 1.2728067824089473e-05, "loss": 1.4508332014083862, "step": 8378 }, { "epoch": 0.7073646887498285, "grad_norm": 0.138671875, "learning_rate": 1.272239678192304e-05, "loss": 1.5629451274871826, "step": 8379 }, { "epoch": 0.7074491098846596, "grad_norm": 0.13671875, "learning_rate": 1.2716726572207604e-05, "loss": 1.5035375356674194, "step": 8380 }, { "epoch": 0.7075335310194907, "grad_norm": 0.1337890625, "learning_rate": 1.2711057195327632e-05, "loss": 1.4621037244796753, "step": 8381 }, { "epoch": 0.7076179521543219, "grad_norm": 0.1435546875, "learning_rate": 1.2705388651667521e-05, "loss": 1.5533020496368408, "step": 8382 }, { "epoch": 0.707702373289153, "grad_norm": 0.146484375, "learning_rate": 1.2699720941611616e-05, "loss": 1.5738688707351685, "step": 8383 }, { "epoch": 0.7077867944239841, "grad_norm": 0.134765625, "learning_rate": 1.2694054065544192e-05, "loss": 1.4723379611968994, "step": 8384 }, { "epoch": 0.7078712155588152, "grad_norm": 0.1396484375, "learning_rate": 1.2688388023849482e-05, "loss": 1.5394972562789917, "step": 8385 }, { "epoch": 0.7079556366936463, "grad_norm": 0.13671875, "learning_rate": 1.2682722816911658e-05, "loss": 1.5065317153930664, "step": 8386 }, { "epoch": 0.7080400578284773, "grad_norm": 0.140625, "learning_rate": 1.2677058445114834e-05, "loss": 1.5870907306671143, "step": 8387 }, { "epoch": 0.7081244789633084, "grad_norm": 0.1357421875, "learning_rate": 1.2671394908843068e-05, "loss": 1.5448925495147705, "step": 8388 }, { "epoch": 0.7082089000981395, "grad_norm": 0.1435546875, "learning_rate": 1.266573220848037e-05, "loss": 1.5335952043533325, "step": 8389 }, { "epoch": 0.7082933212329707, "grad_norm": 0.150390625, "learning_rate": 1.2660070344410668e-05, "loss": 1.5417914390563965, "step": 8390 }, { "epoch": 0.7083777423678018, "grad_norm": 0.1328125, "learning_rate": 1.2654409317017845e-05, "loss": 1.5604208707809448, "step": 8391 }, { "epoch": 0.7084621635026329, "grad_norm": 0.1318359375, "learning_rate": 1.2648749126685772e-05, "loss": 1.5293422937393188, "step": 8392 }, { "epoch": 0.708546584637464, "grad_norm": 0.140625, "learning_rate": 1.2643089773798178e-05, "loss": 1.481387972831726, "step": 8393 }, { "epoch": 0.7086310057722951, "grad_norm": 0.146484375, "learning_rate": 1.2637431258738804e-05, "loss": 1.5668823719024658, "step": 8394 }, { "epoch": 0.7087154269071262, "grad_norm": 0.13671875, "learning_rate": 1.2631773581891307e-05, "loss": 1.5705807209014893, "step": 8395 }, { "epoch": 0.7087998480419573, "grad_norm": 0.1728515625, "learning_rate": 1.2626116743639288e-05, "loss": 1.5148768424987793, "step": 8396 }, { "epoch": 0.7088842691767884, "grad_norm": 0.1474609375, "learning_rate": 1.2620460744366307e-05, "loss": 1.5824990272521973, "step": 8397 }, { "epoch": 0.7089686903116195, "grad_norm": 0.1376953125, "learning_rate": 1.2614805584455827e-05, "loss": 1.5309826135635376, "step": 8398 }, { "epoch": 0.7090531114464507, "grad_norm": 0.134765625, "learning_rate": 1.2609151264291307e-05, "loss": 1.5239115953445435, "step": 8399 }, { "epoch": 0.7091375325812818, "grad_norm": 0.146484375, "learning_rate": 1.2603497784256124e-05, "loss": 1.5780829191207886, "step": 8400 }, { "epoch": 0.7092219537161129, "grad_norm": 0.134765625, "learning_rate": 1.259784514473357e-05, "loss": 1.542925477027893, "step": 8401 }, { "epoch": 0.7093063748509439, "grad_norm": 0.1318359375, "learning_rate": 1.2592193346106946e-05, "loss": 1.4252934455871582, "step": 8402 }, { "epoch": 0.709390795985775, "grad_norm": 0.134765625, "learning_rate": 1.2586542388759426e-05, "loss": 1.498319387435913, "step": 8403 }, { "epoch": 0.7094752171206061, "grad_norm": 0.1435546875, "learning_rate": 1.2580892273074169e-05, "loss": 1.5141173601150513, "step": 8404 }, { "epoch": 0.7095596382554372, "grad_norm": 0.13671875, "learning_rate": 1.2575242999434267e-05, "loss": 1.452695608139038, "step": 8405 }, { "epoch": 0.7096440593902683, "grad_norm": 0.1416015625, "learning_rate": 1.2569594568222758e-05, "loss": 1.5921533107757568, "step": 8406 }, { "epoch": 0.7097284805250994, "grad_norm": 0.13671875, "learning_rate": 1.2563946979822625e-05, "loss": 1.5653594732284546, "step": 8407 }, { "epoch": 0.7098129016599306, "grad_norm": 0.1591796875, "learning_rate": 1.255830023461676e-05, "loss": 1.5589522123336792, "step": 8408 }, { "epoch": 0.7098973227947617, "grad_norm": 0.140625, "learning_rate": 1.2552654332988054e-05, "loss": 1.5503817796707153, "step": 8409 }, { "epoch": 0.7099817439295928, "grad_norm": 0.1318359375, "learning_rate": 1.2547009275319313e-05, "loss": 1.4823943376541138, "step": 8410 }, { "epoch": 0.7100661650644239, "grad_norm": 0.1474609375, "learning_rate": 1.2541365061993265e-05, "loss": 1.505613088607788, "step": 8411 }, { "epoch": 0.710150586199255, "grad_norm": 0.1455078125, "learning_rate": 1.2535721693392616e-05, "loss": 1.5664188861846924, "step": 8412 }, { "epoch": 0.7102350073340861, "grad_norm": 0.1357421875, "learning_rate": 1.2530079169899994e-05, "loss": 1.5200750827789307, "step": 8413 }, { "epoch": 0.7103194284689172, "grad_norm": 0.1435546875, "learning_rate": 1.2524437491897978e-05, "loss": 1.5777616500854492, "step": 8414 }, { "epoch": 0.7104038496037482, "grad_norm": 0.1396484375, "learning_rate": 1.2518796659769089e-05, "loss": 1.5438679456710815, "step": 8415 }, { "epoch": 0.7104882707385795, "grad_norm": 0.140625, "learning_rate": 1.2513156673895788e-05, "loss": 1.5647876262664795, "step": 8416 }, { "epoch": 0.7105726918734105, "grad_norm": 0.142578125, "learning_rate": 1.2507517534660476e-05, "loss": 1.5371376276016235, "step": 8417 }, { "epoch": 0.7106571130082416, "grad_norm": 0.1494140625, "learning_rate": 1.2501879242445506e-05, "loss": 1.5952496528625488, "step": 8418 }, { "epoch": 0.7107415341430727, "grad_norm": 0.1572265625, "learning_rate": 1.2496241797633162e-05, "loss": 1.5843923091888428, "step": 8419 }, { "epoch": 0.7108259552779038, "grad_norm": 0.1357421875, "learning_rate": 1.249060520060569e-05, "loss": 1.5564498901367188, "step": 8420 }, { "epoch": 0.7109103764127349, "grad_norm": 0.134765625, "learning_rate": 1.2484969451745246e-05, "loss": 1.4735853672027588, "step": 8421 }, { "epoch": 0.710994797547566, "grad_norm": 0.1435546875, "learning_rate": 1.2479334551433943e-05, "loss": 1.5586339235305786, "step": 8422 }, { "epoch": 0.7110792186823971, "grad_norm": 0.142578125, "learning_rate": 1.2473700500053873e-05, "loss": 1.5094313621520996, "step": 8423 }, { "epoch": 0.7111636398172282, "grad_norm": 0.1337890625, "learning_rate": 1.246806729798701e-05, "loss": 1.507523775100708, "step": 8424 }, { "epoch": 0.7112480609520594, "grad_norm": 0.138671875, "learning_rate": 1.2462434945615306e-05, "loss": 1.5120275020599365, "step": 8425 }, { "epoch": 0.7113324820868905, "grad_norm": 0.1357421875, "learning_rate": 1.245680344332065e-05, "loss": 1.5547983646392822, "step": 8426 }, { "epoch": 0.7114169032217216, "grad_norm": 0.140625, "learning_rate": 1.245117279148487e-05, "loss": 1.5454336404800415, "step": 8427 }, { "epoch": 0.7115013243565527, "grad_norm": 0.138671875, "learning_rate": 1.2445542990489737e-05, "loss": 1.5146708488464355, "step": 8428 }, { "epoch": 0.7115857454913838, "grad_norm": 0.1396484375, "learning_rate": 1.2439914040716968e-05, "loss": 1.4841265678405762, "step": 8429 }, { "epoch": 0.7116701666262149, "grad_norm": 0.14453125, "learning_rate": 1.2434285942548227e-05, "loss": 1.523374319076538, "step": 8430 }, { "epoch": 0.7117545877610459, "grad_norm": 0.1416015625, "learning_rate": 1.2428658696365092e-05, "loss": 1.5727028846740723, "step": 8431 }, { "epoch": 0.711839008895877, "grad_norm": 0.142578125, "learning_rate": 1.2423032302549107e-05, "loss": 1.5880602598190308, "step": 8432 }, { "epoch": 0.7119234300307082, "grad_norm": 0.13671875, "learning_rate": 1.2417406761481782e-05, "loss": 1.531098484992981, "step": 8433 }, { "epoch": 0.7120078511655393, "grad_norm": 0.142578125, "learning_rate": 1.2411782073544511e-05, "loss": 1.533236026763916, "step": 8434 }, { "epoch": 0.7120922723003704, "grad_norm": 0.1484375, "learning_rate": 1.2406158239118677e-05, "loss": 1.569282054901123, "step": 8435 }, { "epoch": 0.7121766934352015, "grad_norm": 0.1298828125, "learning_rate": 1.2400535258585583e-05, "loss": 1.499674916267395, "step": 8436 }, { "epoch": 0.7122611145700326, "grad_norm": 0.1337890625, "learning_rate": 1.2394913132326485e-05, "loss": 1.5295953750610352, "step": 8437 }, { "epoch": 0.7123455357048637, "grad_norm": 0.1396484375, "learning_rate": 1.2389291860722584e-05, "loss": 1.5190691947937012, "step": 8438 }, { "epoch": 0.7124299568396948, "grad_norm": 0.1591796875, "learning_rate": 1.2383671444154987e-05, "loss": 1.523908019065857, "step": 8439 }, { "epoch": 0.7125143779745259, "grad_norm": 0.1318359375, "learning_rate": 1.2378051883004804e-05, "loss": 1.4762907028198242, "step": 8440 }, { "epoch": 0.712598799109357, "grad_norm": 0.1416015625, "learning_rate": 1.237243317765305e-05, "loss": 1.4773445129394531, "step": 8441 }, { "epoch": 0.7126832202441882, "grad_norm": 0.1591796875, "learning_rate": 1.2366815328480664e-05, "loss": 1.5824776887893677, "step": 8442 }, { "epoch": 0.7127676413790193, "grad_norm": 0.1455078125, "learning_rate": 1.236119833586858e-05, "loss": 1.5837982892990112, "step": 8443 }, { "epoch": 0.7128520625138504, "grad_norm": 0.138671875, "learning_rate": 1.235558220019762e-05, "loss": 1.5297355651855469, "step": 8444 }, { "epoch": 0.7129364836486815, "grad_norm": 0.146484375, "learning_rate": 1.234996692184858e-05, "loss": 1.53506338596344, "step": 8445 }, { "epoch": 0.7130209047835125, "grad_norm": 0.13671875, "learning_rate": 1.2344352501202189e-05, "loss": 1.5052205324172974, "step": 8446 }, { "epoch": 0.7131053259183436, "grad_norm": 0.1376953125, "learning_rate": 1.2338738938639118e-05, "loss": 1.5487738847732544, "step": 8447 }, { "epoch": 0.7131897470531747, "grad_norm": 0.138671875, "learning_rate": 1.2333126234539991e-05, "loss": 1.4958436489105225, "step": 8448 }, { "epoch": 0.7132741681880058, "grad_norm": 0.1357421875, "learning_rate": 1.2327514389285336e-05, "loss": 1.5040249824523926, "step": 8449 }, { "epoch": 0.713358589322837, "grad_norm": 0.1572265625, "learning_rate": 1.2321903403255672e-05, "loss": 1.4820789098739624, "step": 8450 }, { "epoch": 0.7134430104576681, "grad_norm": 0.1396484375, "learning_rate": 1.2316293276831441e-05, "loss": 1.5062447786331177, "step": 8451 }, { "epoch": 0.7135274315924992, "grad_norm": 0.1455078125, "learning_rate": 1.2310684010393006e-05, "loss": 1.5260546207427979, "step": 8452 }, { "epoch": 0.7136118527273303, "grad_norm": 0.1474609375, "learning_rate": 1.2305075604320684e-05, "loss": 1.5451831817626953, "step": 8453 }, { "epoch": 0.7136962738621614, "grad_norm": 0.1396484375, "learning_rate": 1.2299468058994773e-05, "loss": 1.559049367904663, "step": 8454 }, { "epoch": 0.7137806949969925, "grad_norm": 0.1396484375, "learning_rate": 1.2293861374795443e-05, "loss": 1.5731472969055176, "step": 8455 }, { "epoch": 0.7138651161318236, "grad_norm": 0.1416015625, "learning_rate": 1.2288255552102857e-05, "loss": 1.5270428657531738, "step": 8456 }, { "epoch": 0.7139495372666547, "grad_norm": 0.1376953125, "learning_rate": 1.2282650591297095e-05, "loss": 1.562311053276062, "step": 8457 }, { "epoch": 0.7140339584014858, "grad_norm": 0.150390625, "learning_rate": 1.2277046492758195e-05, "loss": 1.6112149953842163, "step": 8458 }, { "epoch": 0.714118379536317, "grad_norm": 0.13671875, "learning_rate": 1.2271443256866123e-05, "loss": 1.47031569480896, "step": 8459 }, { "epoch": 0.714202800671148, "grad_norm": 0.1396484375, "learning_rate": 1.2265840884000792e-05, "loss": 1.526318907737732, "step": 8460 }, { "epoch": 0.7142872218059791, "grad_norm": 0.146484375, "learning_rate": 1.226023937454207e-05, "loss": 1.5274345874786377, "step": 8461 }, { "epoch": 0.7143716429408102, "grad_norm": 0.140625, "learning_rate": 1.2254638728869734e-05, "loss": 1.4435979127883911, "step": 8462 }, { "epoch": 0.7144560640756413, "grad_norm": 0.1376953125, "learning_rate": 1.2249038947363513e-05, "loss": 1.5325469970703125, "step": 8463 }, { "epoch": 0.7145404852104724, "grad_norm": 0.138671875, "learning_rate": 1.2243440030403123e-05, "loss": 1.5295443534851074, "step": 8464 }, { "epoch": 0.7146249063453035, "grad_norm": 0.138671875, "learning_rate": 1.223784197836815e-05, "loss": 1.4762310981750488, "step": 8465 }, { "epoch": 0.7147093274801346, "grad_norm": 0.14453125, "learning_rate": 1.223224479163817e-05, "loss": 1.5841083526611328, "step": 8466 }, { "epoch": 0.7147937486149658, "grad_norm": 0.142578125, "learning_rate": 1.222664847059268e-05, "loss": 1.5966929197311401, "step": 8467 }, { "epoch": 0.7148781697497969, "grad_norm": 0.142578125, "learning_rate": 1.2221053015611128e-05, "loss": 1.611396312713623, "step": 8468 }, { "epoch": 0.714962590884628, "grad_norm": 0.1298828125, "learning_rate": 1.2215458427072898e-05, "loss": 1.4982752799987793, "step": 8469 }, { "epoch": 0.7150470120194591, "grad_norm": 0.1435546875, "learning_rate": 1.2209864705357315e-05, "loss": 1.5551018714904785, "step": 8470 }, { "epoch": 0.7151314331542902, "grad_norm": 0.1669921875, "learning_rate": 1.2204271850843652e-05, "loss": 1.4922442436218262, "step": 8471 }, { "epoch": 0.7152158542891213, "grad_norm": 0.134765625, "learning_rate": 1.2198679863911119e-05, "loss": 1.423919439315796, "step": 8472 }, { "epoch": 0.7153002754239524, "grad_norm": 0.130859375, "learning_rate": 1.2193088744938847e-05, "loss": 1.4756311178207397, "step": 8473 }, { "epoch": 0.7153846965587835, "grad_norm": 0.1484375, "learning_rate": 1.2187498494305957e-05, "loss": 1.5506739616394043, "step": 8474 }, { "epoch": 0.7154691176936145, "grad_norm": 0.1357421875, "learning_rate": 1.2181909112391459e-05, "loss": 1.5541611909866333, "step": 8475 }, { "epoch": 0.7155535388284457, "grad_norm": 0.140625, "learning_rate": 1.2176320599574334e-05, "loss": 1.5319156646728516, "step": 8476 }, { "epoch": 0.7156379599632768, "grad_norm": 0.15234375, "learning_rate": 1.2170732956233496e-05, "loss": 1.5975143909454346, "step": 8477 }, { "epoch": 0.7157223810981079, "grad_norm": 0.1435546875, "learning_rate": 1.2165146182747803e-05, "loss": 1.5173146724700928, "step": 8478 }, { "epoch": 0.715806802232939, "grad_norm": 0.146484375, "learning_rate": 1.2159560279496058e-05, "loss": 1.5699388980865479, "step": 8479 }, { "epoch": 0.7158912233677701, "grad_norm": 0.1435546875, "learning_rate": 1.2153975246856969e-05, "loss": 1.519992709159851, "step": 8480 }, { "epoch": 0.7159756445026012, "grad_norm": 0.1337890625, "learning_rate": 1.2148391085209249e-05, "loss": 1.5148389339447021, "step": 8481 }, { "epoch": 0.7160600656374323, "grad_norm": 0.138671875, "learning_rate": 1.2142807794931513e-05, "loss": 1.5453593730926514, "step": 8482 }, { "epoch": 0.7161444867722634, "grad_norm": 0.1435546875, "learning_rate": 1.2137225376402292e-05, "loss": 1.4803739786148071, "step": 8483 }, { "epoch": 0.7162289079070946, "grad_norm": 0.1650390625, "learning_rate": 1.213164383000012e-05, "loss": 1.5454515218734741, "step": 8484 }, { "epoch": 0.7163133290419257, "grad_norm": 0.1435546875, "learning_rate": 1.2126063156103437e-05, "loss": 1.4959073066711426, "step": 8485 }, { "epoch": 0.7163977501767568, "grad_norm": 0.1337890625, "learning_rate": 1.2120483355090606e-05, "loss": 1.4899789094924927, "step": 8486 }, { "epoch": 0.7164821713115879, "grad_norm": 0.1337890625, "learning_rate": 1.2114904427339966e-05, "loss": 1.5061589479446411, "step": 8487 }, { "epoch": 0.716566592446419, "grad_norm": 0.130859375, "learning_rate": 1.2109326373229773e-05, "loss": 1.504937767982483, "step": 8488 }, { "epoch": 0.71665101358125, "grad_norm": 0.1474609375, "learning_rate": 1.210374919313824e-05, "loss": 1.550481915473938, "step": 8489 }, { "epoch": 0.7167354347160811, "grad_norm": 0.1318359375, "learning_rate": 1.2098172887443507e-05, "loss": 1.502666711807251, "step": 8490 }, { "epoch": 0.7168198558509122, "grad_norm": 0.1513671875, "learning_rate": 1.2092597456523666e-05, "loss": 1.5770835876464844, "step": 8491 }, { "epoch": 0.7169042769857433, "grad_norm": 0.140625, "learning_rate": 1.2087022900756754e-05, "loss": 1.547672986984253, "step": 8492 }, { "epoch": 0.7169886981205745, "grad_norm": 0.1376953125, "learning_rate": 1.2081449220520716e-05, "loss": 1.4705040454864502, "step": 8493 }, { "epoch": 0.7170731192554056, "grad_norm": 0.140625, "learning_rate": 1.2075876416193462e-05, "loss": 1.435758352279663, "step": 8494 }, { "epoch": 0.7171575403902367, "grad_norm": 0.13671875, "learning_rate": 1.2070304488152875e-05, "loss": 1.5008267164230347, "step": 8495 }, { "epoch": 0.7172419615250678, "grad_norm": 0.1337890625, "learning_rate": 1.2064733436776712e-05, "loss": 1.5511603355407715, "step": 8496 }, { "epoch": 0.7173263826598989, "grad_norm": 0.142578125, "learning_rate": 1.2059163262442713e-05, "loss": 1.5462493896484375, "step": 8497 }, { "epoch": 0.71741080379473, "grad_norm": 0.1357421875, "learning_rate": 1.2053593965528554e-05, "loss": 1.534691333770752, "step": 8498 }, { "epoch": 0.7174952249295611, "grad_norm": 0.14453125, "learning_rate": 1.2048025546411839e-05, "loss": 1.477545142173767, "step": 8499 }, { "epoch": 0.7175796460643922, "grad_norm": 0.134765625, "learning_rate": 1.2042458005470127e-05, "loss": 1.5114320516586304, "step": 8500 }, { "epoch": 0.7176640671992234, "grad_norm": 0.140625, "learning_rate": 1.2036891343080909e-05, "loss": 1.5453722476959229, "step": 8501 }, { "epoch": 0.7177484883340545, "grad_norm": 0.15234375, "learning_rate": 1.2031325559621615e-05, "loss": 1.5012949705123901, "step": 8502 }, { "epoch": 0.7178329094688856, "grad_norm": 0.1396484375, "learning_rate": 1.202576065546963e-05, "loss": 1.5890321731567383, "step": 8503 }, { "epoch": 0.7179173306037167, "grad_norm": 0.140625, "learning_rate": 1.202019663100224e-05, "loss": 1.5065819025039673, "step": 8504 }, { "epoch": 0.7180017517385477, "grad_norm": 0.13671875, "learning_rate": 1.2014633486596735e-05, "loss": 1.5576354265213013, "step": 8505 }, { "epoch": 0.7180861728733788, "grad_norm": 0.1337890625, "learning_rate": 1.2009071222630286e-05, "loss": 1.5156645774841309, "step": 8506 }, { "epoch": 0.7181705940082099, "grad_norm": 0.140625, "learning_rate": 1.2003509839480032e-05, "loss": 1.5836557149887085, "step": 8507 }, { "epoch": 0.718255015143041, "grad_norm": 0.1328125, "learning_rate": 1.1997949337523051e-05, "loss": 1.5328818559646606, "step": 8508 }, { "epoch": 0.7183394362778721, "grad_norm": 0.142578125, "learning_rate": 1.1992389717136358e-05, "loss": 1.605791687965393, "step": 8509 }, { "epoch": 0.7184238574127033, "grad_norm": 0.1337890625, "learning_rate": 1.1986830978696908e-05, "loss": 1.5101224184036255, "step": 8510 }, { "epoch": 0.7185082785475344, "grad_norm": 0.13671875, "learning_rate": 1.19812731225816e-05, "loss": 1.512934923171997, "step": 8511 }, { "epoch": 0.7185926996823655, "grad_norm": 0.1328125, "learning_rate": 1.1975716149167262e-05, "loss": 1.4881958961486816, "step": 8512 }, { "epoch": 0.7186771208171966, "grad_norm": 0.1376953125, "learning_rate": 1.1970160058830687e-05, "loss": 1.5259761810302734, "step": 8513 }, { "epoch": 0.7187615419520277, "grad_norm": 0.1328125, "learning_rate": 1.1964604851948564e-05, "loss": 1.4964406490325928, "step": 8514 }, { "epoch": 0.7188459630868588, "grad_norm": 0.140625, "learning_rate": 1.1959050528897578e-05, "loss": 1.5107815265655518, "step": 8515 }, { "epoch": 0.7189303842216899, "grad_norm": 0.1435546875, "learning_rate": 1.1953497090054309e-05, "loss": 1.610369086265564, "step": 8516 }, { "epoch": 0.719014805356521, "grad_norm": 0.1435546875, "learning_rate": 1.1947944535795292e-05, "loss": 1.5722671747207642, "step": 8517 }, { "epoch": 0.7190992264913522, "grad_norm": 0.1376953125, "learning_rate": 1.194239286649701e-05, "loss": 1.4760146141052246, "step": 8518 }, { "epoch": 0.7191836476261833, "grad_norm": 0.1396484375, "learning_rate": 1.1936842082535879e-05, "loss": 1.5877351760864258, "step": 8519 }, { "epoch": 0.7192680687610143, "grad_norm": 0.14453125, "learning_rate": 1.1931292184288254e-05, "loss": 1.5876556634902954, "step": 8520 }, { "epoch": 0.7193524898958454, "grad_norm": 0.140625, "learning_rate": 1.1925743172130433e-05, "loss": 1.499101161956787, "step": 8521 }, { "epoch": 0.7194369110306765, "grad_norm": 0.12890625, "learning_rate": 1.1920195046438649e-05, "loss": 1.488260269165039, "step": 8522 }, { "epoch": 0.7195213321655076, "grad_norm": 0.14453125, "learning_rate": 1.191464780758909e-05, "loss": 1.6005009412765503, "step": 8523 }, { "epoch": 0.7196057533003387, "grad_norm": 0.14453125, "learning_rate": 1.1909101455957846e-05, "loss": 1.4454582929611206, "step": 8524 }, { "epoch": 0.7196901744351698, "grad_norm": 0.134765625, "learning_rate": 1.1903555991920998e-05, "loss": 1.4779465198516846, "step": 8525 }, { "epoch": 0.7197745955700009, "grad_norm": 0.1484375, "learning_rate": 1.1898011415854543e-05, "loss": 1.4985291957855225, "step": 8526 }, { "epoch": 0.7198590167048321, "grad_norm": 0.1318359375, "learning_rate": 1.1892467728134399e-05, "loss": 1.4800382852554321, "step": 8527 }, { "epoch": 0.7199434378396632, "grad_norm": 0.1376953125, "learning_rate": 1.1886924929136447e-05, "loss": 1.5204474925994873, "step": 8528 }, { "epoch": 0.7200278589744943, "grad_norm": 0.1396484375, "learning_rate": 1.1881383019236506e-05, "loss": 1.5304094552993774, "step": 8529 }, { "epoch": 0.7201122801093254, "grad_norm": 0.1435546875, "learning_rate": 1.1875841998810328e-05, "loss": 1.492428183555603, "step": 8530 }, { "epoch": 0.7201967012441565, "grad_norm": 0.140625, "learning_rate": 1.1870301868233611e-05, "loss": 1.4997856616973877, "step": 8531 }, { "epoch": 0.7202811223789876, "grad_norm": 0.130859375, "learning_rate": 1.1864762627881984e-05, "loss": 1.431272268295288, "step": 8532 }, { "epoch": 0.7203655435138187, "grad_norm": 0.15234375, "learning_rate": 1.1859224278131038e-05, "loss": 1.481279969215393, "step": 8533 }, { "epoch": 0.7204499646486497, "grad_norm": 0.1396484375, "learning_rate": 1.1853686819356257e-05, "loss": 1.4943084716796875, "step": 8534 }, { "epoch": 0.720534385783481, "grad_norm": 0.1416015625, "learning_rate": 1.1848150251933102e-05, "loss": 1.5383491516113281, "step": 8535 }, { "epoch": 0.720618806918312, "grad_norm": 0.134765625, "learning_rate": 1.1842614576236994e-05, "loss": 1.5081133842468262, "step": 8536 }, { "epoch": 0.7207032280531431, "grad_norm": 0.140625, "learning_rate": 1.1837079792643232e-05, "loss": 1.467844843864441, "step": 8537 }, { "epoch": 0.7207876491879742, "grad_norm": 0.140625, "learning_rate": 1.1831545901527088e-05, "loss": 1.6011638641357422, "step": 8538 }, { "epoch": 0.7208720703228053, "grad_norm": 0.146484375, "learning_rate": 1.1826012903263808e-05, "loss": 1.5510499477386475, "step": 8539 }, { "epoch": 0.7209564914576364, "grad_norm": 0.1328125, "learning_rate": 1.1820480798228508e-05, "loss": 1.4998583793640137, "step": 8540 }, { "epoch": 0.7210409125924675, "grad_norm": 0.1435546875, "learning_rate": 1.1814949586796289e-05, "loss": 1.568772554397583, "step": 8541 }, { "epoch": 0.7211253337272986, "grad_norm": 0.13671875, "learning_rate": 1.180941926934218e-05, "loss": 1.5318163633346558, "step": 8542 }, { "epoch": 0.7212097548621297, "grad_norm": 0.13671875, "learning_rate": 1.1803889846241153e-05, "loss": 1.5142284631729126, "step": 8543 }, { "epoch": 0.7212941759969609, "grad_norm": 0.13671875, "learning_rate": 1.179836131786812e-05, "loss": 1.4588037729263306, "step": 8544 }, { "epoch": 0.721378597131792, "grad_norm": 0.1484375, "learning_rate": 1.1792833684597907e-05, "loss": 1.5434746742248535, "step": 8545 }, { "epoch": 0.7214630182666231, "grad_norm": 0.140625, "learning_rate": 1.1787306946805332e-05, "loss": 1.4963926076889038, "step": 8546 }, { "epoch": 0.7215474394014542, "grad_norm": 0.1396484375, "learning_rate": 1.1781781104865097e-05, "loss": 1.4952352046966553, "step": 8547 }, { "epoch": 0.7216318605362853, "grad_norm": 0.1318359375, "learning_rate": 1.1776256159151874e-05, "loss": 1.4410830736160278, "step": 8548 }, { "epoch": 0.7217162816711163, "grad_norm": 0.1337890625, "learning_rate": 1.1770732110040273e-05, "loss": 1.5486547946929932, "step": 8549 }, { "epoch": 0.7218007028059474, "grad_norm": 0.134765625, "learning_rate": 1.1765208957904831e-05, "loss": 1.5404525995254517, "step": 8550 }, { "epoch": 0.7218851239407785, "grad_norm": 0.14453125, "learning_rate": 1.1759686703120032e-05, "loss": 1.5688037872314453, "step": 8551 }, { "epoch": 0.7219695450756097, "grad_norm": 0.1455078125, "learning_rate": 1.1754165346060302e-05, "loss": 1.5678831338882446, "step": 8552 }, { "epoch": 0.7220539662104408, "grad_norm": 0.1357421875, "learning_rate": 1.17486448871e-05, "loss": 1.4352993965148926, "step": 8553 }, { "epoch": 0.7221383873452719, "grad_norm": 0.13671875, "learning_rate": 1.1743125326613439e-05, "loss": 1.5806448459625244, "step": 8554 }, { "epoch": 0.722222808480103, "grad_norm": 0.15625, "learning_rate": 1.1737606664974824e-05, "loss": 1.655962347984314, "step": 8555 }, { "epoch": 0.7223072296149341, "grad_norm": 0.1435546875, "learning_rate": 1.1732088902558367e-05, "loss": 1.5226694345474243, "step": 8556 }, { "epoch": 0.7223916507497652, "grad_norm": 0.1337890625, "learning_rate": 1.1726572039738182e-05, "loss": 1.514876365661621, "step": 8557 }, { "epoch": 0.7224760718845963, "grad_norm": 0.1494140625, "learning_rate": 1.1721056076888306e-05, "loss": 1.6316497325897217, "step": 8558 }, { "epoch": 0.7225604930194274, "grad_norm": 0.1474609375, "learning_rate": 1.1715541014382752e-05, "loss": 1.589472770690918, "step": 8559 }, { "epoch": 0.7226449141542585, "grad_norm": 0.138671875, "learning_rate": 1.1710026852595446e-05, "loss": 1.5730891227722168, "step": 8560 }, { "epoch": 0.7227293352890897, "grad_norm": 0.1337890625, "learning_rate": 1.1704513591900266e-05, "loss": 1.5298683643341064, "step": 8561 }, { "epoch": 0.7228137564239208, "grad_norm": 0.1435546875, "learning_rate": 1.169900123267102e-05, "loss": 1.5550042390823364, "step": 8562 }, { "epoch": 0.7228981775587519, "grad_norm": 0.1611328125, "learning_rate": 1.1693489775281463e-05, "loss": 1.5122199058532715, "step": 8563 }, { "epoch": 0.722982598693583, "grad_norm": 0.1396484375, "learning_rate": 1.1687979220105294e-05, "loss": 1.539223313331604, "step": 8564 }, { "epoch": 0.723067019828414, "grad_norm": 0.14453125, "learning_rate": 1.168246956751611e-05, "loss": 1.5173417329788208, "step": 8565 }, { "epoch": 0.7231514409632451, "grad_norm": 0.13671875, "learning_rate": 1.1676960817887513e-05, "loss": 1.5393840074539185, "step": 8566 }, { "epoch": 0.7232358620980762, "grad_norm": 0.1396484375, "learning_rate": 1.1671452971593005e-05, "loss": 1.519897699356079, "step": 8567 }, { "epoch": 0.7233202832329073, "grad_norm": 0.14453125, "learning_rate": 1.1665946029006013e-05, "loss": 1.4249730110168457, "step": 8568 }, { "epoch": 0.7234047043677385, "grad_norm": 0.142578125, "learning_rate": 1.1660439990499925e-05, "loss": 1.5995302200317383, "step": 8569 }, { "epoch": 0.7234891255025696, "grad_norm": 0.142578125, "learning_rate": 1.1654934856448085e-05, "loss": 1.5281965732574463, "step": 8570 }, { "epoch": 0.7235735466374007, "grad_norm": 0.13671875, "learning_rate": 1.1649430627223731e-05, "loss": 1.4871644973754883, "step": 8571 }, { "epoch": 0.7236579677722318, "grad_norm": 0.138671875, "learning_rate": 1.1643927303200073e-05, "loss": 1.5561530590057373, "step": 8572 }, { "epoch": 0.7237423889070629, "grad_norm": 0.1357421875, "learning_rate": 1.1638424884750246e-05, "loss": 1.5346980094909668, "step": 8573 }, { "epoch": 0.723826810041894, "grad_norm": 0.1396484375, "learning_rate": 1.1632923372247329e-05, "loss": 1.5779407024383545, "step": 8574 }, { "epoch": 0.7239112311767251, "grad_norm": 0.1396484375, "learning_rate": 1.1627422766064344e-05, "loss": 1.5060653686523438, "step": 8575 }, { "epoch": 0.7239956523115562, "grad_norm": 0.142578125, "learning_rate": 1.1621923066574222e-05, "loss": 1.4789005517959595, "step": 8576 }, { "epoch": 0.7240800734463873, "grad_norm": 0.142578125, "learning_rate": 1.1616424274149893e-05, "loss": 1.4851139783859253, "step": 8577 }, { "epoch": 0.7241644945812185, "grad_norm": 0.142578125, "learning_rate": 1.1610926389164158e-05, "loss": 1.526963233947754, "step": 8578 }, { "epoch": 0.7242489157160495, "grad_norm": 0.130859375, "learning_rate": 1.1605429411989788e-05, "loss": 1.5166571140289307, "step": 8579 }, { "epoch": 0.7243333368508806, "grad_norm": 0.150390625, "learning_rate": 1.1599933342999516e-05, "loss": 1.5047979354858398, "step": 8580 }, { "epoch": 0.7244177579857117, "grad_norm": 0.1474609375, "learning_rate": 1.1594438182565967e-05, "loss": 1.5076261758804321, "step": 8581 }, { "epoch": 0.7245021791205428, "grad_norm": 0.1474609375, "learning_rate": 1.158894393106173e-05, "loss": 1.526292085647583, "step": 8582 }, { "epoch": 0.7245866002553739, "grad_norm": 0.1318359375, "learning_rate": 1.1583450588859333e-05, "loss": 1.4801383018493652, "step": 8583 }, { "epoch": 0.724671021390205, "grad_norm": 0.1396484375, "learning_rate": 1.1577958156331232e-05, "loss": 1.5008623600006104, "step": 8584 }, { "epoch": 0.7247554425250361, "grad_norm": 0.1435546875, "learning_rate": 1.157246663384984e-05, "loss": 1.5385925769805908, "step": 8585 }, { "epoch": 0.7248398636598673, "grad_norm": 0.142578125, "learning_rate": 1.156697602178747e-05, "loss": 1.5386406183242798, "step": 8586 }, { "epoch": 0.7249242847946984, "grad_norm": 0.1533203125, "learning_rate": 1.1561486320516421e-05, "loss": 1.533443808555603, "step": 8587 }, { "epoch": 0.7250087059295295, "grad_norm": 0.1298828125, "learning_rate": 1.1555997530408914e-05, "loss": 1.4963644742965698, "step": 8588 }, { "epoch": 0.7250931270643606, "grad_norm": 0.13671875, "learning_rate": 1.1550509651837076e-05, "loss": 1.5528641939163208, "step": 8589 }, { "epoch": 0.7251775481991917, "grad_norm": 0.1416015625, "learning_rate": 1.1545022685173012e-05, "loss": 1.5587389469146729, "step": 8590 }, { "epoch": 0.7252619693340228, "grad_norm": 0.130859375, "learning_rate": 1.1539536630788755e-05, "loss": 1.4930137395858765, "step": 8591 }, { "epoch": 0.7253463904688539, "grad_norm": 0.142578125, "learning_rate": 1.1534051489056266e-05, "loss": 1.5325721502304077, "step": 8592 }, { "epoch": 0.7254308116036849, "grad_norm": 0.134765625, "learning_rate": 1.1528567260347457e-05, "loss": 1.531906008720398, "step": 8593 }, { "epoch": 0.725515232738516, "grad_norm": 0.1376953125, "learning_rate": 1.1523083945034166e-05, "loss": 1.5049980878829956, "step": 8594 }, { "epoch": 0.7255996538733472, "grad_norm": 0.1328125, "learning_rate": 1.1517601543488188e-05, "loss": 1.4787483215332031, "step": 8595 }, { "epoch": 0.7256840750081783, "grad_norm": 0.1474609375, "learning_rate": 1.1512120056081215e-05, "loss": 1.5368484258651733, "step": 8596 }, { "epoch": 0.7257684961430094, "grad_norm": 0.1396484375, "learning_rate": 1.1506639483184931e-05, "loss": 1.6076467037200928, "step": 8597 }, { "epoch": 0.7258529172778405, "grad_norm": 0.130859375, "learning_rate": 1.1501159825170934e-05, "loss": 1.4372477531433105, "step": 8598 }, { "epoch": 0.7259373384126716, "grad_norm": 0.13671875, "learning_rate": 1.149568108241074e-05, "loss": 1.4688209295272827, "step": 8599 }, { "epoch": 0.7260217595475027, "grad_norm": 0.14453125, "learning_rate": 1.1490203255275825e-05, "loss": 1.6274120807647705, "step": 8600 }, { "epoch": 0.7261061806823338, "grad_norm": 0.15234375, "learning_rate": 1.1484726344137602e-05, "loss": 1.5330932140350342, "step": 8601 }, { "epoch": 0.7261906018171649, "grad_norm": 0.14453125, "learning_rate": 1.1479250349367423e-05, "loss": 1.5568182468414307, "step": 8602 }, { "epoch": 0.7262750229519961, "grad_norm": 0.134765625, "learning_rate": 1.1473775271336571e-05, "loss": 1.4623894691467285, "step": 8603 }, { "epoch": 0.7263594440868272, "grad_norm": 0.134765625, "learning_rate": 1.1468301110416263e-05, "loss": 1.474534511566162, "step": 8604 }, { "epoch": 0.7264438652216583, "grad_norm": 0.1328125, "learning_rate": 1.1462827866977668e-05, "loss": 1.5016491413116455, "step": 8605 }, { "epoch": 0.7265282863564894, "grad_norm": 0.1484375, "learning_rate": 1.1457355541391896e-05, "loss": 1.5567883253097534, "step": 8606 }, { "epoch": 0.7266127074913205, "grad_norm": 0.1337890625, "learning_rate": 1.1451884134029948e-05, "loss": 1.5577815771102905, "step": 8607 }, { "epoch": 0.7266971286261515, "grad_norm": 0.138671875, "learning_rate": 1.1446413645262838e-05, "loss": 1.4664133787155151, "step": 8608 }, { "epoch": 0.7267815497609826, "grad_norm": 0.1396484375, "learning_rate": 1.1440944075461455e-05, "loss": 1.4725816249847412, "step": 8609 }, { "epoch": 0.7268659708958137, "grad_norm": 0.1455078125, "learning_rate": 1.1435475424996644e-05, "loss": 1.4895167350769043, "step": 8610 }, { "epoch": 0.7269503920306448, "grad_norm": 0.130859375, "learning_rate": 1.1430007694239225e-05, "loss": 1.4476875066757202, "step": 8611 }, { "epoch": 0.727034813165476, "grad_norm": 0.134765625, "learning_rate": 1.1424540883559893e-05, "loss": 1.5164083242416382, "step": 8612 }, { "epoch": 0.7271192343003071, "grad_norm": 0.1328125, "learning_rate": 1.1419074993329318e-05, "loss": 1.5896683931350708, "step": 8613 }, { "epoch": 0.7272036554351382, "grad_norm": 0.138671875, "learning_rate": 1.1413610023918104e-05, "loss": 1.4444620609283447, "step": 8614 }, { "epoch": 0.7272880765699693, "grad_norm": 0.1357421875, "learning_rate": 1.1408145975696788e-05, "loss": 1.5350573062896729, "step": 8615 }, { "epoch": 0.7273724977048004, "grad_norm": 0.140625, "learning_rate": 1.1402682849035854e-05, "loss": 1.4891750812530518, "step": 8616 }, { "epoch": 0.7274569188396315, "grad_norm": 0.140625, "learning_rate": 1.1397220644305687e-05, "loss": 1.4583051204681396, "step": 8617 }, { "epoch": 0.7275413399744626, "grad_norm": 0.1494140625, "learning_rate": 1.1391759361876678e-05, "loss": 1.5971769094467163, "step": 8618 }, { "epoch": 0.7276257611092937, "grad_norm": 0.1435546875, "learning_rate": 1.1386299002119084e-05, "loss": 1.4803247451782227, "step": 8619 }, { "epoch": 0.7277101822441249, "grad_norm": 0.1416015625, "learning_rate": 1.138083956540314e-05, "loss": 1.6160194873809814, "step": 8620 }, { "epoch": 0.727794603378956, "grad_norm": 0.140625, "learning_rate": 1.137538105209901e-05, "loss": 1.5733100175857544, "step": 8621 }, { "epoch": 0.727879024513787, "grad_norm": 0.1337890625, "learning_rate": 1.1369923462576792e-05, "loss": 1.5391795635223389, "step": 8622 }, { "epoch": 0.7279634456486181, "grad_norm": 0.1416015625, "learning_rate": 1.136446679720653e-05, "loss": 1.4895248413085938, "step": 8623 }, { "epoch": 0.7280478667834492, "grad_norm": 0.1513671875, "learning_rate": 1.135901105635819e-05, "loss": 1.571179747581482, "step": 8624 }, { "epoch": 0.7281322879182803, "grad_norm": 0.1337890625, "learning_rate": 1.1353556240401692e-05, "loss": 1.5523064136505127, "step": 8625 }, { "epoch": 0.7282167090531114, "grad_norm": 0.1357421875, "learning_rate": 1.1348102349706891e-05, "loss": 1.5199346542358398, "step": 8626 }, { "epoch": 0.7283011301879425, "grad_norm": 0.138671875, "learning_rate": 1.1342649384643548e-05, "loss": 1.541785717010498, "step": 8627 }, { "epoch": 0.7283855513227736, "grad_norm": 0.1396484375, "learning_rate": 1.1337197345581413e-05, "loss": 1.5921282768249512, "step": 8628 }, { "epoch": 0.7284699724576048, "grad_norm": 0.1376953125, "learning_rate": 1.1331746232890148e-05, "loss": 1.5368781089782715, "step": 8629 }, { "epoch": 0.7285543935924359, "grad_norm": 0.1484375, "learning_rate": 1.1326296046939333e-05, "loss": 1.5442111492156982, "step": 8630 }, { "epoch": 0.728638814727267, "grad_norm": 0.1494140625, "learning_rate": 1.1320846788098513e-05, "loss": 1.518105387687683, "step": 8631 }, { "epoch": 0.7287232358620981, "grad_norm": 0.1376953125, "learning_rate": 1.1315398456737165e-05, "loss": 1.538498878479004, "step": 8632 }, { "epoch": 0.7288076569969292, "grad_norm": 0.134765625, "learning_rate": 1.130995105322469e-05, "loss": 1.525394082069397, "step": 8633 }, { "epoch": 0.7288920781317603, "grad_norm": 0.13671875, "learning_rate": 1.1304504577930442e-05, "loss": 1.529592752456665, "step": 8634 }, { "epoch": 0.7289764992665914, "grad_norm": 0.134765625, "learning_rate": 1.1299059031223706e-05, "loss": 1.4888993501663208, "step": 8635 }, { "epoch": 0.7290609204014225, "grad_norm": 0.1318359375, "learning_rate": 1.1293614413473697e-05, "loss": 1.4883729219436646, "step": 8636 }, { "epoch": 0.7291453415362537, "grad_norm": 0.14453125, "learning_rate": 1.1288170725049577e-05, "loss": 1.5184366703033447, "step": 8637 }, { "epoch": 0.7292297626710847, "grad_norm": 0.1484375, "learning_rate": 1.1282727966320441e-05, "loss": 1.5728991031646729, "step": 8638 }, { "epoch": 0.7293141838059158, "grad_norm": 0.1279296875, "learning_rate": 1.127728613765533e-05, "loss": 1.4887385368347168, "step": 8639 }, { "epoch": 0.7293986049407469, "grad_norm": 0.138671875, "learning_rate": 1.1271845239423196e-05, "loss": 1.5825923681259155, "step": 8640 }, { "epoch": 0.729483026075578, "grad_norm": 0.130859375, "learning_rate": 1.1266405271992942e-05, "loss": 1.505213975906372, "step": 8641 }, { "epoch": 0.7295674472104091, "grad_norm": 0.1435546875, "learning_rate": 1.1260966235733441e-05, "loss": 1.5230114459991455, "step": 8642 }, { "epoch": 0.7296518683452402, "grad_norm": 0.1279296875, "learning_rate": 1.1255528131013443e-05, "loss": 1.426599383354187, "step": 8643 }, { "epoch": 0.7297362894800713, "grad_norm": 0.1630859375, "learning_rate": 1.1250090958201675e-05, "loss": 1.5737191438674927, "step": 8644 }, { "epoch": 0.7298207106149024, "grad_norm": 0.1416015625, "learning_rate": 1.1244654717666795e-05, "loss": 1.50375235080719, "step": 8645 }, { "epoch": 0.7299051317497336, "grad_norm": 0.1494140625, "learning_rate": 1.1239219409777385e-05, "loss": 1.5510244369506836, "step": 8646 }, { "epoch": 0.7299895528845647, "grad_norm": 0.1494140625, "learning_rate": 1.1233785034901984e-05, "loss": 1.5622304677963257, "step": 8647 }, { "epoch": 0.7300739740193958, "grad_norm": 0.1435546875, "learning_rate": 1.1228351593409031e-05, "loss": 1.4942457675933838, "step": 8648 }, { "epoch": 0.7301583951542269, "grad_norm": 0.138671875, "learning_rate": 1.1222919085666958e-05, "loss": 1.5764949321746826, "step": 8649 }, { "epoch": 0.730242816289058, "grad_norm": 0.1376953125, "learning_rate": 1.1217487512044081e-05, "loss": 1.506523847579956, "step": 8650 }, { "epoch": 0.730327237423889, "grad_norm": 0.1484375, "learning_rate": 1.1212056872908669e-05, "loss": 1.5462305545806885, "step": 8651 }, { "epoch": 0.7304116585587201, "grad_norm": 0.138671875, "learning_rate": 1.1206627168628962e-05, "loss": 1.5717285871505737, "step": 8652 }, { "epoch": 0.7304960796935512, "grad_norm": 0.12890625, "learning_rate": 1.1201198399573076e-05, "loss": 1.520451545715332, "step": 8653 }, { "epoch": 0.7305805008283824, "grad_norm": 0.13671875, "learning_rate": 1.1195770566109109e-05, "loss": 1.5196110010147095, "step": 8654 }, { "epoch": 0.7306649219632135, "grad_norm": 0.1435546875, "learning_rate": 1.1190343668605077e-05, "loss": 1.5352585315704346, "step": 8655 }, { "epoch": 0.7307493430980446, "grad_norm": 0.138671875, "learning_rate": 1.1184917707428941e-05, "loss": 1.5014255046844482, "step": 8656 }, { "epoch": 0.7308337642328757, "grad_norm": 0.140625, "learning_rate": 1.1179492682948598e-05, "loss": 1.5272759199142456, "step": 8657 }, { "epoch": 0.7309181853677068, "grad_norm": 0.140625, "learning_rate": 1.1174068595531853e-05, "loss": 1.5728267431259155, "step": 8658 }, { "epoch": 0.7310026065025379, "grad_norm": 0.13671875, "learning_rate": 1.11686454455465e-05, "loss": 1.5023305416107178, "step": 8659 }, { "epoch": 0.731087027637369, "grad_norm": 0.1416015625, "learning_rate": 1.1163223233360243e-05, "loss": 1.56675386428833, "step": 8660 }, { "epoch": 0.7311714487722001, "grad_norm": 0.134765625, "learning_rate": 1.11578019593407e-05, "loss": 1.5527896881103516, "step": 8661 }, { "epoch": 0.7312558699070312, "grad_norm": 0.1416015625, "learning_rate": 1.1152381623855454e-05, "loss": 1.5667065382003784, "step": 8662 }, { "epoch": 0.7313402910418624, "grad_norm": 0.1396484375, "learning_rate": 1.1146962227272021e-05, "loss": 1.587074875831604, "step": 8663 }, { "epoch": 0.7314247121766935, "grad_norm": 0.1376953125, "learning_rate": 1.1141543769957846e-05, "loss": 1.5728696584701538, "step": 8664 }, { "epoch": 0.7315091333115246, "grad_norm": 0.1455078125, "learning_rate": 1.1136126252280318e-05, "loss": 1.5282171964645386, "step": 8665 }, { "epoch": 0.7315935544463557, "grad_norm": 0.1298828125, "learning_rate": 1.1130709674606751e-05, "loss": 1.5200040340423584, "step": 8666 }, { "epoch": 0.7316779755811867, "grad_norm": 0.12890625, "learning_rate": 1.1125294037304417e-05, "loss": 1.4219329357147217, "step": 8667 }, { "epoch": 0.7317623967160178, "grad_norm": 0.140625, "learning_rate": 1.1119879340740478e-05, "loss": 1.5277730226516724, "step": 8668 }, { "epoch": 0.7318468178508489, "grad_norm": 0.1396484375, "learning_rate": 1.1114465585282093e-05, "loss": 1.542129397392273, "step": 8669 }, { "epoch": 0.73193123898568, "grad_norm": 0.1328125, "learning_rate": 1.1109052771296327e-05, "loss": 1.5525399446487427, "step": 8670 }, { "epoch": 0.7320156601205112, "grad_norm": 0.1455078125, "learning_rate": 1.1103640899150164e-05, "loss": 1.5651419162750244, "step": 8671 }, { "epoch": 0.7321000812553423, "grad_norm": 0.1318359375, "learning_rate": 1.1098229969210539e-05, "loss": 1.574286937713623, "step": 8672 }, { "epoch": 0.7321845023901734, "grad_norm": 0.150390625, "learning_rate": 1.1092819981844357e-05, "loss": 1.5438522100448608, "step": 8673 }, { "epoch": 0.7322689235250045, "grad_norm": 0.1533203125, "learning_rate": 1.1087410937418399e-05, "loss": 1.541875958442688, "step": 8674 }, { "epoch": 0.7323533446598356, "grad_norm": 0.158203125, "learning_rate": 1.108200283629942e-05, "loss": 1.6150230169296265, "step": 8675 }, { "epoch": 0.7324377657946667, "grad_norm": 0.1748046875, "learning_rate": 1.1076595678854106e-05, "loss": 1.484078049659729, "step": 8676 }, { "epoch": 0.7325221869294978, "grad_norm": 0.1376953125, "learning_rate": 1.1071189465449072e-05, "loss": 1.5982416868209839, "step": 8677 }, { "epoch": 0.7326066080643289, "grad_norm": 0.158203125, "learning_rate": 1.1065784196450874e-05, "loss": 1.5936640501022339, "step": 8678 }, { "epoch": 0.73269102919916, "grad_norm": 0.1513671875, "learning_rate": 1.1060379872225998e-05, "loss": 1.5297285318374634, "step": 8679 }, { "epoch": 0.7327754503339912, "grad_norm": 0.1435546875, "learning_rate": 1.105497649314088e-05, "loss": 1.534241795539856, "step": 8680 }, { "epoch": 0.7328598714688223, "grad_norm": 0.1376953125, "learning_rate": 1.104957405956187e-05, "loss": 1.5607903003692627, "step": 8681 }, { "epoch": 0.7329442926036533, "grad_norm": 0.14453125, "learning_rate": 1.1044172571855263e-05, "loss": 1.5894696712493896, "step": 8682 }, { "epoch": 0.7330287137384844, "grad_norm": 0.1416015625, "learning_rate": 1.1038772030387317e-05, "loss": 1.5179095268249512, "step": 8683 }, { "epoch": 0.7331131348733155, "grad_norm": 0.1416015625, "learning_rate": 1.1033372435524177e-05, "loss": 1.5081146955490112, "step": 8684 }, { "epoch": 0.7331975560081466, "grad_norm": 0.1318359375, "learning_rate": 1.1027973787631956e-05, "loss": 1.503111720085144, "step": 8685 }, { "epoch": 0.7332819771429777, "grad_norm": 0.1416015625, "learning_rate": 1.10225760870767e-05, "loss": 1.5702033042907715, "step": 8686 }, { "epoch": 0.7333663982778088, "grad_norm": 0.1328125, "learning_rate": 1.1017179334224379e-05, "loss": 1.5118064880371094, "step": 8687 }, { "epoch": 0.73345081941264, "grad_norm": 0.154296875, "learning_rate": 1.1011783529440919e-05, "loss": 1.474786639213562, "step": 8688 }, { "epoch": 0.7335352405474711, "grad_norm": 0.1318359375, "learning_rate": 1.100638867309214e-05, "loss": 1.5396533012390137, "step": 8689 }, { "epoch": 0.7336196616823022, "grad_norm": 0.1474609375, "learning_rate": 1.100099476554386e-05, "loss": 1.5669760704040527, "step": 8690 }, { "epoch": 0.7337040828171333, "grad_norm": 0.134765625, "learning_rate": 1.0995601807161788e-05, "loss": 1.4664082527160645, "step": 8691 }, { "epoch": 0.7337885039519644, "grad_norm": 0.134765625, "learning_rate": 1.0990209798311558e-05, "loss": 1.521702766418457, "step": 8692 }, { "epoch": 0.7338729250867955, "grad_norm": 0.1435546875, "learning_rate": 1.09848187393588e-05, "loss": 1.5149810314178467, "step": 8693 }, { "epoch": 0.7339573462216266, "grad_norm": 0.142578125, "learning_rate": 1.0979428630669006e-05, "loss": 1.5834065675735474, "step": 8694 }, { "epoch": 0.7340417673564577, "grad_norm": 0.1318359375, "learning_rate": 1.0974039472607652e-05, "loss": 1.4859347343444824, "step": 8695 }, { "epoch": 0.7341261884912887, "grad_norm": 0.140625, "learning_rate": 1.096865126554014e-05, "loss": 1.558829426765442, "step": 8696 }, { "epoch": 0.73421060962612, "grad_norm": 0.1337890625, "learning_rate": 1.0963264009831795e-05, "loss": 1.4641869068145752, "step": 8697 }, { "epoch": 0.734295030760951, "grad_norm": 0.1416015625, "learning_rate": 1.0957877705847902e-05, "loss": 1.481566309928894, "step": 8698 }, { "epoch": 0.7343794518957821, "grad_norm": 0.140625, "learning_rate": 1.0952492353953634e-05, "loss": 1.5184508562088013, "step": 8699 }, { "epoch": 0.7344638730306132, "grad_norm": 0.140625, "learning_rate": 1.0947107954514157e-05, "loss": 1.529014229774475, "step": 8700 }, { "epoch": 0.7345482941654443, "grad_norm": 0.1337890625, "learning_rate": 1.0941724507894551e-05, "loss": 1.5090618133544922, "step": 8701 }, { "epoch": 0.7346327153002754, "grad_norm": 0.1337890625, "learning_rate": 1.0936342014459805e-05, "loss": 1.4432750940322876, "step": 8702 }, { "epoch": 0.7347171364351065, "grad_norm": 0.140625, "learning_rate": 1.0930960474574867e-05, "loss": 1.4718250036239624, "step": 8703 }, { "epoch": 0.7348015575699376, "grad_norm": 0.1435546875, "learning_rate": 1.0925579888604645e-05, "loss": 1.5705465078353882, "step": 8704 }, { "epoch": 0.7348859787047688, "grad_norm": 0.1298828125, "learning_rate": 1.0920200256913927e-05, "loss": 1.5365254878997803, "step": 8705 }, { "epoch": 0.7349703998395999, "grad_norm": 0.140625, "learning_rate": 1.0914821579867473e-05, "loss": 1.5300326347351074, "step": 8706 }, { "epoch": 0.735054820974431, "grad_norm": 0.12890625, "learning_rate": 1.0909443857829973e-05, "loss": 1.4982489347457886, "step": 8707 }, { "epoch": 0.7351392421092621, "grad_norm": 0.142578125, "learning_rate": 1.090406709116605e-05, "loss": 1.5523366928100586, "step": 8708 }, { "epoch": 0.7352236632440932, "grad_norm": 0.13671875, "learning_rate": 1.0898691280240261e-05, "loss": 1.4933706521987915, "step": 8709 }, { "epoch": 0.7353080843789243, "grad_norm": 0.14453125, "learning_rate": 1.0893316425417097e-05, "loss": 1.5113753080368042, "step": 8710 }, { "epoch": 0.7353925055137553, "grad_norm": 0.1474609375, "learning_rate": 1.0887942527061e-05, "loss": 1.5735799074172974, "step": 8711 }, { "epoch": 0.7354769266485864, "grad_norm": 0.1474609375, "learning_rate": 1.0882569585536306e-05, "loss": 1.5281128883361816, "step": 8712 }, { "epoch": 0.7355613477834175, "grad_norm": 0.1474609375, "learning_rate": 1.087719760120732e-05, "loss": 1.5309312343597412, "step": 8713 }, { "epoch": 0.7356457689182487, "grad_norm": 0.1396484375, "learning_rate": 1.0871826574438305e-05, "loss": 1.5835670232772827, "step": 8714 }, { "epoch": 0.7357301900530798, "grad_norm": 0.1396484375, "learning_rate": 1.0866456505593395e-05, "loss": 1.571008563041687, "step": 8715 }, { "epoch": 0.7358146111879109, "grad_norm": 0.138671875, "learning_rate": 1.086108739503671e-05, "loss": 1.5310219526290894, "step": 8716 }, { "epoch": 0.735899032322742, "grad_norm": 0.1337890625, "learning_rate": 1.0855719243132282e-05, "loss": 1.495187759399414, "step": 8717 }, { "epoch": 0.7359834534575731, "grad_norm": 0.138671875, "learning_rate": 1.085035205024409e-05, "loss": 1.5181245803833008, "step": 8718 }, { "epoch": 0.7360678745924042, "grad_norm": 0.1416015625, "learning_rate": 1.0844985816736037e-05, "loss": 1.5771610736846924, "step": 8719 }, { "epoch": 0.7361522957272353, "grad_norm": 0.138671875, "learning_rate": 1.0839620542971973e-05, "loss": 1.4641841650009155, "step": 8720 }, { "epoch": 0.7362367168620664, "grad_norm": 0.13671875, "learning_rate": 1.083425622931567e-05, "loss": 1.5201300382614136, "step": 8721 }, { "epoch": 0.7363211379968975, "grad_norm": 0.1455078125, "learning_rate": 1.0828892876130859e-05, "loss": 1.5388514995574951, "step": 8722 }, { "epoch": 0.7364055591317287, "grad_norm": 0.134765625, "learning_rate": 1.082353048378115e-05, "loss": 1.48353111743927, "step": 8723 }, { "epoch": 0.7364899802665598, "grad_norm": 0.134765625, "learning_rate": 1.0818169052630173e-05, "loss": 1.4413044452667236, "step": 8724 }, { "epoch": 0.7365744014013909, "grad_norm": 0.142578125, "learning_rate": 1.0812808583041408e-05, "loss": 1.530377745628357, "step": 8725 }, { "epoch": 0.736658822536222, "grad_norm": 0.140625, "learning_rate": 1.080744907537833e-05, "loss": 1.4970589876174927, "step": 8726 }, { "epoch": 0.736743243671053, "grad_norm": 0.1396484375, "learning_rate": 1.0802090530004313e-05, "loss": 1.6027939319610596, "step": 8727 }, { "epoch": 0.7368276648058841, "grad_norm": 0.1552734375, "learning_rate": 1.0796732947282687e-05, "loss": 1.5465118885040283, "step": 8728 }, { "epoch": 0.7369120859407152, "grad_norm": 0.140625, "learning_rate": 1.0791376327576717e-05, "loss": 1.549240231513977, "step": 8729 }, { "epoch": 0.7369965070755463, "grad_norm": 0.13671875, "learning_rate": 1.0786020671249566e-05, "loss": 1.4272129535675049, "step": 8730 }, { "epoch": 0.7370809282103775, "grad_norm": 0.140625, "learning_rate": 1.0780665978664389e-05, "loss": 1.601239562034607, "step": 8731 }, { "epoch": 0.7371653493452086, "grad_norm": 0.138671875, "learning_rate": 1.0775312250184247e-05, "loss": 1.5652046203613281, "step": 8732 }, { "epoch": 0.7372497704800397, "grad_norm": 0.1396484375, "learning_rate": 1.0769959486172107e-05, "loss": 1.5606142282485962, "step": 8733 }, { "epoch": 0.7373341916148708, "grad_norm": 0.1376953125, "learning_rate": 1.0764607686990938e-05, "loss": 1.5897990465164185, "step": 8734 }, { "epoch": 0.7374186127497019, "grad_norm": 0.14453125, "learning_rate": 1.0759256853003578e-05, "loss": 1.5682812929153442, "step": 8735 }, { "epoch": 0.737503033884533, "grad_norm": 0.1396484375, "learning_rate": 1.075390698457283e-05, "loss": 1.5558494329452515, "step": 8736 }, { "epoch": 0.7375874550193641, "grad_norm": 0.1396484375, "learning_rate": 1.074855808206143e-05, "loss": 1.4369782209396362, "step": 8737 }, { "epoch": 0.7376718761541952, "grad_norm": 0.142578125, "learning_rate": 1.074321014583205e-05, "loss": 1.60714852809906, "step": 8738 }, { "epoch": 0.7377562972890263, "grad_norm": 0.12890625, "learning_rate": 1.0737863176247293e-05, "loss": 1.5049492120742798, "step": 8739 }, { "epoch": 0.7378407184238575, "grad_norm": 0.1357421875, "learning_rate": 1.0732517173669694e-05, "loss": 1.5084854364395142, "step": 8740 }, { "epoch": 0.7379251395586885, "grad_norm": 0.1435546875, "learning_rate": 1.0727172138461723e-05, "loss": 1.5362279415130615, "step": 8741 }, { "epoch": 0.7380095606935196, "grad_norm": 0.1357421875, "learning_rate": 1.0721828070985799e-05, "loss": 1.5203118324279785, "step": 8742 }, { "epoch": 0.7380939818283507, "grad_norm": 0.1435546875, "learning_rate": 1.071648497160424e-05, "loss": 1.538622260093689, "step": 8743 }, { "epoch": 0.7381784029631818, "grad_norm": 0.12890625, "learning_rate": 1.0711142840679326e-05, "loss": 1.4989420175552368, "step": 8744 }, { "epoch": 0.7382628240980129, "grad_norm": 0.1611328125, "learning_rate": 1.0705801678573291e-05, "loss": 1.6211376190185547, "step": 8745 }, { "epoch": 0.738347245232844, "grad_norm": 0.1513671875, "learning_rate": 1.0700461485648253e-05, "loss": 1.6199954748153687, "step": 8746 }, { "epoch": 0.7384316663676751, "grad_norm": 0.1474609375, "learning_rate": 1.0695122262266297e-05, "loss": 1.6084060668945312, "step": 8747 }, { "epoch": 0.7385160875025063, "grad_norm": 0.1494140625, "learning_rate": 1.0689784008789436e-05, "loss": 1.6382315158843994, "step": 8748 }, { "epoch": 0.7386005086373374, "grad_norm": 0.14453125, "learning_rate": 1.0684446725579617e-05, "loss": 1.6046059131622314, "step": 8749 }, { "epoch": 0.7386849297721685, "grad_norm": 0.1416015625, "learning_rate": 1.067911041299872e-05, "loss": 1.5515060424804688, "step": 8750 }, { "epoch": 0.7387693509069996, "grad_norm": 0.138671875, "learning_rate": 1.067377507140856e-05, "loss": 1.576073169708252, "step": 8751 }, { "epoch": 0.7388537720418307, "grad_norm": 0.140625, "learning_rate": 1.0668440701170893e-05, "loss": 1.5462288856506348, "step": 8752 }, { "epoch": 0.7389381931766618, "grad_norm": 0.14453125, "learning_rate": 1.0663107302647388e-05, "loss": 1.5333282947540283, "step": 8753 }, { "epoch": 0.7390226143114929, "grad_norm": 0.1474609375, "learning_rate": 1.0657774876199662e-05, "loss": 1.4795669317245483, "step": 8754 }, { "epoch": 0.739107035446324, "grad_norm": 0.1357421875, "learning_rate": 1.0652443422189287e-05, "loss": 1.506820797920227, "step": 8755 }, { "epoch": 0.739191456581155, "grad_norm": 0.1376953125, "learning_rate": 1.0647112940977727e-05, "loss": 1.555290699005127, "step": 8756 }, { "epoch": 0.7392758777159862, "grad_norm": 0.1435546875, "learning_rate": 1.064178343292641e-05, "loss": 1.5341626405715942, "step": 8757 }, { "epoch": 0.7393602988508173, "grad_norm": 0.13671875, "learning_rate": 1.0636454898396691e-05, "loss": 1.4280345439910889, "step": 8758 }, { "epoch": 0.7394447199856484, "grad_norm": 0.1474609375, "learning_rate": 1.0631127337749856e-05, "loss": 1.4955520629882812, "step": 8759 }, { "epoch": 0.7395291411204795, "grad_norm": 0.1357421875, "learning_rate": 1.062580075134712e-05, "loss": 1.4916948080062866, "step": 8760 }, { "epoch": 0.7396135622553106, "grad_norm": 0.1328125, "learning_rate": 1.0620475139549648e-05, "loss": 1.502476453781128, "step": 8761 }, { "epoch": 0.7396979833901417, "grad_norm": 0.1318359375, "learning_rate": 1.0615150502718526e-05, "loss": 1.4461759328842163, "step": 8762 }, { "epoch": 0.7397824045249728, "grad_norm": 0.13671875, "learning_rate": 1.0609826841214784e-05, "loss": 1.5489892959594727, "step": 8763 }, { "epoch": 0.7398668256598039, "grad_norm": 0.1376953125, "learning_rate": 1.0604504155399352e-05, "loss": 1.460284948348999, "step": 8764 }, { "epoch": 0.7399512467946351, "grad_norm": 0.142578125, "learning_rate": 1.0599182445633162e-05, "loss": 1.5057252645492554, "step": 8765 }, { "epoch": 0.7400356679294662, "grad_norm": 0.1484375, "learning_rate": 1.0593861712277006e-05, "loss": 1.492448091506958, "step": 8766 }, { "epoch": 0.7401200890642973, "grad_norm": 0.140625, "learning_rate": 1.0588541955691656e-05, "loss": 1.4361095428466797, "step": 8767 }, { "epoch": 0.7402045101991284, "grad_norm": 0.12890625, "learning_rate": 1.05832231762378e-05, "loss": 1.4323902130126953, "step": 8768 }, { "epoch": 0.7402889313339595, "grad_norm": 0.150390625, "learning_rate": 1.0577905374276068e-05, "loss": 1.5242105722427368, "step": 8769 }, { "epoch": 0.7403733524687905, "grad_norm": 0.138671875, "learning_rate": 1.0572588550167015e-05, "loss": 1.6051265001296997, "step": 8770 }, { "epoch": 0.7404577736036216, "grad_norm": 0.1337890625, "learning_rate": 1.056727270427114e-05, "loss": 1.5674251317977905, "step": 8771 }, { "epoch": 0.7405421947384527, "grad_norm": 0.1396484375, "learning_rate": 1.0561957836948863e-05, "loss": 1.5134857892990112, "step": 8772 }, { "epoch": 0.7406266158732838, "grad_norm": 0.142578125, "learning_rate": 1.0556643948560563e-05, "loss": 1.5708459615707397, "step": 8773 }, { "epoch": 0.740711037008115, "grad_norm": 0.140625, "learning_rate": 1.05513310394665e-05, "loss": 1.5049018859863281, "step": 8774 }, { "epoch": 0.7407954581429461, "grad_norm": 0.1484375, "learning_rate": 1.0546019110026931e-05, "loss": 1.548804521560669, "step": 8775 }, { "epoch": 0.7408798792777772, "grad_norm": 0.138671875, "learning_rate": 1.054070816060202e-05, "loss": 1.5485661029815674, "step": 8776 }, { "epoch": 0.7409643004126083, "grad_norm": 0.1318359375, "learning_rate": 1.0535398191551841e-05, "loss": 1.5010931491851807, "step": 8777 }, { "epoch": 0.7410487215474394, "grad_norm": 0.1396484375, "learning_rate": 1.0530089203236434e-05, "loss": 1.5638014078140259, "step": 8778 }, { "epoch": 0.7411331426822705, "grad_norm": 0.134765625, "learning_rate": 1.052478119601576e-05, "loss": 1.5830538272857666, "step": 8779 }, { "epoch": 0.7412175638171016, "grad_norm": 0.1357421875, "learning_rate": 1.0519474170249713e-05, "loss": 1.5491242408752441, "step": 8780 }, { "epoch": 0.7413019849519327, "grad_norm": 0.13671875, "learning_rate": 1.0514168126298124e-05, "loss": 1.5420141220092773, "step": 8781 }, { "epoch": 0.7413864060867639, "grad_norm": 0.1337890625, "learning_rate": 1.0508863064520757e-05, "loss": 1.5469361543655396, "step": 8782 }, { "epoch": 0.741470827221595, "grad_norm": 0.1318359375, "learning_rate": 1.0503558985277316e-05, "loss": 1.599885106086731, "step": 8783 }, { "epoch": 0.7415552483564261, "grad_norm": 0.140625, "learning_rate": 1.0498255888927411e-05, "loss": 1.5539920330047607, "step": 8784 }, { "epoch": 0.7416396694912571, "grad_norm": 0.1416015625, "learning_rate": 1.0492953775830603e-05, "loss": 1.5801132917404175, "step": 8785 }, { "epoch": 0.7417240906260882, "grad_norm": 0.14453125, "learning_rate": 1.0487652646346419e-05, "loss": 1.5704978704452515, "step": 8786 }, { "epoch": 0.7418085117609193, "grad_norm": 0.1435546875, "learning_rate": 1.0482352500834261e-05, "loss": 1.5845550298690796, "step": 8787 }, { "epoch": 0.7418929328957504, "grad_norm": 0.1484375, "learning_rate": 1.047705333965349e-05, "loss": 1.5389920473098755, "step": 8788 }, { "epoch": 0.7419773540305815, "grad_norm": 0.1376953125, "learning_rate": 1.0471755163163427e-05, "loss": 1.5187294483184814, "step": 8789 }, { "epoch": 0.7420617751654126, "grad_norm": 0.1435546875, "learning_rate": 1.0466457971723278e-05, "loss": 1.518247127532959, "step": 8790 }, { "epoch": 0.7421461963002438, "grad_norm": 0.1376953125, "learning_rate": 1.0461161765692213e-05, "loss": 1.5480269193649292, "step": 8791 }, { "epoch": 0.7422306174350749, "grad_norm": 0.1484375, "learning_rate": 1.0455866545429324e-05, "loss": 1.5953199863433838, "step": 8792 }, { "epoch": 0.742315038569906, "grad_norm": 0.138671875, "learning_rate": 1.0450572311293644e-05, "loss": 1.5563733577728271, "step": 8793 }, { "epoch": 0.7423994597047371, "grad_norm": 0.126953125, "learning_rate": 1.0445279063644145e-05, "loss": 1.501741647720337, "step": 8794 }, { "epoch": 0.7424838808395682, "grad_norm": 0.1318359375, "learning_rate": 1.0439986802839691e-05, "loss": 1.5969773530960083, "step": 8795 }, { "epoch": 0.7425683019743993, "grad_norm": 0.146484375, "learning_rate": 1.0434695529239147e-05, "loss": 1.4910331964492798, "step": 8796 }, { "epoch": 0.7426527231092304, "grad_norm": 0.140625, "learning_rate": 1.0429405243201246e-05, "loss": 1.508183240890503, "step": 8797 }, { "epoch": 0.7427371442440615, "grad_norm": 0.140625, "learning_rate": 1.0424115945084695e-05, "loss": 1.4175219535827637, "step": 8798 }, { "epoch": 0.7428215653788927, "grad_norm": 0.138671875, "learning_rate": 1.0418827635248118e-05, "loss": 1.4847705364227295, "step": 8799 }, { "epoch": 0.7429059865137237, "grad_norm": 0.140625, "learning_rate": 1.0413540314050076e-05, "loss": 1.4989569187164307, "step": 8800 }, { "epoch": 0.7429904076485548, "grad_norm": 0.1494140625, "learning_rate": 1.0408253981849062e-05, "loss": 1.5843594074249268, "step": 8801 }, { "epoch": 0.7430748287833859, "grad_norm": 0.138671875, "learning_rate": 1.0402968639003501e-05, "loss": 1.40919828414917, "step": 8802 }, { "epoch": 0.743159249918217, "grad_norm": 0.1357421875, "learning_rate": 1.0397684285871753e-05, "loss": 1.5254360437393188, "step": 8803 }, { "epoch": 0.7432436710530481, "grad_norm": 0.130859375, "learning_rate": 1.039240092281212e-05, "loss": 1.5008841753005981, "step": 8804 }, { "epoch": 0.7433280921878792, "grad_norm": 0.1328125, "learning_rate": 1.0387118550182797e-05, "loss": 1.4937018156051636, "step": 8805 }, { "epoch": 0.7434125133227103, "grad_norm": 0.1328125, "learning_rate": 1.0381837168341973e-05, "loss": 1.5127066373825073, "step": 8806 }, { "epoch": 0.7434969344575414, "grad_norm": 0.1318359375, "learning_rate": 1.0376556777647733e-05, "loss": 1.4815505743026733, "step": 8807 }, { "epoch": 0.7435813555923726, "grad_norm": 0.1376953125, "learning_rate": 1.0371277378458086e-05, "loss": 1.473764181137085, "step": 8808 }, { "epoch": 0.7436657767272037, "grad_norm": 0.1484375, "learning_rate": 1.0365998971130994e-05, "loss": 1.5013068914413452, "step": 8809 }, { "epoch": 0.7437501978620348, "grad_norm": 0.1416015625, "learning_rate": 1.0360721556024348e-05, "loss": 1.5474480390548706, "step": 8810 }, { "epoch": 0.7438346189968659, "grad_norm": 0.140625, "learning_rate": 1.0355445133495968e-05, "loss": 1.5501017570495605, "step": 8811 }, { "epoch": 0.743919040131697, "grad_norm": 0.13671875, "learning_rate": 1.0350169703903608e-05, "loss": 1.5186201333999634, "step": 8812 }, { "epoch": 0.744003461266528, "grad_norm": 0.1396484375, "learning_rate": 1.034489526760496e-05, "loss": 1.4989240169525146, "step": 8813 }, { "epoch": 0.7440878824013591, "grad_norm": 0.13671875, "learning_rate": 1.0339621824957643e-05, "loss": 1.4811378717422485, "step": 8814 }, { "epoch": 0.7441723035361902, "grad_norm": 0.1533203125, "learning_rate": 1.0334349376319189e-05, "loss": 1.5124807357788086, "step": 8815 }, { "epoch": 0.7442567246710214, "grad_norm": 0.140625, "learning_rate": 1.032907792204711e-05, "loss": 1.4975569248199463, "step": 8816 }, { "epoch": 0.7443411458058525, "grad_norm": 0.138671875, "learning_rate": 1.0323807462498815e-05, "loss": 1.5756183862686157, "step": 8817 }, { "epoch": 0.7444255669406836, "grad_norm": 0.1328125, "learning_rate": 1.031853799803165e-05, "loss": 1.4459476470947266, "step": 8818 }, { "epoch": 0.7445099880755147, "grad_norm": 0.1435546875, "learning_rate": 1.0313269529002893e-05, "loss": 1.487083911895752, "step": 8819 }, { "epoch": 0.7445944092103458, "grad_norm": 0.1396484375, "learning_rate": 1.0308002055769766e-05, "loss": 1.5504180192947388, "step": 8820 }, { "epoch": 0.7446788303451769, "grad_norm": 0.1318359375, "learning_rate": 1.0302735578689416e-05, "loss": 1.467498540878296, "step": 8821 }, { "epoch": 0.744763251480008, "grad_norm": 0.15234375, "learning_rate": 1.0297470098118916e-05, "loss": 1.5391072034835815, "step": 8822 }, { "epoch": 0.7448476726148391, "grad_norm": 0.1435546875, "learning_rate": 1.029220561441529e-05, "loss": 1.5577404499053955, "step": 8823 }, { "epoch": 0.7449320937496702, "grad_norm": 0.134765625, "learning_rate": 1.0286942127935473e-05, "loss": 1.533523440361023, "step": 8824 }, { "epoch": 0.7450165148845014, "grad_norm": 0.1552734375, "learning_rate": 1.0281679639036354e-05, "loss": 1.6463960409164429, "step": 8825 }, { "epoch": 0.7451009360193325, "grad_norm": 0.1455078125, "learning_rate": 1.0276418148074715e-05, "loss": 1.4866167306900024, "step": 8826 }, { "epoch": 0.7451853571541636, "grad_norm": 0.1435546875, "learning_rate": 1.0271157655407337e-05, "loss": 1.5143465995788574, "step": 8827 }, { "epoch": 0.7452697782889947, "grad_norm": 0.13671875, "learning_rate": 1.0265898161390863e-05, "loss": 1.5011740922927856, "step": 8828 }, { "epoch": 0.7453541994238257, "grad_norm": 0.142578125, "learning_rate": 1.026063966638191e-05, "loss": 1.5683915615081787, "step": 8829 }, { "epoch": 0.7454386205586568, "grad_norm": 0.138671875, "learning_rate": 1.0255382170737017e-05, "loss": 1.562275767326355, "step": 8830 }, { "epoch": 0.7455230416934879, "grad_norm": 0.14453125, "learning_rate": 1.0250125674812652e-05, "loss": 1.5344005823135376, "step": 8831 }, { "epoch": 0.745607462828319, "grad_norm": 0.14453125, "learning_rate": 1.0244870178965221e-05, "loss": 1.541359305381775, "step": 8832 }, { "epoch": 0.7456918839631502, "grad_norm": 0.1484375, "learning_rate": 1.023961568355106e-05, "loss": 1.5595866441726685, "step": 8833 }, { "epoch": 0.7457763050979813, "grad_norm": 0.130859375, "learning_rate": 1.0234362188926436e-05, "loss": 1.5034263134002686, "step": 8834 }, { "epoch": 0.7458607262328124, "grad_norm": 0.1396484375, "learning_rate": 1.0229109695447553e-05, "loss": 1.5487940311431885, "step": 8835 }, { "epoch": 0.7459451473676435, "grad_norm": 0.1376953125, "learning_rate": 1.0223858203470521e-05, "loss": 1.5357239246368408, "step": 8836 }, { "epoch": 0.7460295685024746, "grad_norm": 0.1396484375, "learning_rate": 1.021860771335144e-05, "loss": 1.4977836608886719, "step": 8837 }, { "epoch": 0.7461139896373057, "grad_norm": 0.1376953125, "learning_rate": 1.0213358225446274e-05, "loss": 1.464267611503601, "step": 8838 }, { "epoch": 0.7461984107721368, "grad_norm": 0.1416015625, "learning_rate": 1.0208109740110963e-05, "loss": 1.5344572067260742, "step": 8839 }, { "epoch": 0.7462828319069679, "grad_norm": 0.1318359375, "learning_rate": 1.0202862257701368e-05, "loss": 1.4782395362854004, "step": 8840 }, { "epoch": 0.746367253041799, "grad_norm": 0.1357421875, "learning_rate": 1.0197615778573278e-05, "loss": 1.4132790565490723, "step": 8841 }, { "epoch": 0.7464516741766302, "grad_norm": 0.138671875, "learning_rate": 1.019237030308242e-05, "loss": 1.5555678606033325, "step": 8842 }, { "epoch": 0.7465360953114613, "grad_norm": 0.13671875, "learning_rate": 1.0187125831584446e-05, "loss": 1.4778741598129272, "step": 8843 }, { "epoch": 0.7466205164462923, "grad_norm": 0.1484375, "learning_rate": 1.0181882364434947e-05, "loss": 1.505427598953247, "step": 8844 }, { "epoch": 0.7467049375811234, "grad_norm": 0.142578125, "learning_rate": 1.0176639901989451e-05, "loss": 1.593649983406067, "step": 8845 }, { "epoch": 0.7467893587159545, "grad_norm": 0.134765625, "learning_rate": 1.0171398444603383e-05, "loss": 1.4967671632766724, "step": 8846 }, { "epoch": 0.7468737798507856, "grad_norm": 0.146484375, "learning_rate": 1.0166157992632153e-05, "loss": 1.5783153772354126, "step": 8847 }, { "epoch": 0.7469582009856167, "grad_norm": 0.1328125, "learning_rate": 1.0160918546431075e-05, "loss": 1.4726638793945312, "step": 8848 }, { "epoch": 0.7470426221204478, "grad_norm": 0.1337890625, "learning_rate": 1.0155680106355378e-05, "loss": 1.5561301708221436, "step": 8849 }, { "epoch": 0.747127043255279, "grad_norm": 0.146484375, "learning_rate": 1.0150442672760252e-05, "loss": 1.4882322549819946, "step": 8850 }, { "epoch": 0.7472114643901101, "grad_norm": 0.1298828125, "learning_rate": 1.0145206246000808e-05, "loss": 1.5032719373703003, "step": 8851 }, { "epoch": 0.7472958855249412, "grad_norm": 0.1494140625, "learning_rate": 1.0139970826432085e-05, "loss": 1.4894334077835083, "step": 8852 }, { "epoch": 0.7473803066597723, "grad_norm": 0.1455078125, "learning_rate": 1.013473641440906e-05, "loss": 1.5751792192459106, "step": 8853 }, { "epoch": 0.7474647277946034, "grad_norm": 0.13671875, "learning_rate": 1.0129503010286638e-05, "loss": 1.561703085899353, "step": 8854 }, { "epoch": 0.7475491489294345, "grad_norm": 0.138671875, "learning_rate": 1.0124270614419652e-05, "loss": 1.6009432077407837, "step": 8855 }, { "epoch": 0.7476335700642656, "grad_norm": 0.134765625, "learning_rate": 1.0119039227162885e-05, "loss": 1.5221437215805054, "step": 8856 }, { "epoch": 0.7477179911990967, "grad_norm": 0.1416015625, "learning_rate": 1.0113808848871012e-05, "loss": 1.4711260795593262, "step": 8857 }, { "epoch": 0.7478024123339277, "grad_norm": 0.1357421875, "learning_rate": 1.0108579479898698e-05, "loss": 1.5215082168579102, "step": 8858 }, { "epoch": 0.747886833468759, "grad_norm": 0.140625, "learning_rate": 1.010335112060048e-05, "loss": 1.552248239517212, "step": 8859 }, { "epoch": 0.74797125460359, "grad_norm": 0.138671875, "learning_rate": 1.0098123771330853e-05, "loss": 1.489473819732666, "step": 8860 }, { "epoch": 0.7480556757384211, "grad_norm": 0.1357421875, "learning_rate": 1.0092897432444273e-05, "loss": 1.5053069591522217, "step": 8861 }, { "epoch": 0.7481400968732522, "grad_norm": 0.1396484375, "learning_rate": 1.008767210429507e-05, "loss": 1.5333058834075928, "step": 8862 }, { "epoch": 0.7482245180080833, "grad_norm": 0.1396484375, "learning_rate": 1.0082447787237543e-05, "loss": 1.5218045711517334, "step": 8863 }, { "epoch": 0.7483089391429144, "grad_norm": 0.1435546875, "learning_rate": 1.007722448162591e-05, "loss": 1.559736967086792, "step": 8864 }, { "epoch": 0.7483933602777455, "grad_norm": 0.1455078125, "learning_rate": 1.0072002187814331e-05, "loss": 1.5094493627548218, "step": 8865 }, { "epoch": 0.7484777814125766, "grad_norm": 0.1396484375, "learning_rate": 1.0066780906156894e-05, "loss": 1.58095121383667, "step": 8866 }, { "epoch": 0.7485622025474078, "grad_norm": 0.140625, "learning_rate": 1.0061560637007587e-05, "loss": 1.5832457542419434, "step": 8867 }, { "epoch": 0.7486466236822389, "grad_norm": 0.138671875, "learning_rate": 1.0056341380720394e-05, "loss": 1.4746671915054321, "step": 8868 }, { "epoch": 0.74873104481707, "grad_norm": 0.1416015625, "learning_rate": 1.0051123137649168e-05, "loss": 1.5162663459777832, "step": 8869 }, { "epoch": 0.7488154659519011, "grad_norm": 0.146484375, "learning_rate": 1.0045905908147723e-05, "loss": 1.6274094581604004, "step": 8870 }, { "epoch": 0.7488998870867322, "grad_norm": 0.1376953125, "learning_rate": 1.0040689692569805e-05, "loss": 1.5554394721984863, "step": 8871 }, { "epoch": 0.7489843082215633, "grad_norm": 0.1328125, "learning_rate": 1.0035474491269082e-05, "loss": 1.4692744016647339, "step": 8872 }, { "epoch": 0.7490687293563943, "grad_norm": 0.140625, "learning_rate": 1.003026030459916e-05, "loss": 1.5269312858581543, "step": 8873 }, { "epoch": 0.7491531504912254, "grad_norm": 0.1328125, "learning_rate": 1.0025047132913567e-05, "loss": 1.5144118070602417, "step": 8874 }, { "epoch": 0.7492375716260565, "grad_norm": 0.150390625, "learning_rate": 1.0019834976565779e-05, "loss": 1.526357889175415, "step": 8875 }, { "epoch": 0.7493219927608877, "grad_norm": 0.1416015625, "learning_rate": 1.0014623835909192e-05, "loss": 1.5969265699386597, "step": 8876 }, { "epoch": 0.7494064138957188, "grad_norm": 0.15234375, "learning_rate": 1.0009413711297113e-05, "loss": 1.4259052276611328, "step": 8877 }, { "epoch": 0.7494908350305499, "grad_norm": 0.140625, "learning_rate": 1.0004204603082828e-05, "loss": 1.4952508211135864, "step": 8878 }, { "epoch": 0.749575256165381, "grad_norm": 0.1328125, "learning_rate": 9.998996511619524e-06, "loss": 1.5423697233200073, "step": 8879 }, { "epoch": 0.7496596773002121, "grad_norm": 0.1357421875, "learning_rate": 9.993789437260304e-06, "loss": 1.5159435272216797, "step": 8880 }, { "epoch": 0.7497440984350432, "grad_norm": 0.1396484375, "learning_rate": 9.98858338035823e-06, "loss": 1.5261008739471436, "step": 8881 }, { "epoch": 0.7498285195698743, "grad_norm": 0.1435546875, "learning_rate": 9.983378341266286e-06, "loss": 1.5785014629364014, "step": 8882 }, { "epoch": 0.7499129407047054, "grad_norm": 0.138671875, "learning_rate": 9.978174320337386e-06, "loss": 1.5469690561294556, "step": 8883 }, { "epoch": 0.7499973618395366, "grad_norm": 0.1416015625, "learning_rate": 9.972971317924374e-06, "loss": 1.4987465143203735, "step": 8884 }, { "epoch": 0.7500817829743677, "grad_norm": 0.1416015625, "learning_rate": 9.967769334380029e-06, "loss": 1.5516563653945923, "step": 8885 }, { "epoch": 0.7501662041091988, "grad_norm": 0.140625, "learning_rate": 9.962568370057062e-06, "loss": 1.5246628522872925, "step": 8886 }, { "epoch": 0.7502506252440299, "grad_norm": 0.142578125, "learning_rate": 9.957368425308089e-06, "loss": 1.5410445928573608, "step": 8887 }, { "epoch": 0.750335046378861, "grad_norm": 0.15625, "learning_rate": 9.9521695004857e-06, "loss": 1.584346055984497, "step": 8888 }, { "epoch": 0.750419467513692, "grad_norm": 0.13671875, "learning_rate": 9.946971595942402e-06, "loss": 1.5992858409881592, "step": 8889 }, { "epoch": 0.7505038886485231, "grad_norm": 0.134765625, "learning_rate": 9.941774712030602e-06, "loss": 1.4980394840240479, "step": 8890 }, { "epoch": 0.7505883097833542, "grad_norm": 0.142578125, "learning_rate": 9.936578849102663e-06, "loss": 1.5012552738189697, "step": 8891 }, { "epoch": 0.7506727309181853, "grad_norm": 0.13671875, "learning_rate": 9.931384007510903e-06, "loss": 1.5286619663238525, "step": 8892 }, { "epoch": 0.7507571520530165, "grad_norm": 0.1474609375, "learning_rate": 9.92619018760752e-06, "loss": 1.5440789461135864, "step": 8893 }, { "epoch": 0.7508415731878476, "grad_norm": 0.130859375, "learning_rate": 9.920997389744674e-06, "loss": 1.4787129163742065, "step": 8894 }, { "epoch": 0.7509259943226787, "grad_norm": 0.138671875, "learning_rate": 9.91580561427445e-06, "loss": 1.5492274761199951, "step": 8895 }, { "epoch": 0.7510104154575098, "grad_norm": 0.1337890625, "learning_rate": 9.910614861548862e-06, "loss": 1.5417373180389404, "step": 8896 }, { "epoch": 0.7510948365923409, "grad_norm": 0.140625, "learning_rate": 9.905425131919867e-06, "loss": 1.5998992919921875, "step": 8897 }, { "epoch": 0.751179257727172, "grad_norm": 0.1328125, "learning_rate": 9.900236425739312e-06, "loss": 1.4993269443511963, "step": 8898 }, { "epoch": 0.7512636788620031, "grad_norm": 0.138671875, "learning_rate": 9.895048743359042e-06, "loss": 1.5011564493179321, "step": 8899 }, { "epoch": 0.7513480999968342, "grad_norm": 0.1376953125, "learning_rate": 9.889862085130763e-06, "loss": 1.5521293878555298, "step": 8900 }, { "epoch": 0.7514325211316654, "grad_norm": 0.1435546875, "learning_rate": 9.884676451406146e-06, "loss": 1.5127005577087402, "step": 8901 }, { "epoch": 0.7515169422664965, "grad_norm": 0.140625, "learning_rate": 9.87949184253682e-06, "loss": 1.5271536111831665, "step": 8902 }, { "epoch": 0.7516013634013275, "grad_norm": 0.1357421875, "learning_rate": 9.874308258874278e-06, "loss": 1.529605507850647, "step": 8903 }, { "epoch": 0.7516857845361586, "grad_norm": 0.1357421875, "learning_rate": 9.869125700769997e-06, "loss": 1.559322714805603, "step": 8904 }, { "epoch": 0.7517702056709897, "grad_norm": 0.1337890625, "learning_rate": 9.863944168575361e-06, "loss": 1.498789668083191, "step": 8905 }, { "epoch": 0.7518546268058208, "grad_norm": 0.1328125, "learning_rate": 9.858763662641693e-06, "loss": 1.518790602684021, "step": 8906 }, { "epoch": 0.7519390479406519, "grad_norm": 0.138671875, "learning_rate": 9.853584183320252e-06, "loss": 1.507635474205017, "step": 8907 }, { "epoch": 0.752023469075483, "grad_norm": 0.2041015625, "learning_rate": 9.848405730962195e-06, "loss": 1.5303404331207275, "step": 8908 }, { "epoch": 0.7521078902103141, "grad_norm": 0.1396484375, "learning_rate": 9.843228305918655e-06, "loss": 1.5324578285217285, "step": 8909 }, { "epoch": 0.7521923113451453, "grad_norm": 0.1630859375, "learning_rate": 9.83805190854068e-06, "loss": 1.4951828718185425, "step": 8910 }, { "epoch": 0.7522767324799764, "grad_norm": 0.1416015625, "learning_rate": 9.83287653917922e-06, "loss": 1.5527039766311646, "step": 8911 }, { "epoch": 0.7523611536148075, "grad_norm": 0.140625, "learning_rate": 9.827702198185184e-06, "loss": 1.4878089427947998, "step": 8912 }, { "epoch": 0.7524455747496386, "grad_norm": 0.146484375, "learning_rate": 9.822528885909413e-06, "loss": 1.5429368019104004, "step": 8913 }, { "epoch": 0.7525299958844697, "grad_norm": 0.14453125, "learning_rate": 9.817356602702665e-06, "loss": 1.5711860656738281, "step": 8914 }, { "epoch": 0.7526144170193008, "grad_norm": 0.134765625, "learning_rate": 9.812185348915632e-06, "loss": 1.4524202346801758, "step": 8915 }, { "epoch": 0.7526988381541319, "grad_norm": 0.1396484375, "learning_rate": 9.807015124898939e-06, "loss": 1.5026830434799194, "step": 8916 }, { "epoch": 0.752783259288963, "grad_norm": 0.142578125, "learning_rate": 9.801845931003152e-06, "loss": 1.6388603448867798, "step": 8917 }, { "epoch": 0.7528676804237942, "grad_norm": 0.1416015625, "learning_rate": 9.796677767578718e-06, "loss": 1.4866976737976074, "step": 8918 }, { "epoch": 0.7529521015586252, "grad_norm": 0.134765625, "learning_rate": 9.791510634976089e-06, "loss": 1.5277248620986938, "step": 8919 }, { "epoch": 0.7530365226934563, "grad_norm": 0.1484375, "learning_rate": 9.786344533545603e-06, "loss": 1.593324065208435, "step": 8920 }, { "epoch": 0.7531209438282874, "grad_norm": 0.134765625, "learning_rate": 9.781179463637519e-06, "loss": 1.5029802322387695, "step": 8921 }, { "epoch": 0.7532053649631185, "grad_norm": 0.1396484375, "learning_rate": 9.776015425602037e-06, "loss": 1.5497360229492188, "step": 8922 }, { "epoch": 0.7532897860979496, "grad_norm": 0.1357421875, "learning_rate": 9.770852419789322e-06, "loss": 1.562612771987915, "step": 8923 }, { "epoch": 0.7533742072327807, "grad_norm": 0.150390625, "learning_rate": 9.765690446549412e-06, "loss": 1.4558230638504028, "step": 8924 }, { "epoch": 0.7534586283676118, "grad_norm": 0.1357421875, "learning_rate": 9.760529506232306e-06, "loss": 1.4570095539093018, "step": 8925 }, { "epoch": 0.7535430495024429, "grad_norm": 0.1650390625, "learning_rate": 9.75536959918793e-06, "loss": 1.4607633352279663, "step": 8926 }, { "epoch": 0.7536274706372741, "grad_norm": 0.1416015625, "learning_rate": 9.750210725766138e-06, "loss": 1.4786978960037231, "step": 8927 }, { "epoch": 0.7537118917721052, "grad_norm": 0.140625, "learning_rate": 9.745052886316715e-06, "loss": 1.496127963066101, "step": 8928 }, { "epoch": 0.7537963129069363, "grad_norm": 0.1435546875, "learning_rate": 9.739896081189376e-06, "loss": 1.5465048551559448, "step": 8929 }, { "epoch": 0.7538807340417674, "grad_norm": 0.158203125, "learning_rate": 9.73474031073377e-06, "loss": 1.5786912441253662, "step": 8930 }, { "epoch": 0.7539651551765985, "grad_norm": 0.142578125, "learning_rate": 9.729585575299458e-06, "loss": 1.4662514925003052, "step": 8931 }, { "epoch": 0.7540495763114295, "grad_norm": 0.1396484375, "learning_rate": 9.724431875235937e-06, "loss": 1.483487844467163, "step": 8932 }, { "epoch": 0.7541339974462606, "grad_norm": 0.13671875, "learning_rate": 9.71927921089267e-06, "loss": 1.508756399154663, "step": 8933 }, { "epoch": 0.7542184185810917, "grad_norm": 0.146484375, "learning_rate": 9.714127582618995e-06, "loss": 1.5464866161346436, "step": 8934 }, { "epoch": 0.7543028397159229, "grad_norm": 0.1513671875, "learning_rate": 9.708976990764212e-06, "loss": 1.5443997383117676, "step": 8935 }, { "epoch": 0.754387260850754, "grad_norm": 0.1376953125, "learning_rate": 9.703827435677545e-06, "loss": 1.5039117336273193, "step": 8936 }, { "epoch": 0.7544716819855851, "grad_norm": 0.1572265625, "learning_rate": 9.698678917708145e-06, "loss": 1.5069693326950073, "step": 8937 }, { "epoch": 0.7545561031204162, "grad_norm": 0.142578125, "learning_rate": 9.693531437205103e-06, "loss": 1.540520429611206, "step": 8938 }, { "epoch": 0.7546405242552473, "grad_norm": 0.13671875, "learning_rate": 9.688384994517402e-06, "loss": 1.5017950534820557, "step": 8939 }, { "epoch": 0.7547249453900784, "grad_norm": 0.140625, "learning_rate": 9.683239589994012e-06, "loss": 1.4892752170562744, "step": 8940 }, { "epoch": 0.7548093665249095, "grad_norm": 0.1376953125, "learning_rate": 9.678095223983805e-06, "loss": 1.5630886554718018, "step": 8941 }, { "epoch": 0.7548937876597406, "grad_norm": 0.1396484375, "learning_rate": 9.67295189683555e-06, "loss": 1.4814108610153198, "step": 8942 }, { "epoch": 0.7549782087945717, "grad_norm": 0.154296875, "learning_rate": 9.667809608898019e-06, "loss": 1.525305151939392, "step": 8943 }, { "epoch": 0.7550626299294029, "grad_norm": 0.150390625, "learning_rate": 9.662668360519839e-06, "loss": 1.5057259798049927, "step": 8944 }, { "epoch": 0.755147051064234, "grad_norm": 0.1435546875, "learning_rate": 9.65752815204961e-06, "loss": 1.4908579587936401, "step": 8945 }, { "epoch": 0.7552314721990651, "grad_norm": 0.1318359375, "learning_rate": 9.65238898383585e-06, "loss": 1.5265742540359497, "step": 8946 }, { "epoch": 0.7553158933338961, "grad_norm": 0.1396484375, "learning_rate": 9.64725085622701e-06, "loss": 1.505751609802246, "step": 8947 }, { "epoch": 0.7554003144687272, "grad_norm": 0.1416015625, "learning_rate": 9.642113769571473e-06, "loss": 1.5397403240203857, "step": 8948 }, { "epoch": 0.7554847356035583, "grad_norm": 0.1513671875, "learning_rate": 9.636977724217522e-06, "loss": 1.5164289474487305, "step": 8949 }, { "epoch": 0.7555691567383894, "grad_norm": 0.1435546875, "learning_rate": 9.631842720513414e-06, "loss": 1.5371387004852295, "step": 8950 }, { "epoch": 0.7556535778732205, "grad_norm": 0.140625, "learning_rate": 9.626708758807323e-06, "loss": 1.5033929347991943, "step": 8951 }, { "epoch": 0.7557379990080517, "grad_norm": 0.1435546875, "learning_rate": 9.62157583944732e-06, "loss": 1.4928289651870728, "step": 8952 }, { "epoch": 0.7558224201428828, "grad_norm": 0.1474609375, "learning_rate": 9.616443962781439e-06, "loss": 1.5371335744857788, "step": 8953 }, { "epoch": 0.7559068412777139, "grad_norm": 0.138671875, "learning_rate": 9.611313129157635e-06, "loss": 1.472618818283081, "step": 8954 }, { "epoch": 0.755991262412545, "grad_norm": 0.1669921875, "learning_rate": 9.606183338923791e-06, "loss": 1.5775448083877563, "step": 8955 }, { "epoch": 0.7560756835473761, "grad_norm": 0.138671875, "learning_rate": 9.60105459242772e-06, "loss": 1.4904354810714722, "step": 8956 }, { "epoch": 0.7561601046822072, "grad_norm": 0.134765625, "learning_rate": 9.595926890017157e-06, "loss": 1.5332295894622803, "step": 8957 }, { "epoch": 0.7562445258170383, "grad_norm": 0.1435546875, "learning_rate": 9.590800232039781e-06, "loss": 1.5507372617721558, "step": 8958 }, { "epoch": 0.7563289469518694, "grad_norm": 0.1416015625, "learning_rate": 9.585674618843187e-06, "loss": 1.5321978330612183, "step": 8959 }, { "epoch": 0.7564133680867005, "grad_norm": 0.1435546875, "learning_rate": 9.580550050774906e-06, "loss": 1.4949641227722168, "step": 8960 }, { "epoch": 0.7564977892215317, "grad_norm": 0.1298828125, "learning_rate": 9.575426528182401e-06, "loss": 1.4645344018936157, "step": 8961 }, { "epoch": 0.7565822103563627, "grad_norm": 0.140625, "learning_rate": 9.570304051413048e-06, "loss": 1.5162123441696167, "step": 8962 }, { "epoch": 0.7566666314911938, "grad_norm": 0.142578125, "learning_rate": 9.565182620814159e-06, "loss": 1.510652780532837, "step": 8963 }, { "epoch": 0.7567510526260249, "grad_norm": 0.1396484375, "learning_rate": 9.560062236733006e-06, "loss": 1.5667202472686768, "step": 8964 }, { "epoch": 0.756835473760856, "grad_norm": 0.1416015625, "learning_rate": 9.554942899516735e-06, "loss": 1.5138815641403198, "step": 8965 }, { "epoch": 0.7569198948956871, "grad_norm": 0.1396484375, "learning_rate": 9.549824609512465e-06, "loss": 1.59004807472229, "step": 8966 }, { "epoch": 0.7570043160305182, "grad_norm": 0.1328125, "learning_rate": 9.544707367067221e-06, "loss": 1.4851329326629639, "step": 8967 }, { "epoch": 0.7570887371653493, "grad_norm": 0.1298828125, "learning_rate": 9.539591172527965e-06, "loss": 1.5000333786010742, "step": 8968 }, { "epoch": 0.7571731583001805, "grad_norm": 0.15234375, "learning_rate": 9.534476026241593e-06, "loss": 1.5553761720657349, "step": 8969 }, { "epoch": 0.7572575794350116, "grad_norm": 0.158203125, "learning_rate": 9.529361928554919e-06, "loss": 1.6002804040908813, "step": 8970 }, { "epoch": 0.7573420005698427, "grad_norm": 0.158203125, "learning_rate": 9.524248879814702e-06, "loss": 1.620296835899353, "step": 8971 }, { "epoch": 0.7574264217046738, "grad_norm": 0.1357421875, "learning_rate": 9.519136880367602e-06, "loss": 1.605644941329956, "step": 8972 }, { "epoch": 0.7575108428395049, "grad_norm": 0.1533203125, "learning_rate": 9.514025930560222e-06, "loss": 1.5362987518310547, "step": 8973 }, { "epoch": 0.757595263974336, "grad_norm": 0.1318359375, "learning_rate": 9.508916030739124e-06, "loss": 1.488653302192688, "step": 8974 }, { "epoch": 0.7576796851091671, "grad_norm": 0.1552734375, "learning_rate": 9.503807181250749e-06, "loss": 1.5910791158676147, "step": 8975 }, { "epoch": 0.7577641062439981, "grad_norm": 0.1357421875, "learning_rate": 9.498699382441493e-06, "loss": 1.4701759815216064, "step": 8976 }, { "epoch": 0.7578485273788292, "grad_norm": 0.1396484375, "learning_rate": 9.49359263465768e-06, "loss": 1.5799541473388672, "step": 8977 }, { "epoch": 0.7579329485136604, "grad_norm": 0.134765625, "learning_rate": 9.488486938245559e-06, "loss": 1.4567960500717163, "step": 8978 }, { "epoch": 0.7580173696484915, "grad_norm": 0.1513671875, "learning_rate": 9.483382293551315e-06, "loss": 1.514803171157837, "step": 8979 }, { "epoch": 0.7581017907833226, "grad_norm": 0.146484375, "learning_rate": 9.478278700921035e-06, "loss": 1.5219926834106445, "step": 8980 }, { "epoch": 0.7581862119181537, "grad_norm": 0.134765625, "learning_rate": 9.473176160700772e-06, "loss": 1.479650616645813, "step": 8981 }, { "epoch": 0.7582706330529848, "grad_norm": 0.140625, "learning_rate": 9.468074673236498e-06, "loss": 1.5058815479278564, "step": 8982 }, { "epoch": 0.7583550541878159, "grad_norm": 0.1357421875, "learning_rate": 9.462974238874079e-06, "loss": 1.5533626079559326, "step": 8983 }, { "epoch": 0.758439475322647, "grad_norm": 0.1416015625, "learning_rate": 9.45787485795937e-06, "loss": 1.5035077333450317, "step": 8984 }, { "epoch": 0.7585238964574781, "grad_norm": 0.1435546875, "learning_rate": 9.452776530838096e-06, "loss": 1.554318904876709, "step": 8985 }, { "epoch": 0.7586083175923093, "grad_norm": 0.1396484375, "learning_rate": 9.44767925785594e-06, "loss": 1.5955207347869873, "step": 8986 }, { "epoch": 0.7586927387271404, "grad_norm": 0.1416015625, "learning_rate": 9.442583039358516e-06, "loss": 1.5494097471237183, "step": 8987 }, { "epoch": 0.7587771598619715, "grad_norm": 0.138671875, "learning_rate": 9.437487875691357e-06, "loss": 1.5135653018951416, "step": 8988 }, { "epoch": 0.7588615809968026, "grad_norm": 0.130859375, "learning_rate": 9.432393767199935e-06, "loss": 1.5274938344955444, "step": 8989 }, { "epoch": 0.7589460021316337, "grad_norm": 0.1416015625, "learning_rate": 9.427300714229616e-06, "loss": 1.5037308931350708, "step": 8990 }, { "epoch": 0.7590304232664647, "grad_norm": 0.1337890625, "learning_rate": 9.422208717125752e-06, "loss": 1.4889568090438843, "step": 8991 }, { "epoch": 0.7591148444012958, "grad_norm": 0.142578125, "learning_rate": 9.417117776233588e-06, "loss": 1.5222442150115967, "step": 8992 }, { "epoch": 0.7591992655361269, "grad_norm": 0.146484375, "learning_rate": 9.41202789189829e-06, "loss": 1.5841643810272217, "step": 8993 }, { "epoch": 0.759283686670958, "grad_norm": 0.1357421875, "learning_rate": 9.406939064464957e-06, "loss": 1.5826786756515503, "step": 8994 }, { "epoch": 0.7593681078057892, "grad_norm": 0.1298828125, "learning_rate": 9.401851294278655e-06, "loss": 1.492297887802124, "step": 8995 }, { "epoch": 0.7594525289406203, "grad_norm": 0.1337890625, "learning_rate": 9.39676458168432e-06, "loss": 1.540044903755188, "step": 8996 }, { "epoch": 0.7595369500754514, "grad_norm": 0.142578125, "learning_rate": 9.39167892702685e-06, "loss": 1.5859452486038208, "step": 8997 }, { "epoch": 0.7596213712102825, "grad_norm": 0.1572265625, "learning_rate": 9.386594330651069e-06, "loss": 1.5489155054092407, "step": 8998 }, { "epoch": 0.7597057923451136, "grad_norm": 0.13671875, "learning_rate": 9.381510792901718e-06, "loss": 1.4751847982406616, "step": 8999 }, { "epoch": 0.7597902134799447, "grad_norm": 0.1328125, "learning_rate": 9.37642831412348e-06, "loss": 1.5160175561904907, "step": 9000 }, { "epoch": 0.7598746346147758, "grad_norm": 0.1376953125, "learning_rate": 9.371346894660956e-06, "loss": 1.5832672119140625, "step": 9001 }, { "epoch": 0.7599590557496069, "grad_norm": 0.1357421875, "learning_rate": 9.36626653485869e-06, "loss": 1.4436203241348267, "step": 9002 }, { "epoch": 0.7600434768844381, "grad_norm": 0.1298828125, "learning_rate": 9.36118723506112e-06, "loss": 1.4520090818405151, "step": 9003 }, { "epoch": 0.7601278980192692, "grad_norm": 0.138671875, "learning_rate": 9.356108995612637e-06, "loss": 1.4891471862792969, "step": 9004 }, { "epoch": 0.7602123191541003, "grad_norm": 0.1337890625, "learning_rate": 9.351031816857584e-06, "loss": 1.4680336713790894, "step": 9005 }, { "epoch": 0.7602967402889313, "grad_norm": 0.1396484375, "learning_rate": 9.345955699140182e-06, "loss": 1.5127942562103271, "step": 9006 }, { "epoch": 0.7603811614237624, "grad_norm": 0.140625, "learning_rate": 9.34088064280461e-06, "loss": 1.4870996475219727, "step": 9007 }, { "epoch": 0.7604655825585935, "grad_norm": 0.1376953125, "learning_rate": 9.33580664819497e-06, "loss": 1.4838658571243286, "step": 9008 }, { "epoch": 0.7605500036934246, "grad_norm": 0.1435546875, "learning_rate": 9.330733715655293e-06, "loss": 1.544588327407837, "step": 9009 }, { "epoch": 0.7606344248282557, "grad_norm": 0.1376953125, "learning_rate": 9.325661845529533e-06, "loss": 1.5844041109085083, "step": 9010 }, { "epoch": 0.7607188459630868, "grad_norm": 0.14453125, "learning_rate": 9.320591038161574e-06, "loss": 1.522180199623108, "step": 9011 }, { "epoch": 0.760803267097918, "grad_norm": 0.1572265625, "learning_rate": 9.315521293895232e-06, "loss": 1.6079903841018677, "step": 9012 }, { "epoch": 0.7608876882327491, "grad_norm": 0.134765625, "learning_rate": 9.310452613074259e-06, "loss": 1.5187113285064697, "step": 9013 }, { "epoch": 0.7609721093675802, "grad_norm": 0.142578125, "learning_rate": 9.305384996042287e-06, "loss": 1.488551378250122, "step": 9014 }, { "epoch": 0.7610565305024113, "grad_norm": 0.1630859375, "learning_rate": 9.300318443142961e-06, "loss": 1.6650373935699463, "step": 9015 }, { "epoch": 0.7611409516372424, "grad_norm": 0.138671875, "learning_rate": 9.295252954719772e-06, "loss": 1.5230755805969238, "step": 9016 }, { "epoch": 0.7612253727720735, "grad_norm": 0.14453125, "learning_rate": 9.290188531116179e-06, "loss": 1.506620168685913, "step": 9017 }, { "epoch": 0.7613097939069046, "grad_norm": 0.140625, "learning_rate": 9.285125172675566e-06, "loss": 1.5470011234283447, "step": 9018 }, { "epoch": 0.7613942150417357, "grad_norm": 0.14453125, "learning_rate": 9.280062879741242e-06, "loss": 1.5243557691574097, "step": 9019 }, { "epoch": 0.7614786361765669, "grad_norm": 0.2080078125, "learning_rate": 9.275001652656446e-06, "loss": 1.4878932237625122, "step": 9020 }, { "epoch": 0.761563057311398, "grad_norm": 0.134765625, "learning_rate": 9.26994149176432e-06, "loss": 1.526123285293579, "step": 9021 }, { "epoch": 0.761647478446229, "grad_norm": 0.1376953125, "learning_rate": 9.264882397407981e-06, "loss": 1.5241247415542603, "step": 9022 }, { "epoch": 0.7617318995810601, "grad_norm": 0.1337890625, "learning_rate": 9.259824369930445e-06, "loss": 1.4377975463867188, "step": 9023 }, { "epoch": 0.7618163207158912, "grad_norm": 0.1318359375, "learning_rate": 9.254767409674634e-06, "loss": 1.48634672164917, "step": 9024 }, { "epoch": 0.7619007418507223, "grad_norm": 0.1484375, "learning_rate": 9.249711516983448e-06, "loss": 1.5383987426757812, "step": 9025 }, { "epoch": 0.7619851629855534, "grad_norm": 0.1376953125, "learning_rate": 9.244656692199688e-06, "loss": 1.4471925497055054, "step": 9026 }, { "epoch": 0.7620695841203845, "grad_norm": 0.14453125, "learning_rate": 9.239602935666068e-06, "loss": 1.4926726818084717, "step": 9027 }, { "epoch": 0.7621540052552156, "grad_norm": 0.1376953125, "learning_rate": 9.23455024772525e-06, "loss": 1.538689374923706, "step": 9028 }, { "epoch": 0.7622384263900468, "grad_norm": 0.142578125, "learning_rate": 9.229498628719819e-06, "loss": 1.4813323020935059, "step": 9029 }, { "epoch": 0.7623228475248779, "grad_norm": 0.1513671875, "learning_rate": 9.22444807899229e-06, "loss": 1.6149851083755493, "step": 9030 }, { "epoch": 0.762407268659709, "grad_norm": 0.1416015625, "learning_rate": 9.2193985988851e-06, "loss": 1.553113341331482, "step": 9031 }, { "epoch": 0.7624916897945401, "grad_norm": 0.14453125, "learning_rate": 9.214350188740619e-06, "loss": 1.5650112628936768, "step": 9032 }, { "epoch": 0.7625761109293712, "grad_norm": 0.1376953125, "learning_rate": 9.209302848901147e-06, "loss": 1.516353964805603, "step": 9033 }, { "epoch": 0.7626605320642023, "grad_norm": 0.1474609375, "learning_rate": 9.204256579708887e-06, "loss": 1.5721817016601562, "step": 9034 }, { "epoch": 0.7627449531990333, "grad_norm": 0.142578125, "learning_rate": 9.199211381505993e-06, "loss": 1.525189995765686, "step": 9035 }, { "epoch": 0.7628293743338644, "grad_norm": 0.142578125, "learning_rate": 9.19416725463456e-06, "loss": 1.5233873128890991, "step": 9036 }, { "epoch": 0.7629137954686955, "grad_norm": 0.1376953125, "learning_rate": 9.189124199436574e-06, "loss": 1.4957795143127441, "step": 9037 }, { "epoch": 0.7629982166035267, "grad_norm": 0.1455078125, "learning_rate": 9.184082216253972e-06, "loss": 1.4573523998260498, "step": 9038 }, { "epoch": 0.7630826377383578, "grad_norm": 0.1318359375, "learning_rate": 9.179041305428612e-06, "loss": 1.5068678855895996, "step": 9039 }, { "epoch": 0.7631670588731889, "grad_norm": 0.1435546875, "learning_rate": 9.174001467302278e-06, "loss": 1.55949866771698, "step": 9040 }, { "epoch": 0.76325148000802, "grad_norm": 0.140625, "learning_rate": 9.168962702216687e-06, "loss": 1.4878007173538208, "step": 9041 }, { "epoch": 0.7633359011428511, "grad_norm": 0.1455078125, "learning_rate": 9.16392501051348e-06, "loss": 1.6170809268951416, "step": 9042 }, { "epoch": 0.7634203222776822, "grad_norm": 0.1640625, "learning_rate": 9.158888392534218e-06, "loss": 1.5051509141921997, "step": 9043 }, { "epoch": 0.7635047434125133, "grad_norm": 0.1416015625, "learning_rate": 9.153852848620412e-06, "loss": 1.4796663522720337, "step": 9044 }, { "epoch": 0.7635891645473444, "grad_norm": 0.1328125, "learning_rate": 9.148818379113452e-06, "loss": 1.5561585426330566, "step": 9045 }, { "epoch": 0.7636735856821756, "grad_norm": 0.138671875, "learning_rate": 9.143784984354725e-06, "loss": 1.510244369506836, "step": 9046 }, { "epoch": 0.7637580068170067, "grad_norm": 0.1337890625, "learning_rate": 9.138752664685482e-06, "loss": 1.5509902238845825, "step": 9047 }, { "epoch": 0.7638424279518378, "grad_norm": 0.1416015625, "learning_rate": 9.133721420446934e-06, "loss": 1.5749812126159668, "step": 9048 }, { "epoch": 0.7639268490866689, "grad_norm": 0.1396484375, "learning_rate": 9.12869125198021e-06, "loss": 1.5724754333496094, "step": 9049 }, { "epoch": 0.7640112702215, "grad_norm": 0.1298828125, "learning_rate": 9.123662159626367e-06, "loss": 1.4982188940048218, "step": 9050 }, { "epoch": 0.764095691356331, "grad_norm": 0.1337890625, "learning_rate": 9.118634143726401e-06, "loss": 1.573482632637024, "step": 9051 }, { "epoch": 0.7641801124911621, "grad_norm": 0.150390625, "learning_rate": 9.1136072046212e-06, "loss": 1.4560941457748413, "step": 9052 }, { "epoch": 0.7642645336259932, "grad_norm": 0.1357421875, "learning_rate": 9.10858134265162e-06, "loss": 1.6011734008789062, "step": 9053 }, { "epoch": 0.7643489547608243, "grad_norm": 0.13671875, "learning_rate": 9.103556558158436e-06, "loss": 1.5225536823272705, "step": 9054 }, { "epoch": 0.7644333758956555, "grad_norm": 0.1455078125, "learning_rate": 9.098532851482308e-06, "loss": 1.512168526649475, "step": 9055 }, { "epoch": 0.7645177970304866, "grad_norm": 0.1416015625, "learning_rate": 9.09351022296389e-06, "loss": 1.5371215343475342, "step": 9056 }, { "epoch": 0.7646022181653177, "grad_norm": 0.1328125, "learning_rate": 9.088488672943707e-06, "loss": 1.4722371101379395, "step": 9057 }, { "epoch": 0.7646866393001488, "grad_norm": 0.1318359375, "learning_rate": 9.083468201762238e-06, "loss": 1.4814733266830444, "step": 9058 }, { "epoch": 0.7647710604349799, "grad_norm": 0.138671875, "learning_rate": 9.078448809759881e-06, "loss": 1.4679756164550781, "step": 9059 }, { "epoch": 0.764855481569811, "grad_norm": 0.1455078125, "learning_rate": 9.073430497276969e-06, "loss": 1.488836407661438, "step": 9060 }, { "epoch": 0.7649399027046421, "grad_norm": 0.140625, "learning_rate": 9.06841326465375e-06, "loss": 1.5541132688522339, "step": 9061 }, { "epoch": 0.7650243238394732, "grad_norm": 0.1376953125, "learning_rate": 9.063397112230404e-06, "loss": 1.5764530897140503, "step": 9062 }, { "epoch": 0.7651087449743044, "grad_norm": 0.1337890625, "learning_rate": 9.058382040347044e-06, "loss": 1.4935245513916016, "step": 9063 }, { "epoch": 0.7651931661091355, "grad_norm": 0.1337890625, "learning_rate": 9.053368049343706e-06, "loss": 1.5297285318374634, "step": 9064 }, { "epoch": 0.7652775872439666, "grad_norm": 0.142578125, "learning_rate": 9.048355139560338e-06, "loss": 1.5346794128417969, "step": 9065 }, { "epoch": 0.7653620083787976, "grad_norm": 0.142578125, "learning_rate": 9.043343311336824e-06, "loss": 1.5454038381576538, "step": 9066 }, { "epoch": 0.7654464295136287, "grad_norm": 0.1474609375, "learning_rate": 9.038332565013008e-06, "loss": 1.5746365785598755, "step": 9067 }, { "epoch": 0.7655308506484598, "grad_norm": 0.146484375, "learning_rate": 9.0333229009286e-06, "loss": 1.5201492309570312, "step": 9068 }, { "epoch": 0.7656152717832909, "grad_norm": 0.150390625, "learning_rate": 9.028314319423278e-06, "loss": 1.4695639610290527, "step": 9069 }, { "epoch": 0.765699692918122, "grad_norm": 0.1416015625, "learning_rate": 9.023306820836638e-06, "loss": 1.5584741830825806, "step": 9070 }, { "epoch": 0.7657841140529531, "grad_norm": 0.142578125, "learning_rate": 9.018300405508195e-06, "loss": 1.4983431100845337, "step": 9071 }, { "epoch": 0.7658685351877843, "grad_norm": 0.1484375, "learning_rate": 9.013295073777403e-06, "loss": 1.511303424835205, "step": 9072 }, { "epoch": 0.7659529563226154, "grad_norm": 0.1357421875, "learning_rate": 9.008290825983632e-06, "loss": 1.5030523538589478, "step": 9073 }, { "epoch": 0.7660373774574465, "grad_norm": 0.1279296875, "learning_rate": 9.003287662466181e-06, "loss": 1.5255192518234253, "step": 9074 }, { "epoch": 0.7661217985922776, "grad_norm": 0.1318359375, "learning_rate": 8.998285583564283e-06, "loss": 1.457935094833374, "step": 9075 }, { "epoch": 0.7662062197271087, "grad_norm": 0.1572265625, "learning_rate": 8.993284589617073e-06, "loss": 1.4407340288162231, "step": 9076 }, { "epoch": 0.7662906408619398, "grad_norm": 0.142578125, "learning_rate": 8.988284680963657e-06, "loss": 1.4062625169754028, "step": 9077 }, { "epoch": 0.7663750619967709, "grad_norm": 0.1484375, "learning_rate": 8.98328585794302e-06, "loss": 1.5274118185043335, "step": 9078 }, { "epoch": 0.766459483131602, "grad_norm": 0.14453125, "learning_rate": 8.978288120894101e-06, "loss": 1.5131895542144775, "step": 9079 }, { "epoch": 0.7665439042664332, "grad_norm": 0.1416015625, "learning_rate": 8.973291470155756e-06, "loss": 1.573854923248291, "step": 9080 }, { "epoch": 0.7666283254012642, "grad_norm": 0.138671875, "learning_rate": 8.968295906066776e-06, "loss": 1.6052647829055786, "step": 9081 }, { "epoch": 0.7667127465360953, "grad_norm": 0.1396484375, "learning_rate": 8.963301428965867e-06, "loss": 1.519490122795105, "step": 9082 }, { "epoch": 0.7667971676709264, "grad_norm": 0.1533203125, "learning_rate": 8.958308039191668e-06, "loss": 1.539962649345398, "step": 9083 }, { "epoch": 0.7668815888057575, "grad_norm": 0.1416015625, "learning_rate": 8.953315737082743e-06, "loss": 1.4563827514648438, "step": 9084 }, { "epoch": 0.7669660099405886, "grad_norm": 0.14453125, "learning_rate": 8.94832452297759e-06, "loss": 1.5118255615234375, "step": 9085 }, { "epoch": 0.7670504310754197, "grad_norm": 0.142578125, "learning_rate": 8.943334397214604e-06, "loss": 1.5347321033477783, "step": 9086 }, { "epoch": 0.7671348522102508, "grad_norm": 0.169921875, "learning_rate": 8.938345360132155e-06, "loss": 1.508331298828125, "step": 9087 }, { "epoch": 0.7672192733450819, "grad_norm": 0.1337890625, "learning_rate": 8.933357412068489e-06, "loss": 1.5418927669525146, "step": 9088 }, { "epoch": 0.7673036944799131, "grad_norm": 0.140625, "learning_rate": 8.928370553361812e-06, "loss": 1.584783911705017, "step": 9089 }, { "epoch": 0.7673881156147442, "grad_norm": 0.1279296875, "learning_rate": 8.923384784350239e-06, "loss": 1.4286119937896729, "step": 9090 }, { "epoch": 0.7674725367495753, "grad_norm": 0.18359375, "learning_rate": 8.918400105371824e-06, "loss": 1.578956961631775, "step": 9091 }, { "epoch": 0.7675569578844064, "grad_norm": 0.1484375, "learning_rate": 8.913416516764536e-06, "loss": 1.5044832229614258, "step": 9092 }, { "epoch": 0.7676413790192375, "grad_norm": 0.146484375, "learning_rate": 8.908434018866274e-06, "loss": 1.490065574645996, "step": 9093 }, { "epoch": 0.7677258001540685, "grad_norm": 0.138671875, "learning_rate": 8.903452612014865e-06, "loss": 1.5214155912399292, "step": 9094 }, { "epoch": 0.7678102212888996, "grad_norm": 0.134765625, "learning_rate": 8.89847229654807e-06, "loss": 1.3744980096817017, "step": 9095 }, { "epoch": 0.7678946424237307, "grad_norm": 0.1357421875, "learning_rate": 8.893493072803539e-06, "loss": 1.5157960653305054, "step": 9096 }, { "epoch": 0.7679790635585619, "grad_norm": 0.142578125, "learning_rate": 8.888514941118897e-06, "loss": 1.5754728317260742, "step": 9097 }, { "epoch": 0.768063484693393, "grad_norm": 0.14453125, "learning_rate": 8.883537901831681e-06, "loss": 1.5822219848632812, "step": 9098 }, { "epoch": 0.7681479058282241, "grad_norm": 0.1337890625, "learning_rate": 8.878561955279326e-06, "loss": 1.5087871551513672, "step": 9099 }, { "epoch": 0.7682323269630552, "grad_norm": 0.14453125, "learning_rate": 8.873587101799222e-06, "loss": 1.5562410354614258, "step": 9100 }, { "epoch": 0.7683167480978863, "grad_norm": 0.1357421875, "learning_rate": 8.86861334172867e-06, "loss": 1.5427742004394531, "step": 9101 }, { "epoch": 0.7684011692327174, "grad_norm": 0.13671875, "learning_rate": 8.863640675404913e-06, "loss": 1.474717378616333, "step": 9102 }, { "epoch": 0.7684855903675485, "grad_norm": 0.126953125, "learning_rate": 8.858669103165103e-06, "loss": 1.4729256629943848, "step": 9103 }, { "epoch": 0.7685700115023796, "grad_norm": 0.1396484375, "learning_rate": 8.85369862534633e-06, "loss": 1.556643009185791, "step": 9104 }, { "epoch": 0.7686544326372107, "grad_norm": 0.142578125, "learning_rate": 8.848729242285606e-06, "loss": 1.5236822366714478, "step": 9105 }, { "epoch": 0.7687388537720419, "grad_norm": 0.134765625, "learning_rate": 8.843760954319855e-06, "loss": 1.53607976436615, "step": 9106 }, { "epoch": 0.768823274906873, "grad_norm": 0.1337890625, "learning_rate": 8.838793761785935e-06, "loss": 1.5455405712127686, "step": 9107 }, { "epoch": 0.7689076960417041, "grad_norm": 0.13671875, "learning_rate": 8.833827665020663e-06, "loss": 1.5626187324523926, "step": 9108 }, { "epoch": 0.7689921171765352, "grad_norm": 0.1279296875, "learning_rate": 8.828862664360723e-06, "loss": 1.5008786916732788, "step": 9109 }, { "epoch": 0.7690765383113662, "grad_norm": 0.154296875, "learning_rate": 8.823898760142759e-06, "loss": 1.5555545091629028, "step": 9110 }, { "epoch": 0.7691609594461973, "grad_norm": 0.1416015625, "learning_rate": 8.818935952703359e-06, "loss": 1.5827583074569702, "step": 9111 }, { "epoch": 0.7692453805810284, "grad_norm": 0.1376953125, "learning_rate": 8.813974242378984e-06, "loss": 1.5596071481704712, "step": 9112 }, { "epoch": 0.7693298017158595, "grad_norm": 0.1298828125, "learning_rate": 8.809013629506062e-06, "loss": 1.5046614408493042, "step": 9113 }, { "epoch": 0.7694142228506907, "grad_norm": 0.15234375, "learning_rate": 8.804054114420938e-06, "loss": 1.5506318807601929, "step": 9114 }, { "epoch": 0.7694986439855218, "grad_norm": 0.1435546875, "learning_rate": 8.79909569745987e-06, "loss": 1.4914952516555786, "step": 9115 }, { "epoch": 0.7695830651203529, "grad_norm": 0.1376953125, "learning_rate": 8.794138378959066e-06, "loss": 1.5456572771072388, "step": 9116 }, { "epoch": 0.769667486255184, "grad_norm": 0.1474609375, "learning_rate": 8.789182159254616e-06, "loss": 1.5576122999191284, "step": 9117 }, { "epoch": 0.7697519073900151, "grad_norm": 0.146484375, "learning_rate": 8.784227038682599e-06, "loss": 1.553167700767517, "step": 9118 }, { "epoch": 0.7698363285248462, "grad_norm": 0.15234375, "learning_rate": 8.779273017578956e-06, "loss": 1.49504554271698, "step": 9119 }, { "epoch": 0.7699207496596773, "grad_norm": 0.1337890625, "learning_rate": 8.774320096279595e-06, "loss": 1.5556411743164062, "step": 9120 }, { "epoch": 0.7700051707945084, "grad_norm": 0.1455078125, "learning_rate": 8.769368275120332e-06, "loss": 1.5393059253692627, "step": 9121 }, { "epoch": 0.7700895919293395, "grad_norm": 0.142578125, "learning_rate": 8.764417554436913e-06, "loss": 1.4667268991470337, "step": 9122 }, { "epoch": 0.7701740130641707, "grad_norm": 0.1357421875, "learning_rate": 8.759467934565008e-06, "loss": 1.5359810590744019, "step": 9123 }, { "epoch": 0.7702584341990018, "grad_norm": 0.142578125, "learning_rate": 8.754519415840215e-06, "loss": 1.52428138256073, "step": 9124 }, { "epoch": 0.7703428553338328, "grad_norm": 0.134765625, "learning_rate": 8.749571998598052e-06, "loss": 1.4551868438720703, "step": 9125 }, { "epoch": 0.7704272764686639, "grad_norm": 0.15625, "learning_rate": 8.744625683173979e-06, "loss": 1.493475079536438, "step": 9126 }, { "epoch": 0.770511697603495, "grad_norm": 0.1328125, "learning_rate": 8.739680469903341e-06, "loss": 1.5251952409744263, "step": 9127 }, { "epoch": 0.7705961187383261, "grad_norm": 0.134765625, "learning_rate": 8.734736359121463e-06, "loss": 1.459848165512085, "step": 9128 }, { "epoch": 0.7706805398731572, "grad_norm": 0.1416015625, "learning_rate": 8.72979335116356e-06, "loss": 1.5404844284057617, "step": 9129 }, { "epoch": 0.7707649610079883, "grad_norm": 0.1318359375, "learning_rate": 8.72485144636477e-06, "loss": 1.5367486476898193, "step": 9130 }, { "epoch": 0.7708493821428195, "grad_norm": 0.1337890625, "learning_rate": 8.719910645060172e-06, "loss": 1.5283254384994507, "step": 9131 }, { "epoch": 0.7709338032776506, "grad_norm": 0.138671875, "learning_rate": 8.714970947584764e-06, "loss": 1.503298044204712, "step": 9132 }, { "epoch": 0.7710182244124817, "grad_norm": 0.1435546875, "learning_rate": 8.71003235427347e-06, "loss": 1.5702675580978394, "step": 9133 }, { "epoch": 0.7711026455473128, "grad_norm": 0.1337890625, "learning_rate": 8.70509486546114e-06, "loss": 1.503838062286377, "step": 9134 }, { "epoch": 0.7711870666821439, "grad_norm": 0.14453125, "learning_rate": 8.700158481482543e-06, "loss": 1.5612642765045166, "step": 9135 }, { "epoch": 0.771271487816975, "grad_norm": 0.1494140625, "learning_rate": 8.69522320267239e-06, "loss": 1.5672513246536255, "step": 9136 }, { "epoch": 0.7713559089518061, "grad_norm": 0.138671875, "learning_rate": 8.690289029365279e-06, "loss": 1.486977458000183, "step": 9137 }, { "epoch": 0.7714403300866371, "grad_norm": 0.1337890625, "learning_rate": 8.685355961895784e-06, "loss": 1.4645029306411743, "step": 9138 }, { "epoch": 0.7715247512214682, "grad_norm": 0.14453125, "learning_rate": 8.680424000598378e-06, "loss": 1.4523876905441284, "step": 9139 }, { "epoch": 0.7716091723562994, "grad_norm": 0.138671875, "learning_rate": 8.675493145807443e-06, "loss": 1.623608112335205, "step": 9140 }, { "epoch": 0.7716935934911305, "grad_norm": 0.1396484375, "learning_rate": 8.670563397857311e-06, "loss": 1.6130551099777222, "step": 9141 }, { "epoch": 0.7717780146259616, "grad_norm": 0.1337890625, "learning_rate": 8.665634757082233e-06, "loss": 1.429590106010437, "step": 9142 }, { "epoch": 0.7718624357607927, "grad_norm": 0.1435546875, "learning_rate": 8.66070722381638e-06, "loss": 1.6492677927017212, "step": 9143 }, { "epoch": 0.7719468568956238, "grad_norm": 0.1328125, "learning_rate": 8.655780798393854e-06, "loss": 1.5128774642944336, "step": 9144 }, { "epoch": 0.7720312780304549, "grad_norm": 0.1435546875, "learning_rate": 8.650855481148672e-06, "loss": 1.5490542650222778, "step": 9145 } ], "logging_steps": 1, "max_steps": 12439, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 622, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": true, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 5.25576286316868e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }