{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9983597594313833, "eval_steps": 500, "global_step": 1371, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002186987424822307, "grad_norm": 3.1976592540740967, "learning_rate": 0.0, "loss": 0.7592, "step": 1 }, { "epoch": 0.004373974849644614, "grad_norm": 2.356712818145752, "learning_rate": 3.6231884057971015e-07, "loss": 0.8143, "step": 2 }, { "epoch": 0.0065609622744669215, "grad_norm": 1.8352482318878174, "learning_rate": 7.246376811594203e-07, "loss": 0.8142, "step": 3 }, { "epoch": 0.008747949699289229, "grad_norm": 2.193833589553833, "learning_rate": 1.0869565217391306e-06, "loss": 0.6704, "step": 4 }, { "epoch": 0.010934937124111536, "grad_norm": 5.988864898681641, "learning_rate": 1.4492753623188406e-06, "loss": 0.7474, "step": 5 }, { "epoch": 0.013121924548933843, "grad_norm": 2.2405309677124023, "learning_rate": 1.8115942028985508e-06, "loss": 0.9997, "step": 6 }, { "epoch": 0.01530891197375615, "grad_norm": 2.8080081939697266, "learning_rate": 2.173913043478261e-06, "loss": 0.67, "step": 7 }, { "epoch": 0.017495899398578457, "grad_norm": 3.564610004425049, "learning_rate": 2.5362318840579714e-06, "loss": 0.9505, "step": 8 }, { "epoch": 0.019682886823400764, "grad_norm": 3.3014557361602783, "learning_rate": 2.898550724637681e-06, "loss": 0.9525, "step": 9 }, { "epoch": 0.02186987424822307, "grad_norm": 2.485926866531372, "learning_rate": 3.2608695652173914e-06, "loss": 0.9262, "step": 10 }, { "epoch": 0.02405686167304538, "grad_norm": 2.0801198482513428, "learning_rate": 3.6231884057971017e-06, "loss": 0.8158, "step": 11 }, { "epoch": 0.026243849097867686, "grad_norm": 3.4822592735290527, "learning_rate": 3.9855072463768115e-06, "loss": 0.8672, "step": 12 }, { "epoch": 0.028430836522689993, "grad_norm": 2.4607632160186768, "learning_rate": 4.347826086956522e-06, "loss": 0.7284, "step": 13 }, { "epoch": 0.0306178239475123, "grad_norm": 1.4971569776535034, "learning_rate": 4.710144927536232e-06, "loss": 0.9218, "step": 14 }, { "epoch": 0.03280481137233461, "grad_norm": 2.0144922733306885, "learning_rate": 5.072463768115943e-06, "loss": 0.6179, "step": 15 }, { "epoch": 0.034991798797156914, "grad_norm": 1.468063235282898, "learning_rate": 5.4347826086956525e-06, "loss": 0.7576, "step": 16 }, { "epoch": 0.037178786221979225, "grad_norm": 2.6912102699279785, "learning_rate": 5.797101449275362e-06, "loss": 0.8201, "step": 17 }, { "epoch": 0.03936577364680153, "grad_norm": 2.0281667709350586, "learning_rate": 6.159420289855073e-06, "loss": 0.7535, "step": 18 }, { "epoch": 0.04155276107162384, "grad_norm": 2.9444332122802734, "learning_rate": 6.521739130434783e-06, "loss": 0.9148, "step": 19 }, { "epoch": 0.04373974849644614, "grad_norm": 2.4796011447906494, "learning_rate": 6.884057971014493e-06, "loss": 0.7079, "step": 20 }, { "epoch": 0.045926735921268454, "grad_norm": 2.3065383434295654, "learning_rate": 7.246376811594203e-06, "loss": 0.7343, "step": 21 }, { "epoch": 0.04811372334609076, "grad_norm": 1.8900246620178223, "learning_rate": 7.608695652173914e-06, "loss": 0.7544, "step": 22 }, { "epoch": 0.05030071077091307, "grad_norm": 2.4330220222473145, "learning_rate": 7.971014492753623e-06, "loss": 0.8715, "step": 23 }, { "epoch": 0.05248769819573537, "grad_norm": 1.6717957258224487, "learning_rate": 8.333333333333334e-06, "loss": 0.9491, "step": 24 }, { "epoch": 0.05467468562055768, "grad_norm": 1.8144570589065552, "learning_rate": 8.695652173913044e-06, "loss": 0.6498, "step": 25 }, { "epoch": 0.056861673045379986, "grad_norm": 2.0872952938079834, "learning_rate": 9.057971014492753e-06, "loss": 0.7743, "step": 26 }, { "epoch": 0.0590486604702023, "grad_norm": 1.6117609739303589, "learning_rate": 9.420289855072464e-06, "loss": 0.8178, "step": 27 }, { "epoch": 0.0612356478950246, "grad_norm": 3.766716718673706, "learning_rate": 9.782608695652175e-06, "loss": 0.8153, "step": 28 }, { "epoch": 0.0634226353198469, "grad_norm": 2.0519449710845947, "learning_rate": 1.0144927536231885e-05, "loss": 0.6858, "step": 29 }, { "epoch": 0.06560962274466922, "grad_norm": 2.252877712249756, "learning_rate": 1.0507246376811594e-05, "loss": 0.7609, "step": 30 }, { "epoch": 0.06779661016949153, "grad_norm": 2.585669994354248, "learning_rate": 1.0869565217391305e-05, "loss": 0.9181, "step": 31 }, { "epoch": 0.06998359759431383, "grad_norm": 2.247847080230713, "learning_rate": 1.1231884057971016e-05, "loss": 0.9246, "step": 32 }, { "epoch": 0.07217058501913615, "grad_norm": 1.7748466730117798, "learning_rate": 1.1594202898550725e-05, "loss": 0.7494, "step": 33 }, { "epoch": 0.07435757244395845, "grad_norm": 4.583508491516113, "learning_rate": 1.1956521739130435e-05, "loss": 0.9952, "step": 34 }, { "epoch": 0.07654455986878075, "grad_norm": 1.8106759786605835, "learning_rate": 1.2318840579710146e-05, "loss": 0.7916, "step": 35 }, { "epoch": 0.07873154729360306, "grad_norm": 2.2554540634155273, "learning_rate": 1.2681159420289857e-05, "loss": 0.8296, "step": 36 }, { "epoch": 0.08091853471842538, "grad_norm": 1.9808354377746582, "learning_rate": 1.3043478260869566e-05, "loss": 0.9004, "step": 37 }, { "epoch": 0.08310552214324768, "grad_norm": 1.9113680124282837, "learning_rate": 1.3405797101449276e-05, "loss": 0.9007, "step": 38 }, { "epoch": 0.08529250956806998, "grad_norm": 1.5816103219985962, "learning_rate": 1.3768115942028985e-05, "loss": 0.781, "step": 39 }, { "epoch": 0.08747949699289229, "grad_norm": 1.4521021842956543, "learning_rate": 1.4130434782608694e-05, "loss": 0.6722, "step": 40 }, { "epoch": 0.0896664844177146, "grad_norm": 2.632581949234009, "learning_rate": 1.4492753623188407e-05, "loss": 0.8327, "step": 41 }, { "epoch": 0.09185347184253691, "grad_norm": 1.9105041027069092, "learning_rate": 1.4855072463768116e-05, "loss": 0.7397, "step": 42 }, { "epoch": 0.09404045926735921, "grad_norm": 3.0384719371795654, "learning_rate": 1.5217391304347828e-05, "loss": 0.9699, "step": 43 }, { "epoch": 0.09622744669218151, "grad_norm": 1.663479208946228, "learning_rate": 1.5579710144927537e-05, "loss": 0.7451, "step": 44 }, { "epoch": 0.09841443411700383, "grad_norm": 2.4693617820739746, "learning_rate": 1.5942028985507246e-05, "loss": 0.6704, "step": 45 }, { "epoch": 0.10060142154182614, "grad_norm": 1.7776222229003906, "learning_rate": 1.630434782608696e-05, "loss": 0.7641, "step": 46 }, { "epoch": 0.10278840896664844, "grad_norm": 2.4019672870635986, "learning_rate": 1.6666666666666667e-05, "loss": 0.7877, "step": 47 }, { "epoch": 0.10497539639147074, "grad_norm": 1.5189143419265747, "learning_rate": 1.702898550724638e-05, "loss": 0.8407, "step": 48 }, { "epoch": 0.10716238381629306, "grad_norm": 1.812753438949585, "learning_rate": 1.739130434782609e-05, "loss": 0.9925, "step": 49 }, { "epoch": 0.10934937124111536, "grad_norm": 3.0939464569091797, "learning_rate": 1.7753623188405798e-05, "loss": 0.8573, "step": 50 }, { "epoch": 0.11153635866593767, "grad_norm": 2.8994014263153076, "learning_rate": 1.8115942028985507e-05, "loss": 0.8837, "step": 51 }, { "epoch": 0.11372334609075997, "grad_norm": 2.933915615081787, "learning_rate": 1.8478260869565216e-05, "loss": 1.0724, "step": 52 }, { "epoch": 0.11591033351558229, "grad_norm": 2.2911393642425537, "learning_rate": 1.8840579710144928e-05, "loss": 0.7971, "step": 53 }, { "epoch": 0.1180973209404046, "grad_norm": 2.205787181854248, "learning_rate": 1.9202898550724637e-05, "loss": 0.7682, "step": 54 }, { "epoch": 0.1202843083652269, "grad_norm": 2.1905784606933594, "learning_rate": 1.956521739130435e-05, "loss": 0.8563, "step": 55 }, { "epoch": 0.1224712957900492, "grad_norm": 3.7341701984405518, "learning_rate": 1.992753623188406e-05, "loss": 1.1237, "step": 56 }, { "epoch": 0.12465828321487152, "grad_norm": 2.6624815464019775, "learning_rate": 2.028985507246377e-05, "loss": 0.6689, "step": 57 }, { "epoch": 0.1268452706396938, "grad_norm": 1.298459529876709, "learning_rate": 2.065217391304348e-05, "loss": 0.8144, "step": 58 }, { "epoch": 0.12903225806451613, "grad_norm": 2.022489547729492, "learning_rate": 2.101449275362319e-05, "loss": 0.8159, "step": 59 }, { "epoch": 0.13121924548933844, "grad_norm": 2.074810743331909, "learning_rate": 2.13768115942029e-05, "loss": 0.7955, "step": 60 }, { "epoch": 0.13340623291416073, "grad_norm": 1.559003472328186, "learning_rate": 2.173913043478261e-05, "loss": 0.8816, "step": 61 }, { "epoch": 0.13559322033898305, "grad_norm": 2.661587715148926, "learning_rate": 2.2101449275362323e-05, "loss": 0.8871, "step": 62 }, { "epoch": 0.13778020776380537, "grad_norm": 3.3939554691314697, "learning_rate": 2.246376811594203e-05, "loss": 1.0909, "step": 63 }, { "epoch": 0.13996719518862766, "grad_norm": 2.023322343826294, "learning_rate": 2.282608695652174e-05, "loss": 0.9169, "step": 64 }, { "epoch": 0.14215418261344998, "grad_norm": 2.483898162841797, "learning_rate": 2.318840579710145e-05, "loss": 0.9123, "step": 65 }, { "epoch": 0.1443411700382723, "grad_norm": 2.864353895187378, "learning_rate": 2.355072463768116e-05, "loss": 0.7988, "step": 66 }, { "epoch": 0.14652815746309458, "grad_norm": 1.3771991729736328, "learning_rate": 2.391304347826087e-05, "loss": 0.8198, "step": 67 }, { "epoch": 0.1487151448879169, "grad_norm": 2.0170681476593018, "learning_rate": 2.427536231884058e-05, "loss": 0.8494, "step": 68 }, { "epoch": 0.1509021323127392, "grad_norm": 2.110273838043213, "learning_rate": 2.4637681159420292e-05, "loss": 0.8613, "step": 69 }, { "epoch": 0.1530891197375615, "grad_norm": 3.008437156677246, "learning_rate": 2.5e-05, "loss": 0.8147, "step": 70 }, { "epoch": 0.15527610716238383, "grad_norm": 2.942042589187622, "learning_rate": 2.5362318840579714e-05, "loss": 0.7924, "step": 71 }, { "epoch": 0.15746309458720611, "grad_norm": 1.6272262334823608, "learning_rate": 2.572463768115942e-05, "loss": 0.9872, "step": 72 }, { "epoch": 0.15965008201202843, "grad_norm": 2.631721019744873, "learning_rate": 2.608695652173913e-05, "loss": 0.915, "step": 73 }, { "epoch": 0.16183706943685075, "grad_norm": 2.3148326873779297, "learning_rate": 2.6449275362318844e-05, "loss": 1.1666, "step": 74 }, { "epoch": 0.16402405686167304, "grad_norm": 2.305990219116211, "learning_rate": 2.6811594202898553e-05, "loss": 0.8861, "step": 75 }, { "epoch": 0.16621104428649536, "grad_norm": 2.070218324661255, "learning_rate": 2.7173913043478262e-05, "loss": 0.8852, "step": 76 }, { "epoch": 0.16839803171131765, "grad_norm": 2.017136335372925, "learning_rate": 2.753623188405797e-05, "loss": 0.9735, "step": 77 }, { "epoch": 0.17058501913613996, "grad_norm": 2.5563225746154785, "learning_rate": 2.7898550724637683e-05, "loss": 0.9476, "step": 78 }, { "epoch": 0.17277200656096228, "grad_norm": 2.623014450073242, "learning_rate": 2.826086956521739e-05, "loss": 0.8966, "step": 79 }, { "epoch": 0.17495899398578457, "grad_norm": 1.806972861289978, "learning_rate": 2.86231884057971e-05, "loss": 0.9535, "step": 80 }, { "epoch": 0.1771459814106069, "grad_norm": 2.4754912853240967, "learning_rate": 2.8985507246376814e-05, "loss": 0.9717, "step": 81 }, { "epoch": 0.1793329688354292, "grad_norm": 1.7306474447250366, "learning_rate": 2.9347826086956526e-05, "loss": 0.9162, "step": 82 }, { "epoch": 0.1815199562602515, "grad_norm": 2.0492546558380127, "learning_rate": 2.971014492753623e-05, "loss": 0.9156, "step": 83 }, { "epoch": 0.18370694368507381, "grad_norm": 2.037322998046875, "learning_rate": 3.0072463768115944e-05, "loss": 0.7815, "step": 84 }, { "epoch": 0.1858939311098961, "grad_norm": 3.127880811691284, "learning_rate": 3.0434782608695656e-05, "loss": 1.1797, "step": 85 }, { "epoch": 0.18808091853471842, "grad_norm": 2.8052659034729004, "learning_rate": 3.079710144927536e-05, "loss": 0.8695, "step": 86 }, { "epoch": 0.19026790595954074, "grad_norm": 2.2408835887908936, "learning_rate": 3.1159420289855074e-05, "loss": 0.9283, "step": 87 }, { "epoch": 0.19245489338436303, "grad_norm": 3.389347553253174, "learning_rate": 3.152173913043479e-05, "loss": 0.8905, "step": 88 }, { "epoch": 0.19464188080918535, "grad_norm": 2.477728843688965, "learning_rate": 3.188405797101449e-05, "loss": 0.8776, "step": 89 }, { "epoch": 0.19682886823400766, "grad_norm": 1.9875603914260864, "learning_rate": 3.2246376811594205e-05, "loss": 0.8951, "step": 90 }, { "epoch": 0.19901585565882995, "grad_norm": 1.8823089599609375, "learning_rate": 3.260869565217392e-05, "loss": 0.7575, "step": 91 }, { "epoch": 0.20120284308365227, "grad_norm": 2.4126832485198975, "learning_rate": 3.297101449275363e-05, "loss": 1.0667, "step": 92 }, { "epoch": 0.2033898305084746, "grad_norm": 1.7439600229263306, "learning_rate": 3.3333333333333335e-05, "loss": 0.7679, "step": 93 }, { "epoch": 0.20557681793329688, "grad_norm": 2.0236940383911133, "learning_rate": 3.369565217391305e-05, "loss": 0.9768, "step": 94 }, { "epoch": 0.2077638053581192, "grad_norm": 2.678452491760254, "learning_rate": 3.405797101449276e-05, "loss": 0.7702, "step": 95 }, { "epoch": 0.2099507927829415, "grad_norm": 3.236215353012085, "learning_rate": 3.4420289855072465e-05, "loss": 0.882, "step": 96 }, { "epoch": 0.2121377802077638, "grad_norm": 1.8688530921936035, "learning_rate": 3.478260869565218e-05, "loss": 0.8539, "step": 97 }, { "epoch": 0.21432476763258612, "grad_norm": 1.8514810800552368, "learning_rate": 3.514492753623188e-05, "loss": 0.9036, "step": 98 }, { "epoch": 0.2165117550574084, "grad_norm": 1.7223187685012817, "learning_rate": 3.5507246376811596e-05, "loss": 1.0709, "step": 99 }, { "epoch": 0.21869874248223073, "grad_norm": 2.630122661590576, "learning_rate": 3.58695652173913e-05, "loss": 0.9451, "step": 100 }, { "epoch": 0.22088572990705305, "grad_norm": 1.2811744213104248, "learning_rate": 3.6231884057971014e-05, "loss": 1.095, "step": 101 }, { "epoch": 0.22307271733187534, "grad_norm": 2.0551376342773438, "learning_rate": 3.6594202898550726e-05, "loss": 1.0126, "step": 102 }, { "epoch": 0.22525970475669765, "grad_norm": 2.397703170776367, "learning_rate": 3.695652173913043e-05, "loss": 1.1051, "step": 103 }, { "epoch": 0.22744669218151994, "grad_norm": 2.6909122467041016, "learning_rate": 3.7318840579710144e-05, "loss": 1.0399, "step": 104 }, { "epoch": 0.22963367960634226, "grad_norm": 2.8093209266662598, "learning_rate": 3.7681159420289856e-05, "loss": 0.9784, "step": 105 }, { "epoch": 0.23182066703116458, "grad_norm": 1.4055047035217285, "learning_rate": 3.804347826086957e-05, "loss": 0.7708, "step": 106 }, { "epoch": 0.23400765445598687, "grad_norm": 1.3140136003494263, "learning_rate": 3.8405797101449274e-05, "loss": 0.9203, "step": 107 }, { "epoch": 0.2361946418808092, "grad_norm": 2.109222412109375, "learning_rate": 3.876811594202899e-05, "loss": 0.8761, "step": 108 }, { "epoch": 0.2383816293056315, "grad_norm": 2.722482919692993, "learning_rate": 3.91304347826087e-05, "loss": 1.0874, "step": 109 }, { "epoch": 0.2405686167304538, "grad_norm": 2.1896848678588867, "learning_rate": 3.9492753623188405e-05, "loss": 0.878, "step": 110 }, { "epoch": 0.2427556041552761, "grad_norm": 1.4937201738357544, "learning_rate": 3.985507246376812e-05, "loss": 0.9938, "step": 111 }, { "epoch": 0.2449425915800984, "grad_norm": 2.08168625831604, "learning_rate": 4.021739130434783e-05, "loss": 0.9284, "step": 112 }, { "epoch": 0.24712957900492072, "grad_norm": 1.8039462566375732, "learning_rate": 4.057971014492754e-05, "loss": 1.0262, "step": 113 }, { "epoch": 0.24931656642974304, "grad_norm": 2.3002116680145264, "learning_rate": 4.094202898550725e-05, "loss": 0.8204, "step": 114 }, { "epoch": 0.25150355385456535, "grad_norm": 2.2661798000335693, "learning_rate": 4.130434782608696e-05, "loss": 1.0779, "step": 115 }, { "epoch": 0.2536905412793876, "grad_norm": 3.822631359100342, "learning_rate": 4.166666666666667e-05, "loss": 1.0488, "step": 116 }, { "epoch": 0.25587752870420993, "grad_norm": 2.8496432304382324, "learning_rate": 4.202898550724638e-05, "loss": 1.0334, "step": 117 }, { "epoch": 0.25806451612903225, "grad_norm": 2.542039394378662, "learning_rate": 4.239130434782609e-05, "loss": 1.2228, "step": 118 }, { "epoch": 0.26025150355385457, "grad_norm": 2.4866976737976074, "learning_rate": 4.27536231884058e-05, "loss": 1.0944, "step": 119 }, { "epoch": 0.2624384909786769, "grad_norm": 1.919472336769104, "learning_rate": 4.3115942028985515e-05, "loss": 1.0338, "step": 120 }, { "epoch": 0.2646254784034992, "grad_norm": 1.5738486051559448, "learning_rate": 4.347826086956522e-05, "loss": 0.9665, "step": 121 }, { "epoch": 0.26681246582832147, "grad_norm": 3.311596393585205, "learning_rate": 4.384057971014493e-05, "loss": 1.2065, "step": 122 }, { "epoch": 0.2689994532531438, "grad_norm": 1.8790026903152466, "learning_rate": 4.4202898550724645e-05, "loss": 0.9746, "step": 123 }, { "epoch": 0.2711864406779661, "grad_norm": 2.380589485168457, "learning_rate": 4.456521739130435e-05, "loss": 1.007, "step": 124 }, { "epoch": 0.2733734281027884, "grad_norm": 2.0396158695220947, "learning_rate": 4.492753623188406e-05, "loss": 1.1753, "step": 125 }, { "epoch": 0.27556041552761074, "grad_norm": 1.754359245300293, "learning_rate": 4.528985507246377e-05, "loss": 0.977, "step": 126 }, { "epoch": 0.277747402952433, "grad_norm": 1.6636338233947754, "learning_rate": 4.565217391304348e-05, "loss": 0.896, "step": 127 }, { "epoch": 0.2799343903772553, "grad_norm": 3.549180030822754, "learning_rate": 4.601449275362319e-05, "loss": 0.9525, "step": 128 }, { "epoch": 0.28212137780207763, "grad_norm": 1.6460024118423462, "learning_rate": 4.63768115942029e-05, "loss": 0.9315, "step": 129 }, { "epoch": 0.28430836522689995, "grad_norm": 2.5944056510925293, "learning_rate": 4.673913043478261e-05, "loss": 1.4194, "step": 130 }, { "epoch": 0.28649535265172227, "grad_norm": 2.8856730461120605, "learning_rate": 4.710144927536232e-05, "loss": 1.027, "step": 131 }, { "epoch": 0.2886823400765446, "grad_norm": 1.5593736171722412, "learning_rate": 4.746376811594203e-05, "loss": 1.0004, "step": 132 }, { "epoch": 0.29086932750136685, "grad_norm": 1.9265207052230835, "learning_rate": 4.782608695652174e-05, "loss": 1.1814, "step": 133 }, { "epoch": 0.29305631492618917, "grad_norm": 1.753687858581543, "learning_rate": 4.818840579710145e-05, "loss": 1.0563, "step": 134 }, { "epoch": 0.2952433023510115, "grad_norm": 2.1866250038146973, "learning_rate": 4.855072463768116e-05, "loss": 1.0952, "step": 135 }, { "epoch": 0.2974302897758338, "grad_norm": 1.9316798448562622, "learning_rate": 4.891304347826087e-05, "loss": 1.2219, "step": 136 }, { "epoch": 0.2996172772006561, "grad_norm": 1.8816934823989868, "learning_rate": 4.9275362318840584e-05, "loss": 1.105, "step": 137 }, { "epoch": 0.3018042646254784, "grad_norm": 3.4348785877227783, "learning_rate": 4.963768115942029e-05, "loss": 0.8816, "step": 138 }, { "epoch": 0.3039912520503007, "grad_norm": 1.7511382102966309, "learning_rate": 5e-05, "loss": 1.3547, "step": 139 }, { "epoch": 0.306178239475123, "grad_norm": 2.8826208114624023, "learning_rate": 4.9959448499594485e-05, "loss": 1.1913, "step": 140 }, { "epoch": 0.30836522689994533, "grad_norm": 1.8317208290100098, "learning_rate": 4.9918896999188975e-05, "loss": 0.9629, "step": 141 }, { "epoch": 0.31055221432476765, "grad_norm": 2.453585147857666, "learning_rate": 4.987834549878346e-05, "loss": 1.098, "step": 142 }, { "epoch": 0.3127392017495899, "grad_norm": 2.635082483291626, "learning_rate": 4.983779399837794e-05, "loss": 1.0672, "step": 143 }, { "epoch": 0.31492618917441223, "grad_norm": 2.344113826751709, "learning_rate": 4.979724249797243e-05, "loss": 1.1837, "step": 144 }, { "epoch": 0.31711317659923455, "grad_norm": 1.3790041208267212, "learning_rate": 4.9756690997566914e-05, "loss": 1.0809, "step": 145 }, { "epoch": 0.31930016402405687, "grad_norm": 1.003891110420227, "learning_rate": 4.97161394971614e-05, "loss": 0.9976, "step": 146 }, { "epoch": 0.3214871514488792, "grad_norm": 2.1691856384277344, "learning_rate": 4.967558799675589e-05, "loss": 1.3402, "step": 147 }, { "epoch": 0.3236741388737015, "grad_norm": 1.6184922456741333, "learning_rate": 4.963503649635037e-05, "loss": 0.9565, "step": 148 }, { "epoch": 0.32586112629852376, "grad_norm": 2.0422651767730713, "learning_rate": 4.959448499594485e-05, "loss": 1.0489, "step": 149 }, { "epoch": 0.3280481137233461, "grad_norm": 2.7193377017974854, "learning_rate": 4.9553933495539336e-05, "loss": 1.0239, "step": 150 }, { "epoch": 0.3302351011481684, "grad_norm": 2.1208291053771973, "learning_rate": 4.9513381995133826e-05, "loss": 0.929, "step": 151 }, { "epoch": 0.3324220885729907, "grad_norm": 1.7765867710113525, "learning_rate": 4.947283049472831e-05, "loss": 1.0841, "step": 152 }, { "epoch": 0.33460907599781303, "grad_norm": 5.469010829925537, "learning_rate": 4.943227899432279e-05, "loss": 1.0226, "step": 153 }, { "epoch": 0.3367960634226353, "grad_norm": 2.1029326915740967, "learning_rate": 4.9391727493917275e-05, "loss": 1.1175, "step": 154 }, { "epoch": 0.3389830508474576, "grad_norm": 1.418423056602478, "learning_rate": 4.935117599351176e-05, "loss": 1.0922, "step": 155 }, { "epoch": 0.34117003827227993, "grad_norm": 1.9201970100402832, "learning_rate": 4.931062449310625e-05, "loss": 1.1195, "step": 156 }, { "epoch": 0.34335702569710225, "grad_norm": 4.21011209487915, "learning_rate": 4.927007299270073e-05, "loss": 1.3117, "step": 157 }, { "epoch": 0.34554401312192456, "grad_norm": 1.379827618598938, "learning_rate": 4.9229521492295215e-05, "loss": 1.1322, "step": 158 }, { "epoch": 0.3477310005467469, "grad_norm": 2.4212160110473633, "learning_rate": 4.91889699918897e-05, "loss": 1.1294, "step": 159 }, { "epoch": 0.34991798797156914, "grad_norm": 2.637714385986328, "learning_rate": 4.914841849148419e-05, "loss": 1.1793, "step": 160 }, { "epoch": 0.35210497539639146, "grad_norm": 1.2108877897262573, "learning_rate": 4.910786699107867e-05, "loss": 1.1176, "step": 161 }, { "epoch": 0.3542919628212138, "grad_norm": 2.0345876216888428, "learning_rate": 4.9067315490673154e-05, "loss": 1.1416, "step": 162 }, { "epoch": 0.3564789502460361, "grad_norm": 2.4347381591796875, "learning_rate": 4.9026763990267643e-05, "loss": 1.1606, "step": 163 }, { "epoch": 0.3586659376708584, "grad_norm": 3.678926944732666, "learning_rate": 4.8986212489862126e-05, "loss": 1.1874, "step": 164 }, { "epoch": 0.3608529250956807, "grad_norm": 1.870200514793396, "learning_rate": 4.894566098945661e-05, "loss": 1.0968, "step": 165 }, { "epoch": 0.363039912520503, "grad_norm": 3.3238580226898193, "learning_rate": 4.89051094890511e-05, "loss": 1.3105, "step": 166 }, { "epoch": 0.3652268999453253, "grad_norm": 2.3204662799835205, "learning_rate": 4.886455798864558e-05, "loss": 0.9442, "step": 167 }, { "epoch": 0.36741388737014763, "grad_norm": 2.5980489253997803, "learning_rate": 4.8824006488240065e-05, "loss": 1.4901, "step": 168 }, { "epoch": 0.36960087479496995, "grad_norm": 2.017000913619995, "learning_rate": 4.8783454987834555e-05, "loss": 1.059, "step": 169 }, { "epoch": 0.3717878622197922, "grad_norm": 2.1691343784332275, "learning_rate": 4.874290348742904e-05, "loss": 1.2879, "step": 170 }, { "epoch": 0.3739748496446145, "grad_norm": 1.449963927268982, "learning_rate": 4.870235198702352e-05, "loss": 1.1367, "step": 171 }, { "epoch": 0.37616183706943684, "grad_norm": 2.2905354499816895, "learning_rate": 4.866180048661801e-05, "loss": 1.1504, "step": 172 }, { "epoch": 0.37834882449425916, "grad_norm": 1.1732892990112305, "learning_rate": 4.8621248986212494e-05, "loss": 1.0891, "step": 173 }, { "epoch": 0.3805358119190815, "grad_norm": 2.455528497695923, "learning_rate": 4.858069748580698e-05, "loss": 1.1952, "step": 174 }, { "epoch": 0.3827227993439038, "grad_norm": 2.0356338024139404, "learning_rate": 4.854014598540147e-05, "loss": 0.9897, "step": 175 }, { "epoch": 0.38490978676872606, "grad_norm": 2.3370890617370605, "learning_rate": 4.849959448499595e-05, "loss": 1.0701, "step": 176 }, { "epoch": 0.3870967741935484, "grad_norm": 1.429998517036438, "learning_rate": 4.8459042984590433e-05, "loss": 1.0804, "step": 177 }, { "epoch": 0.3892837616183707, "grad_norm": 3.7434303760528564, "learning_rate": 4.8418491484184916e-05, "loss": 1.079, "step": 178 }, { "epoch": 0.391470749043193, "grad_norm": 2.309058666229248, "learning_rate": 4.83779399837794e-05, "loss": 1.2942, "step": 179 }, { "epoch": 0.39365773646801533, "grad_norm": 1.899711012840271, "learning_rate": 4.833738848337388e-05, "loss": 1.21, "step": 180 }, { "epoch": 0.3958447238928376, "grad_norm": 2.379348039627075, "learning_rate": 4.829683698296837e-05, "loss": 0.9068, "step": 181 }, { "epoch": 0.3980317113176599, "grad_norm": 2.8025002479553223, "learning_rate": 4.8256285482562856e-05, "loss": 1.2171, "step": 182 }, { "epoch": 0.4002186987424822, "grad_norm": 2.1540169715881348, "learning_rate": 4.821573398215734e-05, "loss": 0.9893, "step": 183 }, { "epoch": 0.40240568616730454, "grad_norm": 3.671858787536621, "learning_rate": 4.817518248175183e-05, "loss": 1.3933, "step": 184 }, { "epoch": 0.40459267359212686, "grad_norm": 2.084385633468628, "learning_rate": 4.813463098134631e-05, "loss": 1.1436, "step": 185 }, { "epoch": 0.4067796610169492, "grad_norm": 1.746883511543274, "learning_rate": 4.8094079480940795e-05, "loss": 1.1243, "step": 186 }, { "epoch": 0.40896664844177144, "grad_norm": 2.9982082843780518, "learning_rate": 4.8053527980535284e-05, "loss": 1.1656, "step": 187 }, { "epoch": 0.41115363586659376, "grad_norm": 2.8833553791046143, "learning_rate": 4.801297648012977e-05, "loss": 1.2151, "step": 188 }, { "epoch": 0.4133406232914161, "grad_norm": 2.189779758453369, "learning_rate": 4.797242497972425e-05, "loss": 1.2765, "step": 189 }, { "epoch": 0.4155276107162384, "grad_norm": 1.9267719984054565, "learning_rate": 4.793187347931874e-05, "loss": 1.0686, "step": 190 }, { "epoch": 0.4177145981410607, "grad_norm": 1.2397915124893188, "learning_rate": 4.7891321978913223e-05, "loss": 1.3123, "step": 191 }, { "epoch": 0.419901585565883, "grad_norm": 2.0948214530944824, "learning_rate": 4.7850770478507706e-05, "loss": 1.2059, "step": 192 }, { "epoch": 0.4220885729907053, "grad_norm": 1.6937896013259888, "learning_rate": 4.7810218978102196e-05, "loss": 1.2955, "step": 193 }, { "epoch": 0.4242755604155276, "grad_norm": 1.7256088256835938, "learning_rate": 4.776966747769668e-05, "loss": 0.9785, "step": 194 }, { "epoch": 0.4264625478403499, "grad_norm": 2.050034999847412, "learning_rate": 4.772911597729116e-05, "loss": 1.2147, "step": 195 }, { "epoch": 0.42864953526517224, "grad_norm": 1.9703772068023682, "learning_rate": 4.7688564476885646e-05, "loss": 1.1599, "step": 196 }, { "epoch": 0.4308365226899945, "grad_norm": 4.888108253479004, "learning_rate": 4.7648012976480135e-05, "loss": 1.067, "step": 197 }, { "epoch": 0.4330235101148168, "grad_norm": 2.1976687908172607, "learning_rate": 4.760746147607462e-05, "loss": 1.0384, "step": 198 }, { "epoch": 0.43521049753963914, "grad_norm": 1.8646868467330933, "learning_rate": 4.75669099756691e-05, "loss": 1.2947, "step": 199 }, { "epoch": 0.43739748496446146, "grad_norm": 1.4350502490997314, "learning_rate": 4.752635847526359e-05, "loss": 1.3753, "step": 200 }, { "epoch": 0.4395844723892838, "grad_norm": 2.8373196125030518, "learning_rate": 4.7485806974858074e-05, "loss": 1.188, "step": 201 }, { "epoch": 0.4417714598141061, "grad_norm": 2.9520294666290283, "learning_rate": 4.744525547445256e-05, "loss": 1.2727, "step": 202 }, { "epoch": 0.44395844723892836, "grad_norm": 1.2276339530944824, "learning_rate": 4.740470397404704e-05, "loss": 1.2186, "step": 203 }, { "epoch": 0.4461454346637507, "grad_norm": 3.29460072517395, "learning_rate": 4.7364152473641524e-05, "loss": 1.1513, "step": 204 }, { "epoch": 0.448332422088573, "grad_norm": 1.5819822549819946, "learning_rate": 4.732360097323601e-05, "loss": 1.2745, "step": 205 }, { "epoch": 0.4505194095133953, "grad_norm": 1.1773879528045654, "learning_rate": 4.7283049472830496e-05, "loss": 1.0505, "step": 206 }, { "epoch": 0.4527063969382176, "grad_norm": 2.6593480110168457, "learning_rate": 4.724249797242498e-05, "loss": 1.1671, "step": 207 }, { "epoch": 0.4548933843630399, "grad_norm": 3.3596503734588623, "learning_rate": 4.720194647201946e-05, "loss": 1.149, "step": 208 }, { "epoch": 0.4570803717878622, "grad_norm": 1.9473880529403687, "learning_rate": 4.716139497161395e-05, "loss": 1.1143, "step": 209 }, { "epoch": 0.4592673592126845, "grad_norm": 3.236248731613159, "learning_rate": 4.7120843471208436e-05, "loss": 1.3599, "step": 210 }, { "epoch": 0.46145434663750684, "grad_norm": 1.4021092653274536, "learning_rate": 4.708029197080292e-05, "loss": 1.2198, "step": 211 }, { "epoch": 0.46364133406232916, "grad_norm": 1.7261958122253418, "learning_rate": 4.703974047039741e-05, "loss": 1.1273, "step": 212 }, { "epoch": 0.4658283214871515, "grad_norm": 1.6745117902755737, "learning_rate": 4.699918896999189e-05, "loss": 1.0206, "step": 213 }, { "epoch": 0.46801530891197374, "grad_norm": 1.921740174293518, "learning_rate": 4.6958637469586375e-05, "loss": 1.4577, "step": 214 }, { "epoch": 0.47020229633679606, "grad_norm": 1.7835532426834106, "learning_rate": 4.6918085969180864e-05, "loss": 1.0227, "step": 215 }, { "epoch": 0.4723892837616184, "grad_norm": 1.6086561679840088, "learning_rate": 4.687753446877535e-05, "loss": 1.1875, "step": 216 }, { "epoch": 0.4745762711864407, "grad_norm": 1.9839692115783691, "learning_rate": 4.683698296836983e-05, "loss": 1.397, "step": 217 }, { "epoch": 0.476763258611263, "grad_norm": 1.529381513595581, "learning_rate": 4.679643146796432e-05, "loss": 1.1089, "step": 218 }, { "epoch": 0.47895024603608527, "grad_norm": 2.583024263381958, "learning_rate": 4.6755879967558803e-05, "loss": 1.2241, "step": 219 }, { "epoch": 0.4811372334609076, "grad_norm": 2.6843819618225098, "learning_rate": 4.6715328467153287e-05, "loss": 1.3028, "step": 220 }, { "epoch": 0.4833242208857299, "grad_norm": 3.2758848667144775, "learning_rate": 4.6674776966747776e-05, "loss": 1.1774, "step": 221 }, { "epoch": 0.4855112083105522, "grad_norm": 3.6219236850738525, "learning_rate": 4.663422546634226e-05, "loss": 1.2971, "step": 222 }, { "epoch": 0.48769819573537454, "grad_norm": 1.1974763870239258, "learning_rate": 4.659367396593674e-05, "loss": 1.0418, "step": 223 }, { "epoch": 0.4898851831601968, "grad_norm": 2.30288028717041, "learning_rate": 4.655312246553123e-05, "loss": 0.9606, "step": 224 }, { "epoch": 0.4920721705850191, "grad_norm": 1.3493553400039673, "learning_rate": 4.6512570965125715e-05, "loss": 1.1734, "step": 225 }, { "epoch": 0.49425915800984144, "grad_norm": 2.724222183227539, "learning_rate": 4.64720194647202e-05, "loss": 1.2618, "step": 226 }, { "epoch": 0.49644614543466375, "grad_norm": 2.0903713703155518, "learning_rate": 4.643146796431468e-05, "loss": 1.1895, "step": 227 }, { "epoch": 0.4986331328594861, "grad_norm": 1.9104057550430298, "learning_rate": 4.6390916463909165e-05, "loss": 1.3911, "step": 228 }, { "epoch": 0.5008201202843083, "grad_norm": 2.01275634765625, "learning_rate": 4.635036496350365e-05, "loss": 1.1961, "step": 229 }, { "epoch": 0.5030071077091307, "grad_norm": 1.85329008102417, "learning_rate": 4.630981346309814e-05, "loss": 1.3116, "step": 230 }, { "epoch": 0.505194095133953, "grad_norm": 1.8847073316574097, "learning_rate": 4.626926196269262e-05, "loss": 1.2001, "step": 231 }, { "epoch": 0.5073810825587752, "grad_norm": 1.313421607017517, "learning_rate": 4.6228710462287104e-05, "loss": 1.5228, "step": 232 }, { "epoch": 0.5095680699835976, "grad_norm": 8.092373847961426, "learning_rate": 4.618815896188159e-05, "loss": 1.3429, "step": 233 }, { "epoch": 0.5117550574084199, "grad_norm": 3.680309534072876, "learning_rate": 4.6147607461476077e-05, "loss": 1.4443, "step": 234 }, { "epoch": 0.5139420448332422, "grad_norm": 13.905643463134766, "learning_rate": 4.610705596107056e-05, "loss": 1.3954, "step": 235 }, { "epoch": 0.5161290322580645, "grad_norm": 2.9164795875549316, "learning_rate": 4.606650446066504e-05, "loss": 1.1845, "step": 236 }, { "epoch": 0.5183160196828869, "grad_norm": 1.76926589012146, "learning_rate": 4.602595296025953e-05, "loss": 1.456, "step": 237 }, { "epoch": 0.5205030071077091, "grad_norm": 3.0440237522125244, "learning_rate": 4.5985401459854016e-05, "loss": 1.7692, "step": 238 }, { "epoch": 0.5226899945325314, "grad_norm": 2.857888698577881, "learning_rate": 4.59448499594485e-05, "loss": 1.4431, "step": 239 }, { "epoch": 0.5248769819573538, "grad_norm": 2.319401264190674, "learning_rate": 4.590429845904299e-05, "loss": 1.3494, "step": 240 }, { "epoch": 0.527063969382176, "grad_norm": 2.6024351119995117, "learning_rate": 4.586374695863747e-05, "loss": 1.1956, "step": 241 }, { "epoch": 0.5292509568069984, "grad_norm": 3.3069851398468018, "learning_rate": 4.5823195458231955e-05, "loss": 1.3718, "step": 242 }, { "epoch": 0.5314379442318207, "grad_norm": 1.765444278717041, "learning_rate": 4.5782643957826444e-05, "loss": 1.1936, "step": 243 }, { "epoch": 0.5336249316566429, "grad_norm": 1.294309139251709, "learning_rate": 4.574209245742093e-05, "loss": 1.3929, "step": 244 }, { "epoch": 0.5358119190814653, "grad_norm": 1.547410488128662, "learning_rate": 4.570154095701541e-05, "loss": 1.2822, "step": 245 }, { "epoch": 0.5379989065062876, "grad_norm": 2.2634878158569336, "learning_rate": 4.56609894566099e-05, "loss": 1.2404, "step": 246 }, { "epoch": 0.5401858939311099, "grad_norm": 1.7115137577056885, "learning_rate": 4.5620437956204383e-05, "loss": 1.4314, "step": 247 }, { "epoch": 0.5423728813559322, "grad_norm": 1.239267110824585, "learning_rate": 4.5579886455798867e-05, "loss": 1.4057, "step": 248 }, { "epoch": 0.5445598687807545, "grad_norm": 1.7016183137893677, "learning_rate": 4.5539334955393356e-05, "loss": 1.1324, "step": 249 }, { "epoch": 0.5467468562055768, "grad_norm": 1.6047818660736084, "learning_rate": 4.549878345498784e-05, "loss": 1.0564, "step": 250 }, { "epoch": 0.5489338436303991, "grad_norm": 2.2856409549713135, "learning_rate": 4.545823195458232e-05, "loss": 1.1856, "step": 251 }, { "epoch": 0.5511208310552215, "grad_norm": 1.325461506843567, "learning_rate": 4.5417680454176806e-05, "loss": 1.0998, "step": 252 }, { "epoch": 0.5533078184800437, "grad_norm": 1.8437037467956543, "learning_rate": 4.537712895377129e-05, "loss": 1.0358, "step": 253 }, { "epoch": 0.555494805904866, "grad_norm": 1.244157314300537, "learning_rate": 4.533657745336577e-05, "loss": 1.0218, "step": 254 }, { "epoch": 0.5576817933296884, "grad_norm": 1.5284663438796997, "learning_rate": 4.529602595296026e-05, "loss": 1.2936, "step": 255 }, { "epoch": 0.5598687807545106, "grad_norm": 1.2469964027404785, "learning_rate": 4.5255474452554745e-05, "loss": 1.0879, "step": 256 }, { "epoch": 0.562055768179333, "grad_norm": 2.2410120964050293, "learning_rate": 4.521492295214923e-05, "loss": 0.9485, "step": 257 }, { "epoch": 0.5642427556041553, "grad_norm": 2.1136138439178467, "learning_rate": 4.517437145174372e-05, "loss": 1.3126, "step": 258 }, { "epoch": 0.5664297430289775, "grad_norm": 2.0895469188690186, "learning_rate": 4.51338199513382e-05, "loss": 1.5372, "step": 259 }, { "epoch": 0.5686167304537999, "grad_norm": 1.779615044593811, "learning_rate": 4.5093268450932684e-05, "loss": 1.085, "step": 260 }, { "epoch": 0.5708037178786222, "grad_norm": 1.6126189231872559, "learning_rate": 4.5052716950527173e-05, "loss": 1.2936, "step": 261 }, { "epoch": 0.5729907053034445, "grad_norm": 2.1765153408050537, "learning_rate": 4.5012165450121657e-05, "loss": 0.9023, "step": 262 }, { "epoch": 0.5751776927282668, "grad_norm": 1.5139387845993042, "learning_rate": 4.497161394971614e-05, "loss": 1.327, "step": 263 }, { "epoch": 0.5773646801530892, "grad_norm": 1.1349142789840698, "learning_rate": 4.493106244931063e-05, "loss": 1.2285, "step": 264 }, { "epoch": 0.5795516675779114, "grad_norm": 1.902031421661377, "learning_rate": 4.489051094890511e-05, "loss": 1.2283, "step": 265 }, { "epoch": 0.5817386550027337, "grad_norm": 2.426229238510132, "learning_rate": 4.4849959448499596e-05, "loss": 1.1459, "step": 266 }, { "epoch": 0.5839256424275561, "grad_norm": 1.5062717199325562, "learning_rate": 4.4809407948094085e-05, "loss": 1.247, "step": 267 }, { "epoch": 0.5861126298523783, "grad_norm": 1.7767912149429321, "learning_rate": 4.476885644768857e-05, "loss": 0.9742, "step": 268 }, { "epoch": 0.5882996172772007, "grad_norm": 1.9232147932052612, "learning_rate": 4.472830494728305e-05, "loss": 1.2011, "step": 269 }, { "epoch": 0.590486604702023, "grad_norm": 1.5708249807357788, "learning_rate": 4.4687753446877535e-05, "loss": 1.2679, "step": 270 }, { "epoch": 0.5926735921268452, "grad_norm": 1.689527988433838, "learning_rate": 4.4647201946472024e-05, "loss": 1.4715, "step": 271 }, { "epoch": 0.5948605795516676, "grad_norm": 1.6786547899246216, "learning_rate": 4.460665044606651e-05, "loss": 1.3883, "step": 272 }, { "epoch": 0.5970475669764899, "grad_norm": 4.3073039054870605, "learning_rate": 4.456609894566099e-05, "loss": 1.2794, "step": 273 }, { "epoch": 0.5992345544013122, "grad_norm": 3.4215524196624756, "learning_rate": 4.452554744525548e-05, "loss": 1.1978, "step": 274 }, { "epoch": 0.6014215418261345, "grad_norm": 1.6689937114715576, "learning_rate": 4.4484995944849964e-05, "loss": 1.1645, "step": 275 }, { "epoch": 0.6036085292509568, "grad_norm": 2.8367671966552734, "learning_rate": 4.4444444444444447e-05, "loss": 0.9965, "step": 276 }, { "epoch": 0.6057955166757791, "grad_norm": 1.2923420667648315, "learning_rate": 4.440389294403893e-05, "loss": 1.1223, "step": 277 }, { "epoch": 0.6079825041006014, "grad_norm": 1.3446835279464722, "learning_rate": 4.436334144363341e-05, "loss": 1.1683, "step": 278 }, { "epoch": 0.6101694915254238, "grad_norm": 1.538405418395996, "learning_rate": 4.43227899432279e-05, "loss": 1.1064, "step": 279 }, { "epoch": 0.612356478950246, "grad_norm": 1.7521491050720215, "learning_rate": 4.4282238442822386e-05, "loss": 1.0848, "step": 280 }, { "epoch": 0.6145434663750683, "grad_norm": 1.6750338077545166, "learning_rate": 4.424168694241687e-05, "loss": 1.2256, "step": 281 }, { "epoch": 0.6167304537998907, "grad_norm": 2.019124984741211, "learning_rate": 4.420113544201135e-05, "loss": 1.3562, "step": 282 }, { "epoch": 0.6189174412247129, "grad_norm": 1.7491199970245361, "learning_rate": 4.416058394160584e-05, "loss": 1.3944, "step": 283 }, { "epoch": 0.6211044286495353, "grad_norm": 1.8598893880844116, "learning_rate": 4.4120032441200325e-05, "loss": 1.0741, "step": 284 }, { "epoch": 0.6232914160743576, "grad_norm": 1.3468443155288696, "learning_rate": 4.407948094079481e-05, "loss": 1.2334, "step": 285 }, { "epoch": 0.6254784034991798, "grad_norm": 1.4871859550476074, "learning_rate": 4.40389294403893e-05, "loss": 1.4773, "step": 286 }, { "epoch": 0.6276653909240022, "grad_norm": 2.6744163036346436, "learning_rate": 4.399837793998378e-05, "loss": 1.1493, "step": 287 }, { "epoch": 0.6298523783488245, "grad_norm": 1.6915841102600098, "learning_rate": 4.3957826439578264e-05, "loss": 1.096, "step": 288 }, { "epoch": 0.6320393657736468, "grad_norm": 2.331700086593628, "learning_rate": 4.3917274939172754e-05, "loss": 1.463, "step": 289 }, { "epoch": 0.6342263531984691, "grad_norm": 2.1814820766448975, "learning_rate": 4.3876723438767237e-05, "loss": 1.2401, "step": 290 }, { "epoch": 0.6364133406232915, "grad_norm": 2.3164024353027344, "learning_rate": 4.383617193836172e-05, "loss": 1.2857, "step": 291 }, { "epoch": 0.6386003280481137, "grad_norm": 1.2428425550460815, "learning_rate": 4.379562043795621e-05, "loss": 1.1856, "step": 292 }, { "epoch": 0.640787315472936, "grad_norm": 1.7818957567214966, "learning_rate": 4.375506893755069e-05, "loss": 1.2311, "step": 293 }, { "epoch": 0.6429743028977584, "grad_norm": 1.9172413349151611, "learning_rate": 4.3714517437145176e-05, "loss": 1.1825, "step": 294 }, { "epoch": 0.6451612903225806, "grad_norm": 2.0414235591888428, "learning_rate": 4.3673965936739665e-05, "loss": 1.2817, "step": 295 }, { "epoch": 0.647348277747403, "grad_norm": 1.0798546075820923, "learning_rate": 4.363341443633415e-05, "loss": 1.3423, "step": 296 }, { "epoch": 0.6495352651722253, "grad_norm": 1.7121816873550415, "learning_rate": 4.359286293592863e-05, "loss": 1.0739, "step": 297 }, { "epoch": 0.6517222525970475, "grad_norm": 1.6311484575271606, "learning_rate": 4.355231143552312e-05, "loss": 1.229, "step": 298 }, { "epoch": 0.6539092400218699, "grad_norm": 1.9347124099731445, "learning_rate": 4.3511759935117605e-05, "loss": 1.3741, "step": 299 }, { "epoch": 0.6560962274466922, "grad_norm": 1.4366708993911743, "learning_rate": 4.347120843471209e-05, "loss": 1.2284, "step": 300 }, { "epoch": 0.6582832148715145, "grad_norm": 2.8098061084747314, "learning_rate": 4.343065693430657e-05, "loss": 1.2151, "step": 301 }, { "epoch": 0.6604702022963368, "grad_norm": 2.2224972248077393, "learning_rate": 4.339010543390106e-05, "loss": 1.3994, "step": 302 }, { "epoch": 0.6626571897211591, "grad_norm": 1.8587361574172974, "learning_rate": 4.3349553933495544e-05, "loss": 1.1907, "step": 303 }, { "epoch": 0.6648441771459814, "grad_norm": 1.2250243425369263, "learning_rate": 4.3309002433090027e-05, "loss": 1.2504, "step": 304 }, { "epoch": 0.6670311645708037, "grad_norm": 2.3996808528900146, "learning_rate": 4.326845093268451e-05, "loss": 1.3979, "step": 305 }, { "epoch": 0.6692181519956261, "grad_norm": 1.8444247245788574, "learning_rate": 4.322789943227899e-05, "loss": 1.1628, "step": 306 }, { "epoch": 0.6714051394204483, "grad_norm": 2.724317789077759, "learning_rate": 4.318734793187348e-05, "loss": 1.3164, "step": 307 }, { "epoch": 0.6735921268452706, "grad_norm": 1.8894436359405518, "learning_rate": 4.3146796431467966e-05, "loss": 1.2272, "step": 308 }, { "epoch": 0.675779114270093, "grad_norm": 1.7506622076034546, "learning_rate": 4.310624493106245e-05, "loss": 1.2897, "step": 309 }, { "epoch": 0.6779661016949152, "grad_norm": 3.4432599544525146, "learning_rate": 4.306569343065693e-05, "loss": 1.1941, "step": 310 }, { "epoch": 0.6801530891197376, "grad_norm": 1.3863381147384644, "learning_rate": 4.302514193025142e-05, "loss": 1.1211, "step": 311 }, { "epoch": 0.6823400765445599, "grad_norm": 1.573891043663025, "learning_rate": 4.2984590429845905e-05, "loss": 1.2369, "step": 312 }, { "epoch": 0.6845270639693821, "grad_norm": 1.2822139263153076, "learning_rate": 4.294403892944039e-05, "loss": 1.5466, "step": 313 }, { "epoch": 0.6867140513942045, "grad_norm": 1.8434617519378662, "learning_rate": 4.290348742903488e-05, "loss": 1.204, "step": 314 }, { "epoch": 0.6889010388190268, "grad_norm": 1.6288913488388062, "learning_rate": 4.286293592862936e-05, "loss": 1.2171, "step": 315 }, { "epoch": 0.6910880262438491, "grad_norm": 1.5104482173919678, "learning_rate": 4.2822384428223844e-05, "loss": 1.2589, "step": 316 }, { "epoch": 0.6932750136686714, "grad_norm": 1.1719133853912354, "learning_rate": 4.2781832927818334e-05, "loss": 1.0678, "step": 317 }, { "epoch": 0.6954620010934938, "grad_norm": 1.4282548427581787, "learning_rate": 4.274128142741282e-05, "loss": 1.0907, "step": 318 }, { "epoch": 0.697648988518316, "grad_norm": 2.0306692123413086, "learning_rate": 4.27007299270073e-05, "loss": 1.1912, "step": 319 }, { "epoch": 0.6998359759431383, "grad_norm": 2.0419068336486816, "learning_rate": 4.266017842660179e-05, "loss": 1.4596, "step": 320 }, { "epoch": 0.7020229633679607, "grad_norm": 1.7995816469192505, "learning_rate": 4.261962692619627e-05, "loss": 1.4086, "step": 321 }, { "epoch": 0.7042099507927829, "grad_norm": 2.1125080585479736, "learning_rate": 4.2579075425790756e-05, "loss": 1.2632, "step": 322 }, { "epoch": 0.7063969382176053, "grad_norm": 1.1004726886749268, "learning_rate": 4.2538523925385245e-05, "loss": 1.1005, "step": 323 }, { "epoch": 0.7085839256424276, "grad_norm": 1.5614429712295532, "learning_rate": 4.249797242497973e-05, "loss": 1.2059, "step": 324 }, { "epoch": 0.7107709130672498, "grad_norm": 2.553251266479492, "learning_rate": 4.245742092457421e-05, "loss": 1.1755, "step": 325 }, { "epoch": 0.7129579004920722, "grad_norm": 2.2272415161132812, "learning_rate": 4.24168694241687e-05, "loss": 1.2507, "step": 326 }, { "epoch": 0.7151448879168945, "grad_norm": 1.808928370475769, "learning_rate": 4.2376317923763185e-05, "loss": 1.5271, "step": 327 }, { "epoch": 0.7173318753417168, "grad_norm": 1.6885762214660645, "learning_rate": 4.233576642335767e-05, "loss": 1.1466, "step": 328 }, { "epoch": 0.7195188627665391, "grad_norm": 3.372645854949951, "learning_rate": 4.229521492295215e-05, "loss": 1.1796, "step": 329 }, { "epoch": 0.7217058501913614, "grad_norm": 2.3676037788391113, "learning_rate": 4.2254663422546634e-05, "loss": 1.4862, "step": 330 }, { "epoch": 0.7238928376161837, "grad_norm": 2.7641923427581787, "learning_rate": 4.221411192214112e-05, "loss": 1.0245, "step": 331 }, { "epoch": 0.726079825041006, "grad_norm": 2.0231285095214844, "learning_rate": 4.217356042173561e-05, "loss": 1.0405, "step": 332 }, { "epoch": 0.7282668124658284, "grad_norm": 1.591491460800171, "learning_rate": 4.213300892133009e-05, "loss": 1.3503, "step": 333 }, { "epoch": 0.7304537998906506, "grad_norm": 1.2020149230957031, "learning_rate": 4.209245742092457e-05, "loss": 0.9677, "step": 334 }, { "epoch": 0.7326407873154729, "grad_norm": 1.2406749725341797, "learning_rate": 4.205190592051906e-05, "loss": 1.0208, "step": 335 }, { "epoch": 0.7348277747402953, "grad_norm": 1.9359235763549805, "learning_rate": 4.2011354420113546e-05, "loss": 1.5334, "step": 336 }, { "epoch": 0.7370147621651175, "grad_norm": 1.9538333415985107, "learning_rate": 4.197080291970803e-05, "loss": 1.1872, "step": 337 }, { "epoch": 0.7392017495899399, "grad_norm": 2.254984140396118, "learning_rate": 4.193025141930252e-05, "loss": 1.5328, "step": 338 }, { "epoch": 0.7413887370147622, "grad_norm": 1.234540343284607, "learning_rate": 4.1889699918897e-05, "loss": 1.0245, "step": 339 }, { "epoch": 0.7435757244395844, "grad_norm": 1.7763786315917969, "learning_rate": 4.1849148418491485e-05, "loss": 1.284, "step": 340 }, { "epoch": 0.7457627118644068, "grad_norm": 2.633087158203125, "learning_rate": 4.1808596918085975e-05, "loss": 1.2542, "step": 341 }, { "epoch": 0.747949699289229, "grad_norm": 3.4212827682495117, "learning_rate": 4.176804541768046e-05, "loss": 1.4558, "step": 342 }, { "epoch": 0.7501366867140514, "grad_norm": 1.2153875827789307, "learning_rate": 4.172749391727494e-05, "loss": 1.0781, "step": 343 }, { "epoch": 0.7523236741388737, "grad_norm": 1.9739311933517456, "learning_rate": 4.168694241686943e-05, "loss": 1.2359, "step": 344 }, { "epoch": 0.7545106615636961, "grad_norm": 2.8915135860443115, "learning_rate": 4.1646390916463914e-05, "loss": 1.3944, "step": 345 }, { "epoch": 0.7566976489885183, "grad_norm": 3.3456287384033203, "learning_rate": 4.16058394160584e-05, "loss": 1.6615, "step": 346 }, { "epoch": 0.7588846364133406, "grad_norm": 2.997915267944336, "learning_rate": 4.156528791565288e-05, "loss": 1.1662, "step": 347 }, { "epoch": 0.761071623838163, "grad_norm": 1.819941759109497, "learning_rate": 4.152473641524737e-05, "loss": 1.4373, "step": 348 }, { "epoch": 0.7632586112629852, "grad_norm": 1.381791353225708, "learning_rate": 4.148418491484185e-05, "loss": 1.261, "step": 349 }, { "epoch": 0.7654455986878076, "grad_norm": 2.392831802368164, "learning_rate": 4.1443633414436336e-05, "loss": 1.1276, "step": 350 }, { "epoch": 0.7676325861126299, "grad_norm": 3.014312505722046, "learning_rate": 4.1403081914030826e-05, "loss": 1.1964, "step": 351 }, { "epoch": 0.7698195735374521, "grad_norm": 1.5462740659713745, "learning_rate": 4.136253041362531e-05, "loss": 1.2098, "step": 352 }, { "epoch": 0.7720065609622745, "grad_norm": 1.3114067316055298, "learning_rate": 4.132197891321979e-05, "loss": 1.3671, "step": 353 }, { "epoch": 0.7741935483870968, "grad_norm": 2.00374698638916, "learning_rate": 4.1281427412814275e-05, "loss": 1.3511, "step": 354 }, { "epoch": 0.7763805358119191, "grad_norm": 1.6881613731384277, "learning_rate": 4.124087591240876e-05, "loss": 1.2304, "step": 355 }, { "epoch": 0.7785675232367414, "grad_norm": 2.1436409950256348, "learning_rate": 4.120032441200324e-05, "loss": 1.404, "step": 356 }, { "epoch": 0.7807545106615636, "grad_norm": 1.7499324083328247, "learning_rate": 4.115977291159773e-05, "loss": 1.3482, "step": 357 }, { "epoch": 0.782941498086386, "grad_norm": 1.1961318254470825, "learning_rate": 4.1119221411192214e-05, "loss": 1.2335, "step": 358 }, { "epoch": 0.7851284855112083, "grad_norm": 1.5581930875778198, "learning_rate": 4.10786699107867e-05, "loss": 1.253, "step": 359 }, { "epoch": 0.7873154729360307, "grad_norm": 1.7077997922897339, "learning_rate": 4.103811841038119e-05, "loss": 0.9453, "step": 360 }, { "epoch": 0.7895024603608529, "grad_norm": 2.6736340522766113, "learning_rate": 4.099756690997567e-05, "loss": 1.2248, "step": 361 }, { "epoch": 0.7916894477856752, "grad_norm": 1.8983545303344727, "learning_rate": 4.095701540957015e-05, "loss": 1.0332, "step": 362 }, { "epoch": 0.7938764352104976, "grad_norm": 1.2666733264923096, "learning_rate": 4.091646390916464e-05, "loss": 1.3345, "step": 363 }, { "epoch": 0.7960634226353198, "grad_norm": 3.0591135025024414, "learning_rate": 4.0875912408759126e-05, "loss": 1.2395, "step": 364 }, { "epoch": 0.7982504100601422, "grad_norm": 1.8795924186706543, "learning_rate": 4.083536090835361e-05, "loss": 1.3894, "step": 365 }, { "epoch": 0.8004373974849645, "grad_norm": 1.8043549060821533, "learning_rate": 4.07948094079481e-05, "loss": 1.3787, "step": 366 }, { "epoch": 0.8026243849097867, "grad_norm": 2.5423436164855957, "learning_rate": 4.075425790754258e-05, "loss": 1.492, "step": 367 }, { "epoch": 0.8048113723346091, "grad_norm": 1.5784680843353271, "learning_rate": 4.0713706407137065e-05, "loss": 1.3216, "step": 368 }, { "epoch": 0.8069983597594313, "grad_norm": 1.9340240955352783, "learning_rate": 4.0673154906731555e-05, "loss": 1.2497, "step": 369 }, { "epoch": 0.8091853471842537, "grad_norm": 2.406505823135376, "learning_rate": 4.063260340632604e-05, "loss": 1.3352, "step": 370 }, { "epoch": 0.811372334609076, "grad_norm": 2.14868426322937, "learning_rate": 4.059205190592052e-05, "loss": 1.1846, "step": 371 }, { "epoch": 0.8135593220338984, "grad_norm": 3.698284387588501, "learning_rate": 4.055150040551501e-05, "loss": 0.9934, "step": 372 }, { "epoch": 0.8157463094587206, "grad_norm": 2.1104233264923096, "learning_rate": 4.0510948905109494e-05, "loss": 1.3811, "step": 373 }, { "epoch": 0.8179332968835429, "grad_norm": 1.7712186574935913, "learning_rate": 4.047039740470398e-05, "loss": 1.1814, "step": 374 }, { "epoch": 0.8201202843083653, "grad_norm": 1.4420323371887207, "learning_rate": 4.0429845904298467e-05, "loss": 1.2111, "step": 375 }, { "epoch": 0.8223072717331875, "grad_norm": 1.2447831630706787, "learning_rate": 4.038929440389295e-05, "loss": 1.2899, "step": 376 }, { "epoch": 0.8244942591580099, "grad_norm": 1.461362361907959, "learning_rate": 4.034874290348743e-05, "loss": 1.2259, "step": 377 }, { "epoch": 0.8266812465828322, "grad_norm": 1.3350125551223755, "learning_rate": 4.0308191403081916e-05, "loss": 0.9294, "step": 378 }, { "epoch": 0.8288682340076544, "grad_norm": 2.481240749359131, "learning_rate": 4.02676399026764e-05, "loss": 1.2547, "step": 379 }, { "epoch": 0.8310552214324768, "grad_norm": 1.6677141189575195, "learning_rate": 4.022708840227088e-05, "loss": 0.9647, "step": 380 }, { "epoch": 0.833242208857299, "grad_norm": 1.6543183326721191, "learning_rate": 4.018653690186537e-05, "loss": 1.3569, "step": 381 }, { "epoch": 0.8354291962821214, "grad_norm": 1.575474739074707, "learning_rate": 4.0145985401459855e-05, "loss": 1.1004, "step": 382 }, { "epoch": 0.8376161837069437, "grad_norm": 2.3073768615722656, "learning_rate": 4.010543390105434e-05, "loss": 1.5126, "step": 383 }, { "epoch": 0.839803171131766, "grad_norm": 1.9105490446090698, "learning_rate": 4.006488240064882e-05, "loss": 1.3045, "step": 384 }, { "epoch": 0.8419901585565883, "grad_norm": 2.1091814041137695, "learning_rate": 4.002433090024331e-05, "loss": 1.3368, "step": 385 }, { "epoch": 0.8441771459814106, "grad_norm": 1.3038783073425293, "learning_rate": 3.9983779399837794e-05, "loss": 1.2571, "step": 386 }, { "epoch": 0.846364133406233, "grad_norm": 1.6786741018295288, "learning_rate": 3.994322789943228e-05, "loss": 1.23, "step": 387 }, { "epoch": 0.8485511208310552, "grad_norm": 2.2502193450927734, "learning_rate": 3.990267639902677e-05, "loss": 1.1699, "step": 388 }, { "epoch": 0.8507381082558775, "grad_norm": 2.073580741882324, "learning_rate": 3.986212489862125e-05, "loss": 1.3401, "step": 389 }, { "epoch": 0.8529250956806999, "grad_norm": 1.3595247268676758, "learning_rate": 3.982157339821573e-05, "loss": 0.9704, "step": 390 }, { "epoch": 0.8551120831055221, "grad_norm": 2.179640769958496, "learning_rate": 3.978102189781022e-05, "loss": 1.5997, "step": 391 }, { "epoch": 0.8572990705303445, "grad_norm": 1.2254271507263184, "learning_rate": 3.9740470397404706e-05, "loss": 0.9437, "step": 392 }, { "epoch": 0.8594860579551667, "grad_norm": 1.7013218402862549, "learning_rate": 3.969991889699919e-05, "loss": 1.2593, "step": 393 }, { "epoch": 0.861673045379989, "grad_norm": 1.6208447217941284, "learning_rate": 3.965936739659368e-05, "loss": 1.209, "step": 394 }, { "epoch": 0.8638600328048114, "grad_norm": 2.6023013591766357, "learning_rate": 3.961881589618816e-05, "loss": 1.2554, "step": 395 }, { "epoch": 0.8660470202296336, "grad_norm": 1.5439281463623047, "learning_rate": 3.9578264395782645e-05, "loss": 1.0845, "step": 396 }, { "epoch": 0.868234007654456, "grad_norm": 1.444728970527649, "learning_rate": 3.9537712895377135e-05, "loss": 0.8915, "step": 397 }, { "epoch": 0.8704209950792783, "grad_norm": 2.0641324520111084, "learning_rate": 3.949716139497162e-05, "loss": 1.1446, "step": 398 }, { "epoch": 0.8726079825041007, "grad_norm": 1.799673318862915, "learning_rate": 3.94566098945661e-05, "loss": 1.2146, "step": 399 }, { "epoch": 0.8747949699289229, "grad_norm": 1.445273995399475, "learning_rate": 3.941605839416059e-05, "loss": 1.2593, "step": 400 }, { "epoch": 0.8769819573537452, "grad_norm": 2.029047727584839, "learning_rate": 3.9375506893755074e-05, "loss": 1.195, "step": 401 }, { "epoch": 0.8791689447785676, "grad_norm": 1.4377449750900269, "learning_rate": 3.933495539334956e-05, "loss": 1.1959, "step": 402 }, { "epoch": 0.8813559322033898, "grad_norm": 1.79544997215271, "learning_rate": 3.929440389294404e-05, "loss": 1.3383, "step": 403 }, { "epoch": 0.8835429196282122, "grad_norm": 1.376664638519287, "learning_rate": 3.925385239253852e-05, "loss": 1.1496, "step": 404 }, { "epoch": 0.8857299070530344, "grad_norm": 3.202341079711914, "learning_rate": 3.9213300892133006e-05, "loss": 1.3176, "step": 405 }, { "epoch": 0.8879168944778567, "grad_norm": 1.5556436777114868, "learning_rate": 3.9172749391727496e-05, "loss": 1.4377, "step": 406 }, { "epoch": 0.8901038819026791, "grad_norm": 2.141373634338379, "learning_rate": 3.913219789132198e-05, "loss": 1.1471, "step": 407 }, { "epoch": 0.8922908693275013, "grad_norm": 1.4080469608306885, "learning_rate": 3.909164639091646e-05, "loss": 1.1073, "step": 408 }, { "epoch": 0.8944778567523237, "grad_norm": 1.2130626440048218, "learning_rate": 3.905109489051095e-05, "loss": 1.0126, "step": 409 }, { "epoch": 0.896664844177146, "grad_norm": 1.5379283428192139, "learning_rate": 3.9010543390105435e-05, "loss": 1.2833, "step": 410 }, { "epoch": 0.8988518316019682, "grad_norm": 1.019129753112793, "learning_rate": 3.896999188969992e-05, "loss": 1.3111, "step": 411 }, { "epoch": 0.9010388190267906, "grad_norm": 1.710167407989502, "learning_rate": 3.892944038929441e-05, "loss": 1.1322, "step": 412 }, { "epoch": 0.9032258064516129, "grad_norm": 1.5367594957351685, "learning_rate": 3.888888888888889e-05, "loss": 1.2438, "step": 413 }, { "epoch": 0.9054127938764353, "grad_norm": 1.8477466106414795, "learning_rate": 3.8848337388483374e-05, "loss": 1.15, "step": 414 }, { "epoch": 0.9075997813012575, "grad_norm": 2.1580653190612793, "learning_rate": 3.8807785888077864e-05, "loss": 1.2621, "step": 415 }, { "epoch": 0.9097867687260798, "grad_norm": 3.065197467803955, "learning_rate": 3.876723438767235e-05, "loss": 1.4293, "step": 416 }, { "epoch": 0.9119737561509021, "grad_norm": 1.3358650207519531, "learning_rate": 3.872668288726683e-05, "loss": 1.0547, "step": 417 }, { "epoch": 0.9141607435757244, "grad_norm": 1.3536818027496338, "learning_rate": 3.868613138686132e-05, "loss": 1.2675, "step": 418 }, { "epoch": 0.9163477310005468, "grad_norm": 1.6324467658996582, "learning_rate": 3.86455798864558e-05, "loss": 1.101, "step": 419 }, { "epoch": 0.918534718425369, "grad_norm": 2.3156228065490723, "learning_rate": 3.8605028386050286e-05, "loss": 1.0931, "step": 420 }, { "epoch": 0.9207217058501913, "grad_norm": 1.7464854717254639, "learning_rate": 3.856447688564477e-05, "loss": 1.229, "step": 421 }, { "epoch": 0.9229086932750137, "grad_norm": 1.5220204591751099, "learning_rate": 3.852392538523926e-05, "loss": 1.3105, "step": 422 }, { "epoch": 0.9250956806998359, "grad_norm": 1.3729076385498047, "learning_rate": 3.848337388483374e-05, "loss": 1.2593, "step": 423 }, { "epoch": 0.9272826681246583, "grad_norm": 1.597056269645691, "learning_rate": 3.8442822384428225e-05, "loss": 1.2578, "step": 424 }, { "epoch": 0.9294696555494806, "grad_norm": 1.604997158050537, "learning_rate": 3.8402270884022715e-05, "loss": 1.1684, "step": 425 }, { "epoch": 0.931656642974303, "grad_norm": 1.2845187187194824, "learning_rate": 3.83617193836172e-05, "loss": 1.1573, "step": 426 }, { "epoch": 0.9338436303991252, "grad_norm": 1.7821863889694214, "learning_rate": 3.832116788321168e-05, "loss": 1.2183, "step": 427 }, { "epoch": 0.9360306178239475, "grad_norm": 2.0126750469207764, "learning_rate": 3.8280616382806164e-05, "loss": 1.4971, "step": 428 }, { "epoch": 0.9382176052487698, "grad_norm": 1.3579193353652954, "learning_rate": 3.824006488240065e-05, "loss": 1.0294, "step": 429 }, { "epoch": 0.9404045926735921, "grad_norm": 1.4105063676834106, "learning_rate": 3.819951338199514e-05, "loss": 1.3727, "step": 430 }, { "epoch": 0.9425915800984145, "grad_norm": 1.8188258409500122, "learning_rate": 3.815896188158962e-05, "loss": 1.031, "step": 431 }, { "epoch": 0.9447785675232367, "grad_norm": 2.3146791458129883, "learning_rate": 3.81184103811841e-05, "loss": 1.3725, "step": 432 }, { "epoch": 0.946965554948059, "grad_norm": 1.7835323810577393, "learning_rate": 3.8077858880778586e-05, "loss": 1.1787, "step": 433 }, { "epoch": 0.9491525423728814, "grad_norm": 1.1906533241271973, "learning_rate": 3.8037307380373076e-05, "loss": 1.1694, "step": 434 }, { "epoch": 0.9513395297977036, "grad_norm": 2.6073074340820312, "learning_rate": 3.799675587996756e-05, "loss": 1.2947, "step": 435 }, { "epoch": 0.953526517222526, "grad_norm": 1.6654317378997803, "learning_rate": 3.795620437956204e-05, "loss": 1.5213, "step": 436 }, { "epoch": 0.9557135046473483, "grad_norm": 1.4062565565109253, "learning_rate": 3.791565287915653e-05, "loss": 1.1667, "step": 437 }, { "epoch": 0.9579004920721705, "grad_norm": 1.178652048110962, "learning_rate": 3.7875101378751015e-05, "loss": 1.167, "step": 438 }, { "epoch": 0.9600874794969929, "grad_norm": 1.239072561264038, "learning_rate": 3.78345498783455e-05, "loss": 1.0755, "step": 439 }, { "epoch": 0.9622744669218152, "grad_norm": 2.0977180004119873, "learning_rate": 3.779399837793999e-05, "loss": 1.3497, "step": 440 }, { "epoch": 0.9644614543466375, "grad_norm": 1.2090554237365723, "learning_rate": 3.775344687753447e-05, "loss": 1.0536, "step": 441 }, { "epoch": 0.9666484417714598, "grad_norm": 1.5191102027893066, "learning_rate": 3.7712895377128954e-05, "loss": 0.9831, "step": 442 }, { "epoch": 0.9688354291962821, "grad_norm": 1.598800778388977, "learning_rate": 3.7672343876723444e-05, "loss": 0.9993, "step": 443 }, { "epoch": 0.9710224166211044, "grad_norm": 1.2385090589523315, "learning_rate": 3.763179237631793e-05, "loss": 1.0997, "step": 444 }, { "epoch": 0.9732094040459267, "grad_norm": 2.266714096069336, "learning_rate": 3.759124087591241e-05, "loss": 1.0083, "step": 445 }, { "epoch": 0.9753963914707491, "grad_norm": 1.774715542793274, "learning_rate": 3.75506893755069e-05, "loss": 1.1791, "step": 446 }, { "epoch": 0.9775833788955713, "grad_norm": 2.2417657375335693, "learning_rate": 3.751013787510138e-05, "loss": 1.2661, "step": 447 }, { "epoch": 0.9797703663203936, "grad_norm": 2.228820323944092, "learning_rate": 3.7469586374695866e-05, "loss": 1.0991, "step": 448 }, { "epoch": 0.981957353745216, "grad_norm": 1.7126444578170776, "learning_rate": 3.7429034874290356e-05, "loss": 1.3724, "step": 449 }, { "epoch": 0.9841443411700382, "grad_norm": 2.116145372390747, "learning_rate": 3.738848337388484e-05, "loss": 0.9018, "step": 450 }, { "epoch": 0.9863313285948606, "grad_norm": 1.7316856384277344, "learning_rate": 3.734793187347932e-05, "loss": 1.4001, "step": 451 }, { "epoch": 0.9885183160196829, "grad_norm": 2.181330442428589, "learning_rate": 3.7307380373073805e-05, "loss": 1.5624, "step": 452 }, { "epoch": 0.9907053034445052, "grad_norm": 1.6795828342437744, "learning_rate": 3.726682887266829e-05, "loss": 1.2474, "step": 453 }, { "epoch": 0.9928922908693275, "grad_norm": 1.7936421632766724, "learning_rate": 3.722627737226278e-05, "loss": 1.2165, "step": 454 }, { "epoch": 0.9950792782941498, "grad_norm": 1.0812389850616455, "learning_rate": 3.718572587185726e-05, "loss": 1.1555, "step": 455 }, { "epoch": 0.9972662657189721, "grad_norm": 1.583435297012329, "learning_rate": 3.7145174371451744e-05, "loss": 1.3861, "step": 456 }, { "epoch": 0.9994532531437944, "grad_norm": 2.147641658782959, "learning_rate": 3.710462287104623e-05, "loss": 1.1794, "step": 457 }, { "epoch": 1.0016402405686167, "grad_norm": 1.2491430044174194, "learning_rate": 3.706407137064071e-05, "loss": 1.0296, "step": 458 }, { "epoch": 1.003827227993439, "grad_norm": 1.7700275182724, "learning_rate": 3.70235198702352e-05, "loss": 1.1445, "step": 459 }, { "epoch": 1.0060142154182614, "grad_norm": 1.5746709108352661, "learning_rate": 3.698296836982968e-05, "loss": 1.1504, "step": 460 }, { "epoch": 1.0082012028430836, "grad_norm": 2.5550432205200195, "learning_rate": 3.6942416869424166e-05, "loss": 0.9884, "step": 461 }, { "epoch": 1.010388190267906, "grad_norm": 1.3825803995132446, "learning_rate": 3.6901865369018656e-05, "loss": 1.0516, "step": 462 }, { "epoch": 1.0125751776927283, "grad_norm": 2.5480241775512695, "learning_rate": 3.686131386861314e-05, "loss": 0.9635, "step": 463 }, { "epoch": 1.0147621651175505, "grad_norm": 2.013044834136963, "learning_rate": 3.682076236820762e-05, "loss": 1.5938, "step": 464 }, { "epoch": 1.0169491525423728, "grad_norm": 1.1404300928115845, "learning_rate": 3.678021086780211e-05, "loss": 1.1326, "step": 465 }, { "epoch": 1.0191361399671952, "grad_norm": 0.9538056254386902, "learning_rate": 3.6739659367396595e-05, "loss": 0.8319, "step": 466 }, { "epoch": 1.0213231273920176, "grad_norm": 1.3901396989822388, "learning_rate": 3.669910786699108e-05, "loss": 0.9194, "step": 467 }, { "epoch": 1.0235101148168397, "grad_norm": 1.368876576423645, "learning_rate": 3.665855636658557e-05, "loss": 1.0367, "step": 468 }, { "epoch": 1.025697102241662, "grad_norm": 1.7443093061447144, "learning_rate": 3.661800486618005e-05, "loss": 1.1474, "step": 469 }, { "epoch": 1.0278840896664845, "grad_norm": 2.536716938018799, "learning_rate": 3.6577453365774534e-05, "loss": 0.9111, "step": 470 }, { "epoch": 1.0300710770913066, "grad_norm": 1.3219335079193115, "learning_rate": 3.6536901865369024e-05, "loss": 1.1244, "step": 471 }, { "epoch": 1.032258064516129, "grad_norm": 1.488257646560669, "learning_rate": 3.649635036496351e-05, "loss": 1.2059, "step": 472 }, { "epoch": 1.0344450519409514, "grad_norm": 1.873935341835022, "learning_rate": 3.645579886455799e-05, "loss": 1.2318, "step": 473 }, { "epoch": 1.0366320393657737, "grad_norm": 1.7419514656066895, "learning_rate": 3.641524736415248e-05, "loss": 1.1954, "step": 474 }, { "epoch": 1.038819026790596, "grad_norm": 1.4764482975006104, "learning_rate": 3.637469586374696e-05, "loss": 1.0499, "step": 475 }, { "epoch": 1.0410060142154183, "grad_norm": 1.9208378791809082, "learning_rate": 3.6334144363341446e-05, "loss": 1.3494, "step": 476 }, { "epoch": 1.0431930016402406, "grad_norm": 1.4284610748291016, "learning_rate": 3.6293592862935936e-05, "loss": 0.914, "step": 477 }, { "epoch": 1.0453799890650628, "grad_norm": 1.5983939170837402, "learning_rate": 3.625304136253042e-05, "loss": 0.8798, "step": 478 }, { "epoch": 1.0475669764898852, "grad_norm": 1.797193169593811, "learning_rate": 3.62124898621249e-05, "loss": 0.9256, "step": 479 }, { "epoch": 1.0497539639147075, "grad_norm": 1.9687570333480835, "learning_rate": 3.6171938361719385e-05, "loss": 0.9595, "step": 480 }, { "epoch": 1.0519409513395297, "grad_norm": 2.113931179046631, "learning_rate": 3.613138686131387e-05, "loss": 1.079, "step": 481 }, { "epoch": 1.054127938764352, "grad_norm": 1.9601927995681763, "learning_rate": 3.609083536090835e-05, "loss": 1.329, "step": 482 }, { "epoch": 1.0563149261891744, "grad_norm": 1.3063193559646606, "learning_rate": 3.605028386050284e-05, "loss": 1.0574, "step": 483 }, { "epoch": 1.0585019136139968, "grad_norm": 1.3675932884216309, "learning_rate": 3.6009732360097324e-05, "loss": 1.0137, "step": 484 }, { "epoch": 1.060688901038819, "grad_norm": 1.5369495153427124, "learning_rate": 3.596918085969181e-05, "loss": 1.1231, "step": 485 }, { "epoch": 1.0628758884636413, "grad_norm": 2.206226348876953, "learning_rate": 3.59286293592863e-05, "loss": 1.2143, "step": 486 }, { "epoch": 1.0650628758884637, "grad_norm": 1.472771167755127, "learning_rate": 3.588807785888078e-05, "loss": 1.1485, "step": 487 }, { "epoch": 1.0672498633132859, "grad_norm": 1.6909104585647583, "learning_rate": 3.584752635847526e-05, "loss": 0.8583, "step": 488 }, { "epoch": 1.0694368507381082, "grad_norm": 2.266188859939575, "learning_rate": 3.580697485806975e-05, "loss": 1.1025, "step": 489 }, { "epoch": 1.0716238381629306, "grad_norm": 3.0968472957611084, "learning_rate": 3.5766423357664236e-05, "loss": 1.3942, "step": 490 }, { "epoch": 1.0738108255877528, "grad_norm": 0.9615070223808289, "learning_rate": 3.572587185725872e-05, "loss": 1.247, "step": 491 }, { "epoch": 1.0759978130125751, "grad_norm": 1.8224518299102783, "learning_rate": 3.568532035685321e-05, "loss": 0.9981, "step": 492 }, { "epoch": 1.0781848004373975, "grad_norm": 1.2193702459335327, "learning_rate": 3.564476885644769e-05, "loss": 1.0422, "step": 493 }, { "epoch": 1.0803717878622199, "grad_norm": 1.945477843284607, "learning_rate": 3.5604217356042175e-05, "loss": 1.0219, "step": 494 }, { "epoch": 1.082558775287042, "grad_norm": 1.3169317245483398, "learning_rate": 3.556366585563666e-05, "loss": 0.992, "step": 495 }, { "epoch": 1.0847457627118644, "grad_norm": 1.534543752670288, "learning_rate": 3.552311435523115e-05, "loss": 1.0224, "step": 496 }, { "epoch": 1.0869327501366868, "grad_norm": 1.250248908996582, "learning_rate": 3.548256285482563e-05, "loss": 1.196, "step": 497 }, { "epoch": 1.089119737561509, "grad_norm": 1.641183853149414, "learning_rate": 3.5442011354420114e-05, "loss": 1.0248, "step": 498 }, { "epoch": 1.0913067249863313, "grad_norm": 1.508020281791687, "learning_rate": 3.5401459854014604e-05, "loss": 1.0346, "step": 499 }, { "epoch": 1.0934937124111537, "grad_norm": 1.6471333503723145, "learning_rate": 3.536090835360909e-05, "loss": 1.0293, "step": 500 }, { "epoch": 1.095680699835976, "grad_norm": 1.8233013153076172, "learning_rate": 3.532035685320357e-05, "loss": 1.2006, "step": 501 }, { "epoch": 1.0978676872607982, "grad_norm": 1.9216625690460205, "learning_rate": 3.527980535279806e-05, "loss": 1.1707, "step": 502 }, { "epoch": 1.1000546746856206, "grad_norm": 1.1982905864715576, "learning_rate": 3.523925385239254e-05, "loss": 1.2627, "step": 503 }, { "epoch": 1.102241662110443, "grad_norm": 1.7955820560455322, "learning_rate": 3.5198702351987026e-05, "loss": 1.0955, "step": 504 }, { "epoch": 1.104428649535265, "grad_norm": 2.3441812992095947, "learning_rate": 3.515815085158151e-05, "loss": 1.1592, "step": 505 }, { "epoch": 1.1066156369600875, "grad_norm": 1.6856995820999146, "learning_rate": 3.511759935117599e-05, "loss": 1.1462, "step": 506 }, { "epoch": 1.1088026243849098, "grad_norm": 1.5831382274627686, "learning_rate": 3.5077047850770475e-05, "loss": 1.096, "step": 507 }, { "epoch": 1.110989611809732, "grad_norm": 1.6314855813980103, "learning_rate": 3.5036496350364965e-05, "loss": 1.0406, "step": 508 }, { "epoch": 1.1131765992345544, "grad_norm": 2.071168899536133, "learning_rate": 3.499594484995945e-05, "loss": 1.2177, "step": 509 }, { "epoch": 1.1153635866593767, "grad_norm": 3.0173611640930176, "learning_rate": 3.495539334955393e-05, "loss": 1.0498, "step": 510 }, { "epoch": 1.117550574084199, "grad_norm": 1.9596067667007446, "learning_rate": 3.491484184914842e-05, "loss": 0.9466, "step": 511 }, { "epoch": 1.1197375615090213, "grad_norm": 1.7626456022262573, "learning_rate": 3.4874290348742904e-05, "loss": 1.3765, "step": 512 }, { "epoch": 1.1219245489338436, "grad_norm": 1.2153733968734741, "learning_rate": 3.483373884833739e-05, "loss": 1.4146, "step": 513 }, { "epoch": 1.124111536358666, "grad_norm": 2.3280398845672607, "learning_rate": 3.479318734793188e-05, "loss": 1.2834, "step": 514 }, { "epoch": 1.1262985237834882, "grad_norm": 1.8355602025985718, "learning_rate": 3.475263584752636e-05, "loss": 0.9843, "step": 515 }, { "epoch": 1.1284855112083105, "grad_norm": 1.5347975492477417, "learning_rate": 3.471208434712084e-05, "loss": 0.9488, "step": 516 }, { "epoch": 1.130672498633133, "grad_norm": 2.625126838684082, "learning_rate": 3.467153284671533e-05, "loss": 0.7321, "step": 517 }, { "epoch": 1.132859486057955, "grad_norm": 2.0756213665008545, "learning_rate": 3.4630981346309816e-05, "loss": 1.0723, "step": 518 }, { "epoch": 1.1350464734827774, "grad_norm": 1.4918804168701172, "learning_rate": 3.45904298459043e-05, "loss": 0.7196, "step": 519 }, { "epoch": 1.1372334609075998, "grad_norm": 1.4285305738449097, "learning_rate": 3.454987834549879e-05, "loss": 1.0419, "step": 520 }, { "epoch": 1.1394204483324222, "grad_norm": 2.0764875411987305, "learning_rate": 3.450932684509327e-05, "loss": 0.9296, "step": 521 }, { "epoch": 1.1416074357572443, "grad_norm": 2.9169929027557373, "learning_rate": 3.4468775344687755e-05, "loss": 0.9977, "step": 522 }, { "epoch": 1.1437944231820667, "grad_norm": 1.3462270498275757, "learning_rate": 3.4428223844282245e-05, "loss": 1.202, "step": 523 }, { "epoch": 1.145981410606889, "grad_norm": 1.1320356130599976, "learning_rate": 3.438767234387673e-05, "loss": 1.1037, "step": 524 }, { "epoch": 1.1481683980317112, "grad_norm": 2.0254011154174805, "learning_rate": 3.434712084347121e-05, "loss": 1.042, "step": 525 }, { "epoch": 1.1503553854565336, "grad_norm": 1.6895188093185425, "learning_rate": 3.43065693430657e-05, "loss": 0.8799, "step": 526 }, { "epoch": 1.152542372881356, "grad_norm": 0.8571317195892334, "learning_rate": 3.4266017842660184e-05, "loss": 0.768, "step": 527 }, { "epoch": 1.1547293603061783, "grad_norm": 1.6994755268096924, "learning_rate": 3.422546634225467e-05, "loss": 1.0466, "step": 528 }, { "epoch": 1.1569163477310005, "grad_norm": 1.5832433700561523, "learning_rate": 3.418491484184915e-05, "loss": 1.2946, "step": 529 }, { "epoch": 1.1591033351558229, "grad_norm": 1.4605438709259033, "learning_rate": 3.414436334144363e-05, "loss": 1.2164, "step": 530 }, { "epoch": 1.1612903225806452, "grad_norm": 1.8534467220306396, "learning_rate": 3.4103811841038116e-05, "loss": 1.1588, "step": 531 }, { "epoch": 1.1634773100054674, "grad_norm": 1.59779691696167, "learning_rate": 3.40632603406326e-05, "loss": 0.925, "step": 532 }, { "epoch": 1.1656642974302898, "grad_norm": 1.476476788520813, "learning_rate": 3.402270884022709e-05, "loss": 0.9778, "step": 533 }, { "epoch": 1.1678512848551121, "grad_norm": 2.6784133911132812, "learning_rate": 3.398215733982157e-05, "loss": 1.0672, "step": 534 }, { "epoch": 1.1700382722799345, "grad_norm": 1.9519327878952026, "learning_rate": 3.3941605839416055e-05, "loss": 1.0133, "step": 535 }, { "epoch": 1.1722252597047567, "grad_norm": 1.5686060190200806, "learning_rate": 3.3901054339010545e-05, "loss": 1.0003, "step": 536 }, { "epoch": 1.174412247129579, "grad_norm": 1.8115992546081543, "learning_rate": 3.386050283860503e-05, "loss": 1.1157, "step": 537 }, { "epoch": 1.1765992345544014, "grad_norm": 1.441066861152649, "learning_rate": 3.381995133819951e-05, "loss": 0.8834, "step": 538 }, { "epoch": 1.1787862219792236, "grad_norm": 1.3640106916427612, "learning_rate": 3.3779399837794e-05, "loss": 1.0209, "step": 539 }, { "epoch": 1.180973209404046, "grad_norm": 2.124795913696289, "learning_rate": 3.3738848337388484e-05, "loss": 1.045, "step": 540 }, { "epoch": 1.1831601968288683, "grad_norm": 1.9038399457931519, "learning_rate": 3.369829683698297e-05, "loss": 1.1683, "step": 541 }, { "epoch": 1.1853471842536905, "grad_norm": 2.208097219467163, "learning_rate": 3.365774533657746e-05, "loss": 1.0444, "step": 542 }, { "epoch": 1.1875341716785128, "grad_norm": 2.335313081741333, "learning_rate": 3.361719383617194e-05, "loss": 0.9064, "step": 543 }, { "epoch": 1.1897211591033352, "grad_norm": 2.292243480682373, "learning_rate": 3.357664233576642e-05, "loss": 1.2267, "step": 544 }, { "epoch": 1.1919081465281574, "grad_norm": 1.733549952507019, "learning_rate": 3.353609083536091e-05, "loss": 1.0652, "step": 545 }, { "epoch": 1.1940951339529797, "grad_norm": 3.766594648361206, "learning_rate": 3.3495539334955396e-05, "loss": 1.1742, "step": 546 }, { "epoch": 1.196282121377802, "grad_norm": 1.2802308797836304, "learning_rate": 3.345498783454988e-05, "loss": 0.9065, "step": 547 }, { "epoch": 1.1984691088026245, "grad_norm": 1.822237491607666, "learning_rate": 3.341443633414437e-05, "loss": 1.0266, "step": 548 }, { "epoch": 1.2006560962274466, "grad_norm": 1.230053424835205, "learning_rate": 3.337388483373885e-05, "loss": 0.8105, "step": 549 }, { "epoch": 1.202843083652269, "grad_norm": 1.500394582748413, "learning_rate": 3.3333333333333335e-05, "loss": 0.9971, "step": 550 }, { "epoch": 1.2050300710770914, "grad_norm": 1.5969089269638062, "learning_rate": 3.3292781832927825e-05, "loss": 1.1795, "step": 551 }, { "epoch": 1.2072170585019135, "grad_norm": 1.4337689876556396, "learning_rate": 3.325223033252231e-05, "loss": 1.0064, "step": 552 }, { "epoch": 1.209404045926736, "grad_norm": 1.5033226013183594, "learning_rate": 3.321167883211679e-05, "loss": 0.9732, "step": 553 }, { "epoch": 1.2115910333515583, "grad_norm": 1.9927486181259155, "learning_rate": 3.3171127331711274e-05, "loss": 1.1634, "step": 554 }, { "epoch": 1.2137780207763806, "grad_norm": 1.5096718072891235, "learning_rate": 3.313057583130576e-05, "loss": 1.0742, "step": 555 }, { "epoch": 1.2159650082012028, "grad_norm": 1.6208289861679077, "learning_rate": 3.309002433090024e-05, "loss": 1.0267, "step": 556 }, { "epoch": 1.2181519956260252, "grad_norm": 1.3574730157852173, "learning_rate": 3.304947283049473e-05, "loss": 0.8804, "step": 557 }, { "epoch": 1.2203389830508475, "grad_norm": 1.4106029272079468, "learning_rate": 3.300892133008921e-05, "loss": 1.0979, "step": 558 }, { "epoch": 1.2225259704756697, "grad_norm": 1.3993502855300903, "learning_rate": 3.2968369829683696e-05, "loss": 1.0056, "step": 559 }, { "epoch": 1.224712957900492, "grad_norm": 1.5626221895217896, "learning_rate": 3.2927818329278186e-05, "loss": 0.9432, "step": 560 }, { "epoch": 1.2268999453253144, "grad_norm": 1.6591813564300537, "learning_rate": 3.288726682887267e-05, "loss": 1.254, "step": 561 }, { "epoch": 1.2290869327501368, "grad_norm": 1.1141971349716187, "learning_rate": 3.284671532846715e-05, "loss": 0.8607, "step": 562 }, { "epoch": 1.231273920174959, "grad_norm": 1.052256464958191, "learning_rate": 3.280616382806164e-05, "loss": 0.9968, "step": 563 }, { "epoch": 1.2334609075997813, "grad_norm": 1.602264642715454, "learning_rate": 3.2765612327656125e-05, "loss": 1.1631, "step": 564 }, { "epoch": 1.2356478950246037, "grad_norm": 1.1931110620498657, "learning_rate": 3.272506082725061e-05, "loss": 0.855, "step": 565 }, { "epoch": 1.2378348824494259, "grad_norm": 1.3527902364730835, "learning_rate": 3.26845093268451e-05, "loss": 0.879, "step": 566 }, { "epoch": 1.2400218698742482, "grad_norm": 2.007213830947876, "learning_rate": 3.264395782643958e-05, "loss": 1.28, "step": 567 }, { "epoch": 1.2422088572990706, "grad_norm": 1.7016750574111938, "learning_rate": 3.2603406326034064e-05, "loss": 0.9581, "step": 568 }, { "epoch": 1.2443958447238928, "grad_norm": 1.8226912021636963, "learning_rate": 3.256285482562855e-05, "loss": 0.9338, "step": 569 }, { "epoch": 1.2465828321487151, "grad_norm": 1.568877935409546, "learning_rate": 3.252230332522304e-05, "loss": 1.1179, "step": 570 }, { "epoch": 1.2487698195735375, "grad_norm": 1.8205167055130005, "learning_rate": 3.248175182481752e-05, "loss": 1.0303, "step": 571 }, { "epoch": 1.2509568069983596, "grad_norm": 2.146737813949585, "learning_rate": 3.2441200324412e-05, "loss": 0.9382, "step": 572 }, { "epoch": 1.253143794423182, "grad_norm": 1.492611050605774, "learning_rate": 3.240064882400649e-05, "loss": 1.3328, "step": 573 }, { "epoch": 1.2553307818480044, "grad_norm": 1.6467738151550293, "learning_rate": 3.2360097323600976e-05, "loss": 0.9272, "step": 574 }, { "epoch": 1.2575177692728268, "grad_norm": 6.203010559082031, "learning_rate": 3.231954582319546e-05, "loss": 1.0956, "step": 575 }, { "epoch": 1.259704756697649, "grad_norm": 2.156064987182617, "learning_rate": 3.227899432278995e-05, "loss": 1.0929, "step": 576 }, { "epoch": 1.2618917441224713, "grad_norm": 1.9331228733062744, "learning_rate": 3.223844282238443e-05, "loss": 0.8643, "step": 577 }, { "epoch": 1.2640787315472937, "grad_norm": 1.650031328201294, "learning_rate": 3.2197891321978915e-05, "loss": 1.0194, "step": 578 }, { "epoch": 1.2662657189721158, "grad_norm": 1.0394580364227295, "learning_rate": 3.21573398215734e-05, "loss": 0.9681, "step": 579 }, { "epoch": 1.2684527063969382, "grad_norm": 2.026949882507324, "learning_rate": 3.211678832116788e-05, "loss": 1.2008, "step": 580 }, { "epoch": 1.2706396938217606, "grad_norm": 1.3180269002914429, "learning_rate": 3.207623682076237e-05, "loss": 1.0707, "step": 581 }, { "epoch": 1.272826681246583, "grad_norm": 1.5769938230514526, "learning_rate": 3.2035685320356854e-05, "loss": 1.2325, "step": 582 }, { "epoch": 1.275013668671405, "grad_norm": 1.4135606288909912, "learning_rate": 3.199513381995134e-05, "loss": 0.989, "step": 583 }, { "epoch": 1.2772006560962275, "grad_norm": 1.5491902828216553, "learning_rate": 3.195458231954582e-05, "loss": 1.0053, "step": 584 }, { "epoch": 1.2793876435210498, "grad_norm": 2.331817388534546, "learning_rate": 3.191403081914031e-05, "loss": 1.1289, "step": 585 }, { "epoch": 1.281574630945872, "grad_norm": 1.745554804801941, "learning_rate": 3.187347931873479e-05, "loss": 1.0016, "step": 586 }, { "epoch": 1.2837616183706944, "grad_norm": 1.413426399230957, "learning_rate": 3.1832927818329276e-05, "loss": 0.8592, "step": 587 }, { "epoch": 1.2859486057955167, "grad_norm": 1.2044061422348022, "learning_rate": 3.1792376317923766e-05, "loss": 0.921, "step": 588 }, { "epoch": 1.288135593220339, "grad_norm": 1.174408197402954, "learning_rate": 3.175182481751825e-05, "loss": 0.8647, "step": 589 }, { "epoch": 1.2903225806451613, "grad_norm": 1.3047147989273071, "learning_rate": 3.171127331711273e-05, "loss": 0.9797, "step": 590 }, { "epoch": 1.2925095680699836, "grad_norm": 1.2132624387741089, "learning_rate": 3.167072181670722e-05, "loss": 0.8751, "step": 591 }, { "epoch": 1.2946965554948058, "grad_norm": 1.0107461214065552, "learning_rate": 3.1630170316301705e-05, "loss": 1.0741, "step": 592 }, { "epoch": 1.2968835429196282, "grad_norm": 1.0941015481948853, "learning_rate": 3.158961881589619e-05, "loss": 1.0091, "step": 593 }, { "epoch": 1.2990705303444505, "grad_norm": 1.1402095556259155, "learning_rate": 3.154906731549068e-05, "loss": 0.9863, "step": 594 }, { "epoch": 1.301257517769273, "grad_norm": 1.387197732925415, "learning_rate": 3.150851581508516e-05, "loss": 1.1933, "step": 595 }, { "epoch": 1.3034445051940953, "grad_norm": 1.573848009109497, "learning_rate": 3.1467964314679644e-05, "loss": 1.076, "step": 596 }, { "epoch": 1.3056314926189174, "grad_norm": 1.5490944385528564, "learning_rate": 3.1427412814274134e-05, "loss": 1.0499, "step": 597 }, { "epoch": 1.3078184800437398, "grad_norm": 1.8000141382217407, "learning_rate": 3.138686131386862e-05, "loss": 0.9959, "step": 598 }, { "epoch": 1.310005467468562, "grad_norm": 1.744747281074524, "learning_rate": 3.13463098134631e-05, "loss": 0.9569, "step": 599 }, { "epoch": 1.3121924548933843, "grad_norm": 1.4420640468597412, "learning_rate": 3.130575831305759e-05, "loss": 0.9261, "step": 600 }, { "epoch": 1.3143794423182067, "grad_norm": 1.476227045059204, "learning_rate": 3.126520681265207e-05, "loss": 0.8503, "step": 601 }, { "epoch": 1.316566429743029, "grad_norm": 1.4446251392364502, "learning_rate": 3.1224655312246556e-05, "loss": 0.9961, "step": 602 }, { "epoch": 1.3187534171678512, "grad_norm": 2.3027143478393555, "learning_rate": 3.118410381184104e-05, "loss": 0.9252, "step": 603 }, { "epoch": 1.3209404045926736, "grad_norm": 1.3223471641540527, "learning_rate": 3.114355231143552e-05, "loss": 1.1308, "step": 604 }, { "epoch": 1.323127392017496, "grad_norm": 2.32096791267395, "learning_rate": 3.110300081103001e-05, "loss": 1.0364, "step": 605 }, { "epoch": 1.3253143794423181, "grad_norm": 2.836334466934204, "learning_rate": 3.1062449310624495e-05, "loss": 1.1977, "step": 606 }, { "epoch": 1.3275013668671405, "grad_norm": 2.377372980117798, "learning_rate": 3.102189781021898e-05, "loss": 0.982, "step": 607 }, { "epoch": 1.3296883542919629, "grad_norm": 1.2869899272918701, "learning_rate": 3.098134630981346e-05, "loss": 1.1418, "step": 608 }, { "epoch": 1.3318753417167852, "grad_norm": 1.4724993705749512, "learning_rate": 3.0940794809407944e-05, "loss": 1.1055, "step": 609 }, { "epoch": 1.3340623291416074, "grad_norm": 1.1791735887527466, "learning_rate": 3.0900243309002434e-05, "loss": 0.9177, "step": 610 }, { "epoch": 1.3362493165664298, "grad_norm": 1.0309617519378662, "learning_rate": 3.085969180859692e-05, "loss": 0.9292, "step": 611 }, { "epoch": 1.3384363039912521, "grad_norm": 3.586951732635498, "learning_rate": 3.08191403081914e-05, "loss": 1.1589, "step": 612 }, { "epoch": 1.3406232914160743, "grad_norm": 0.8787151575088501, "learning_rate": 3.077858880778589e-05, "loss": 0.8539, "step": 613 }, { "epoch": 1.3428102788408967, "grad_norm": 1.0108096599578857, "learning_rate": 3.073803730738037e-05, "loss": 0.741, "step": 614 }, { "epoch": 1.344997266265719, "grad_norm": 1.537246823310852, "learning_rate": 3.0697485806974856e-05, "loss": 1.1815, "step": 615 }, { "epoch": 1.3471842536905414, "grad_norm": 1.5666526556015015, "learning_rate": 3.0656934306569346e-05, "loss": 0.9683, "step": 616 }, { "epoch": 1.3493712411153636, "grad_norm": 1.2946183681488037, "learning_rate": 3.061638280616383e-05, "loss": 0.9653, "step": 617 }, { "epoch": 1.351558228540186, "grad_norm": 1.1476538181304932, "learning_rate": 3.057583130575831e-05, "loss": 1.0276, "step": 618 }, { "epoch": 1.353745215965008, "grad_norm": 2.401901960372925, "learning_rate": 3.05352798053528e-05, "loss": 1.2042, "step": 619 }, { "epoch": 1.3559322033898304, "grad_norm": 2.0693418979644775, "learning_rate": 3.0494728304947285e-05, "loss": 1.058, "step": 620 }, { "epoch": 1.3581191908146528, "grad_norm": 2.1389665603637695, "learning_rate": 3.0454176804541768e-05, "loss": 1.0841, "step": 621 }, { "epoch": 1.3603061782394752, "grad_norm": 1.558362603187561, "learning_rate": 3.0413625304136255e-05, "loss": 1.2297, "step": 622 }, { "epoch": 1.3624931656642976, "grad_norm": 1.8200467824935913, "learning_rate": 3.037307380373074e-05, "loss": 1.0717, "step": 623 }, { "epoch": 1.3646801530891197, "grad_norm": 1.1881017684936523, "learning_rate": 3.0332522303325224e-05, "loss": 0.8706, "step": 624 }, { "epoch": 1.366867140513942, "grad_norm": 1.432917594909668, "learning_rate": 3.029197080291971e-05, "loss": 0.8339, "step": 625 }, { "epoch": 1.3690541279387642, "grad_norm": 1.1706491708755493, "learning_rate": 3.0251419302514194e-05, "loss": 1.0724, "step": 626 }, { "epoch": 1.3712411153635866, "grad_norm": 1.6585934162139893, "learning_rate": 3.0210867802108677e-05, "loss": 0.9033, "step": 627 }, { "epoch": 1.373428102788409, "grad_norm": 1.4109675884246826, "learning_rate": 3.0170316301703166e-05, "loss": 0.9815, "step": 628 }, { "epoch": 1.3756150902132314, "grad_norm": 1.4569016695022583, "learning_rate": 3.012976480129765e-05, "loss": 1.2483, "step": 629 }, { "epoch": 1.3778020776380535, "grad_norm": 2.193230390548706, "learning_rate": 3.0089213300892133e-05, "loss": 1.2065, "step": 630 }, { "epoch": 1.3799890650628759, "grad_norm": 1.0881385803222656, "learning_rate": 3.0048661800486622e-05, "loss": 0.925, "step": 631 }, { "epoch": 1.3821760524876983, "grad_norm": 1.5361953973770142, "learning_rate": 3.0008110300081106e-05, "loss": 0.9586, "step": 632 }, { "epoch": 1.3843630399125204, "grad_norm": 1.9613838195800781, "learning_rate": 2.996755879967559e-05, "loss": 1.2107, "step": 633 }, { "epoch": 1.3865500273373428, "grad_norm": 1.4123404026031494, "learning_rate": 2.992700729927008e-05, "loss": 0.9714, "step": 634 }, { "epoch": 1.3887370147621652, "grad_norm": 1.138398289680481, "learning_rate": 2.988645579886456e-05, "loss": 0.9764, "step": 635 }, { "epoch": 1.3909240021869875, "grad_norm": 1.1524354219436646, "learning_rate": 2.9845904298459045e-05, "loss": 0.9283, "step": 636 }, { "epoch": 1.3931109896118097, "grad_norm": 1.398655652999878, "learning_rate": 2.980535279805353e-05, "loss": 0.8712, "step": 637 }, { "epoch": 1.395297977036632, "grad_norm": 1.5040078163146973, "learning_rate": 2.9764801297648014e-05, "loss": 1.4732, "step": 638 }, { "epoch": 1.3974849644614544, "grad_norm": 1.506087303161621, "learning_rate": 2.9724249797242497e-05, "loss": 1.1228, "step": 639 }, { "epoch": 1.3996719518862766, "grad_norm": 1.5314371585845947, "learning_rate": 2.9683698296836987e-05, "loss": 0.956, "step": 640 }, { "epoch": 1.401858939311099, "grad_norm": 1.2406127452850342, "learning_rate": 2.964314679643147e-05, "loss": 0.8794, "step": 641 }, { "epoch": 1.4040459267359213, "grad_norm": 0.9923226237297058, "learning_rate": 2.9602595296025953e-05, "loss": 0.8008, "step": 642 }, { "epoch": 1.4062329141607437, "grad_norm": 2.000128984451294, "learning_rate": 2.9562043795620443e-05, "loss": 0.8063, "step": 643 }, { "epoch": 1.4084199015855658, "grad_norm": 1.7870972156524658, "learning_rate": 2.9521492295214926e-05, "loss": 1.2203, "step": 644 }, { "epoch": 1.4106068890103882, "grad_norm": 1.70360267162323, "learning_rate": 2.948094079480941e-05, "loss": 1.2187, "step": 645 }, { "epoch": 1.4127938764352104, "grad_norm": 1.8835248947143555, "learning_rate": 2.9440389294403892e-05, "loss": 1.0928, "step": 646 }, { "epoch": 1.4149808638600327, "grad_norm": 1.6198487281799316, "learning_rate": 2.9399837793998382e-05, "loss": 1.0198, "step": 647 }, { "epoch": 1.4171678512848551, "grad_norm": 1.4094990491867065, "learning_rate": 2.9359286293592865e-05, "loss": 1.0278, "step": 648 }, { "epoch": 1.4193548387096775, "grad_norm": 2.5848069190979004, "learning_rate": 2.9318734793187348e-05, "loss": 1.1004, "step": 649 }, { "epoch": 1.4215418261344999, "grad_norm": 1.273293375968933, "learning_rate": 2.9278183292781835e-05, "loss": 0.8184, "step": 650 }, { "epoch": 1.423728813559322, "grad_norm": 1.3217560052871704, "learning_rate": 2.9237631792376318e-05, "loss": 1.008, "step": 651 }, { "epoch": 1.4259158009841444, "grad_norm": 2.2982676029205322, "learning_rate": 2.91970802919708e-05, "loss": 0.867, "step": 652 }, { "epoch": 1.4281027884089665, "grad_norm": 1.3366150856018066, "learning_rate": 2.915652879156529e-05, "loss": 1.0597, "step": 653 }, { "epoch": 1.430289775833789, "grad_norm": 0.8784253597259521, "learning_rate": 2.9115977291159774e-05, "loss": 0.8437, "step": 654 }, { "epoch": 1.4324767632586113, "grad_norm": 1.3183534145355225, "learning_rate": 2.9075425790754257e-05, "loss": 1.1867, "step": 655 }, { "epoch": 1.4346637506834337, "grad_norm": 1.8120551109313965, "learning_rate": 2.9034874290348746e-05, "loss": 1.0222, "step": 656 }, { "epoch": 1.4368507381082558, "grad_norm": 1.65785551071167, "learning_rate": 2.899432278994323e-05, "loss": 1.0388, "step": 657 }, { "epoch": 1.4390377255330782, "grad_norm": 1.673722743988037, "learning_rate": 2.8953771289537713e-05, "loss": 1.0477, "step": 658 }, { "epoch": 1.4412247129579006, "grad_norm": 1.6851401329040527, "learning_rate": 2.8913219789132202e-05, "loss": 0.9866, "step": 659 }, { "epoch": 1.4434117003827227, "grad_norm": 2.072787284851074, "learning_rate": 2.8872668288726686e-05, "loss": 0.8207, "step": 660 }, { "epoch": 1.445598687807545, "grad_norm": 1.2528955936431885, "learning_rate": 2.883211678832117e-05, "loss": 1.3393, "step": 661 }, { "epoch": 1.4477856752323675, "grad_norm": 1.7180964946746826, "learning_rate": 2.8791565287915655e-05, "loss": 1.2499, "step": 662 }, { "epoch": 1.4499726626571898, "grad_norm": 2.269991397857666, "learning_rate": 2.8751013787510138e-05, "loss": 1.2149, "step": 663 }, { "epoch": 1.452159650082012, "grad_norm": 2.061849355697632, "learning_rate": 2.871046228710462e-05, "loss": 1.18, "step": 664 }, { "epoch": 1.4543466375068343, "grad_norm": 2.452923059463501, "learning_rate": 2.866991078669911e-05, "loss": 0.9989, "step": 665 }, { "epoch": 1.4565336249316567, "grad_norm": 1.051559329032898, "learning_rate": 2.8629359286293594e-05, "loss": 1.2044, "step": 666 }, { "epoch": 1.4587206123564789, "grad_norm": 1.7850217819213867, "learning_rate": 2.8588807785888077e-05, "loss": 0.9434, "step": 667 }, { "epoch": 1.4609075997813012, "grad_norm": 1.943331003189087, "learning_rate": 2.8548256285482567e-05, "loss": 1.1368, "step": 668 }, { "epoch": 1.4630945872061236, "grad_norm": 1.3304661512374878, "learning_rate": 2.850770478507705e-05, "loss": 1.0816, "step": 669 }, { "epoch": 1.465281574630946, "grad_norm": 1.3743139505386353, "learning_rate": 2.8467153284671533e-05, "loss": 0.9027, "step": 670 }, { "epoch": 1.4674685620557681, "grad_norm": 2.1829004287719727, "learning_rate": 2.8426601784266023e-05, "loss": 0.9777, "step": 671 }, { "epoch": 1.4696555494805905, "grad_norm": 1.3668421506881714, "learning_rate": 2.8386050283860506e-05, "loss": 0.8622, "step": 672 }, { "epoch": 1.4718425369054127, "grad_norm": 1.907059907913208, "learning_rate": 2.834549878345499e-05, "loss": 1.1825, "step": 673 }, { "epoch": 1.474029524330235, "grad_norm": 1.3839157819747925, "learning_rate": 2.8304947283049476e-05, "loss": 1.1329, "step": 674 }, { "epoch": 1.4762165117550574, "grad_norm": 1.3117161989212036, "learning_rate": 2.826439578264396e-05, "loss": 0.9857, "step": 675 }, { "epoch": 1.4784034991798798, "grad_norm": 2.148076057434082, "learning_rate": 2.822384428223844e-05, "loss": 0.892, "step": 676 }, { "epoch": 1.4805904866047022, "grad_norm": 1.5976066589355469, "learning_rate": 2.818329278183293e-05, "loss": 1.0201, "step": 677 }, { "epoch": 1.4827774740295243, "grad_norm": 1.4692186117172241, "learning_rate": 2.8142741281427415e-05, "loss": 1.289, "step": 678 }, { "epoch": 1.4849644614543467, "grad_norm": 2.480440378189087, "learning_rate": 2.8102189781021898e-05, "loss": 0.9768, "step": 679 }, { "epoch": 1.4871514488791688, "grad_norm": 1.2911291122436523, "learning_rate": 2.8061638280616387e-05, "loss": 1.3338, "step": 680 }, { "epoch": 1.4893384363039912, "grad_norm": 2.5851263999938965, "learning_rate": 2.802108678021087e-05, "loss": 1.0846, "step": 681 }, { "epoch": 1.4915254237288136, "grad_norm": 2.4977951049804688, "learning_rate": 2.7980535279805354e-05, "loss": 1.1304, "step": 682 }, { "epoch": 1.493712411153636, "grad_norm": 1.0844966173171997, "learning_rate": 2.7939983779399837e-05, "loss": 0.8811, "step": 683 }, { "epoch": 1.495899398578458, "grad_norm": 1.3038057088851929, "learning_rate": 2.7899432278994327e-05, "loss": 1.008, "step": 684 }, { "epoch": 1.4980863860032805, "grad_norm": 1.231572151184082, "learning_rate": 2.785888077858881e-05, "loss": 1.0405, "step": 685 }, { "epoch": 1.5002733734281026, "grad_norm": 1.8893858194351196, "learning_rate": 2.7818329278183293e-05, "loss": 0.8445, "step": 686 }, { "epoch": 1.502460360852925, "grad_norm": 2.9871528148651123, "learning_rate": 2.777777777777778e-05, "loss": 1.1411, "step": 687 }, { "epoch": 1.5046473482777474, "grad_norm": 1.4981170892715454, "learning_rate": 2.7737226277372262e-05, "loss": 0.7994, "step": 688 }, { "epoch": 1.5068343357025697, "grad_norm": 1.1372278928756714, "learning_rate": 2.7696674776966745e-05, "loss": 1.0542, "step": 689 }, { "epoch": 1.5090213231273921, "grad_norm": 1.5029011964797974, "learning_rate": 2.7656123276561235e-05, "loss": 1.0299, "step": 690 }, { "epoch": 1.5112083105522143, "grad_norm": 1.5507975816726685, "learning_rate": 2.7615571776155718e-05, "loss": 1.2328, "step": 691 }, { "epoch": 1.5133952979770366, "grad_norm": 1.1695964336395264, "learning_rate": 2.75750202757502e-05, "loss": 1.2093, "step": 692 }, { "epoch": 1.5155822854018588, "grad_norm": 7.262062072753906, "learning_rate": 2.753446877534469e-05, "loss": 1.0667, "step": 693 }, { "epoch": 1.5177692728266812, "grad_norm": 1.4902487993240356, "learning_rate": 2.7493917274939174e-05, "loss": 0.9025, "step": 694 }, { "epoch": 1.5199562602515035, "grad_norm": 1.2173442840576172, "learning_rate": 2.7453365774533657e-05, "loss": 0.8652, "step": 695 }, { "epoch": 1.522143247676326, "grad_norm": 2.2417051792144775, "learning_rate": 2.7412814274128147e-05, "loss": 1.0323, "step": 696 }, { "epoch": 1.5243302351011483, "grad_norm": 2.1615347862243652, "learning_rate": 2.737226277372263e-05, "loss": 0.9234, "step": 697 }, { "epoch": 1.5265172225259704, "grad_norm": 1.1185311079025269, "learning_rate": 2.7331711273317113e-05, "loss": 0.9157, "step": 698 }, { "epoch": 1.5287042099507928, "grad_norm": 2.249903917312622, "learning_rate": 2.72911597729116e-05, "loss": 0.9194, "step": 699 }, { "epoch": 1.530891197375615, "grad_norm": 1.0687757730484009, "learning_rate": 2.7250608272506083e-05, "loss": 0.9406, "step": 700 }, { "epoch": 1.5330781848004373, "grad_norm": 2.2132675647735596, "learning_rate": 2.7210056772100566e-05, "loss": 0.9717, "step": 701 }, { "epoch": 1.5352651722252597, "grad_norm": 1.3518428802490234, "learning_rate": 2.7169505271695056e-05, "loss": 0.9794, "step": 702 }, { "epoch": 1.537452159650082, "grad_norm": 0.8067867755889893, "learning_rate": 2.712895377128954e-05, "loss": 1.1401, "step": 703 }, { "epoch": 1.5396391470749045, "grad_norm": 1.5813891887664795, "learning_rate": 2.7088402270884022e-05, "loss": 1.1176, "step": 704 }, { "epoch": 1.5418261344997266, "grad_norm": 1.6611734628677368, "learning_rate": 2.704785077047851e-05, "loss": 1.083, "step": 705 }, { "epoch": 1.544013121924549, "grad_norm": 2.5548391342163086, "learning_rate": 2.7007299270072995e-05, "loss": 1.0792, "step": 706 }, { "epoch": 1.5462001093493711, "grad_norm": 1.6398601531982422, "learning_rate": 2.6966747769667478e-05, "loss": 1.1997, "step": 707 }, { "epoch": 1.5483870967741935, "grad_norm": 1.5494269132614136, "learning_rate": 2.6926196269261968e-05, "loss": 1.1691, "step": 708 }, { "epoch": 1.5505740841990159, "grad_norm": 1.4408408403396606, "learning_rate": 2.688564476885645e-05, "loss": 0.966, "step": 709 }, { "epoch": 1.5527610716238383, "grad_norm": 2.183953046798706, "learning_rate": 2.6845093268450934e-05, "loss": 1.1748, "step": 710 }, { "epoch": 1.5549480590486606, "grad_norm": 1.2972882986068726, "learning_rate": 2.680454176804542e-05, "loss": 0.8089, "step": 711 }, { "epoch": 1.5571350464734828, "grad_norm": 1.4603959321975708, "learning_rate": 2.6763990267639903e-05, "loss": 1.3402, "step": 712 }, { "epoch": 1.559322033898305, "grad_norm": 1.3804490566253662, "learning_rate": 2.6723438767234386e-05, "loss": 1.2731, "step": 713 }, { "epoch": 1.5615090213231273, "grad_norm": 1.2469534873962402, "learning_rate": 2.6682887266828876e-05, "loss": 1.045, "step": 714 }, { "epoch": 1.5636960087479497, "grad_norm": 1.3326971530914307, "learning_rate": 2.664233576642336e-05, "loss": 0.9844, "step": 715 }, { "epoch": 1.565882996172772, "grad_norm": 1.5639369487762451, "learning_rate": 2.6601784266017842e-05, "loss": 0.8168, "step": 716 }, { "epoch": 1.5680699835975944, "grad_norm": 1.3720163106918335, "learning_rate": 2.6561232765612332e-05, "loss": 1.1259, "step": 717 }, { "epoch": 1.5702569710224166, "grad_norm": 1.7701537609100342, "learning_rate": 2.6520681265206815e-05, "loss": 1.1222, "step": 718 }, { "epoch": 1.572443958447239, "grad_norm": 1.9116886854171753, "learning_rate": 2.6480129764801298e-05, "loss": 0.7639, "step": 719 }, { "epoch": 1.574630945872061, "grad_norm": 0.928368091583252, "learning_rate": 2.643957826439578e-05, "loss": 0.8649, "step": 720 }, { "epoch": 1.5768179332968835, "grad_norm": 1.6091198921203613, "learning_rate": 2.639902676399027e-05, "loss": 1.2211, "step": 721 }, { "epoch": 1.5790049207217058, "grad_norm": 1.6006994247436523, "learning_rate": 2.6358475263584754e-05, "loss": 1.0736, "step": 722 }, { "epoch": 1.5811919081465282, "grad_norm": 1.5489883422851562, "learning_rate": 2.6317923763179237e-05, "loss": 0.8836, "step": 723 }, { "epoch": 1.5833788955713506, "grad_norm": 1.6098401546478271, "learning_rate": 2.6277372262773724e-05, "loss": 0.7434, "step": 724 }, { "epoch": 1.5855658829961727, "grad_norm": 1.6521259546279907, "learning_rate": 2.6236820762368207e-05, "loss": 0.8984, "step": 725 }, { "epoch": 1.587752870420995, "grad_norm": 1.122748613357544, "learning_rate": 2.6196269261962693e-05, "loss": 0.8208, "step": 726 }, { "epoch": 1.5899398578458173, "grad_norm": 1.3627665042877197, "learning_rate": 2.615571776155718e-05, "loss": 1.1196, "step": 727 }, { "epoch": 1.5921268452706396, "grad_norm": 1.3348376750946045, "learning_rate": 2.6115166261151663e-05, "loss": 0.9828, "step": 728 }, { "epoch": 1.594313832695462, "grad_norm": 2.115302562713623, "learning_rate": 2.6074614760746146e-05, "loss": 1.0438, "step": 729 }, { "epoch": 1.5965008201202844, "grad_norm": 2.215904951095581, "learning_rate": 2.6034063260340636e-05, "loss": 1.0855, "step": 730 }, { "epoch": 1.5986878075451068, "grad_norm": 1.733070731163025, "learning_rate": 2.599351175993512e-05, "loss": 0.8409, "step": 731 }, { "epoch": 1.600874794969929, "grad_norm": 1.7204647064208984, "learning_rate": 2.5952960259529602e-05, "loss": 1.1559, "step": 732 }, { "epoch": 1.6030617823947513, "grad_norm": 1.0793389081954956, "learning_rate": 2.591240875912409e-05, "loss": 0.9284, "step": 733 }, { "epoch": 1.6052487698195734, "grad_norm": 2.024123191833496, "learning_rate": 2.5871857258718575e-05, "loss": 1.0087, "step": 734 }, { "epoch": 1.6074357572443958, "grad_norm": 1.4198509454727173, "learning_rate": 2.5831305758313058e-05, "loss": 1.0506, "step": 735 }, { "epoch": 1.6096227446692182, "grad_norm": 1.2509183883666992, "learning_rate": 2.5790754257907544e-05, "loss": 1.1083, "step": 736 }, { "epoch": 1.6118097320940405, "grad_norm": 1.1314994096755981, "learning_rate": 2.5750202757502027e-05, "loss": 0.8719, "step": 737 }, { "epoch": 1.613996719518863, "grad_norm": 2.187678575515747, "learning_rate": 2.5709651257096514e-05, "loss": 1.1858, "step": 738 }, { "epoch": 1.616183706943685, "grad_norm": 1.3705053329467773, "learning_rate": 2.5669099756691e-05, "loss": 0.7971, "step": 739 }, { "epoch": 1.6183706943685072, "grad_norm": 2.6198980808258057, "learning_rate": 2.5628548256285483e-05, "loss": 1.2901, "step": 740 }, { "epoch": 1.6205576817933296, "grad_norm": 1.5001429319381714, "learning_rate": 2.5587996755879966e-05, "loss": 0.9336, "step": 741 }, { "epoch": 1.622744669218152, "grad_norm": 2.3261349201202393, "learning_rate": 2.5547445255474456e-05, "loss": 0.9465, "step": 742 }, { "epoch": 1.6249316566429743, "grad_norm": 2.5625455379486084, "learning_rate": 2.550689375506894e-05, "loss": 0.9256, "step": 743 }, { "epoch": 1.6271186440677967, "grad_norm": 1.4571309089660645, "learning_rate": 2.5466342254663422e-05, "loss": 1.1126, "step": 744 }, { "epoch": 1.6293056314926189, "grad_norm": 2.930521249771118, "learning_rate": 2.5425790754257912e-05, "loss": 0.9215, "step": 745 }, { "epoch": 1.6314926189174412, "grad_norm": 1.474174976348877, "learning_rate": 2.5385239253852395e-05, "loss": 1.0157, "step": 746 }, { "epoch": 1.6336796063422634, "grad_norm": 2.1626808643341064, "learning_rate": 2.5344687753446878e-05, "loss": 0.8858, "step": 747 }, { "epoch": 1.6358665937670858, "grad_norm": 1.4376909732818604, "learning_rate": 2.5304136253041365e-05, "loss": 1.0191, "step": 748 }, { "epoch": 1.6380535811919081, "grad_norm": 1.2904880046844482, "learning_rate": 2.5263584752635848e-05, "loss": 1.1488, "step": 749 }, { "epoch": 1.6402405686167305, "grad_norm": 1.280037760734558, "learning_rate": 2.5223033252230334e-05, "loss": 0.9103, "step": 750 }, { "epoch": 1.6424275560415529, "grad_norm": 1.4530301094055176, "learning_rate": 2.518248175182482e-05, "loss": 0.7187, "step": 751 }, { "epoch": 1.644614543466375, "grad_norm": 1.4060955047607422, "learning_rate": 2.5141930251419304e-05, "loss": 1.0062, "step": 752 }, { "epoch": 1.6468015308911974, "grad_norm": 3.3684253692626953, "learning_rate": 2.5101378751013787e-05, "loss": 1.1838, "step": 753 }, { "epoch": 1.6489885183160196, "grad_norm": 1.287484884262085, "learning_rate": 2.5060827250608277e-05, "loss": 1.199, "step": 754 }, { "epoch": 1.651175505740842, "grad_norm": 0.9964923858642578, "learning_rate": 2.502027575020276e-05, "loss": 0.653, "step": 755 }, { "epoch": 1.6533624931656643, "grad_norm": 1.7606700658798218, "learning_rate": 2.4979724249797243e-05, "loss": 1.0243, "step": 756 }, { "epoch": 1.6555494805904867, "grad_norm": 1.8851219415664673, "learning_rate": 2.493917274939173e-05, "loss": 1.3369, "step": 757 }, { "epoch": 1.657736468015309, "grad_norm": 1.83774995803833, "learning_rate": 2.4898621248986216e-05, "loss": 0.8459, "step": 758 }, { "epoch": 1.6599234554401312, "grad_norm": 1.8637070655822754, "learning_rate": 2.48580697485807e-05, "loss": 1.0093, "step": 759 }, { "epoch": 1.6621104428649536, "grad_norm": 1.423207402229309, "learning_rate": 2.4817518248175185e-05, "loss": 0.986, "step": 760 }, { "epoch": 1.6642974302897757, "grad_norm": 1.5694395303726196, "learning_rate": 2.4776966747769668e-05, "loss": 1.1363, "step": 761 }, { "epoch": 1.666484417714598, "grad_norm": 1.8063995838165283, "learning_rate": 2.4736415247364155e-05, "loss": 0.8102, "step": 762 }, { "epoch": 1.6686714051394205, "grad_norm": 0.9730278849601746, "learning_rate": 2.4695863746958638e-05, "loss": 0.8516, "step": 763 }, { "epoch": 1.6708583925642428, "grad_norm": 0.9870968461036682, "learning_rate": 2.4655312246553124e-05, "loss": 1.1244, "step": 764 }, { "epoch": 1.6730453799890652, "grad_norm": 2.259260416030884, "learning_rate": 2.4614760746147607e-05, "loss": 0.9847, "step": 765 }, { "epoch": 1.6752323674138874, "grad_norm": 1.3961234092712402, "learning_rate": 2.4574209245742094e-05, "loss": 0.9775, "step": 766 }, { "epoch": 1.6774193548387095, "grad_norm": 1.094936728477478, "learning_rate": 2.4533657745336577e-05, "loss": 1.1428, "step": 767 }, { "epoch": 1.679606342263532, "grad_norm": 1.04390549659729, "learning_rate": 2.4493106244931063e-05, "loss": 0.913, "step": 768 }, { "epoch": 1.6817933296883543, "grad_norm": 1.51487135887146, "learning_rate": 2.445255474452555e-05, "loss": 1.0312, "step": 769 }, { "epoch": 1.6839803171131766, "grad_norm": 1.662974238395691, "learning_rate": 2.4412003244120033e-05, "loss": 1.148, "step": 770 }, { "epoch": 1.686167304537999, "grad_norm": 1.265647292137146, "learning_rate": 2.437145174371452e-05, "loss": 0.877, "step": 771 }, { "epoch": 1.6883542919628212, "grad_norm": 1.9699134826660156, "learning_rate": 2.4330900243309006e-05, "loss": 0.8821, "step": 772 }, { "epoch": 1.6905412793876435, "grad_norm": 1.4179115295410156, "learning_rate": 2.429034874290349e-05, "loss": 1.0569, "step": 773 }, { "epoch": 1.6927282668124657, "grad_norm": 2.3327324390411377, "learning_rate": 2.4249797242497975e-05, "loss": 0.9898, "step": 774 }, { "epoch": 1.694915254237288, "grad_norm": 1.583465576171875, "learning_rate": 2.4209245742092458e-05, "loss": 1.0361, "step": 775 }, { "epoch": 1.6971022416621104, "grad_norm": 1.5192774534225464, "learning_rate": 2.416869424168694e-05, "loss": 1.0637, "step": 776 }, { "epoch": 1.6992892290869328, "grad_norm": 1.4682255983352661, "learning_rate": 2.4128142741281428e-05, "loss": 1.0632, "step": 777 }, { "epoch": 1.7014762165117552, "grad_norm": 0.9498540163040161, "learning_rate": 2.4087591240875914e-05, "loss": 0.8482, "step": 778 }, { "epoch": 1.7036632039365773, "grad_norm": 1.0649384260177612, "learning_rate": 2.4047039740470397e-05, "loss": 0.9275, "step": 779 }, { "epoch": 1.7058501913613997, "grad_norm": 1.0233219861984253, "learning_rate": 2.4006488240064884e-05, "loss": 0.9512, "step": 780 }, { "epoch": 1.7080371787862219, "grad_norm": 2.3574366569519043, "learning_rate": 2.396593673965937e-05, "loss": 0.9044, "step": 781 }, { "epoch": 1.7102241662110442, "grad_norm": 4.048834323883057, "learning_rate": 2.3925385239253853e-05, "loss": 1.2442, "step": 782 }, { "epoch": 1.7124111536358666, "grad_norm": 1.603959083557129, "learning_rate": 2.388483373884834e-05, "loss": 0.9528, "step": 783 }, { "epoch": 1.714598141060689, "grad_norm": 1.374941349029541, "learning_rate": 2.3844282238442823e-05, "loss": 1.019, "step": 784 }, { "epoch": 1.7167851284855113, "grad_norm": 1.4967550039291382, "learning_rate": 2.380373073803731e-05, "loss": 1.0507, "step": 785 }, { "epoch": 1.7189721159103335, "grad_norm": 1.1086132526397705, "learning_rate": 2.3763179237631796e-05, "loss": 0.7562, "step": 786 }, { "epoch": 1.7211591033351559, "grad_norm": 1.425864577293396, "learning_rate": 2.372262773722628e-05, "loss": 0.7828, "step": 787 }, { "epoch": 1.723346090759978, "grad_norm": 1.1623787879943848, "learning_rate": 2.3682076236820762e-05, "loss": 0.8251, "step": 788 }, { "epoch": 1.7255330781848004, "grad_norm": 1.1072317361831665, "learning_rate": 2.3641524736415248e-05, "loss": 0.9672, "step": 789 }, { "epoch": 1.7277200656096228, "grad_norm": 2.197674036026001, "learning_rate": 2.360097323600973e-05, "loss": 1.0413, "step": 790 }, { "epoch": 1.7299070530344451, "grad_norm": 1.4915660619735718, "learning_rate": 2.3560421735604218e-05, "loss": 1.188, "step": 791 }, { "epoch": 1.7320940404592675, "grad_norm": 1.2871671915054321, "learning_rate": 2.3519870235198704e-05, "loss": 1.0008, "step": 792 }, { "epoch": 1.7342810278840897, "grad_norm": 1.9435328245162964, "learning_rate": 2.3479318734793187e-05, "loss": 1.0002, "step": 793 }, { "epoch": 1.7364680153089118, "grad_norm": 1.1067068576812744, "learning_rate": 2.3438767234387674e-05, "loss": 0.8178, "step": 794 }, { "epoch": 1.7386550027337342, "grad_norm": 1.9979357719421387, "learning_rate": 2.339821573398216e-05, "loss": 0.9118, "step": 795 }, { "epoch": 1.7408419901585566, "grad_norm": 1.9968189001083374, "learning_rate": 2.3357664233576643e-05, "loss": 0.8991, "step": 796 }, { "epoch": 1.743028977583379, "grad_norm": 1.732962965965271, "learning_rate": 2.331711273317113e-05, "loss": 0.9437, "step": 797 }, { "epoch": 1.7452159650082013, "grad_norm": 1.5777456760406494, "learning_rate": 2.3276561232765616e-05, "loss": 0.9717, "step": 798 }, { "epoch": 1.7474029524330235, "grad_norm": 1.3690989017486572, "learning_rate": 2.32360097323601e-05, "loss": 0.9075, "step": 799 }, { "epoch": 1.7495899398578458, "grad_norm": 1.5229700803756714, "learning_rate": 2.3195458231954582e-05, "loss": 0.869, "step": 800 }, { "epoch": 1.751776927282668, "grad_norm": 1.0158123970031738, "learning_rate": 2.315490673154907e-05, "loss": 0.8839, "step": 801 }, { "epoch": 1.7539639147074904, "grad_norm": 1.9029816389083862, "learning_rate": 2.3114355231143552e-05, "loss": 0.9033, "step": 802 }, { "epoch": 1.7561509021323127, "grad_norm": 1.474724292755127, "learning_rate": 2.3073803730738038e-05, "loss": 1.1682, "step": 803 }, { "epoch": 1.758337889557135, "grad_norm": 1.9852144718170166, "learning_rate": 2.303325223033252e-05, "loss": 1.2983, "step": 804 }, { "epoch": 1.7605248769819575, "grad_norm": 0.9804924130439758, "learning_rate": 2.2992700729927008e-05, "loss": 0.817, "step": 805 }, { "epoch": 1.7627118644067796, "grad_norm": 1.9569218158721924, "learning_rate": 2.2952149229521494e-05, "loss": 1.0604, "step": 806 }, { "epoch": 1.764898851831602, "grad_norm": 0.8989382982254028, "learning_rate": 2.2911597729115977e-05, "loss": 1.0338, "step": 807 }, { "epoch": 1.7670858392564242, "grad_norm": 1.5806984901428223, "learning_rate": 2.2871046228710464e-05, "loss": 0.9029, "step": 808 }, { "epoch": 1.7692728266812465, "grad_norm": 1.5797624588012695, "learning_rate": 2.283049472830495e-05, "loss": 0.9942, "step": 809 }, { "epoch": 1.771459814106069, "grad_norm": 1.3938391208648682, "learning_rate": 2.2789943227899433e-05, "loss": 0.9615, "step": 810 }, { "epoch": 1.7736468015308913, "grad_norm": 1.284523606300354, "learning_rate": 2.274939172749392e-05, "loss": 0.8762, "step": 811 }, { "epoch": 1.7758337889557136, "grad_norm": 1.241369366645813, "learning_rate": 2.2708840227088403e-05, "loss": 0.8068, "step": 812 }, { "epoch": 1.7780207763805358, "grad_norm": 1.082217812538147, "learning_rate": 2.2668288726682886e-05, "loss": 1.3574, "step": 813 }, { "epoch": 1.7802077638053582, "grad_norm": 1.6762464046478271, "learning_rate": 2.2627737226277372e-05, "loss": 0.8791, "step": 814 }, { "epoch": 1.7823947512301803, "grad_norm": 2.3479504585266113, "learning_rate": 2.258718572587186e-05, "loss": 0.967, "step": 815 }, { "epoch": 1.7845817386550027, "grad_norm": 1.546452283859253, "learning_rate": 2.2546634225466342e-05, "loss": 0.9049, "step": 816 }, { "epoch": 1.786768726079825, "grad_norm": 1.138462781906128, "learning_rate": 2.2506082725060828e-05, "loss": 0.8842, "step": 817 }, { "epoch": 1.7889557135046474, "grad_norm": 1.8350077867507935, "learning_rate": 2.2465531224655315e-05, "loss": 1.0419, "step": 818 }, { "epoch": 1.7911427009294698, "grad_norm": 2.041625499725342, "learning_rate": 2.2424979724249798e-05, "loss": 0.8179, "step": 819 }, { "epoch": 1.793329688354292, "grad_norm": 1.4574394226074219, "learning_rate": 2.2384428223844284e-05, "loss": 0.9016, "step": 820 }, { "epoch": 1.7955166757791141, "grad_norm": 1.613033413887024, "learning_rate": 2.2343876723438767e-05, "loss": 1.2726, "step": 821 }, { "epoch": 1.7977036632039365, "grad_norm": 1.770085096359253, "learning_rate": 2.2303325223033254e-05, "loss": 0.9036, "step": 822 }, { "epoch": 1.7998906506287589, "grad_norm": 1.4616780281066895, "learning_rate": 2.226277372262774e-05, "loss": 0.9773, "step": 823 }, { "epoch": 1.8020776380535812, "grad_norm": 1.5661598443984985, "learning_rate": 2.2222222222222223e-05, "loss": 1.1106, "step": 824 }, { "epoch": 1.8042646254784036, "grad_norm": 1.9936821460723877, "learning_rate": 2.2181670721816706e-05, "loss": 1.2189, "step": 825 }, { "epoch": 1.8064516129032258, "grad_norm": 1.940483570098877, "learning_rate": 2.2141119221411193e-05, "loss": 1.0471, "step": 826 }, { "epoch": 1.8086386003280481, "grad_norm": 2.320462942123413, "learning_rate": 2.2100567721005676e-05, "loss": 1.0636, "step": 827 }, { "epoch": 1.8108255877528703, "grad_norm": 1.2037211656570435, "learning_rate": 2.2060016220600162e-05, "loss": 0.8499, "step": 828 }, { "epoch": 1.8130125751776927, "grad_norm": 1.7456927299499512, "learning_rate": 2.201946472019465e-05, "loss": 1.0144, "step": 829 }, { "epoch": 1.815199562602515, "grad_norm": 1.0314974784851074, "learning_rate": 2.1978913219789132e-05, "loss": 0.9426, "step": 830 }, { "epoch": 1.8173865500273374, "grad_norm": 0.8701378703117371, "learning_rate": 2.1938361719383618e-05, "loss": 0.9365, "step": 831 }, { "epoch": 1.8195735374521598, "grad_norm": 2.2479121685028076, "learning_rate": 2.1897810218978105e-05, "loss": 1.082, "step": 832 }, { "epoch": 1.821760524876982, "grad_norm": 0.9647157788276672, "learning_rate": 2.1857258718572588e-05, "loss": 1.19, "step": 833 }, { "epoch": 1.8239475123018043, "grad_norm": 2.129983901977539, "learning_rate": 2.1816707218167074e-05, "loss": 1.0198, "step": 834 }, { "epoch": 1.8261344997266264, "grad_norm": 1.5526658296585083, "learning_rate": 2.177615571776156e-05, "loss": 1.0163, "step": 835 }, { "epoch": 1.8283214871514488, "grad_norm": 1.0336556434631348, "learning_rate": 2.1735604217356044e-05, "loss": 0.8404, "step": 836 }, { "epoch": 1.8305084745762712, "grad_norm": 2.317970037460327, "learning_rate": 2.169505271695053e-05, "loss": 0.9402, "step": 837 }, { "epoch": 1.8326954620010936, "grad_norm": 1.1321872472763062, "learning_rate": 2.1654501216545013e-05, "loss": 1.2147, "step": 838 }, { "epoch": 1.834882449425916, "grad_norm": 1.1826746463775635, "learning_rate": 2.1613949716139496e-05, "loss": 0.9039, "step": 839 }, { "epoch": 1.837069436850738, "grad_norm": 1.134161114692688, "learning_rate": 2.1573398215733983e-05, "loss": 0.8439, "step": 840 }, { "epoch": 1.8392564242755605, "grad_norm": 1.013657808303833, "learning_rate": 2.1532846715328466e-05, "loss": 1.0156, "step": 841 }, { "epoch": 1.8414434117003826, "grad_norm": 1.327208161354065, "learning_rate": 2.1492295214922952e-05, "loss": 0.8417, "step": 842 }, { "epoch": 1.843630399125205, "grad_norm": 1.5910999774932861, "learning_rate": 2.145174371451744e-05, "loss": 1.1879, "step": 843 }, { "epoch": 1.8458173865500274, "grad_norm": 1.2069684267044067, "learning_rate": 2.1411192214111922e-05, "loss": 0.7589, "step": 844 }, { "epoch": 1.8480043739748497, "grad_norm": 1.90011465549469, "learning_rate": 2.137064071370641e-05, "loss": 0.9646, "step": 845 }, { "epoch": 1.850191361399672, "grad_norm": 1.5969653129577637, "learning_rate": 2.1330089213300895e-05, "loss": 1.0267, "step": 846 }, { "epoch": 1.8523783488244943, "grad_norm": 1.925655722618103, "learning_rate": 2.1289537712895378e-05, "loss": 0.7012, "step": 847 }, { "epoch": 1.8545653362493164, "grad_norm": 1.6828029155731201, "learning_rate": 2.1248986212489864e-05, "loss": 0.8636, "step": 848 }, { "epoch": 1.8567523236741388, "grad_norm": 1.3727010488510132, "learning_rate": 2.120843471208435e-05, "loss": 1.0519, "step": 849 }, { "epoch": 1.8589393110989612, "grad_norm": 1.1897894144058228, "learning_rate": 2.1167883211678834e-05, "loss": 0.9292, "step": 850 }, { "epoch": 1.8611262985237835, "grad_norm": 1.7477644681930542, "learning_rate": 2.1127331711273317e-05, "loss": 0.8783, "step": 851 }, { "epoch": 1.863313285948606, "grad_norm": 1.595096230506897, "learning_rate": 2.1086780210867803e-05, "loss": 1.102, "step": 852 }, { "epoch": 1.865500273373428, "grad_norm": 0.9647570252418518, "learning_rate": 2.1046228710462286e-05, "loss": 1.207, "step": 853 }, { "epoch": 1.8676872607982504, "grad_norm": 1.2224453687667847, "learning_rate": 2.1005677210056773e-05, "loss": 1.0061, "step": 854 }, { "epoch": 1.8698742482230726, "grad_norm": 1.883169174194336, "learning_rate": 2.096512570965126e-05, "loss": 1.0825, "step": 855 }, { "epoch": 1.872061235647895, "grad_norm": 1.5861616134643555, "learning_rate": 2.0924574209245742e-05, "loss": 1.0875, "step": 856 }, { "epoch": 1.8742482230727173, "grad_norm": 1.128961443901062, "learning_rate": 2.088402270884023e-05, "loss": 1.0968, "step": 857 }, { "epoch": 1.8764352104975397, "grad_norm": 1.6911673545837402, "learning_rate": 2.0843471208434715e-05, "loss": 1.059, "step": 858 }, { "epoch": 1.878622197922362, "grad_norm": 1.0278905630111694, "learning_rate": 2.08029197080292e-05, "loss": 0.8156, "step": 859 }, { "epoch": 1.8808091853471842, "grad_norm": 1.3379169702529907, "learning_rate": 2.0762368207623685e-05, "loss": 1.2933, "step": 860 }, { "epoch": 1.8829961727720066, "grad_norm": 1.533151626586914, "learning_rate": 2.0721816707218168e-05, "loss": 1.1173, "step": 861 }, { "epoch": 1.8851831601968287, "grad_norm": 2.9706287384033203, "learning_rate": 2.0681265206812654e-05, "loss": 1.1459, "step": 862 }, { "epoch": 1.8873701476216511, "grad_norm": 1.1777406930923462, "learning_rate": 2.0640713706407137e-05, "loss": 0.8772, "step": 863 }, { "epoch": 1.8895571350464735, "grad_norm": 1.2535638809204102, "learning_rate": 2.060016220600162e-05, "loss": 0.9325, "step": 864 }, { "epoch": 1.8917441224712959, "grad_norm": 1.2347840070724487, "learning_rate": 2.0559610705596107e-05, "loss": 0.9299, "step": 865 }, { "epoch": 1.8939311098961182, "grad_norm": 1.0956156253814697, "learning_rate": 2.0519059205190593e-05, "loss": 0.8191, "step": 866 }, { "epoch": 1.8961180973209404, "grad_norm": 1.8971076011657715, "learning_rate": 2.0478507704785076e-05, "loss": 0.9973, "step": 867 }, { "epoch": 1.8983050847457628, "grad_norm": 2.012946128845215, "learning_rate": 2.0437956204379563e-05, "loss": 1.0999, "step": 868 }, { "epoch": 1.900492072170585, "grad_norm": 1.1727793216705322, "learning_rate": 2.039740470397405e-05, "loss": 0.769, "step": 869 }, { "epoch": 1.9026790595954073, "grad_norm": 1.6265904903411865, "learning_rate": 2.0356853203568532e-05, "loss": 1.0168, "step": 870 }, { "epoch": 1.9048660470202297, "grad_norm": 2.4736404418945312, "learning_rate": 2.031630170316302e-05, "loss": 0.9296, "step": 871 }, { "epoch": 1.907053034445052, "grad_norm": 0.8909472227096558, "learning_rate": 2.0275750202757505e-05, "loss": 0.9956, "step": 872 }, { "epoch": 1.9092400218698744, "grad_norm": 1.964398980140686, "learning_rate": 2.023519870235199e-05, "loss": 1.0191, "step": 873 }, { "epoch": 1.9114270092946966, "grad_norm": 1.371237874031067, "learning_rate": 2.0194647201946475e-05, "loss": 1.0132, "step": 874 }, { "epoch": 1.9136139967195187, "grad_norm": 1.0257424116134644, "learning_rate": 2.0154095701540958e-05, "loss": 0.987, "step": 875 }, { "epoch": 1.915800984144341, "grad_norm": 1.6842166185379028, "learning_rate": 2.011354420113544e-05, "loss": 1.0178, "step": 876 }, { "epoch": 1.9179879715691635, "grad_norm": 1.5755685567855835, "learning_rate": 2.0072992700729927e-05, "loss": 1.076, "step": 877 }, { "epoch": 1.9201749589939858, "grad_norm": 1.5296376943588257, "learning_rate": 2.003244120032441e-05, "loss": 0.7937, "step": 878 }, { "epoch": 1.9223619464188082, "grad_norm": 7.159977912902832, "learning_rate": 1.9991889699918897e-05, "loss": 1.2374, "step": 879 }, { "epoch": 1.9245489338436303, "grad_norm": 0.8219045400619507, "learning_rate": 1.9951338199513383e-05, "loss": 1.0018, "step": 880 }, { "epoch": 1.9267359212684527, "grad_norm": 2.7027664184570312, "learning_rate": 1.9910786699107866e-05, "loss": 1.0354, "step": 881 }, { "epoch": 1.9289229086932749, "grad_norm": 1.0640149116516113, "learning_rate": 1.9870235198702353e-05, "loss": 1.0456, "step": 882 }, { "epoch": 1.9311098961180972, "grad_norm": 1.1895917654037476, "learning_rate": 1.982968369829684e-05, "loss": 1.0026, "step": 883 }, { "epoch": 1.9332968835429196, "grad_norm": 3.8359994888305664, "learning_rate": 1.9789132197891322e-05, "loss": 1.0895, "step": 884 }, { "epoch": 1.935483870967742, "grad_norm": 1.7034809589385986, "learning_rate": 1.974858069748581e-05, "loss": 1.001, "step": 885 }, { "epoch": 1.9376708583925644, "grad_norm": 1.8492923974990845, "learning_rate": 1.9708029197080295e-05, "loss": 0.9301, "step": 886 }, { "epoch": 1.9398578458173865, "grad_norm": 1.7066060304641724, "learning_rate": 1.966747769667478e-05, "loss": 1.0635, "step": 887 }, { "epoch": 1.942044833242209, "grad_norm": 1.1481786966323853, "learning_rate": 1.962692619626926e-05, "loss": 0.9166, "step": 888 }, { "epoch": 1.944231820667031, "grad_norm": 0.7982181310653687, "learning_rate": 1.9586374695863748e-05, "loss": 0.6579, "step": 889 }, { "epoch": 1.9464188080918534, "grad_norm": 1.1367932558059692, "learning_rate": 1.954582319545823e-05, "loss": 0.8388, "step": 890 }, { "epoch": 1.9486057955166758, "grad_norm": 1.5530800819396973, "learning_rate": 1.9505271695052717e-05, "loss": 0.9884, "step": 891 }, { "epoch": 1.9507927829414982, "grad_norm": 1.3473409414291382, "learning_rate": 1.9464720194647204e-05, "loss": 1.0247, "step": 892 }, { "epoch": 1.9529797703663205, "grad_norm": 1.2664942741394043, "learning_rate": 1.9424168694241687e-05, "loss": 0.8409, "step": 893 }, { "epoch": 1.9551667577911427, "grad_norm": 1.5024454593658447, "learning_rate": 1.9383617193836173e-05, "loss": 1.2103, "step": 894 }, { "epoch": 1.957353745215965, "grad_norm": 1.0440127849578857, "learning_rate": 1.934306569343066e-05, "loss": 0.9339, "step": 895 }, { "epoch": 1.9595407326407872, "grad_norm": 1.184495210647583, "learning_rate": 1.9302514193025143e-05, "loss": 0.8889, "step": 896 }, { "epoch": 1.9617277200656096, "grad_norm": 1.1903482675552368, "learning_rate": 1.926196269261963e-05, "loss": 0.9451, "step": 897 }, { "epoch": 1.963914707490432, "grad_norm": 1.690199375152588, "learning_rate": 1.9221411192214112e-05, "loss": 1.0416, "step": 898 }, { "epoch": 1.9661016949152543, "grad_norm": 1.2120870351791382, "learning_rate": 1.91808596918086e-05, "loss": 1.0808, "step": 899 }, { "epoch": 1.9682886823400767, "grad_norm": 0.9378510117530823, "learning_rate": 1.9140308191403082e-05, "loss": 0.8193, "step": 900 }, { "epoch": 1.9704756697648989, "grad_norm": 1.6660701036453247, "learning_rate": 1.909975669099757e-05, "loss": 1.0607, "step": 901 }, { "epoch": 1.972662657189721, "grad_norm": 1.578331470489502, "learning_rate": 1.905920519059205e-05, "loss": 0.922, "step": 902 }, { "epoch": 1.9748496446145434, "grad_norm": 1.1139328479766846, "learning_rate": 1.9018653690186538e-05, "loss": 0.8124, "step": 903 }, { "epoch": 1.9770366320393657, "grad_norm": 1.279841423034668, "learning_rate": 1.897810218978102e-05, "loss": 0.7108, "step": 904 }, { "epoch": 1.9792236194641881, "grad_norm": 2.4592409133911133, "learning_rate": 1.8937550689375507e-05, "loss": 0.8876, "step": 905 }, { "epoch": 1.9814106068890105, "grad_norm": 1.6535536050796509, "learning_rate": 1.8896999188969994e-05, "loss": 1.0279, "step": 906 }, { "epoch": 1.9835975943138326, "grad_norm": 1.7786993980407715, "learning_rate": 1.8856447688564477e-05, "loss": 0.8723, "step": 907 }, { "epoch": 1.985784581738655, "grad_norm": 1.2447621822357178, "learning_rate": 1.8815896188158963e-05, "loss": 0.9737, "step": 908 }, { "epoch": 1.9879715691634772, "grad_norm": 2.035595417022705, "learning_rate": 1.877534468775345e-05, "loss": 0.8834, "step": 909 }, { "epoch": 1.9901585565882995, "grad_norm": 0.9963703751564026, "learning_rate": 1.8734793187347933e-05, "loss": 1.0737, "step": 910 }, { "epoch": 1.992345544013122, "grad_norm": 1.155404806137085, "learning_rate": 1.869424168694242e-05, "loss": 0.9087, "step": 911 }, { "epoch": 1.9945325314379443, "grad_norm": 1.5832840204238892, "learning_rate": 1.8653690186536902e-05, "loss": 0.9529, "step": 912 }, { "epoch": 1.9967195188627667, "grad_norm": 1.355150818824768, "learning_rate": 1.861313868613139e-05, "loss": 0.679, "step": 913 }, { "epoch": 1.9989065062875888, "grad_norm": 1.5814801454544067, "learning_rate": 1.8572587185725872e-05, "loss": 0.859, "step": 914 }, { "epoch": 2.001093493712411, "grad_norm": 2.485177755355835, "learning_rate": 1.8532035685320355e-05, "loss": 0.7848, "step": 915 }, { "epoch": 2.0032804811372333, "grad_norm": 1.2883012294769287, "learning_rate": 1.849148418491484e-05, "loss": 0.7525, "step": 916 }, { "epoch": 2.0054674685620557, "grad_norm": 0.9651603102684021, "learning_rate": 1.8450932684509328e-05, "loss": 0.5357, "step": 917 }, { "epoch": 2.007654455986878, "grad_norm": 1.3948854207992554, "learning_rate": 1.841038118410381e-05, "loss": 0.8478, "step": 918 }, { "epoch": 2.0098414434117005, "grad_norm": 0.9440335631370544, "learning_rate": 1.8369829683698297e-05, "loss": 0.6279, "step": 919 }, { "epoch": 2.012028430836523, "grad_norm": 0.9379680752754211, "learning_rate": 1.8329278183292784e-05, "loss": 0.678, "step": 920 }, { "epoch": 2.014215418261345, "grad_norm": 1.3431659936904907, "learning_rate": 1.8288726682887267e-05, "loss": 0.8218, "step": 921 }, { "epoch": 2.016402405686167, "grad_norm": 1.497155785560608, "learning_rate": 1.8248175182481753e-05, "loss": 0.9868, "step": 922 }, { "epoch": 2.0185893931109895, "grad_norm": 1.8747317790985107, "learning_rate": 1.820762368207624e-05, "loss": 0.9406, "step": 923 }, { "epoch": 2.020776380535812, "grad_norm": 1.0625616312026978, "learning_rate": 1.8167072181670723e-05, "loss": 0.7625, "step": 924 }, { "epoch": 2.0229633679606343, "grad_norm": 2.2236316204071045, "learning_rate": 1.812652068126521e-05, "loss": 0.5797, "step": 925 }, { "epoch": 2.0251503553854566, "grad_norm": 1.1630890369415283, "learning_rate": 1.8085969180859692e-05, "loss": 0.9249, "step": 926 }, { "epoch": 2.027337342810279, "grad_norm": 4.773909568786621, "learning_rate": 1.8045417680454175e-05, "loss": 1.1641, "step": 927 }, { "epoch": 2.029524330235101, "grad_norm": 2.485139846801758, "learning_rate": 1.8004866180048662e-05, "loss": 0.991, "step": 928 }, { "epoch": 2.0317113176599233, "grad_norm": 1.3184558153152466, "learning_rate": 1.796431467964315e-05, "loss": 0.9434, "step": 929 }, { "epoch": 2.0338983050847457, "grad_norm": 1.6002469062805176, "learning_rate": 1.792376317923763e-05, "loss": 0.8085, "step": 930 }, { "epoch": 2.036085292509568, "grad_norm": 0.9738695025444031, "learning_rate": 1.7883211678832118e-05, "loss": 0.8256, "step": 931 }, { "epoch": 2.0382722799343904, "grad_norm": 1.3171101808547974, "learning_rate": 1.7842660178426604e-05, "loss": 0.843, "step": 932 }, { "epoch": 2.040459267359213, "grad_norm": 1.7942155599594116, "learning_rate": 1.7802108678021087e-05, "loss": 0.7111, "step": 933 }, { "epoch": 2.042646254784035, "grad_norm": 1.674403429031372, "learning_rate": 1.7761557177615574e-05, "loss": 0.8185, "step": 934 }, { "epoch": 2.044833242208857, "grad_norm": 1.2915693521499634, "learning_rate": 1.7721005677210057e-05, "loss": 0.9955, "step": 935 }, { "epoch": 2.0470202296336795, "grad_norm": 1.6613247394561768, "learning_rate": 1.7680454176804543e-05, "loss": 0.6758, "step": 936 }, { "epoch": 2.049207217058502, "grad_norm": 1.1298788785934448, "learning_rate": 1.763990267639903e-05, "loss": 0.8232, "step": 937 }, { "epoch": 2.051394204483324, "grad_norm": 0.6572903990745544, "learning_rate": 1.7599351175993513e-05, "loss": 1.076, "step": 938 }, { "epoch": 2.0535811919081466, "grad_norm": 1.4049177169799805, "learning_rate": 1.7558799675587996e-05, "loss": 0.8187, "step": 939 }, { "epoch": 2.055768179332969, "grad_norm": 0.8734551072120667, "learning_rate": 1.7518248175182482e-05, "loss": 0.5826, "step": 940 }, { "epoch": 2.0579551667577913, "grad_norm": 2.446927070617676, "learning_rate": 1.7477696674776966e-05, "loss": 0.6826, "step": 941 }, { "epoch": 2.0601421541826133, "grad_norm": 1.1771522760391235, "learning_rate": 1.7437145174371452e-05, "loss": 0.7893, "step": 942 }, { "epoch": 2.0623291416074356, "grad_norm": 1.0351836681365967, "learning_rate": 1.739659367396594e-05, "loss": 0.7643, "step": 943 }, { "epoch": 2.064516129032258, "grad_norm": 1.9325096607208252, "learning_rate": 1.735604217356042e-05, "loss": 0.9435, "step": 944 }, { "epoch": 2.0667031164570804, "grad_norm": 1.633297324180603, "learning_rate": 1.7315490673154908e-05, "loss": 0.6918, "step": 945 }, { "epoch": 2.0688901038819028, "grad_norm": 1.4818955659866333, "learning_rate": 1.7274939172749394e-05, "loss": 0.8667, "step": 946 }, { "epoch": 2.071077091306725, "grad_norm": 2.1938328742980957, "learning_rate": 1.7234387672343877e-05, "loss": 0.8483, "step": 947 }, { "epoch": 2.0732640787315475, "grad_norm": 1.2209322452545166, "learning_rate": 1.7193836171938364e-05, "loss": 0.9719, "step": 948 }, { "epoch": 2.0754510661563694, "grad_norm": 1.1632466316223145, "learning_rate": 1.715328467153285e-05, "loss": 0.7609, "step": 949 }, { "epoch": 2.077638053581192, "grad_norm": 0.9603205323219299, "learning_rate": 1.7112733171127333e-05, "loss": 0.6842, "step": 950 }, { "epoch": 2.079825041006014, "grad_norm": 1.140539288520813, "learning_rate": 1.7072181670721816e-05, "loss": 0.7548, "step": 951 }, { "epoch": 2.0820120284308365, "grad_norm": 1.120163083076477, "learning_rate": 1.70316301703163e-05, "loss": 0.5713, "step": 952 }, { "epoch": 2.084199015855659, "grad_norm": 1.4765040874481201, "learning_rate": 1.6991078669910786e-05, "loss": 0.6359, "step": 953 }, { "epoch": 2.0863860032804813, "grad_norm": 3.152650833129883, "learning_rate": 1.6950527169505272e-05, "loss": 1.0586, "step": 954 }, { "epoch": 2.0885729907053037, "grad_norm": 1.0131175518035889, "learning_rate": 1.6909975669099756e-05, "loss": 0.7805, "step": 955 }, { "epoch": 2.0907599781301256, "grad_norm": 0.8599899411201477, "learning_rate": 1.6869424168694242e-05, "loss": 0.8554, "step": 956 }, { "epoch": 2.092946965554948, "grad_norm": 1.2261124849319458, "learning_rate": 1.682887266828873e-05, "loss": 0.8094, "step": 957 }, { "epoch": 2.0951339529797703, "grad_norm": 1.7776283025741577, "learning_rate": 1.678832116788321e-05, "loss": 0.7708, "step": 958 }, { "epoch": 2.0973209404045927, "grad_norm": 1.1675063371658325, "learning_rate": 1.6747769667477698e-05, "loss": 0.6749, "step": 959 }, { "epoch": 2.099507927829415, "grad_norm": 0.6730952262878418, "learning_rate": 1.6707218167072184e-05, "loss": 0.7162, "step": 960 }, { "epoch": 2.1016949152542375, "grad_norm": 1.1775892972946167, "learning_rate": 1.6666666666666667e-05, "loss": 0.9121, "step": 961 }, { "epoch": 2.1038819026790594, "grad_norm": 1.1023653745651245, "learning_rate": 1.6626115166261154e-05, "loss": 0.8112, "step": 962 }, { "epoch": 2.1060688901038818, "grad_norm": 0.9472550749778748, "learning_rate": 1.6585563665855637e-05, "loss": 0.7291, "step": 963 }, { "epoch": 2.108255877528704, "grad_norm": 1.373024582862854, "learning_rate": 1.654501216545012e-05, "loss": 0.6967, "step": 964 }, { "epoch": 2.1104428649535265, "grad_norm": 1.1234303712844849, "learning_rate": 1.6504460665044607e-05, "loss": 0.8256, "step": 965 }, { "epoch": 2.112629852378349, "grad_norm": 0.9149262309074402, "learning_rate": 1.6463909164639093e-05, "loss": 0.6716, "step": 966 }, { "epoch": 2.1148168398031713, "grad_norm": 1.4481924772262573, "learning_rate": 1.6423357664233576e-05, "loss": 0.8701, "step": 967 }, { "epoch": 2.1170038272279936, "grad_norm": 1.4338946342468262, "learning_rate": 1.6382806163828062e-05, "loss": 0.8764, "step": 968 }, { "epoch": 2.1191908146528156, "grad_norm": 1.4253469705581665, "learning_rate": 1.634225466342255e-05, "loss": 0.8067, "step": 969 }, { "epoch": 2.121377802077638, "grad_norm": 1.5842149257659912, "learning_rate": 1.6301703163017032e-05, "loss": 1.1009, "step": 970 }, { "epoch": 2.1235647895024603, "grad_norm": 1.640146017074585, "learning_rate": 1.626115166261152e-05, "loss": 0.8092, "step": 971 }, { "epoch": 2.1257517769272827, "grad_norm": 1.207505226135254, "learning_rate": 1.6220600162206e-05, "loss": 0.8393, "step": 972 }, { "epoch": 2.127938764352105, "grad_norm": 1.252209186553955, "learning_rate": 1.6180048661800488e-05, "loss": 0.6706, "step": 973 }, { "epoch": 2.1301257517769274, "grad_norm": 1.346919059753418, "learning_rate": 1.6139497161394974e-05, "loss": 0.754, "step": 974 }, { "epoch": 2.13231273920175, "grad_norm": 0.9678462147712708, "learning_rate": 1.6098945660989457e-05, "loss": 0.7071, "step": 975 }, { "epoch": 2.1344997266265717, "grad_norm": 1.0313513278961182, "learning_rate": 1.605839416058394e-05, "loss": 0.8366, "step": 976 }, { "epoch": 2.136686714051394, "grad_norm": 1.566942811012268, "learning_rate": 1.6017842660178427e-05, "loss": 1.0635, "step": 977 }, { "epoch": 2.1388737014762165, "grad_norm": 1.6899473667144775, "learning_rate": 1.597729115977291e-05, "loss": 0.8461, "step": 978 }, { "epoch": 2.141060688901039, "grad_norm": 0.9646878838539124, "learning_rate": 1.5936739659367397e-05, "loss": 0.8322, "step": 979 }, { "epoch": 2.143247676325861, "grad_norm": 1.1947306394577026, "learning_rate": 1.5896188158961883e-05, "loss": 0.7357, "step": 980 }, { "epoch": 2.1454346637506836, "grad_norm": 1.016286849975586, "learning_rate": 1.5855636658556366e-05, "loss": 0.6186, "step": 981 }, { "epoch": 2.1476216511755055, "grad_norm": 0.8885013461112976, "learning_rate": 1.5815085158150852e-05, "loss": 0.6325, "step": 982 }, { "epoch": 2.149808638600328, "grad_norm": 1.1831783056259155, "learning_rate": 1.577453365774534e-05, "loss": 0.6034, "step": 983 }, { "epoch": 2.1519956260251503, "grad_norm": 1.3540970087051392, "learning_rate": 1.5733982157339822e-05, "loss": 0.7389, "step": 984 }, { "epoch": 2.1541826134499726, "grad_norm": 1.218010663986206, "learning_rate": 1.569343065693431e-05, "loss": 0.7692, "step": 985 }, { "epoch": 2.156369600874795, "grad_norm": 1.4038283824920654, "learning_rate": 1.5652879156528795e-05, "loss": 0.8792, "step": 986 }, { "epoch": 2.1585565882996174, "grad_norm": 1.276294469833374, "learning_rate": 1.5612327656123278e-05, "loss": 0.7397, "step": 987 }, { "epoch": 2.1607435757244398, "grad_norm": 0.8709433674812317, "learning_rate": 1.557177615571776e-05, "loss": 1.0475, "step": 988 }, { "epoch": 2.1629305631492617, "grad_norm": 0.9444726705551147, "learning_rate": 1.5531224655312247e-05, "loss": 0.9976, "step": 989 }, { "epoch": 2.165117550574084, "grad_norm": 1.4064675569534302, "learning_rate": 1.549067315490673e-05, "loss": 0.9505, "step": 990 }, { "epoch": 2.1673045379989064, "grad_norm": 0.7164079546928406, "learning_rate": 1.5450121654501217e-05, "loss": 0.7791, "step": 991 }, { "epoch": 2.169491525423729, "grad_norm": 1.1197065114974976, "learning_rate": 1.54095701540957e-05, "loss": 0.8676, "step": 992 }, { "epoch": 2.171678512848551, "grad_norm": 1.174988865852356, "learning_rate": 1.5369018653690187e-05, "loss": 0.659, "step": 993 }, { "epoch": 2.1738655002733736, "grad_norm": 1.7912452220916748, "learning_rate": 1.5328467153284673e-05, "loss": 0.6628, "step": 994 }, { "epoch": 2.176052487698196, "grad_norm": 1.294090986251831, "learning_rate": 1.5287915652879156e-05, "loss": 1.006, "step": 995 }, { "epoch": 2.178239475123018, "grad_norm": 1.0277974605560303, "learning_rate": 1.5247364152473643e-05, "loss": 0.7772, "step": 996 }, { "epoch": 2.1804264625478402, "grad_norm": 0.859675943851471, "learning_rate": 1.5206812652068127e-05, "loss": 0.649, "step": 997 }, { "epoch": 2.1826134499726626, "grad_norm": 2.1222243309020996, "learning_rate": 1.5166261151662612e-05, "loss": 0.8132, "step": 998 }, { "epoch": 2.184800437397485, "grad_norm": 0.6391716003417969, "learning_rate": 1.5125709651257097e-05, "loss": 0.8822, "step": 999 }, { "epoch": 2.1869874248223073, "grad_norm": 1.182211995124817, "learning_rate": 1.5085158150851583e-05, "loss": 1.0316, "step": 1000 }, { "epoch": 2.1891744122471297, "grad_norm": 1.404892086982727, "learning_rate": 1.5044606650446066e-05, "loss": 0.5827, "step": 1001 }, { "epoch": 2.191361399671952, "grad_norm": 0.8307010531425476, "learning_rate": 1.5004055150040553e-05, "loss": 0.7019, "step": 1002 }, { "epoch": 2.193548387096774, "grad_norm": 1.0612499713897705, "learning_rate": 1.496350364963504e-05, "loss": 0.7963, "step": 1003 }, { "epoch": 2.1957353745215964, "grad_norm": 1.2308467626571655, "learning_rate": 1.4922952149229522e-05, "loss": 0.6946, "step": 1004 }, { "epoch": 2.1979223619464188, "grad_norm": 1.0509589910507202, "learning_rate": 1.4882400648824007e-05, "loss": 0.6968, "step": 1005 }, { "epoch": 2.200109349371241, "grad_norm": 1.3209277391433716, "learning_rate": 1.4841849148418493e-05, "loss": 0.6862, "step": 1006 }, { "epoch": 2.2022963367960635, "grad_norm": 1.4590058326721191, "learning_rate": 1.4801297648012977e-05, "loss": 0.6644, "step": 1007 }, { "epoch": 2.204483324220886, "grad_norm": 1.1118968725204468, "learning_rate": 1.4760746147607463e-05, "loss": 0.6123, "step": 1008 }, { "epoch": 2.2066703116457083, "grad_norm": 1.3556759357452393, "learning_rate": 1.4720194647201946e-05, "loss": 0.7208, "step": 1009 }, { "epoch": 2.20885729907053, "grad_norm": 1.5545029640197754, "learning_rate": 1.4679643146796433e-05, "loss": 0.817, "step": 1010 }, { "epoch": 2.2110442864953526, "grad_norm": 0.6834763288497925, "learning_rate": 1.4639091646390917e-05, "loss": 1.1801, "step": 1011 }, { "epoch": 2.213231273920175, "grad_norm": 1.7177108526229858, "learning_rate": 1.45985401459854e-05, "loss": 0.9279, "step": 1012 }, { "epoch": 2.2154182613449973, "grad_norm": 1.6980525255203247, "learning_rate": 1.4557988645579887e-05, "loss": 0.7036, "step": 1013 }, { "epoch": 2.2176052487698197, "grad_norm": 1.7500015497207642, "learning_rate": 1.4517437145174373e-05, "loss": 0.7624, "step": 1014 }, { "epoch": 2.219792236194642, "grad_norm": 0.9455114006996155, "learning_rate": 1.4476885644768856e-05, "loss": 0.9698, "step": 1015 }, { "epoch": 2.221979223619464, "grad_norm": 2.814690113067627, "learning_rate": 1.4436334144363343e-05, "loss": 0.9822, "step": 1016 }, { "epoch": 2.2241662110442864, "grad_norm": 1.68293035030365, "learning_rate": 1.4395782643957828e-05, "loss": 0.9271, "step": 1017 }, { "epoch": 2.2263531984691087, "grad_norm": 1.3931039571762085, "learning_rate": 1.435523114355231e-05, "loss": 0.7742, "step": 1018 }, { "epoch": 2.228540185893931, "grad_norm": 1.1640081405639648, "learning_rate": 1.4314679643146797e-05, "loss": 0.9177, "step": 1019 }, { "epoch": 2.2307271733187535, "grad_norm": 1.6405117511749268, "learning_rate": 1.4274128142741283e-05, "loss": 0.7142, "step": 1020 }, { "epoch": 2.232914160743576, "grad_norm": 0.9828827977180481, "learning_rate": 1.4233576642335767e-05, "loss": 0.5087, "step": 1021 }, { "epoch": 2.235101148168398, "grad_norm": 1.5597370862960815, "learning_rate": 1.4193025141930253e-05, "loss": 0.6615, "step": 1022 }, { "epoch": 2.23728813559322, "grad_norm": 1.8974511623382568, "learning_rate": 1.4152473641524738e-05, "loss": 0.9439, "step": 1023 }, { "epoch": 2.2394751230180425, "grad_norm": 1.2067925930023193, "learning_rate": 1.411192214111922e-05, "loss": 0.832, "step": 1024 }, { "epoch": 2.241662110442865, "grad_norm": 1.2459200620651245, "learning_rate": 1.4071370640713707e-05, "loss": 0.7881, "step": 1025 }, { "epoch": 2.2438490978676873, "grad_norm": 1.8207327127456665, "learning_rate": 1.4030819140308194e-05, "loss": 1.2137, "step": 1026 }, { "epoch": 2.2460360852925096, "grad_norm": 0.9799403548240662, "learning_rate": 1.3990267639902677e-05, "loss": 0.6219, "step": 1027 }, { "epoch": 2.248223072717332, "grad_norm": 1.9541126489639282, "learning_rate": 1.3949716139497163e-05, "loss": 0.8844, "step": 1028 }, { "epoch": 2.250410060142154, "grad_norm": 1.8121858835220337, "learning_rate": 1.3909164639091646e-05, "loss": 0.8385, "step": 1029 }, { "epoch": 2.2525970475669763, "grad_norm": 2.4143075942993164, "learning_rate": 1.3868613138686131e-05, "loss": 0.6924, "step": 1030 }, { "epoch": 2.2547840349917987, "grad_norm": 1.4028592109680176, "learning_rate": 1.3828061638280618e-05, "loss": 0.8933, "step": 1031 }, { "epoch": 2.256971022416621, "grad_norm": 2.341029405593872, "learning_rate": 1.37875101378751e-05, "loss": 0.7779, "step": 1032 }, { "epoch": 2.2591580098414434, "grad_norm": 0.861836314201355, "learning_rate": 1.3746958637469587e-05, "loss": 0.9071, "step": 1033 }, { "epoch": 2.261344997266266, "grad_norm": 2.038280725479126, "learning_rate": 1.3706407137064074e-05, "loss": 1.0789, "step": 1034 }, { "epoch": 2.263531984691088, "grad_norm": 1.0756237506866455, "learning_rate": 1.3665855636658557e-05, "loss": 0.821, "step": 1035 }, { "epoch": 2.26571897211591, "grad_norm": 1.2637927532196045, "learning_rate": 1.3625304136253041e-05, "loss": 1.1142, "step": 1036 }, { "epoch": 2.2679059595407325, "grad_norm": 0.8377043604850769, "learning_rate": 1.3584752635847528e-05, "loss": 0.9726, "step": 1037 }, { "epoch": 2.270092946965555, "grad_norm": 2.8273656368255615, "learning_rate": 1.3544201135442011e-05, "loss": 0.9351, "step": 1038 }, { "epoch": 2.2722799343903772, "grad_norm": 1.0960334539413452, "learning_rate": 1.3503649635036497e-05, "loss": 1.0613, "step": 1039 }, { "epoch": 2.2744669218151996, "grad_norm": 6.3283514976501465, "learning_rate": 1.3463098134630984e-05, "loss": 0.9449, "step": 1040 }, { "epoch": 2.276653909240022, "grad_norm": 1.522585153579712, "learning_rate": 1.3422546634225467e-05, "loss": 0.8773, "step": 1041 }, { "epoch": 2.2788408966648444, "grad_norm": 0.9904917478561401, "learning_rate": 1.3381995133819952e-05, "loss": 0.7303, "step": 1042 }, { "epoch": 2.2810278840896663, "grad_norm": 1.5973548889160156, "learning_rate": 1.3341443633414438e-05, "loss": 0.9647, "step": 1043 }, { "epoch": 2.2832148715144887, "grad_norm": 1.5934083461761475, "learning_rate": 1.3300892133008921e-05, "loss": 0.9742, "step": 1044 }, { "epoch": 2.285401858939311, "grad_norm": 1.610560417175293, "learning_rate": 1.3260340632603408e-05, "loss": 0.6719, "step": 1045 }, { "epoch": 2.2875888463641334, "grad_norm": 1.0306094884872437, "learning_rate": 1.321978913219789e-05, "loss": 1.0564, "step": 1046 }, { "epoch": 2.2897758337889558, "grad_norm": 1.7010867595672607, "learning_rate": 1.3179237631792377e-05, "loss": 0.7204, "step": 1047 }, { "epoch": 2.291962821213778, "grad_norm": 1.2326537370681763, "learning_rate": 1.3138686131386862e-05, "loss": 0.8669, "step": 1048 }, { "epoch": 2.2941498086386005, "grad_norm": 1.3844677209854126, "learning_rate": 1.3098134630981347e-05, "loss": 0.8115, "step": 1049 }, { "epoch": 2.2963367960634224, "grad_norm": 1.1779239177703857, "learning_rate": 1.3057583130575831e-05, "loss": 0.6228, "step": 1050 }, { "epoch": 2.298523783488245, "grad_norm": 1.0366896390914917, "learning_rate": 1.3017031630170318e-05, "loss": 0.8918, "step": 1051 }, { "epoch": 2.300710770913067, "grad_norm": 1.3332747220993042, "learning_rate": 1.2976480129764801e-05, "loss": 0.8866, "step": 1052 }, { "epoch": 2.3028977583378896, "grad_norm": 1.6586980819702148, "learning_rate": 1.2935928629359287e-05, "loss": 0.6652, "step": 1053 }, { "epoch": 2.305084745762712, "grad_norm": 1.2624136209487915, "learning_rate": 1.2895377128953772e-05, "loss": 0.7292, "step": 1054 }, { "epoch": 2.3072717331875343, "grad_norm": 1.5325928926467896, "learning_rate": 1.2854825628548257e-05, "loss": 0.6824, "step": 1055 }, { "epoch": 2.3094587206123567, "grad_norm": 0.9341633915901184, "learning_rate": 1.2814274128142742e-05, "loss": 0.7074, "step": 1056 }, { "epoch": 2.3116457080371786, "grad_norm": 1.0597721338272095, "learning_rate": 1.2773722627737228e-05, "loss": 0.9395, "step": 1057 }, { "epoch": 2.313832695462001, "grad_norm": 1.125878095626831, "learning_rate": 1.2733171127331711e-05, "loss": 0.6667, "step": 1058 }, { "epoch": 2.3160196828868234, "grad_norm": 1.362362265586853, "learning_rate": 1.2692619626926198e-05, "loss": 0.5031, "step": 1059 }, { "epoch": 2.3182066703116457, "grad_norm": 1.1168161630630493, "learning_rate": 1.2652068126520682e-05, "loss": 0.644, "step": 1060 }, { "epoch": 2.320393657736468, "grad_norm": 1.787891149520874, "learning_rate": 1.2611516626115167e-05, "loss": 0.7318, "step": 1061 }, { "epoch": 2.3225806451612905, "grad_norm": 1.5552399158477783, "learning_rate": 1.2570965125709652e-05, "loss": 0.7584, "step": 1062 }, { "epoch": 2.324767632586113, "grad_norm": 1.8017922639846802, "learning_rate": 1.2530413625304138e-05, "loss": 0.6666, "step": 1063 }, { "epoch": 2.326954620010935, "grad_norm": 1.5591821670532227, "learning_rate": 1.2489862124898621e-05, "loss": 1.0045, "step": 1064 }, { "epoch": 2.329141607435757, "grad_norm": 0.8470662832260132, "learning_rate": 1.2449310624493108e-05, "loss": 0.6981, "step": 1065 }, { "epoch": 2.3313285948605795, "grad_norm": 1.2033611536026, "learning_rate": 1.2408759124087593e-05, "loss": 0.6036, "step": 1066 }, { "epoch": 2.333515582285402, "grad_norm": 1.2030003070831299, "learning_rate": 1.2368207623682077e-05, "loss": 0.8272, "step": 1067 }, { "epoch": 2.3357025697102243, "grad_norm": 2.042344808578491, "learning_rate": 1.2327656123276562e-05, "loss": 0.9503, "step": 1068 }, { "epoch": 2.3378895571350466, "grad_norm": 1.8004951477050781, "learning_rate": 1.2287104622871047e-05, "loss": 1.1884, "step": 1069 }, { "epoch": 2.340076544559869, "grad_norm": 1.7595882415771484, "learning_rate": 1.2246553122465532e-05, "loss": 1.0057, "step": 1070 }, { "epoch": 2.342263531984691, "grad_norm": 1.9779390096664429, "learning_rate": 1.2206001622060016e-05, "loss": 1.1618, "step": 1071 }, { "epoch": 2.3444505194095133, "grad_norm": 1.1844338178634644, "learning_rate": 1.2165450121654503e-05, "loss": 0.946, "step": 1072 }, { "epoch": 2.3466375068343357, "grad_norm": 1.6877304315567017, "learning_rate": 1.2124898621248988e-05, "loss": 0.9357, "step": 1073 }, { "epoch": 2.348824494259158, "grad_norm": 1.2200840711593628, "learning_rate": 1.208434712084347e-05, "loss": 0.6755, "step": 1074 }, { "epoch": 2.3510114816839804, "grad_norm": 0.8738909959793091, "learning_rate": 1.2043795620437957e-05, "loss": 0.5637, "step": 1075 }, { "epoch": 2.353198469108803, "grad_norm": 1.2802790403366089, "learning_rate": 1.2003244120032442e-05, "loss": 0.7201, "step": 1076 }, { "epoch": 2.3553854565336247, "grad_norm": 2.0975217819213867, "learning_rate": 1.1962692619626927e-05, "loss": 0.7174, "step": 1077 }, { "epoch": 2.357572443958447, "grad_norm": 1.6411463022232056, "learning_rate": 1.1922141119221411e-05, "loss": 1.2966, "step": 1078 }, { "epoch": 2.3597594313832695, "grad_norm": 0.921008288860321, "learning_rate": 1.1881589618815898e-05, "loss": 0.7478, "step": 1079 }, { "epoch": 2.361946418808092, "grad_norm": 0.8602957129478455, "learning_rate": 1.1841038118410381e-05, "loss": 0.78, "step": 1080 }, { "epoch": 2.3641334062329142, "grad_norm": 1.7533910274505615, "learning_rate": 1.1800486618004866e-05, "loss": 0.8555, "step": 1081 }, { "epoch": 2.3663203936577366, "grad_norm": 0.844523012638092, "learning_rate": 1.1759935117599352e-05, "loss": 0.7119, "step": 1082 }, { "epoch": 2.3685073810825585, "grad_norm": 1.0230821371078491, "learning_rate": 1.1719383617193837e-05, "loss": 0.7728, "step": 1083 }, { "epoch": 2.370694368507381, "grad_norm": 2.0517702102661133, "learning_rate": 1.1678832116788322e-05, "loss": 0.5633, "step": 1084 }, { "epoch": 2.3728813559322033, "grad_norm": 1.5436774492263794, "learning_rate": 1.1638280616382808e-05, "loss": 0.9042, "step": 1085 }, { "epoch": 2.3750683433570257, "grad_norm": 1.5256388187408447, "learning_rate": 1.1597729115977291e-05, "loss": 0.7749, "step": 1086 }, { "epoch": 2.377255330781848, "grad_norm": 1.344870686531067, "learning_rate": 1.1557177615571776e-05, "loss": 0.8108, "step": 1087 }, { "epoch": 2.3794423182066704, "grad_norm": 1.0892130136489868, "learning_rate": 1.151662611516626e-05, "loss": 0.6872, "step": 1088 }, { "epoch": 2.3816293056314928, "grad_norm": 2.94130277633667, "learning_rate": 1.1476074614760747e-05, "loss": 0.9758, "step": 1089 }, { "epoch": 2.3838162930563147, "grad_norm": 1.5244641304016113, "learning_rate": 1.1435523114355232e-05, "loss": 0.778, "step": 1090 }, { "epoch": 2.386003280481137, "grad_norm": 1.3784693479537964, "learning_rate": 1.1394971613949717e-05, "loss": 0.8426, "step": 1091 }, { "epoch": 2.3881902679059595, "grad_norm": 1.5367156267166138, "learning_rate": 1.1354420113544201e-05, "loss": 0.7513, "step": 1092 }, { "epoch": 2.390377255330782, "grad_norm": 1.5739291906356812, "learning_rate": 1.1313868613138686e-05, "loss": 0.6922, "step": 1093 }, { "epoch": 2.392564242755604, "grad_norm": 1.2463433742523193, "learning_rate": 1.1273317112733171e-05, "loss": 0.8491, "step": 1094 }, { "epoch": 2.3947512301804266, "grad_norm": 1.8704092502593994, "learning_rate": 1.1232765612327657e-05, "loss": 0.8773, "step": 1095 }, { "epoch": 2.396938217605249, "grad_norm": 0.8870313763618469, "learning_rate": 1.1192214111922142e-05, "loss": 0.7019, "step": 1096 }, { "epoch": 2.399125205030071, "grad_norm": 1.8858847618103027, "learning_rate": 1.1151662611516627e-05, "loss": 0.7108, "step": 1097 }, { "epoch": 2.4013121924548932, "grad_norm": 3.2740561962127686, "learning_rate": 1.1111111111111112e-05, "loss": 0.8309, "step": 1098 }, { "epoch": 2.4034991798797156, "grad_norm": 1.3838295936584473, "learning_rate": 1.1070559610705596e-05, "loss": 0.8246, "step": 1099 }, { "epoch": 2.405686167304538, "grad_norm": 1.744537115097046, "learning_rate": 1.1030008110300081e-05, "loss": 0.7126, "step": 1100 }, { "epoch": 2.4078731547293604, "grad_norm": 2.2818408012390137, "learning_rate": 1.0989456609894566e-05, "loss": 0.7802, "step": 1101 }, { "epoch": 2.4100601421541827, "grad_norm": 2.215186834335327, "learning_rate": 1.0948905109489052e-05, "loss": 0.6507, "step": 1102 }, { "epoch": 2.412247129579005, "grad_norm": 1.5528634786605835, "learning_rate": 1.0908353609083537e-05, "loss": 0.8186, "step": 1103 }, { "epoch": 2.414434117003827, "grad_norm": 1.135749101638794, "learning_rate": 1.0867802108678022e-05, "loss": 0.6594, "step": 1104 }, { "epoch": 2.4166211044286494, "grad_norm": 1.6633915901184082, "learning_rate": 1.0827250608272507e-05, "loss": 0.6689, "step": 1105 }, { "epoch": 2.418808091853472, "grad_norm": 1.1183667182922363, "learning_rate": 1.0786699107866991e-05, "loss": 0.8374, "step": 1106 }, { "epoch": 2.420995079278294, "grad_norm": 1.4072012901306152, "learning_rate": 1.0746147607461476e-05, "loss": 0.7815, "step": 1107 }, { "epoch": 2.4231820667031165, "grad_norm": 1.6484023332595825, "learning_rate": 1.0705596107055961e-05, "loss": 0.804, "step": 1108 }, { "epoch": 2.425369054127939, "grad_norm": 1.1572465896606445, "learning_rate": 1.0665044606650447e-05, "loss": 0.8575, "step": 1109 }, { "epoch": 2.4275560415527613, "grad_norm": 1.2840930223464966, "learning_rate": 1.0624493106244932e-05, "loss": 0.8134, "step": 1110 }, { "epoch": 2.429743028977583, "grad_norm": 1.109953761100769, "learning_rate": 1.0583941605839417e-05, "loss": 0.7974, "step": 1111 }, { "epoch": 2.4319300164024056, "grad_norm": 1.2292791604995728, "learning_rate": 1.0543390105433902e-05, "loss": 0.8591, "step": 1112 }, { "epoch": 2.434117003827228, "grad_norm": 1.2584034204483032, "learning_rate": 1.0502838605028386e-05, "loss": 0.9543, "step": 1113 }, { "epoch": 2.4363039912520503, "grad_norm": 1.6038156747817993, "learning_rate": 1.0462287104622871e-05, "loss": 0.9162, "step": 1114 }, { "epoch": 2.4384909786768727, "grad_norm": 1.0964059829711914, "learning_rate": 1.0421735604217358e-05, "loss": 0.5908, "step": 1115 }, { "epoch": 2.440677966101695, "grad_norm": 1.622799277305603, "learning_rate": 1.0381184103811842e-05, "loss": 0.9662, "step": 1116 }, { "epoch": 2.4428649535265174, "grad_norm": 1.2752150297164917, "learning_rate": 1.0340632603406327e-05, "loss": 0.7876, "step": 1117 }, { "epoch": 2.4450519409513394, "grad_norm": 1.388074278831482, "learning_rate": 1.030008110300081e-05, "loss": 0.9269, "step": 1118 }, { "epoch": 2.4472389283761617, "grad_norm": 0.9508733153343201, "learning_rate": 1.0259529602595297e-05, "loss": 0.7613, "step": 1119 }, { "epoch": 2.449425915800984, "grad_norm": 1.0427885055541992, "learning_rate": 1.0218978102189781e-05, "loss": 0.7593, "step": 1120 }, { "epoch": 2.4516129032258065, "grad_norm": 1.4241914749145508, "learning_rate": 1.0178426601784266e-05, "loss": 0.681, "step": 1121 }, { "epoch": 2.453799890650629, "grad_norm": 1.0486629009246826, "learning_rate": 1.0137875101378753e-05, "loss": 0.5328, "step": 1122 }, { "epoch": 2.4559868780754512, "grad_norm": 2.052527666091919, "learning_rate": 1.0097323600973237e-05, "loss": 0.5736, "step": 1123 }, { "epoch": 2.4581738655002736, "grad_norm": 1.2652926445007324, "learning_rate": 1.005677210056772e-05, "loss": 0.7536, "step": 1124 }, { "epoch": 2.4603608529250955, "grad_norm": 0.886055052280426, "learning_rate": 1.0016220600162205e-05, "loss": 0.6375, "step": 1125 }, { "epoch": 2.462547840349918, "grad_norm": 1.375707745552063, "learning_rate": 9.975669099756692e-06, "loss": 0.842, "step": 1126 }, { "epoch": 2.4647348277747403, "grad_norm": 1.5919983386993408, "learning_rate": 9.935117599351176e-06, "loss": 0.7864, "step": 1127 }, { "epoch": 2.4669218151995627, "grad_norm": 0.7367779612541199, "learning_rate": 9.894566098945661e-06, "loss": 0.7153, "step": 1128 }, { "epoch": 2.469108802624385, "grad_norm": 0.791888952255249, "learning_rate": 9.854014598540148e-06, "loss": 0.6167, "step": 1129 }, { "epoch": 2.4712957900492074, "grad_norm": 1.2401846647262573, "learning_rate": 9.81346309813463e-06, "loss": 0.7705, "step": 1130 }, { "epoch": 2.4734827774740293, "grad_norm": 1.3826247453689575, "learning_rate": 9.772911597729115e-06, "loss": 0.8044, "step": 1131 }, { "epoch": 2.4756697648988517, "grad_norm": 0.9505245685577393, "learning_rate": 9.732360097323602e-06, "loss": 0.7604, "step": 1132 }, { "epoch": 2.477856752323674, "grad_norm": 1.0143723487854004, "learning_rate": 9.691808596918087e-06, "loss": 0.9078, "step": 1133 }, { "epoch": 2.4800437397484965, "grad_norm": 2.3022472858428955, "learning_rate": 9.651257096512571e-06, "loss": 1.0623, "step": 1134 }, { "epoch": 2.482230727173319, "grad_norm": 1.314038634300232, "learning_rate": 9.610705596107056e-06, "loss": 0.771, "step": 1135 }, { "epoch": 2.484417714598141, "grad_norm": 0.7796556353569031, "learning_rate": 9.570154095701541e-06, "loss": 0.4935, "step": 1136 }, { "epoch": 2.486604702022963, "grad_norm": 1.3897145986557007, "learning_rate": 9.529602595296026e-06, "loss": 0.9618, "step": 1137 }, { "epoch": 2.4887916894477855, "grad_norm": 1.125646948814392, "learning_rate": 9.48905109489051e-06, "loss": 0.969, "step": 1138 }, { "epoch": 2.490978676872608, "grad_norm": 1.185454249382019, "learning_rate": 9.448499594484997e-06, "loss": 0.7695, "step": 1139 }, { "epoch": 2.4931656642974303, "grad_norm": 1.2373055219650269, "learning_rate": 9.407948094079482e-06, "loss": 0.7243, "step": 1140 }, { "epoch": 2.4953526517222526, "grad_norm": 1.1820663213729858, "learning_rate": 9.367396593673966e-06, "loss": 0.9088, "step": 1141 }, { "epoch": 2.497539639147075, "grad_norm": 1.5532386302947998, "learning_rate": 9.326845093268451e-06, "loss": 0.6773, "step": 1142 }, { "epoch": 2.4997266265718974, "grad_norm": 0.8900976777076721, "learning_rate": 9.286293592862936e-06, "loss": 0.5111, "step": 1143 }, { "epoch": 2.5019136139967193, "grad_norm": 1.2813800573349, "learning_rate": 9.24574209245742e-06, "loss": 0.833, "step": 1144 }, { "epoch": 2.5041006014215417, "grad_norm": 1.6572743654251099, "learning_rate": 9.205190592051905e-06, "loss": 0.7674, "step": 1145 }, { "epoch": 2.506287588846364, "grad_norm": 1.0724363327026367, "learning_rate": 9.164639091646392e-06, "loss": 0.643, "step": 1146 }, { "epoch": 2.5084745762711864, "grad_norm": 0.9566395282745361, "learning_rate": 9.124087591240877e-06, "loss": 0.62, "step": 1147 }, { "epoch": 2.510661563696009, "grad_norm": 1.4465469121932983, "learning_rate": 9.083536090835361e-06, "loss": 0.7014, "step": 1148 }, { "epoch": 2.512848551120831, "grad_norm": 1.0669327974319458, "learning_rate": 9.042984590429846e-06, "loss": 0.9513, "step": 1149 }, { "epoch": 2.5150355385456535, "grad_norm": 1.4890185594558716, "learning_rate": 9.002433090024331e-06, "loss": 0.7551, "step": 1150 }, { "epoch": 2.5172225259704755, "grad_norm": 0.7905449271202087, "learning_rate": 8.961881589618816e-06, "loss": 0.887, "step": 1151 }, { "epoch": 2.519409513395298, "grad_norm": 1.5447129011154175, "learning_rate": 8.921330089213302e-06, "loss": 0.6772, "step": 1152 }, { "epoch": 2.52159650082012, "grad_norm": 1.5693113803863525, "learning_rate": 8.880778588807787e-06, "loss": 0.7891, "step": 1153 }, { "epoch": 2.5237834882449426, "grad_norm": 1.059196949005127, "learning_rate": 8.840227088402272e-06, "loss": 0.6397, "step": 1154 }, { "epoch": 2.525970475669765, "grad_norm": 2.3431689739227295, "learning_rate": 8.799675587996756e-06, "loss": 0.762, "step": 1155 }, { "epoch": 2.5281574630945873, "grad_norm": 1.3474012613296509, "learning_rate": 8.759124087591241e-06, "loss": 0.749, "step": 1156 }, { "epoch": 2.5303444505194097, "grad_norm": 2.235961675643921, "learning_rate": 8.718572587185726e-06, "loss": 0.9289, "step": 1157 }, { "epoch": 2.5325314379442316, "grad_norm": 1.549843668937683, "learning_rate": 8.67802108678021e-06, "loss": 0.7166, "step": 1158 }, { "epoch": 2.534718425369054, "grad_norm": 1.5338433980941772, "learning_rate": 8.637469586374697e-06, "loss": 0.7322, "step": 1159 }, { "epoch": 2.5369054127938764, "grad_norm": 1.285668134689331, "learning_rate": 8.596918085969182e-06, "loss": 0.8012, "step": 1160 }, { "epoch": 2.5390924002186988, "grad_norm": 0.9487924575805664, "learning_rate": 8.556366585563667e-06, "loss": 0.8058, "step": 1161 }, { "epoch": 2.541279387643521, "grad_norm": 1.962924599647522, "learning_rate": 8.51581508515815e-06, "loss": 0.6743, "step": 1162 }, { "epoch": 2.5434663750683435, "grad_norm": 1.5893644094467163, "learning_rate": 8.475263584752636e-06, "loss": 0.732, "step": 1163 }, { "epoch": 2.545653362493166, "grad_norm": 1.3191111087799072, "learning_rate": 8.434712084347121e-06, "loss": 0.757, "step": 1164 }, { "epoch": 2.547840349917988, "grad_norm": 1.6765128374099731, "learning_rate": 8.394160583941606e-06, "loss": 0.6917, "step": 1165 }, { "epoch": 2.55002733734281, "grad_norm": 0.8606542348861694, "learning_rate": 8.353609083536092e-06, "loss": 0.4919, "step": 1166 }, { "epoch": 2.5522143247676325, "grad_norm": 1.1297454833984375, "learning_rate": 8.313057583130577e-06, "loss": 0.7874, "step": 1167 }, { "epoch": 2.554401312192455, "grad_norm": 0.9808480143547058, "learning_rate": 8.27250608272506e-06, "loss": 0.6416, "step": 1168 }, { "epoch": 2.5565882996172773, "grad_norm": 1.7476130723953247, "learning_rate": 8.231954582319546e-06, "loss": 0.5674, "step": 1169 }, { "epoch": 2.5587752870420997, "grad_norm": 1.5865588188171387, "learning_rate": 8.191403081914031e-06, "loss": 0.6575, "step": 1170 }, { "epoch": 2.560962274466922, "grad_norm": 1.5678445100784302, "learning_rate": 8.150851581508516e-06, "loss": 0.6032, "step": 1171 }, { "epoch": 2.563149261891744, "grad_norm": 1.0644606351852417, "learning_rate": 8.110300081103e-06, "loss": 0.6996, "step": 1172 }, { "epoch": 2.5653362493165663, "grad_norm": 1.4271342754364014, "learning_rate": 8.069748580697487e-06, "loss": 0.5325, "step": 1173 }, { "epoch": 2.5675232367413887, "grad_norm": 0.7317719459533691, "learning_rate": 8.02919708029197e-06, "loss": 0.7079, "step": 1174 }, { "epoch": 2.569710224166211, "grad_norm": 1.4712001085281372, "learning_rate": 7.988645579886455e-06, "loss": 0.5507, "step": 1175 }, { "epoch": 2.5718972115910335, "grad_norm": 2.0776877403259277, "learning_rate": 7.948094079480941e-06, "loss": 0.8082, "step": 1176 }, { "epoch": 2.5740841990158554, "grad_norm": 0.834148108959198, "learning_rate": 7.907542579075426e-06, "loss": 0.8303, "step": 1177 }, { "epoch": 2.576271186440678, "grad_norm": 0.935935378074646, "learning_rate": 7.866991078669911e-06, "loss": 0.6032, "step": 1178 }, { "epoch": 2.5784581738655, "grad_norm": 1.3817602396011353, "learning_rate": 7.826439578264397e-06, "loss": 1.1109, "step": 1179 }, { "epoch": 2.5806451612903225, "grad_norm": 1.3290483951568604, "learning_rate": 7.78588807785888e-06, "loss": 0.7985, "step": 1180 }, { "epoch": 2.582832148715145, "grad_norm": 1.4025375843048096, "learning_rate": 7.745336577453365e-06, "loss": 0.6804, "step": 1181 }, { "epoch": 2.5850191361399673, "grad_norm": 1.6154764890670776, "learning_rate": 7.70478507704785e-06, "loss": 0.9247, "step": 1182 }, { "epoch": 2.5872061235647896, "grad_norm": 0.9209964871406555, "learning_rate": 7.664233576642336e-06, "loss": 0.602, "step": 1183 }, { "epoch": 2.5893931109896116, "grad_norm": 0.9985991716384888, "learning_rate": 7.623682076236821e-06, "loss": 0.7428, "step": 1184 }, { "epoch": 2.5915800984144344, "grad_norm": 1.3727548122406006, "learning_rate": 7.583130575831306e-06, "loss": 0.5911, "step": 1185 }, { "epoch": 2.5937670858392563, "grad_norm": 1.1715668439865112, "learning_rate": 7.542579075425792e-06, "loss": 0.6955, "step": 1186 }, { "epoch": 2.5959540732640787, "grad_norm": 1.1449137926101685, "learning_rate": 7.502027575020276e-06, "loss": 0.6468, "step": 1187 }, { "epoch": 2.598141060688901, "grad_norm": 1.518968105316162, "learning_rate": 7.461476074614761e-06, "loss": 0.6448, "step": 1188 }, { "epoch": 2.6003280481137234, "grad_norm": 1.1887353658676147, "learning_rate": 7.420924574209247e-06, "loss": 0.6392, "step": 1189 }, { "epoch": 2.602515035538546, "grad_norm": 1.987765908241272, "learning_rate": 7.3803730738037315e-06, "loss": 0.7237, "step": 1190 }, { "epoch": 2.6047020229633677, "grad_norm": 2.0195271968841553, "learning_rate": 7.339821573398216e-06, "loss": 0.6331, "step": 1191 }, { "epoch": 2.6068890103881905, "grad_norm": 1.7075891494750977, "learning_rate": 7.2992700729927e-06, "loss": 0.8811, "step": 1192 }, { "epoch": 2.6090759978130125, "grad_norm": 1.7577861547470093, "learning_rate": 7.258718572587187e-06, "loss": 0.6796, "step": 1193 }, { "epoch": 2.611262985237835, "grad_norm": 0.8261253237724304, "learning_rate": 7.218167072181671e-06, "loss": 0.6123, "step": 1194 }, { "epoch": 2.613449972662657, "grad_norm": 1.6505314111709595, "learning_rate": 7.177615571776155e-06, "loss": 0.6162, "step": 1195 }, { "epoch": 2.6156369600874796, "grad_norm": 1.2743268013000488, "learning_rate": 7.137064071370642e-06, "loss": 0.7719, "step": 1196 }, { "epoch": 2.617823947512302, "grad_norm": 1.1997958421707153, "learning_rate": 7.0965125709651265e-06, "loss": 0.7985, "step": 1197 }, { "epoch": 2.620010934937124, "grad_norm": 0.9850471615791321, "learning_rate": 7.05596107055961e-06, "loss": 0.7646, "step": 1198 }, { "epoch": 2.6221979223619463, "grad_norm": 0.9918181896209717, "learning_rate": 7.015409570154097e-06, "loss": 0.74, "step": 1199 }, { "epoch": 2.6243849097867686, "grad_norm": 1.184875249862671, "learning_rate": 6.974858069748582e-06, "loss": 0.6079, "step": 1200 }, { "epoch": 2.626571897211591, "grad_norm": 0.747799277305603, "learning_rate": 6.9343065693430655e-06, "loss": 0.47, "step": 1201 }, { "epoch": 2.6287588846364134, "grad_norm": 0.8698580861091614, "learning_rate": 6.89375506893755e-06, "loss": 0.7049, "step": 1202 }, { "epoch": 2.6309458720612358, "grad_norm": 1.31757390499115, "learning_rate": 6.853203568532037e-06, "loss": 1.1575, "step": 1203 }, { "epoch": 2.633132859486058, "grad_norm": 1.073734164237976, "learning_rate": 6.812652068126521e-06, "loss": 0.7261, "step": 1204 }, { "epoch": 2.63531984691088, "grad_norm": 3.056334972381592, "learning_rate": 6.7721005677210054e-06, "loss": 0.7923, "step": 1205 }, { "epoch": 2.6375068343357024, "grad_norm": 1.3995060920715332, "learning_rate": 6.731549067315492e-06, "loss": 0.7147, "step": 1206 }, { "epoch": 2.639693821760525, "grad_norm": 1.315277338027954, "learning_rate": 6.690997566909976e-06, "loss": 0.9269, "step": 1207 }, { "epoch": 2.641880809185347, "grad_norm": 1.2155823707580566, "learning_rate": 6.6504460665044606e-06, "loss": 0.793, "step": 1208 }, { "epoch": 2.6440677966101696, "grad_norm": 1.6471173763275146, "learning_rate": 6.609894566098945e-06, "loss": 0.6609, "step": 1209 }, { "epoch": 2.646254784034992, "grad_norm": 1.2644174098968506, "learning_rate": 6.569343065693431e-06, "loss": 0.8443, "step": 1210 }, { "epoch": 2.6484417714598143, "grad_norm": 2.067613363265991, "learning_rate": 6.528791565287916e-06, "loss": 0.7755, "step": 1211 }, { "epoch": 2.6506287588846362, "grad_norm": 1.1052587032318115, "learning_rate": 6.4882400648824004e-06, "loss": 0.819, "step": 1212 }, { "epoch": 2.6528157463094586, "grad_norm": 1.3607964515686035, "learning_rate": 6.447688564476886e-06, "loss": 0.6769, "step": 1213 }, { "epoch": 2.655002733734281, "grad_norm": 1.373448371887207, "learning_rate": 6.407137064071371e-06, "loss": 0.7452, "step": 1214 }, { "epoch": 2.6571897211591033, "grad_norm": 1.0746222734451294, "learning_rate": 6.3665855636658556e-06, "loss": 0.6933, "step": 1215 }, { "epoch": 2.6593767085839257, "grad_norm": 1.6520344018936157, "learning_rate": 6.326034063260341e-06, "loss": 0.7616, "step": 1216 }, { "epoch": 2.661563696008748, "grad_norm": 2.020744562149048, "learning_rate": 6.285482562854826e-06, "loss": 0.8534, "step": 1217 }, { "epoch": 2.6637506834335705, "grad_norm": 2.13696551322937, "learning_rate": 6.244931062449311e-06, "loss": 0.9319, "step": 1218 }, { "epoch": 2.6659376708583924, "grad_norm": 1.0201656818389893, "learning_rate": 6.204379562043796e-06, "loss": 1.1087, "step": 1219 }, { "epoch": 2.6681246582832148, "grad_norm": 1.3194042444229126, "learning_rate": 6.163828061638281e-06, "loss": 0.6483, "step": 1220 }, { "epoch": 2.670311645708037, "grad_norm": 1.2643121480941772, "learning_rate": 6.123276561232766e-06, "loss": 0.8157, "step": 1221 }, { "epoch": 2.6724986331328595, "grad_norm": 0.9495997428894043, "learning_rate": 6.082725060827251e-06, "loss": 0.9106, "step": 1222 }, { "epoch": 2.674685620557682, "grad_norm": 2.122220039367676, "learning_rate": 6.042173560421735e-06, "loss": 0.823, "step": 1223 }, { "epoch": 2.6768726079825043, "grad_norm": 1.246187448501587, "learning_rate": 6.001622060016221e-06, "loss": 0.9167, "step": 1224 }, { "epoch": 2.6790595954073266, "grad_norm": 1.6039838790893555, "learning_rate": 5.961070559610706e-06, "loss": 0.6992, "step": 1225 }, { "epoch": 2.6812465828321486, "grad_norm": 1.3627378940582275, "learning_rate": 5.9205190592051904e-06, "loss": 0.9277, "step": 1226 }, { "epoch": 2.683433570256971, "grad_norm": 1.1532552242279053, "learning_rate": 5.879967558799676e-06, "loss": 0.8799, "step": 1227 }, { "epoch": 2.6856205576817933, "grad_norm": 1.6292390823364258, "learning_rate": 5.839416058394161e-06, "loss": 0.555, "step": 1228 }, { "epoch": 2.6878075451066157, "grad_norm": 0.8081088066101074, "learning_rate": 5.7988645579886456e-06, "loss": 0.7031, "step": 1229 }, { "epoch": 2.689994532531438, "grad_norm": 1.0862112045288086, "learning_rate": 5.75831305758313e-06, "loss": 0.8586, "step": 1230 }, { "epoch": 2.69218151995626, "grad_norm": 1.0101604461669922, "learning_rate": 5.717761557177616e-06, "loss": 0.6754, "step": 1231 }, { "epoch": 2.694368507381083, "grad_norm": 1.7337979078292847, "learning_rate": 5.677210056772101e-06, "loss": 0.7249, "step": 1232 }, { "epoch": 2.6965554948059047, "grad_norm": 3.222620964050293, "learning_rate": 5.6366585563665855e-06, "loss": 0.9878, "step": 1233 }, { "epoch": 2.698742482230727, "grad_norm": 0.990831196308136, "learning_rate": 5.596107055961071e-06, "loss": 0.5517, "step": 1234 }, { "epoch": 2.7009294696555495, "grad_norm": 1.229943871498108, "learning_rate": 5.555555555555556e-06, "loss": 0.5837, "step": 1235 }, { "epoch": 2.703116457080372, "grad_norm": 1.966077208518982, "learning_rate": 5.515004055150041e-06, "loss": 0.8195, "step": 1236 }, { "epoch": 2.705303444505194, "grad_norm": 2.1930038928985596, "learning_rate": 5.474452554744526e-06, "loss": 0.7067, "step": 1237 }, { "epoch": 2.707490431930016, "grad_norm": 1.3722200393676758, "learning_rate": 5.433901054339011e-06, "loss": 0.7491, "step": 1238 }, { "epoch": 2.709677419354839, "grad_norm": 1.1802952289581299, "learning_rate": 5.393349553933496e-06, "loss": 0.7507, "step": 1239 }, { "epoch": 2.711864406779661, "grad_norm": 1.0628564357757568, "learning_rate": 5.3527980535279805e-06, "loss": 0.833, "step": 1240 }, { "epoch": 2.7140513942044833, "grad_norm": 0.8905409574508667, "learning_rate": 5.312246553122466e-06, "loss": 0.5444, "step": 1241 }, { "epoch": 2.7162383816293056, "grad_norm": 1.3018263578414917, "learning_rate": 5.271695052716951e-06, "loss": 0.5773, "step": 1242 }, { "epoch": 2.718425369054128, "grad_norm": 1.2983074188232422, "learning_rate": 5.231143552311436e-06, "loss": 1.0523, "step": 1243 }, { "epoch": 2.7206123564789504, "grad_norm": 2.03822922706604, "learning_rate": 5.190592051905921e-06, "loss": 0.7046, "step": 1244 }, { "epoch": 2.7227993439037723, "grad_norm": 1.4151402711868286, "learning_rate": 5.150040551500405e-06, "loss": 0.8315, "step": 1245 }, { "epoch": 2.724986331328595, "grad_norm": 1.2823673486709595, "learning_rate": 5.109489051094891e-06, "loss": 0.7391, "step": 1246 }, { "epoch": 2.727173318753417, "grad_norm": 1.9715447425842285, "learning_rate": 5.068937550689376e-06, "loss": 0.6516, "step": 1247 }, { "epoch": 2.7293603061782394, "grad_norm": 0.5390704870223999, "learning_rate": 5.02838605028386e-06, "loss": 0.5166, "step": 1248 }, { "epoch": 2.731547293603062, "grad_norm": 2.403184175491333, "learning_rate": 4.987834549878346e-06, "loss": 0.9255, "step": 1249 }, { "epoch": 2.733734281027884, "grad_norm": 1.357041358947754, "learning_rate": 4.947283049472831e-06, "loss": 0.652, "step": 1250 }, { "epoch": 2.7359212684527066, "grad_norm": 1.5450878143310547, "learning_rate": 4.906731549067315e-06, "loss": 0.9002, "step": 1251 }, { "epoch": 2.7381082558775285, "grad_norm": 1.0977497100830078, "learning_rate": 4.866180048661801e-06, "loss": 0.6023, "step": 1252 }, { "epoch": 2.740295243302351, "grad_norm": 1.8691314458847046, "learning_rate": 4.825628548256286e-06, "loss": 0.6907, "step": 1253 }, { "epoch": 2.7424822307271732, "grad_norm": 0.7539710402488708, "learning_rate": 4.7850770478507705e-06, "loss": 0.9338, "step": 1254 }, { "epoch": 2.7446692181519956, "grad_norm": 1.1119807958602905, "learning_rate": 4.744525547445255e-06, "loss": 0.8023, "step": 1255 }, { "epoch": 2.746856205576818, "grad_norm": 2.4212183952331543, "learning_rate": 4.703974047039741e-06, "loss": 1.0262, "step": 1256 }, { "epoch": 2.7490431930016404, "grad_norm": 2.3209235668182373, "learning_rate": 4.663422546634226e-06, "loss": 0.5783, "step": 1257 }, { "epoch": 2.7512301804264627, "grad_norm": 1.485458493232727, "learning_rate": 4.62287104622871e-06, "loss": 0.7239, "step": 1258 }, { "epoch": 2.7534171678512847, "grad_norm": 1.9166754484176636, "learning_rate": 4.582319545823196e-06, "loss": 0.9013, "step": 1259 }, { "epoch": 2.755604155276107, "grad_norm": 1.2489042282104492, "learning_rate": 4.541768045417681e-06, "loss": 0.7683, "step": 1260 }, { "epoch": 2.7577911427009294, "grad_norm": 0.9307185411453247, "learning_rate": 4.5012165450121655e-06, "loss": 0.8394, "step": 1261 }, { "epoch": 2.7599781301257518, "grad_norm": 1.6403664350509644, "learning_rate": 4.460665044606651e-06, "loss": 1.0257, "step": 1262 }, { "epoch": 2.762165117550574, "grad_norm": 2.0175230503082275, "learning_rate": 4.420113544201136e-06, "loss": 0.8693, "step": 1263 }, { "epoch": 2.7643521049753965, "grad_norm": 1.6045912504196167, "learning_rate": 4.379562043795621e-06, "loss": 0.6816, "step": 1264 }, { "epoch": 2.766539092400219, "grad_norm": 1.3528201580047607, "learning_rate": 4.339010543390105e-06, "loss": 0.6261, "step": 1265 }, { "epoch": 2.768726079825041, "grad_norm": 1.2912421226501465, "learning_rate": 4.298459042984591e-06, "loss": 0.9108, "step": 1266 }, { "epoch": 2.770913067249863, "grad_norm": 1.2495743036270142, "learning_rate": 4.257907542579075e-06, "loss": 0.7049, "step": 1267 }, { "epoch": 2.7731000546746856, "grad_norm": 1.164976716041565, "learning_rate": 4.2173560421735605e-06, "loss": 0.7344, "step": 1268 }, { "epoch": 2.775287042099508, "grad_norm": 0.5846396684646606, "learning_rate": 4.176804541768046e-06, "loss": 0.7629, "step": 1269 }, { "epoch": 2.7774740295243303, "grad_norm": 1.0745964050292969, "learning_rate": 4.13625304136253e-06, "loss": 0.7751, "step": 1270 }, { "epoch": 2.7796610169491527, "grad_norm": 1.6087266206741333, "learning_rate": 4.095701540957016e-06, "loss": 0.9041, "step": 1271 }, { "epoch": 2.781848004373975, "grad_norm": 1.6926146745681763, "learning_rate": 4.0551500405515e-06, "loss": 0.866, "step": 1272 }, { "epoch": 2.784034991798797, "grad_norm": 1.4971140623092651, "learning_rate": 4.014598540145985e-06, "loss": 0.8946, "step": 1273 }, { "epoch": 2.7862219792236194, "grad_norm": 1.528369426727295, "learning_rate": 3.974047039740471e-06, "loss": 0.7981, "step": 1274 }, { "epoch": 2.7884089666484417, "grad_norm": 1.1017677783966064, "learning_rate": 3.9334955393349555e-06, "loss": 0.8033, "step": 1275 }, { "epoch": 2.790595954073264, "grad_norm": 1.0705029964447021, "learning_rate": 3.89294403892944e-06, "loss": 0.6479, "step": 1276 }, { "epoch": 2.7927829414980865, "grad_norm": 1.1367233991622925, "learning_rate": 3.852392538523925e-06, "loss": 0.6373, "step": 1277 }, { "epoch": 2.794969928922909, "grad_norm": 1.3972508907318115, "learning_rate": 3.8118410381184106e-06, "loss": 0.956, "step": 1278 }, { "epoch": 2.7971569163477312, "grad_norm": 1.1225905418395996, "learning_rate": 3.771289537712896e-06, "loss": 0.5382, "step": 1279 }, { "epoch": 2.799343903772553, "grad_norm": 1.1100654602050781, "learning_rate": 3.7307380373073806e-06, "loss": 0.9511, "step": 1280 }, { "epoch": 2.8015308911973755, "grad_norm": 1.1963266134262085, "learning_rate": 3.6901865369018657e-06, "loss": 0.8244, "step": 1281 }, { "epoch": 2.803717878622198, "grad_norm": 0.8933132290840149, "learning_rate": 3.64963503649635e-06, "loss": 0.697, "step": 1282 }, { "epoch": 2.8059048660470203, "grad_norm": 1.0875051021575928, "learning_rate": 3.6090835360908357e-06, "loss": 0.6961, "step": 1283 }, { "epoch": 2.8080918534718426, "grad_norm": 3.6406803131103516, "learning_rate": 3.568532035685321e-06, "loss": 0.9963, "step": 1284 }, { "epoch": 2.8102788408966646, "grad_norm": 1.3587076663970947, "learning_rate": 3.527980535279805e-06, "loss": 0.749, "step": 1285 }, { "epoch": 2.8124658283214874, "grad_norm": 1.889060378074646, "learning_rate": 3.487429034874291e-06, "loss": 0.5931, "step": 1286 }, { "epoch": 2.8146528157463093, "grad_norm": 1.1032036542892456, "learning_rate": 3.446877534468775e-06, "loss": 1.0975, "step": 1287 }, { "epoch": 2.8168398031711317, "grad_norm": 1.7494933605194092, "learning_rate": 3.4063260340632603e-06, "loss": 0.7591, "step": 1288 }, { "epoch": 2.819026790595954, "grad_norm": 1.0387543439865112, "learning_rate": 3.365774533657746e-06, "loss": 0.6726, "step": 1289 }, { "epoch": 2.8212137780207764, "grad_norm": 0.7574595808982849, "learning_rate": 3.3252230332522303e-06, "loss": 0.6856, "step": 1290 }, { "epoch": 2.823400765445599, "grad_norm": 0.7481341361999512, "learning_rate": 3.2846715328467155e-06, "loss": 0.5178, "step": 1291 }, { "epoch": 2.8255877528704207, "grad_norm": 1.4169808626174927, "learning_rate": 3.2441200324412002e-06, "loss": 0.7515, "step": 1292 }, { "epoch": 2.8277747402952436, "grad_norm": 1.1583516597747803, "learning_rate": 3.2035685320356854e-06, "loss": 0.6437, "step": 1293 }, { "epoch": 2.8299617277200655, "grad_norm": 1.2981252670288086, "learning_rate": 3.1630170316301706e-06, "loss": 0.7318, "step": 1294 }, { "epoch": 2.832148715144888, "grad_norm": 1.5253961086273193, "learning_rate": 3.1224655312246553e-06, "loss": 0.7149, "step": 1295 }, { "epoch": 2.8343357025697102, "grad_norm": 0.8095445036888123, "learning_rate": 3.0819140308191405e-06, "loss": 0.8373, "step": 1296 }, { "epoch": 2.8365226899945326, "grad_norm": 0.9438583850860596, "learning_rate": 3.0413625304136257e-06, "loss": 0.5719, "step": 1297 }, { "epoch": 2.838709677419355, "grad_norm": 1.5693120956420898, "learning_rate": 3.0008110300081105e-06, "loss": 0.5576, "step": 1298 }, { "epoch": 2.840896664844177, "grad_norm": 1.9088305234909058, "learning_rate": 2.9602595296025952e-06, "loss": 0.8535, "step": 1299 }, { "epoch": 2.8430836522689997, "grad_norm": 1.5087040662765503, "learning_rate": 2.9197080291970804e-06, "loss": 0.9079, "step": 1300 }, { "epoch": 2.8452706396938217, "grad_norm": 1.2334426641464233, "learning_rate": 2.879156528791565e-06, "loss": 0.7624, "step": 1301 }, { "epoch": 2.847457627118644, "grad_norm": 1.4639253616333008, "learning_rate": 2.8386050283860503e-06, "loss": 1.0354, "step": 1302 }, { "epoch": 2.8496446145434664, "grad_norm": 1.3180317878723145, "learning_rate": 2.7980535279805355e-06, "loss": 0.6799, "step": 1303 }, { "epoch": 2.8518316019682888, "grad_norm": 1.5624186992645264, "learning_rate": 2.7575020275750203e-06, "loss": 0.7484, "step": 1304 }, { "epoch": 2.854018589393111, "grad_norm": 1.1304352283477783, "learning_rate": 2.7169505271695055e-06, "loss": 0.578, "step": 1305 }, { "epoch": 2.856205576817933, "grad_norm": 1.1317391395568848, "learning_rate": 2.6763990267639902e-06, "loss": 0.8303, "step": 1306 }, { "epoch": 2.8583925642427555, "grad_norm": 2.2583820819854736, "learning_rate": 2.6358475263584754e-06, "loss": 0.8581, "step": 1307 }, { "epoch": 2.860579551667578, "grad_norm": 1.2871750593185425, "learning_rate": 2.5952960259529606e-06, "loss": 0.6671, "step": 1308 }, { "epoch": 2.8627665390924, "grad_norm": 2.4534285068511963, "learning_rate": 2.5547445255474454e-06, "loss": 0.8793, "step": 1309 }, { "epoch": 2.8649535265172226, "grad_norm": 1.0103739500045776, "learning_rate": 2.51419302514193e-06, "loss": 0.8261, "step": 1310 }, { "epoch": 2.867140513942045, "grad_norm": 0.8739585280418396, "learning_rate": 2.4736415247364153e-06, "loss": 0.516, "step": 1311 }, { "epoch": 2.8693275013668673, "grad_norm": 1.5831140279769897, "learning_rate": 2.4330900243309005e-06, "loss": 1.0191, "step": 1312 }, { "epoch": 2.8715144887916892, "grad_norm": 0.8464304208755493, "learning_rate": 2.3925385239253852e-06, "loss": 0.6408, "step": 1313 }, { "epoch": 2.8737014762165116, "grad_norm": 1.1309232711791992, "learning_rate": 2.3519870235198704e-06, "loss": 0.5183, "step": 1314 }, { "epoch": 2.875888463641334, "grad_norm": 0.981147825717926, "learning_rate": 2.311435523114355e-06, "loss": 0.7185, "step": 1315 }, { "epoch": 2.8780754510661564, "grad_norm": 1.0053104162216187, "learning_rate": 2.2708840227088404e-06, "loss": 0.7439, "step": 1316 }, { "epoch": 2.8802624384909787, "grad_norm": 1.4941085577011108, "learning_rate": 2.2303325223033255e-06, "loss": 0.7645, "step": 1317 }, { "epoch": 2.882449425915801, "grad_norm": 0.9878971576690674, "learning_rate": 2.1897810218978103e-06, "loss": 0.5394, "step": 1318 }, { "epoch": 2.8846364133406235, "grad_norm": 1.3839359283447266, "learning_rate": 2.1492295214922955e-06, "loss": 0.8252, "step": 1319 }, { "epoch": 2.8868234007654454, "grad_norm": 1.739042043685913, "learning_rate": 2.1086780210867802e-06, "loss": 0.6861, "step": 1320 }, { "epoch": 2.889010388190268, "grad_norm": 1.760859489440918, "learning_rate": 2.068126520681265e-06, "loss": 0.7873, "step": 1321 }, { "epoch": 2.89119737561509, "grad_norm": 1.633622407913208, "learning_rate": 2.02757502027575e-06, "loss": 0.7694, "step": 1322 }, { "epoch": 2.8933843630399125, "grad_norm": 1.2996716499328613, "learning_rate": 1.9870235198702354e-06, "loss": 0.7011, "step": 1323 }, { "epoch": 2.895571350464735, "grad_norm": 2.004753589630127, "learning_rate": 1.94647201946472e-06, "loss": 0.6315, "step": 1324 }, { "epoch": 2.8977583378895573, "grad_norm": 1.4992320537567139, "learning_rate": 1.9059205190592053e-06, "loss": 0.7739, "step": 1325 }, { "epoch": 2.8999453253143797, "grad_norm": 0.8833658695220947, "learning_rate": 1.8653690186536903e-06, "loss": 0.8292, "step": 1326 }, { "epoch": 2.9021323127392016, "grad_norm": 1.486072063446045, "learning_rate": 1.824817518248175e-06, "loss": 0.4882, "step": 1327 }, { "epoch": 2.904319300164024, "grad_norm": 1.8136156797409058, "learning_rate": 1.7842660178426604e-06, "loss": 0.7029, "step": 1328 }, { "epoch": 2.9065062875888463, "grad_norm": 1.1018986701965332, "learning_rate": 1.7437145174371454e-06, "loss": 0.5832, "step": 1329 }, { "epoch": 2.9086932750136687, "grad_norm": 0.8620420694351196, "learning_rate": 1.7031630170316302e-06, "loss": 0.5729, "step": 1330 }, { "epoch": 2.910880262438491, "grad_norm": 0.9364961981773376, "learning_rate": 1.6626115166261151e-06, "loss": 0.4688, "step": 1331 }, { "epoch": 2.9130672498633134, "grad_norm": 0.991184651851654, "learning_rate": 1.6220600162206001e-06, "loss": 0.717, "step": 1332 }, { "epoch": 2.915254237288136, "grad_norm": 1.932542085647583, "learning_rate": 1.5815085158150853e-06, "loss": 0.9159, "step": 1333 }, { "epoch": 2.9174412247129577, "grad_norm": 0.8263562321662903, "learning_rate": 1.5409570154095703e-06, "loss": 0.7923, "step": 1334 }, { "epoch": 2.91962821213778, "grad_norm": 1.7953425645828247, "learning_rate": 1.5004055150040552e-06, "loss": 0.7362, "step": 1335 }, { "epoch": 2.9218151995626025, "grad_norm": 1.7761998176574707, "learning_rate": 1.4598540145985402e-06, "loss": 0.9918, "step": 1336 }, { "epoch": 2.924002186987425, "grad_norm": 1.0605494976043701, "learning_rate": 1.4193025141930252e-06, "loss": 0.7578, "step": 1337 }, { "epoch": 2.9261891744122472, "grad_norm": 1.2843929529190063, "learning_rate": 1.3787510137875101e-06, "loss": 0.8904, "step": 1338 }, { "epoch": 2.928376161837069, "grad_norm": 1.6330130100250244, "learning_rate": 1.3381995133819951e-06, "loss": 0.6705, "step": 1339 }, { "epoch": 2.930563149261892, "grad_norm": 1.0138980150222778, "learning_rate": 1.2976480129764803e-06, "loss": 0.8128, "step": 1340 }, { "epoch": 2.932750136686714, "grad_norm": 1.7197630405426025, "learning_rate": 1.257096512570965e-06, "loss": 0.7128, "step": 1341 }, { "epoch": 2.9349371241115363, "grad_norm": 1.0136772394180298, "learning_rate": 1.2165450121654502e-06, "loss": 0.9328, "step": 1342 }, { "epoch": 2.9371241115363587, "grad_norm": 1.1689707040786743, "learning_rate": 1.1759935117599352e-06, "loss": 1.0574, "step": 1343 }, { "epoch": 2.939311098961181, "grad_norm": 1.2898248434066772, "learning_rate": 1.1354420113544202e-06, "loss": 1.0475, "step": 1344 }, { "epoch": 2.9414980863860034, "grad_norm": 0.9986676573753357, "learning_rate": 1.0948905109489052e-06, "loss": 0.8364, "step": 1345 }, { "epoch": 2.9436850738108253, "grad_norm": 1.2313567399978638, "learning_rate": 1.0543390105433901e-06, "loss": 0.694, "step": 1346 }, { "epoch": 2.945872061235648, "grad_norm": 1.4028866291046143, "learning_rate": 1.013787510137875e-06, "loss": 0.7367, "step": 1347 }, { "epoch": 2.94805904866047, "grad_norm": 1.0225236415863037, "learning_rate": 9.7323600973236e-07, "loss": 0.7185, "step": 1348 }, { "epoch": 2.9502460360852925, "grad_norm": 1.0077977180480957, "learning_rate": 9.326845093268451e-07, "loss": 0.7411, "step": 1349 }, { "epoch": 2.952433023510115, "grad_norm": 0.8722079396247864, "learning_rate": 8.921330089213302e-07, "loss": 0.4894, "step": 1350 }, { "epoch": 2.954620010934937, "grad_norm": 0.9436647295951843, "learning_rate": 8.515815085158151e-07, "loss": 0.5427, "step": 1351 }, { "epoch": 2.9568069983597596, "grad_norm": 1.4931648969650269, "learning_rate": 8.110300081103001e-07, "loss": 0.7468, "step": 1352 }, { "epoch": 2.9589939857845815, "grad_norm": 1.5878164768218994, "learning_rate": 7.704785077047851e-07, "loss": 1.1852, "step": 1353 }, { "epoch": 2.9611809732094043, "grad_norm": 1.8645153045654297, "learning_rate": 7.299270072992701e-07, "loss": 0.725, "step": 1354 }, { "epoch": 2.9633679606342263, "grad_norm": 0.9318771958351135, "learning_rate": 6.893755068937551e-07, "loss": 0.6059, "step": 1355 }, { "epoch": 2.9655549480590486, "grad_norm": 1.4928923845291138, "learning_rate": 6.488240064882401e-07, "loss": 0.9129, "step": 1356 }, { "epoch": 2.967741935483871, "grad_norm": 1.182731032371521, "learning_rate": 6.082725060827251e-07, "loss": 0.6933, "step": 1357 }, { "epoch": 2.9699289229086934, "grad_norm": 1.1260507106781006, "learning_rate": 5.677210056772101e-07, "loss": 0.7652, "step": 1358 }, { "epoch": 2.9721159103335157, "grad_norm": 1.2366056442260742, "learning_rate": 5.271695052716951e-07, "loss": 0.8477, "step": 1359 }, { "epoch": 2.9743028977583377, "grad_norm": 1.0487123727798462, "learning_rate": 4.8661800486618e-07, "loss": 0.6123, "step": 1360 }, { "epoch": 2.97648988518316, "grad_norm": 0.8265807628631592, "learning_rate": 4.460665044606651e-07, "loss": 0.6602, "step": 1361 }, { "epoch": 2.9786768726079824, "grad_norm": 1.92697274684906, "learning_rate": 4.0551500405515003e-07, "loss": 0.6551, "step": 1362 }, { "epoch": 2.980863860032805, "grad_norm": 1.2632496356964111, "learning_rate": 3.6496350364963505e-07, "loss": 0.7511, "step": 1363 }, { "epoch": 2.983050847457627, "grad_norm": 1.58042573928833, "learning_rate": 3.244120032441201e-07, "loss": 0.9974, "step": 1364 }, { "epoch": 2.9852378348824495, "grad_norm": 2.2959277629852295, "learning_rate": 2.8386050283860505e-07, "loss": 0.8596, "step": 1365 }, { "epoch": 2.987424822307272, "grad_norm": 0.9238201379776001, "learning_rate": 2.4330900243309e-07, "loss": 0.6042, "step": 1366 }, { "epoch": 2.989611809732094, "grad_norm": 1.2317500114440918, "learning_rate": 2.0275750202757501e-07, "loss": 0.8345, "step": 1367 }, { "epoch": 2.991798797156916, "grad_norm": 1.560782790184021, "learning_rate": 1.6220600162206004e-07, "loss": 0.5039, "step": 1368 }, { "epoch": 2.9939857845817386, "grad_norm": 1.7069331407546997, "learning_rate": 1.21654501216545e-07, "loss": 0.874, "step": 1369 }, { "epoch": 2.996172772006561, "grad_norm": 1.180812954902649, "learning_rate": 8.110300081103002e-08, "loss": 0.7128, "step": 1370 }, { "epoch": 2.9983597594313833, "grad_norm": 1.5445131063461304, "learning_rate": 4.055150040551501e-08, "loss": 0.6125, "step": 1371 }, { "epoch": 2.9983597594313833, "step": 1371, "total_flos": 4.319734516542341e+17, "train_loss": 0.9727319801140666, "train_runtime": 17359.298, "train_samples_per_second": 1.264, "train_steps_per_second": 0.079 } ], "logging_steps": 1.0, "max_steps": 1371, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.319734516542341e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }