lmg-anon's picture
Upload folder using huggingface_hub
63215f7 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7045088566827697,
"eval_steps": 500,
"global_step": 350,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002012882447665056,
"grad_norm": 22.921390533447266,
"learning_rate": 6.5e-06,
"loss": 1.3427,
"step": 1
},
{
"epoch": 0.004025764895330112,
"grad_norm": 14.772722244262695,
"learning_rate": 1.3e-05,
"loss": 1.3647,
"step": 2
},
{
"epoch": 0.006038647342995169,
"grad_norm": 11.458742141723633,
"learning_rate": 1.9499999999999996e-05,
"loss": 1.2841,
"step": 3
},
{
"epoch": 0.008051529790660225,
"grad_norm": 4.747677326202393,
"learning_rate": 2.6e-05,
"loss": 1.1644,
"step": 4
},
{
"epoch": 0.010064412238325281,
"grad_norm": 3.687121629714966,
"learning_rate": 3.25e-05,
"loss": 1.1084,
"step": 5
},
{
"epoch": 0.012077294685990338,
"grad_norm": 3.178232431411743,
"learning_rate": 3.899999999999999e-05,
"loss": 1.0753,
"step": 6
},
{
"epoch": 0.014090177133655395,
"grad_norm": 2.476033926010132,
"learning_rate": 4.5499999999999995e-05,
"loss": 1.075,
"step": 7
},
{
"epoch": 0.01610305958132045,
"grad_norm": 1.9162139892578125,
"learning_rate": 5.2e-05,
"loss": 1.0195,
"step": 8
},
{
"epoch": 0.018115942028985508,
"grad_norm": 1.797377109527588,
"learning_rate": 5.85e-05,
"loss": 0.9884,
"step": 9
},
{
"epoch": 0.020128824476650563,
"grad_norm": 1.816100835800171,
"learning_rate": 6.5e-05,
"loss": 0.9945,
"step": 10
},
{
"epoch": 0.02214170692431562,
"grad_norm": 1.843664526939392,
"learning_rate": 6.499932098548219e-05,
"loss": 0.8802,
"step": 11
},
{
"epoch": 0.024154589371980676,
"grad_norm": 1.7202250957489014,
"learning_rate": 6.49972839703017e-05,
"loss": 0.9833,
"step": 12
},
{
"epoch": 0.026167471819645734,
"grad_norm": 1.4981484413146973,
"learning_rate": 6.499388903957628e-05,
"loss": 0.9481,
"step": 13
},
{
"epoch": 0.02818035426731079,
"grad_norm": 1.4716213941574097,
"learning_rate": 6.498913633516483e-05,
"loss": 0.8809,
"step": 14
},
{
"epoch": 0.030193236714975844,
"grad_norm": 1.3817026615142822,
"learning_rate": 6.498302605566152e-05,
"loss": 0.9264,
"step": 15
},
{
"epoch": 0.0322061191626409,
"grad_norm": 1.509097695350647,
"learning_rate": 6.497555845638748e-05,
"loss": 0.8829,
"step": 16
},
{
"epoch": 0.03421900161030596,
"grad_norm": 1.5498337745666504,
"learning_rate": 6.496673384938014e-05,
"loss": 0.9227,
"step": 17
},
{
"epoch": 0.036231884057971016,
"grad_norm": 1.527828574180603,
"learning_rate": 6.49565526033802e-05,
"loss": 0.9488,
"step": 18
},
{
"epoch": 0.038244766505636074,
"grad_norm": 1.4578592777252197,
"learning_rate": 6.494501514381621e-05,
"loss": 0.8845,
"step": 19
},
{
"epoch": 0.040257648953301126,
"grad_norm": 1.4198046922683716,
"learning_rate": 6.493212195278678e-05,
"loss": 0.8809,
"step": 20
},
{
"epoch": 0.042270531400966184,
"grad_norm": 1.4455400705337524,
"learning_rate": 6.491787356904047e-05,
"loss": 0.8686,
"step": 21
},
{
"epoch": 0.04428341384863124,
"grad_norm": 1.5711616277694702,
"learning_rate": 6.490227058795323e-05,
"loss": 0.96,
"step": 22
},
{
"epoch": 0.046296296296296294,
"grad_norm": 1.4603729248046875,
"learning_rate": 6.488531366150359e-05,
"loss": 0.9026,
"step": 23
},
{
"epoch": 0.04830917874396135,
"grad_norm": 1.4184608459472656,
"learning_rate": 6.48670034982453e-05,
"loss": 0.9426,
"step": 24
},
{
"epoch": 0.05032206119162641,
"grad_norm": 1.4080291986465454,
"learning_rate": 6.484734086327788e-05,
"loss": 0.8857,
"step": 25
},
{
"epoch": 0.05233494363929147,
"grad_norm": 1.4739091396331787,
"learning_rate": 6.482632657821454e-05,
"loss": 0.8897,
"step": 26
},
{
"epoch": 0.05434782608695652,
"grad_norm": 1.320746898651123,
"learning_rate": 6.480396152114787e-05,
"loss": 0.8512,
"step": 27
},
{
"epoch": 0.05636070853462158,
"grad_norm": 1.4142905473709106,
"learning_rate": 6.478024662661315e-05,
"loss": 0.9459,
"step": 28
},
{
"epoch": 0.05837359098228664,
"grad_norm": 1.3830432891845703,
"learning_rate": 6.47551828855493e-05,
"loss": 0.8605,
"step": 29
},
{
"epoch": 0.06038647342995169,
"grad_norm": 1.3653528690338135,
"learning_rate": 6.472877134525753e-05,
"loss": 0.8446,
"step": 30
},
{
"epoch": 0.06239935587761675,
"grad_norm": 1.3041807413101196,
"learning_rate": 6.470101310935746e-05,
"loss": 0.8407,
"step": 31
},
{
"epoch": 0.0644122383252818,
"grad_norm": 1.3803820610046387,
"learning_rate": 6.467190933774112e-05,
"loss": 0.8505,
"step": 32
},
{
"epoch": 0.06642512077294686,
"grad_norm": 1.3407087326049805,
"learning_rate": 6.464146124652441e-05,
"loss": 0.794,
"step": 33
},
{
"epoch": 0.06843800322061191,
"grad_norm": 1.4283268451690674,
"learning_rate": 6.460967010799629e-05,
"loss": 0.9139,
"step": 34
},
{
"epoch": 0.07045088566827697,
"grad_norm": 1.3512784242630005,
"learning_rate": 6.457653725056568e-05,
"loss": 0.807,
"step": 35
},
{
"epoch": 0.07246376811594203,
"grad_norm": 1.3088512420654297,
"learning_rate": 6.454206405870587e-05,
"loss": 0.8968,
"step": 36
},
{
"epoch": 0.07447665056360708,
"grad_norm": 1.2908034324645996,
"learning_rate": 6.450625197289675e-05,
"loss": 0.8447,
"step": 37
},
{
"epoch": 0.07648953301127215,
"grad_norm": 1.3444992303848267,
"learning_rate": 6.446910248956453e-05,
"loss": 0.8891,
"step": 38
},
{
"epoch": 0.0785024154589372,
"grad_norm": 1.2567275762557983,
"learning_rate": 6.443061716101926e-05,
"loss": 0.8134,
"step": 39
},
{
"epoch": 0.08051529790660225,
"grad_norm": 1.3401930332183838,
"learning_rate": 6.439079759539e-05,
"loss": 0.8751,
"step": 40
},
{
"epoch": 0.08252818035426732,
"grad_norm": 1.3348793983459473,
"learning_rate": 6.434964545655754e-05,
"loss": 0.7942,
"step": 41
},
{
"epoch": 0.08454106280193237,
"grad_norm": 1.311357021331787,
"learning_rate": 6.430716246408493e-05,
"loss": 0.8461,
"step": 42
},
{
"epoch": 0.08655394524959742,
"grad_norm": 1.3319345712661743,
"learning_rate": 6.426335039314566e-05,
"loss": 0.8821,
"step": 43
},
{
"epoch": 0.08856682769726248,
"grad_norm": 1.304795742034912,
"learning_rate": 6.421821107444936e-05,
"loss": 0.8655,
"step": 44
},
{
"epoch": 0.09057971014492754,
"grad_norm": 1.422869086265564,
"learning_rate": 6.417174639416547e-05,
"loss": 0.9261,
"step": 45
},
{
"epoch": 0.09259259259259259,
"grad_norm": 1.2931973934173584,
"learning_rate": 6.412395829384427e-05,
"loss": 0.8157,
"step": 46
},
{
"epoch": 0.09460547504025765,
"grad_norm": 1.2984646558761597,
"learning_rate": 6.407484877033586e-05,
"loss": 0.7919,
"step": 47
},
{
"epoch": 0.0966183574879227,
"grad_norm": 1.2596486806869507,
"learning_rate": 6.402441987570665e-05,
"loss": 0.7682,
"step": 48
},
{
"epoch": 0.09863123993558776,
"grad_norm": 1.3544796705245972,
"learning_rate": 6.397267371715368e-05,
"loss": 0.9084,
"step": 49
},
{
"epoch": 0.10064412238325282,
"grad_norm": 1.2623202800750732,
"learning_rate": 6.391961245691652e-05,
"loss": 0.8482,
"step": 50
},
{
"epoch": 0.10265700483091787,
"grad_norm": 1.320026159286499,
"learning_rate": 6.386523831218689e-05,
"loss": 0.8436,
"step": 51
},
{
"epoch": 0.10466988727858294,
"grad_norm": 1.4064967632293701,
"learning_rate": 6.38095535550161e-05,
"loss": 0.8962,
"step": 52
},
{
"epoch": 0.10668276972624799,
"grad_norm": 1.3178116083145142,
"learning_rate": 6.375256051222009e-05,
"loss": 0.8064,
"step": 53
},
{
"epoch": 0.10869565217391304,
"grad_norm": 1.2729371786117554,
"learning_rate": 6.369426156528213e-05,
"loss": 0.8338,
"step": 54
},
{
"epoch": 0.1107085346215781,
"grad_norm": 1.2167425155639648,
"learning_rate": 6.363465915025339e-05,
"loss": 0.8078,
"step": 55
},
{
"epoch": 0.11272141706924316,
"grad_norm": 1.3006845712661743,
"learning_rate": 6.357375575765108e-05,
"loss": 0.8462,
"step": 56
},
{
"epoch": 0.11473429951690821,
"grad_norm": 1.245822787284851,
"learning_rate": 6.351155393235449e-05,
"loss": 0.8394,
"step": 57
},
{
"epoch": 0.11674718196457327,
"grad_norm": 1.2608625888824463,
"learning_rate": 6.34480562734985e-05,
"loss": 0.8606,
"step": 58
},
{
"epoch": 0.11876006441223833,
"grad_norm": 1.2614774703979492,
"learning_rate": 6.33832654343651e-05,
"loss": 0.7633,
"step": 59
},
{
"epoch": 0.12077294685990338,
"grad_norm": 1.3382893800735474,
"learning_rate": 6.331718412227247e-05,
"loss": 0.8514,
"step": 60
},
{
"epoch": 0.12278582930756844,
"grad_norm": 1.2239303588867188,
"learning_rate": 6.324981509846189e-05,
"loss": 0.8319,
"step": 61
},
{
"epoch": 0.1247987117552335,
"grad_norm": 1.3828685283660889,
"learning_rate": 6.318116117798225e-05,
"loss": 0.8683,
"step": 62
},
{
"epoch": 0.12681159420289856,
"grad_norm": 1.304027795791626,
"learning_rate": 6.311122522957255e-05,
"loss": 0.887,
"step": 63
},
{
"epoch": 0.1288244766505636,
"grad_norm": 1.3097902536392212,
"learning_rate": 6.304001017554202e-05,
"loss": 0.8636,
"step": 64
},
{
"epoch": 0.13083735909822866,
"grad_norm": 1.281269907951355,
"learning_rate": 6.296751899164788e-05,
"loss": 0.7537,
"step": 65
},
{
"epoch": 0.13285024154589373,
"grad_norm": 1.2349010705947876,
"learning_rate": 6.289375470697116e-05,
"loss": 0.8451,
"step": 66
},
{
"epoch": 0.13486312399355876,
"grad_norm": 1.2939257621765137,
"learning_rate": 6.281872040379001e-05,
"loss": 0.8249,
"step": 67
},
{
"epoch": 0.13687600644122383,
"grad_norm": 1.308341145515442,
"learning_rate": 6.274241921745097e-05,
"loss": 0.8764,
"step": 68
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.311805009841919,
"learning_rate": 6.266485433623794e-05,
"loss": 0.8308,
"step": 69
},
{
"epoch": 0.14090177133655393,
"grad_norm": 1.6127303838729858,
"learning_rate": 6.258602900123894e-05,
"loss": 0.8069,
"step": 70
},
{
"epoch": 0.142914653784219,
"grad_norm": 1.292090654373169,
"learning_rate": 6.250594650621067e-05,
"loss": 0.8174,
"step": 71
},
{
"epoch": 0.14492753623188406,
"grad_norm": 1.256778359413147,
"learning_rate": 6.2424610197441e-05,
"loss": 0.7956,
"step": 72
},
{
"epoch": 0.1469404186795491,
"grad_norm": 1.2579149007797241,
"learning_rate": 6.23420234736089e-05,
"loss": 0.8267,
"step": 73
},
{
"epoch": 0.14895330112721417,
"grad_norm": 1.3226171731948853,
"learning_rate": 6.225818978564269e-05,
"loss": 0.9322,
"step": 74
},
{
"epoch": 0.15096618357487923,
"grad_norm": 1.1891167163848877,
"learning_rate": 6.217311263657565e-05,
"loss": 0.7886,
"step": 75
},
{
"epoch": 0.1529790660225443,
"grad_norm": 1.2481876611709595,
"learning_rate": 6.208679558139977e-05,
"loss": 0.7832,
"step": 76
},
{
"epoch": 0.15499194847020933,
"grad_norm": 1.2592449188232422,
"learning_rate": 6.199924222691707e-05,
"loss": 0.8061,
"step": 77
},
{
"epoch": 0.1570048309178744,
"grad_norm": 1.250359058380127,
"learning_rate": 6.191045623158907e-05,
"loss": 0.7942,
"step": 78
},
{
"epoch": 0.15901771336553946,
"grad_norm": 1.2406524419784546,
"learning_rate": 6.182044130538373e-05,
"loss": 0.7766,
"step": 79
},
{
"epoch": 0.1610305958132045,
"grad_norm": 1.2620049715042114,
"learning_rate": 6.172920120962052e-05,
"loss": 0.8445,
"step": 80
},
{
"epoch": 0.16304347826086957,
"grad_norm": 1.2618622779846191,
"learning_rate": 6.16367397568133e-05,
"loss": 0.812,
"step": 81
},
{
"epoch": 0.16505636070853463,
"grad_norm": 1.2560168504714966,
"learning_rate": 6.15430608105109e-05,
"loss": 0.8331,
"step": 82
},
{
"epoch": 0.16706924315619967,
"grad_norm": 1.2386751174926758,
"learning_rate": 6.144816828513576e-05,
"loss": 0.7318,
"step": 83
},
{
"epoch": 0.16908212560386474,
"grad_norm": 1.3558485507965088,
"learning_rate": 6.135206614582031e-05,
"loss": 0.8476,
"step": 84
},
{
"epoch": 0.1710950080515298,
"grad_norm": 1.2461968660354614,
"learning_rate": 6.125475840824137e-05,
"loss": 0.8012,
"step": 85
},
{
"epoch": 0.17310789049919484,
"grad_norm": 1.2398920059204102,
"learning_rate": 6.115624913845225e-05,
"loss": 0.8033,
"step": 86
},
{
"epoch": 0.1751207729468599,
"grad_norm": 1.3263791799545288,
"learning_rate": 6.105654245271292e-05,
"loss": 0.8511,
"step": 87
},
{
"epoch": 0.17713365539452497,
"grad_norm": 1.2072999477386475,
"learning_rate": 6.095564251731795e-05,
"loss": 0.7478,
"step": 88
},
{
"epoch": 0.17914653784219,
"grad_norm": 1.287801742553711,
"learning_rate": 6.085355354842249e-05,
"loss": 0.8152,
"step": 89
},
{
"epoch": 0.18115942028985507,
"grad_norm": 1.2826151847839355,
"learning_rate": 6.0750279811866046e-05,
"loss": 0.7918,
"step": 90
},
{
"epoch": 0.18317230273752014,
"grad_norm": 1.276780605316162,
"learning_rate": 6.0645825622994254e-05,
"loss": 0.8774,
"step": 91
},
{
"epoch": 0.18518518518518517,
"grad_norm": 1.2205020189285278,
"learning_rate": 6.0540195346478515e-05,
"loss": 0.8398,
"step": 92
},
{
"epoch": 0.18719806763285024,
"grad_norm": 1.2247477769851685,
"learning_rate": 6.043339339613371e-05,
"loss": 0.8322,
"step": 93
},
{
"epoch": 0.1892109500805153,
"grad_norm": 1.3282443284988403,
"learning_rate": 6.0325424234733656e-05,
"loss": 0.8003,
"step": 94
},
{
"epoch": 0.19122383252818034,
"grad_norm": 1.3472024202346802,
"learning_rate": 6.0216292373824696e-05,
"loss": 0.8305,
"step": 95
},
{
"epoch": 0.1932367149758454,
"grad_norm": 1.2812607288360596,
"learning_rate": 6.010600237353716e-05,
"loss": 0.7657,
"step": 96
},
{
"epoch": 0.19524959742351047,
"grad_norm": 1.2958053350448608,
"learning_rate": 5.999455884239483e-05,
"loss": 0.869,
"step": 97
},
{
"epoch": 0.1972624798711755,
"grad_norm": 1.2021034955978394,
"learning_rate": 5.988196643712235e-05,
"loss": 0.7798,
"step": 98
},
{
"epoch": 0.19927536231884058,
"grad_norm": 1.2430065870285034,
"learning_rate": 5.976822986245067e-05,
"loss": 0.7496,
"step": 99
},
{
"epoch": 0.20128824476650564,
"grad_norm": 1.2749730348587036,
"learning_rate": 5.9653353870920434e-05,
"loss": 0.831,
"step": 100
},
{
"epoch": 0.20330112721417068,
"grad_norm": 1.2621365785598755,
"learning_rate": 5.953734326268337e-05,
"loss": 0.8051,
"step": 101
},
{
"epoch": 0.20531400966183574,
"grad_norm": 1.1950538158416748,
"learning_rate": 5.94202028853018e-05,
"loss": 0.7866,
"step": 102
},
{
"epoch": 0.2073268921095008,
"grad_norm": 1.3278518915176392,
"learning_rate": 5.930193763354597e-05,
"loss": 0.8374,
"step": 103
},
{
"epoch": 0.20933977455716588,
"grad_norm": 1.281888484954834,
"learning_rate": 5.91825524491896e-05,
"loss": 0.8255,
"step": 104
},
{
"epoch": 0.2113526570048309,
"grad_norm": 1.270607352256775,
"learning_rate": 5.906205232080336e-05,
"loss": 0.7782,
"step": 105
},
{
"epoch": 0.21336553945249598,
"grad_norm": 1.2177718877792358,
"learning_rate": 5.894044228354644e-05,
"loss": 0.7506,
"step": 106
},
{
"epoch": 0.21537842190016104,
"grad_norm": 1.247755765914917,
"learning_rate": 5.88177274189561e-05,
"loss": 0.8135,
"step": 107
},
{
"epoch": 0.21739130434782608,
"grad_norm": 1.2848960161209106,
"learning_rate": 5.869391285473541e-05,
"loss": 0.8259,
"step": 108
},
{
"epoch": 0.21940418679549115,
"grad_norm": 1.197343349456787,
"learning_rate": 5.856900376453892e-05,
"loss": 0.7872,
"step": 109
},
{
"epoch": 0.2214170692431562,
"grad_norm": 1.2160040140151978,
"learning_rate": 5.844300536775651e-05,
"loss": 0.7725,
"step": 110
},
{
"epoch": 0.22342995169082125,
"grad_norm": 1.2862228155136108,
"learning_rate": 5.831592292929532e-05,
"loss": 0.7808,
"step": 111
},
{
"epoch": 0.22544283413848631,
"grad_norm": 1.2369639873504639,
"learning_rate": 5.818776175935967e-05,
"loss": 0.7898,
"step": 112
},
{
"epoch": 0.22745571658615138,
"grad_norm": 1.2040680646896362,
"learning_rate": 5.805852721322927e-05,
"loss": 0.8068,
"step": 113
},
{
"epoch": 0.22946859903381642,
"grad_norm": 1.28532075881958,
"learning_rate": 5.792822469103539e-05,
"loss": 0.8117,
"step": 114
},
{
"epoch": 0.23148148148148148,
"grad_norm": 1.2590646743774414,
"learning_rate": 5.7796859637535194e-05,
"loss": 0.7806,
"step": 115
},
{
"epoch": 0.23349436392914655,
"grad_norm": 1.223161220550537,
"learning_rate": 5.76644375418843e-05,
"loss": 0.7477,
"step": 116
},
{
"epoch": 0.23550724637681159,
"grad_norm": 1.2891532182693481,
"learning_rate": 5.753096393740734e-05,
"loss": 0.8055,
"step": 117
},
{
"epoch": 0.23752012882447665,
"grad_norm": 1.352499008178711,
"learning_rate": 5.739644440136678e-05,
"loss": 0.8192,
"step": 118
},
{
"epoch": 0.23953301127214172,
"grad_norm": 1.2987629175186157,
"learning_rate": 5.726088455472989e-05,
"loss": 0.8279,
"step": 119
},
{
"epoch": 0.24154589371980675,
"grad_norm": 1.2705352306365967,
"learning_rate": 5.7124290061933827e-05,
"loss": 0.826,
"step": 120
},
{
"epoch": 0.24355877616747182,
"grad_norm": 1.3219701051712036,
"learning_rate": 5.698666663064896e-05,
"loss": 0.8321,
"step": 121
},
{
"epoch": 0.24557165861513688,
"grad_norm": 1.3087178468704224,
"learning_rate": 5.6848020011540414e-05,
"loss": 0.8629,
"step": 122
},
{
"epoch": 0.24758454106280192,
"grad_norm": 1.2457053661346436,
"learning_rate": 5.670835599802768e-05,
"loss": 0.8092,
"step": 123
},
{
"epoch": 0.249597423510467,
"grad_norm": 1.2432583570480347,
"learning_rate": 5.656768042604265e-05,
"loss": 0.7889,
"step": 124
},
{
"epoch": 0.25161030595813205,
"grad_norm": 1.3183501958847046,
"learning_rate": 5.6425999173785643e-05,
"loss": 0.8554,
"step": 125
},
{
"epoch": 0.2536231884057971,
"grad_norm": 1.2189457416534424,
"learning_rate": 5.628331816147989e-05,
"loss": 0.7932,
"step": 126
},
{
"epoch": 0.2556360708534622,
"grad_norm": 1.143637776374817,
"learning_rate": 5.6139643351124076e-05,
"loss": 0.7668,
"step": 127
},
{
"epoch": 0.2576489533011272,
"grad_norm": 1.1862376928329468,
"learning_rate": 5.5994980746243264e-05,
"loss": 0.8165,
"step": 128
},
{
"epoch": 0.25966183574879226,
"grad_norm": 1.1560195684432983,
"learning_rate": 5.5849336391637995e-05,
"loss": 0.8122,
"step": 129
},
{
"epoch": 0.2616747181964573,
"grad_norm": 1.2094959020614624,
"learning_rate": 5.5702716373131716e-05,
"loss": 0.7955,
"step": 130
},
{
"epoch": 0.2636876006441224,
"grad_norm": 1.2558305263519287,
"learning_rate": 5.5555126817316515e-05,
"loss": 0.8399,
"step": 131
},
{
"epoch": 0.26570048309178745,
"grad_norm": 1.297591209411621,
"learning_rate": 5.540657389129707e-05,
"loss": 0.8398,
"step": 132
},
{
"epoch": 0.2677133655394525,
"grad_norm": 1.3282864093780518,
"learning_rate": 5.525706380243297e-05,
"loss": 0.8156,
"step": 133
},
{
"epoch": 0.26972624798711753,
"grad_norm": 1.3417863845825195,
"learning_rate": 5.510660279807935e-05,
"loss": 0.8105,
"step": 134
},
{
"epoch": 0.2717391304347826,
"grad_norm": 1.2470736503601074,
"learning_rate": 5.495519716532585e-05,
"loss": 0.7849,
"step": 135
},
{
"epoch": 0.27375201288244766,
"grad_norm": 1.2911748886108398,
"learning_rate": 5.480285323073384e-05,
"loss": 0.836,
"step": 136
},
{
"epoch": 0.2757648953301127,
"grad_norm": 1.2390037775039673,
"learning_rate": 5.464957736007215e-05,
"loss": 0.7556,
"step": 137
},
{
"epoch": 0.2777777777777778,
"grad_norm": 1.2093883752822876,
"learning_rate": 5.449537595805101e-05,
"loss": 0.8173,
"step": 138
},
{
"epoch": 0.27979066022544286,
"grad_norm": 1.2018241882324219,
"learning_rate": 5.434025546805447e-05,
"loss": 0.7983,
"step": 139
},
{
"epoch": 0.28180354267310787,
"grad_norm": 1.2486872673034668,
"learning_rate": 5.418422237187113e-05,
"loss": 0.813,
"step": 140
},
{
"epoch": 0.28381642512077293,
"grad_norm": 1.1954402923583984,
"learning_rate": 5.4027283189423296e-05,
"loss": 0.7999,
"step": 141
},
{
"epoch": 0.285829307568438,
"grad_norm": 1.1647478342056274,
"learning_rate": 5.386944447849457e-05,
"loss": 0.7872,
"step": 142
},
{
"epoch": 0.28784219001610306,
"grad_norm": 1.3171889781951904,
"learning_rate": 5.371071283445577e-05,
"loss": 0.8074,
"step": 143
},
{
"epoch": 0.2898550724637681,
"grad_norm": 1.3020223379135132,
"learning_rate": 5.355109488998941e-05,
"loss": 0.8068,
"step": 144
},
{
"epoch": 0.2918679549114332,
"grad_norm": 1.1892728805541992,
"learning_rate": 5.339059731481252e-05,
"loss": 0.7863,
"step": 145
},
{
"epoch": 0.2938808373590982,
"grad_norm": 1.2545976638793945,
"learning_rate": 5.322922681539793e-05,
"loss": 0.8486,
"step": 146
},
{
"epoch": 0.29589371980676327,
"grad_norm": 1.1874210834503174,
"learning_rate": 5.3066990134694086e-05,
"loss": 0.7702,
"step": 147
},
{
"epoch": 0.29790660225442833,
"grad_norm": 1.2464886903762817,
"learning_rate": 5.2903894051843204e-05,
"loss": 0.8313,
"step": 148
},
{
"epoch": 0.2999194847020934,
"grad_norm": 1.3062876462936401,
"learning_rate": 5.2739945381898095e-05,
"loss": 0.8076,
"step": 149
},
{
"epoch": 0.30193236714975846,
"grad_norm": 1.2185595035552979,
"learning_rate": 5.2575150975537353e-05,
"loss": 0.7585,
"step": 150
},
{
"epoch": 0.30394524959742353,
"grad_norm": 1.1846880912780762,
"learning_rate": 5.240951771877909e-05,
"loss": 0.7762,
"step": 151
},
{
"epoch": 0.3059581320450886,
"grad_norm": 1.1666184663772583,
"learning_rate": 5.224305253269321e-05,
"loss": 0.7539,
"step": 152
},
{
"epoch": 0.3079710144927536,
"grad_norm": 1.2293246984481812,
"learning_rate": 5.207576237311223e-05,
"loss": 0.8013,
"step": 153
},
{
"epoch": 0.30998389694041867,
"grad_norm": 1.184094786643982,
"learning_rate": 5.1907654230340546e-05,
"loss": 0.7686,
"step": 154
},
{
"epoch": 0.31199677938808373,
"grad_norm": 1.1998686790466309,
"learning_rate": 5.1738735128862465e-05,
"loss": 0.7596,
"step": 155
},
{
"epoch": 0.3140096618357488,
"grad_norm": 1.1767568588256836,
"learning_rate": 5.156901212704858e-05,
"loss": 0.7535,
"step": 156
},
{
"epoch": 0.31602254428341386,
"grad_norm": 1.1981345415115356,
"learning_rate": 5.139849231686086e-05,
"loss": 0.7971,
"step": 157
},
{
"epoch": 0.31803542673107893,
"grad_norm": 1.2676053047180176,
"learning_rate": 5.122718282355635e-05,
"loss": 0.7575,
"step": 158
},
{
"epoch": 0.32004830917874394,
"grad_norm": 1.2075040340423584,
"learning_rate": 5.105509080538939e-05,
"loss": 0.8187,
"step": 159
},
{
"epoch": 0.322061191626409,
"grad_norm": 1.2567739486694336,
"learning_rate": 5.08822234533125e-05,
"loss": 0.7754,
"step": 160
},
{
"epoch": 0.32407407407407407,
"grad_norm": 1.1478137969970703,
"learning_rate": 5.0708587990675954e-05,
"loss": 0.7744,
"step": 161
},
{
"epoch": 0.32608695652173914,
"grad_norm": 1.2385374307632446,
"learning_rate": 5.05341916729259e-05,
"loss": 0.7852,
"step": 162
},
{
"epoch": 0.3280998389694042,
"grad_norm": 1.2898869514465332,
"learning_rate": 5.035904178730119e-05,
"loss": 0.8475,
"step": 163
},
{
"epoch": 0.33011272141706927,
"grad_norm": 1.2359830141067505,
"learning_rate": 5.018314565252893e-05,
"loss": 0.8417,
"step": 164
},
{
"epoch": 0.3321256038647343,
"grad_norm": 1.224368929862976,
"learning_rate": 5.00065106185186e-05,
"loss": 0.7904,
"step": 165
},
{
"epoch": 0.33413848631239934,
"grad_norm": 1.229744553565979,
"learning_rate": 4.9829144066054964e-05,
"loss": 0.7969,
"step": 166
},
{
"epoch": 0.3361513687600644,
"grad_norm": 1.1933088302612305,
"learning_rate": 4.9651053406489656e-05,
"loss": 0.7646,
"step": 167
},
{
"epoch": 0.33816425120772947,
"grad_norm": 1.2042123079299927,
"learning_rate": 4.9472246081431494e-05,
"loss": 0.779,
"step": 168
},
{
"epoch": 0.34017713365539454,
"grad_norm": 1.1418585777282715,
"learning_rate": 4.9292729562435545e-05,
"loss": 0.7586,
"step": 169
},
{
"epoch": 0.3421900161030596,
"grad_norm": 1.2688250541687012,
"learning_rate": 4.9112511350690876e-05,
"loss": 0.7275,
"step": 170
},
{
"epoch": 0.3442028985507246,
"grad_norm": 1.1605274677276611,
"learning_rate": 4.893159897670716e-05,
"loss": 0.7784,
"step": 171
},
{
"epoch": 0.3462157809983897,
"grad_norm": 1.1853288412094116,
"learning_rate": 4.874999999999999e-05,
"loss": 0.7872,
"step": 172
},
{
"epoch": 0.34822866344605474,
"grad_norm": 1.180342197418213,
"learning_rate": 4.856772200877502e-05,
"loss": 0.7877,
"step": 173
},
{
"epoch": 0.3502415458937198,
"grad_norm": 1.1545747518539429,
"learning_rate": 4.838477261961083e-05,
"loss": 0.7554,
"step": 174
},
{
"epoch": 0.3522544283413849,
"grad_norm": 1.4341752529144287,
"learning_rate": 4.820115947714075e-05,
"loss": 0.7872,
"step": 175
},
{
"epoch": 0.35426731078904994,
"grad_norm": 1.254834532737732,
"learning_rate": 4.801689025373334e-05,
"loss": 0.8164,
"step": 176
},
{
"epoch": 0.35628019323671495,
"grad_norm": 1.18601393699646,
"learning_rate": 4.783197264917187e-05,
"loss": 0.7879,
"step": 177
},
{
"epoch": 0.35829307568438,
"grad_norm": 1.2259867191314697,
"learning_rate": 4.764641439033251e-05,
"loss": 0.8213,
"step": 178
},
{
"epoch": 0.3603059581320451,
"grad_norm": 1.2177544832229614,
"learning_rate": 4.746022323086153e-05,
"loss": 0.7674,
"step": 179
},
{
"epoch": 0.36231884057971014,
"grad_norm": 1.2497576475143433,
"learning_rate": 4.7273406950851265e-05,
"loss": 0.7512,
"step": 180
},
{
"epoch": 0.3643317230273752,
"grad_norm": 1.192671537399292,
"learning_rate": 4.708597335651502e-05,
"loss": 0.7917,
"step": 181
},
{
"epoch": 0.3663446054750403,
"grad_norm": 1.2135677337646484,
"learning_rate": 4.689793027986089e-05,
"loss": 0.7944,
"step": 182
},
{
"epoch": 0.36835748792270534,
"grad_norm": 1.2164232730865479,
"learning_rate": 4.670928557836452e-05,
"loss": 0.762,
"step": 183
},
{
"epoch": 0.37037037037037035,
"grad_norm": 1.175716757774353,
"learning_rate": 4.6520047134640736e-05,
"loss": 0.7313,
"step": 184
},
{
"epoch": 0.3723832528180354,
"grad_norm": 1.2479422092437744,
"learning_rate": 4.633022285611418e-05,
"loss": 0.831,
"step": 185
},
{
"epoch": 0.3743961352657005,
"grad_norm": 1.2672486305236816,
"learning_rate": 4.613982067468894e-05,
"loss": 0.7899,
"step": 186
},
{
"epoch": 0.37640901771336555,
"grad_norm": 1.3110653162002563,
"learning_rate": 4.594884854641702e-05,
"loss": 0.7759,
"step": 187
},
{
"epoch": 0.3784219001610306,
"grad_norm": 1.2542824745178223,
"learning_rate": 4.575731445116596e-05,
"loss": 0.785,
"step": 188
},
{
"epoch": 0.3804347826086957,
"grad_norm": 1.144977331161499,
"learning_rate": 4.55652263922854e-05,
"loss": 0.7398,
"step": 189
},
{
"epoch": 0.3824476650563607,
"grad_norm": 1.1065174341201782,
"learning_rate": 4.537259239627259e-05,
"loss": 0.7622,
"step": 190
},
{
"epoch": 0.38446054750402575,
"grad_norm": 1.227591872215271,
"learning_rate": 4.5179420512437075e-05,
"loss": 0.7603,
"step": 191
},
{
"epoch": 0.3864734299516908,
"grad_norm": 1.2493457794189453,
"learning_rate": 4.498571881256432e-05,
"loss": 0.7863,
"step": 192
},
{
"epoch": 0.3884863123993559,
"grad_norm": 1.3239022493362427,
"learning_rate": 4.479149539057838e-05,
"loss": 0.849,
"step": 193
},
{
"epoch": 0.39049919484702095,
"grad_norm": 1.2450414896011353,
"learning_rate": 4.4596758362203775e-05,
"loss": 0.7802,
"step": 194
},
{
"epoch": 0.392512077294686,
"grad_norm": 1.3064862489700317,
"learning_rate": 4.44015158646263e-05,
"loss": 0.7597,
"step": 195
},
{
"epoch": 0.394524959742351,
"grad_norm": 1.2286595106124878,
"learning_rate": 4.4205776056153084e-05,
"loss": 0.7863,
"step": 196
},
{
"epoch": 0.3965378421900161,
"grad_norm": 1.1941579580307007,
"learning_rate": 4.4009547115871594e-05,
"loss": 0.7199,
"step": 197
},
{
"epoch": 0.39855072463768115,
"grad_norm": 1.2539899349212646,
"learning_rate": 4.3812837243307933e-05,
"loss": 0.7807,
"step": 198
},
{
"epoch": 0.4005636070853462,
"grad_norm": 1.2592153549194336,
"learning_rate": 4.3615654658084234e-05,
"loss": 0.7657,
"step": 199
},
{
"epoch": 0.4025764895330113,
"grad_norm": 1.1356335878372192,
"learning_rate": 4.341800759957512e-05,
"loss": 0.6915,
"step": 200
},
{
"epoch": 0.40458937198067635,
"grad_norm": 1.1767053604125977,
"learning_rate": 4.32199043265635e-05,
"loss": 0.781,
"step": 201
},
{
"epoch": 0.40660225442834136,
"grad_norm": 1.3261032104492188,
"learning_rate": 4.302135311689543e-05,
"loss": 0.7527,
"step": 202
},
{
"epoch": 0.4086151368760064,
"grad_norm": 1.2210772037506104,
"learning_rate": 4.282236226713422e-05,
"loss": 0.7815,
"step": 203
},
{
"epoch": 0.4106280193236715,
"grad_norm": 1.2168560028076172,
"learning_rate": 4.26229400922138e-05,
"loss": 0.7397,
"step": 204
},
{
"epoch": 0.41264090177133655,
"grad_norm": 1.24334716796875,
"learning_rate": 4.2423094925091174e-05,
"loss": 0.8202,
"step": 205
},
{
"epoch": 0.4146537842190016,
"grad_norm": 1.22861647605896,
"learning_rate": 4.2222835116398354e-05,
"loss": 0.7951,
"step": 206
},
{
"epoch": 0.4166666666666667,
"grad_norm": 1.2528316974639893,
"learning_rate": 4.2022169034093314e-05,
"loss": 0.7412,
"step": 207
},
{
"epoch": 0.41867954911433175,
"grad_norm": 1.259413242340088,
"learning_rate": 4.182110506311043e-05,
"loss": 0.8283,
"step": 208
},
{
"epoch": 0.42069243156199676,
"grad_norm": 1.1932429075241089,
"learning_rate": 4.161965160501001e-05,
"loss": 0.7777,
"step": 209
},
{
"epoch": 0.4227053140096618,
"grad_norm": 1.2518868446350098,
"learning_rate": 4.14178170776273e-05,
"loss": 0.8084,
"step": 210
},
{
"epoch": 0.4247181964573269,
"grad_norm": 1.1913188695907593,
"learning_rate": 4.1215609914720716e-05,
"loss": 0.7893,
"step": 211
},
{
"epoch": 0.42673107890499196,
"grad_norm": 1.174193024635315,
"learning_rate": 4.1013038565619436e-05,
"loss": 0.75,
"step": 212
},
{
"epoch": 0.428743961352657,
"grad_norm": 1.2024927139282227,
"learning_rate": 4.081011149487037e-05,
"loss": 0.7476,
"step": 213
},
{
"epoch": 0.4307568438003221,
"grad_norm": 1.2005985975265503,
"learning_rate": 4.060683718188439e-05,
"loss": 0.7445,
"step": 214
},
{
"epoch": 0.4327697262479871,
"grad_norm": 1.2409402132034302,
"learning_rate": 4.0403224120582105e-05,
"loss": 0.754,
"step": 215
},
{
"epoch": 0.43478260869565216,
"grad_norm": 1.1732304096221924,
"learning_rate": 4.0199280819038866e-05,
"loss": 0.7627,
"step": 216
},
{
"epoch": 0.4367954911433172,
"grad_norm": 1.1297844648361206,
"learning_rate": 3.9995015799129304e-05,
"loss": 0.7363,
"step": 217
},
{
"epoch": 0.4388083735909823,
"grad_norm": 1.1647371053695679,
"learning_rate": 3.9790437596171196e-05,
"loss": 0.7578,
"step": 218
},
{
"epoch": 0.44082125603864736,
"grad_norm": 1.2122061252593994,
"learning_rate": 3.9585554758568836e-05,
"loss": 0.7232,
"step": 219
},
{
"epoch": 0.4428341384863124,
"grad_norm": 1.1666353940963745,
"learning_rate": 3.938037584745585e-05,
"loss": 0.7585,
"step": 220
},
{
"epoch": 0.44484702093397743,
"grad_norm": 1.1572037935256958,
"learning_rate": 3.917490943633741e-05,
"loss": 0.7167,
"step": 221
},
{
"epoch": 0.4468599033816425,
"grad_norm": 1.1842679977416992,
"learning_rate": 3.896916411073206e-05,
"loss": 0.7835,
"step": 222
},
{
"epoch": 0.44887278582930756,
"grad_norm": 1.2700228691101074,
"learning_rate": 3.8763148467812915e-05,
"loss": 0.7771,
"step": 223
},
{
"epoch": 0.45088566827697263,
"grad_norm": 1.2174429893493652,
"learning_rate": 3.8556871116048424e-05,
"loss": 0.7462,
"step": 224
},
{
"epoch": 0.4528985507246377,
"grad_norm": 1.2977925539016724,
"learning_rate": 3.835034067484267e-05,
"loss": 0.7824,
"step": 225
},
{
"epoch": 0.45491143317230276,
"grad_norm": 1.2482331991195679,
"learning_rate": 3.814356577417524e-05,
"loss": 0.7877,
"step": 226
},
{
"epoch": 0.45692431561996777,
"grad_norm": 1.1702152490615845,
"learning_rate": 3.793655505424054e-05,
"loss": 0.7245,
"step": 227
},
{
"epoch": 0.45893719806763283,
"grad_norm": 1.1979886293411255,
"learning_rate": 3.772931716508686e-05,
"loss": 0.7637,
"step": 228
},
{
"epoch": 0.4609500805152979,
"grad_norm": 1.202635407447815,
"learning_rate": 3.752186076625482e-05,
"loss": 0.8038,
"step": 229
},
{
"epoch": 0.46296296296296297,
"grad_norm": 1.2843554019927979,
"learning_rate": 3.731419452641559e-05,
"loss": 0.7628,
"step": 230
},
{
"epoch": 0.46497584541062803,
"grad_norm": 1.2422301769256592,
"learning_rate": 3.710632712300867e-05,
"loss": 0.7793,
"step": 231
},
{
"epoch": 0.4669887278582931,
"grad_norm": 1.229872465133667,
"learning_rate": 3.6898267241879266e-05,
"loss": 0.787,
"step": 232
},
{
"epoch": 0.4690016103059581,
"grad_norm": 1.1803100109100342,
"learning_rate": 3.669002357691536e-05,
"loss": 0.7118,
"step": 233
},
{
"epoch": 0.47101449275362317,
"grad_norm": 1.2324291467666626,
"learning_rate": 3.648160482968447e-05,
"loss": 0.7781,
"step": 234
},
{
"epoch": 0.47302737520128824,
"grad_norm": 1.2399364709854126,
"learning_rate": 3.627301970906998e-05,
"loss": 0.8275,
"step": 235
},
{
"epoch": 0.4750402576489533,
"grad_norm": 1.167107343673706,
"learning_rate": 3.6064276930907275e-05,
"loss": 0.8124,
"step": 236
},
{
"epoch": 0.47705314009661837,
"grad_norm": 1.1939244270324707,
"learning_rate": 3.585538521761956e-05,
"loss": 0.7746,
"step": 237
},
{
"epoch": 0.47906602254428343,
"grad_norm": 1.151248574256897,
"learning_rate": 3.564635329785332e-05,
"loss": 0.7189,
"step": 238
},
{
"epoch": 0.4810789049919485,
"grad_norm": 1.225353479385376,
"learning_rate": 3.543718990611371e-05,
"loss": 0.7178,
"step": 239
},
{
"epoch": 0.4830917874396135,
"grad_norm": 1.1944713592529297,
"learning_rate": 3.5227903782399465e-05,
"loss": 0.7887,
"step": 240
},
{
"epoch": 0.4851046698872786,
"grad_norm": 1.2270437479019165,
"learning_rate": 3.501850367183775e-05,
"loss": 0.7748,
"step": 241
},
{
"epoch": 0.48711755233494364,
"grad_norm": 1.2102910280227661,
"learning_rate": 3.4808998324318723e-05,
"loss": 0.7739,
"step": 242
},
{
"epoch": 0.4891304347826087,
"grad_norm": 1.2025328874588013,
"learning_rate": 3.459939649412993e-05,
"loss": 0.7636,
"step": 243
},
{
"epoch": 0.49114331723027377,
"grad_norm": 1.2945396900177002,
"learning_rate": 3.438970693959046e-05,
"loss": 0.801,
"step": 244
},
{
"epoch": 0.49315619967793883,
"grad_norm": 1.1986439228057861,
"learning_rate": 3.417993842268507e-05,
"loss": 0.7242,
"step": 245
},
{
"epoch": 0.49516908212560384,
"grad_norm": 1.2383544445037842,
"learning_rate": 3.397009970869796e-05,
"loss": 0.7916,
"step": 246
},
{
"epoch": 0.4971819645732689,
"grad_norm": 1.2588520050048828,
"learning_rate": 3.376019956584654e-05,
"loss": 0.7865,
"step": 247
},
{
"epoch": 0.499194847020934,
"grad_norm": 1.2207812070846558,
"learning_rate": 3.35502467649151e-05,
"loss": 0.7671,
"step": 248
},
{
"epoch": 0.501207729468599,
"grad_norm": 1.1526901721954346,
"learning_rate": 3.334025007888823e-05,
"loss": 0.7068,
"step": 249
},
{
"epoch": 0.5032206119162641,
"grad_norm": 1.2134076356887817,
"learning_rate": 3.313021828258429e-05,
"loss": 0.7811,
"step": 250
},
{
"epoch": 0.5052334943639292,
"grad_norm": 1.1232891082763672,
"learning_rate": 3.292016015228877e-05,
"loss": 0.7456,
"step": 251
},
{
"epoch": 0.5072463768115942,
"grad_norm": 1.1962013244628906,
"learning_rate": 3.271008446538752e-05,
"loss": 0.7699,
"step": 252
},
{
"epoch": 0.5092592592592593,
"grad_norm": 1.2679433822631836,
"learning_rate": 3.25e-05,
"loss": 0.7838,
"step": 253
},
{
"epoch": 0.5112721417069244,
"grad_norm": 1.1369578838348389,
"learning_rate": 3.2289915534612466e-05,
"loss": 0.7326,
"step": 254
},
{
"epoch": 0.5132850241545893,
"grad_norm": 1.20002281665802,
"learning_rate": 3.207983984771123e-05,
"loss": 0.7554,
"step": 255
},
{
"epoch": 0.5152979066022544,
"grad_norm": 1.1573915481567383,
"learning_rate": 3.186978171741571e-05,
"loss": 0.682,
"step": 256
},
{
"epoch": 0.5173107890499195,
"grad_norm": 1.1725130081176758,
"learning_rate": 3.165974992111178e-05,
"loss": 0.7674,
"step": 257
},
{
"epoch": 0.5193236714975845,
"grad_norm": 1.2105400562286377,
"learning_rate": 3.1449753235084904e-05,
"loss": 0.7425,
"step": 258
},
{
"epoch": 0.5213365539452496,
"grad_norm": 1.1620723009109497,
"learning_rate": 3.123980043415345e-05,
"loss": 0.7396,
"step": 259
},
{
"epoch": 0.5233494363929146,
"grad_norm": 1.163138508796692,
"learning_rate": 3.102990029130204e-05,
"loss": 0.7131,
"step": 260
},
{
"epoch": 0.5253623188405797,
"grad_norm": 1.2142436504364014,
"learning_rate": 3.082006157731492e-05,
"loss": 0.724,
"step": 261
},
{
"epoch": 0.5273752012882448,
"grad_norm": 1.1541523933410645,
"learning_rate": 3.061029306040954e-05,
"loss": 0.7305,
"step": 262
},
{
"epoch": 0.5293880837359098,
"grad_norm": 1.208058476448059,
"learning_rate": 3.040060350587007e-05,
"loss": 0.7625,
"step": 263
},
{
"epoch": 0.5314009661835749,
"grad_norm": 1.1648660898208618,
"learning_rate": 3.0191001675681278e-05,
"loss": 0.7422,
"step": 264
},
{
"epoch": 0.53341384863124,
"grad_norm": 1.175646424293518,
"learning_rate": 2.9981496328162244e-05,
"loss": 0.7202,
"step": 265
},
{
"epoch": 0.535426731078905,
"grad_norm": 1.1440715789794922,
"learning_rate": 2.9772096217600523e-05,
"loss": 0.6784,
"step": 266
},
{
"epoch": 0.5374396135265701,
"grad_norm": 1.2752009630203247,
"learning_rate": 2.956281009388629e-05,
"loss": 0.7446,
"step": 267
},
{
"epoch": 0.5394524959742351,
"grad_norm": 1.2139878273010254,
"learning_rate": 2.9353646702146676e-05,
"loss": 0.7583,
"step": 268
},
{
"epoch": 0.5414653784219001,
"grad_norm": 1.2297486066818237,
"learning_rate": 2.9144614782380454e-05,
"loss": 0.7103,
"step": 269
},
{
"epoch": 0.5434782608695652,
"grad_norm": 1.1957374811172485,
"learning_rate": 2.893572306909272e-05,
"loss": 0.763,
"step": 270
},
{
"epoch": 0.5454911433172303,
"grad_norm": 1.1861435174942017,
"learning_rate": 2.872698029093001e-05,
"loss": 0.8011,
"step": 271
},
{
"epoch": 0.5475040257648953,
"grad_norm": 1.232905626296997,
"learning_rate": 2.8518395170315524e-05,
"loss": 0.8291,
"step": 272
},
{
"epoch": 0.5495169082125604,
"grad_norm": 1.2735815048217773,
"learning_rate": 2.830997642308463e-05,
"loss": 0.7339,
"step": 273
},
{
"epoch": 0.5515297906602254,
"grad_norm": 1.256100058555603,
"learning_rate": 2.8101732758120746e-05,
"loss": 0.8017,
"step": 274
},
{
"epoch": 0.5535426731078905,
"grad_norm": 1.228579044342041,
"learning_rate": 2.7893672876991337e-05,
"loss": 0.7774,
"step": 275
},
{
"epoch": 0.5555555555555556,
"grad_norm": 1.1710914373397827,
"learning_rate": 2.768580547358442e-05,
"loss": 0.7252,
"step": 276
},
{
"epoch": 0.5575684380032206,
"grad_norm": 1.1470144987106323,
"learning_rate": 2.7478139233745183e-05,
"loss": 0.7662,
"step": 277
},
{
"epoch": 0.5595813204508857,
"grad_norm": 1.1679579019546509,
"learning_rate": 2.7270682834913133e-05,
"loss": 0.7748,
"step": 278
},
{
"epoch": 0.5615942028985508,
"grad_norm": 1.1878283023834229,
"learning_rate": 2.7063444945759455e-05,
"loss": 0.7375,
"step": 279
},
{
"epoch": 0.5636070853462157,
"grad_norm": 1.1710705757141113,
"learning_rate": 2.6856434225824763e-05,
"loss": 0.757,
"step": 280
},
{
"epoch": 0.5656199677938808,
"grad_norm": 1.1414003372192383,
"learning_rate": 2.6649659325157332e-05,
"loss": 0.7062,
"step": 281
},
{
"epoch": 0.5676328502415459,
"grad_norm": 1.189766764640808,
"learning_rate": 2.644312888395158e-05,
"loss": 0.7539,
"step": 282
},
{
"epoch": 0.5696457326892109,
"grad_norm": 1.2260947227478027,
"learning_rate": 2.6236851532187076e-05,
"loss": 0.7388,
"step": 283
},
{
"epoch": 0.571658615136876,
"grad_norm": 1.328162431716919,
"learning_rate": 2.6030835889267932e-05,
"loss": 0.7612,
"step": 284
},
{
"epoch": 0.5736714975845411,
"grad_norm": 1.1704083681106567,
"learning_rate": 2.582509056366258e-05,
"loss": 0.7511,
"step": 285
},
{
"epoch": 0.5756843800322061,
"grad_norm": 1.1261523962020874,
"learning_rate": 2.561962415254416e-05,
"loss": 0.7225,
"step": 286
},
{
"epoch": 0.5776972624798712,
"grad_norm": 1.2048742771148682,
"learning_rate": 2.541444524143116e-05,
"loss": 0.7864,
"step": 287
},
{
"epoch": 0.5797101449275363,
"grad_norm": 1.2203797101974487,
"learning_rate": 2.5209562403828805e-05,
"loss": 0.7114,
"step": 288
},
{
"epoch": 0.5817230273752013,
"grad_norm": 1.2502771615982056,
"learning_rate": 2.5004984200870694e-05,
"loss": 0.8076,
"step": 289
},
{
"epoch": 0.5837359098228664,
"grad_norm": 1.1746399402618408,
"learning_rate": 2.480071918096112e-05,
"loss": 0.7951,
"step": 290
},
{
"epoch": 0.5857487922705314,
"grad_norm": 1.1511627435684204,
"learning_rate": 2.45967758794179e-05,
"loss": 0.7189,
"step": 291
},
{
"epoch": 0.5877616747181964,
"grad_norm": 1.1979589462280273,
"learning_rate": 2.4393162818115607e-05,
"loss": 0.7739,
"step": 292
},
{
"epoch": 0.5897745571658615,
"grad_norm": 1.1766811609268188,
"learning_rate": 2.4189888505129634e-05,
"loss": 0.7609,
"step": 293
},
{
"epoch": 0.5917874396135265,
"grad_norm": 1.177783727645874,
"learning_rate": 2.3986961434380555e-05,
"loss": 0.7161,
"step": 294
},
{
"epoch": 0.5938003220611916,
"grad_norm": 1.1824970245361328,
"learning_rate": 2.378439008527928e-05,
"loss": 0.7752,
"step": 295
},
{
"epoch": 0.5958132045088567,
"grad_norm": 1.1629244089126587,
"learning_rate": 2.3582182922372703e-05,
"loss": 0.7514,
"step": 296
},
{
"epoch": 0.5978260869565217,
"grad_norm": 1.193488359451294,
"learning_rate": 2.3380348394989985e-05,
"loss": 0.7257,
"step": 297
},
{
"epoch": 0.5998389694041868,
"grad_norm": 1.2829092741012573,
"learning_rate": 2.3178894936889573e-05,
"loss": 0.8165,
"step": 298
},
{
"epoch": 0.6018518518518519,
"grad_norm": 1.1431480646133423,
"learning_rate": 2.2977830965906677e-05,
"loss": 0.7237,
"step": 299
},
{
"epoch": 0.6038647342995169,
"grad_norm": 1.1849764585494995,
"learning_rate": 2.277716488360165e-05,
"loss": 0.7758,
"step": 300
},
{
"epoch": 0.605877616747182,
"grad_norm": 1.1299766302108765,
"learning_rate": 2.2576905074908823e-05,
"loss": 0.7272,
"step": 301
},
{
"epoch": 0.6078904991948471,
"grad_norm": 1.1116759777069092,
"learning_rate": 2.2377059907786196e-05,
"loss": 0.7152,
"step": 302
},
{
"epoch": 0.6099033816425121,
"grad_norm": 1.1651757955551147,
"learning_rate": 2.217763773286577e-05,
"loss": 0.7587,
"step": 303
},
{
"epoch": 0.6119162640901772,
"grad_norm": 1.1139724254608154,
"learning_rate": 2.1978646883104566e-05,
"loss": 0.7187,
"step": 304
},
{
"epoch": 0.6139291465378421,
"grad_norm": 1.1941097974777222,
"learning_rate": 2.1780095673436497e-05,
"loss": 0.7337,
"step": 305
},
{
"epoch": 0.6159420289855072,
"grad_norm": 1.1893556118011475,
"learning_rate": 2.1581992400424884e-05,
"loss": 0.7453,
"step": 306
},
{
"epoch": 0.6179549114331723,
"grad_norm": 1.2010302543640137,
"learning_rate": 2.1384345341915767e-05,
"loss": 0.7541,
"step": 307
},
{
"epoch": 0.6199677938808373,
"grad_norm": 1.0827986001968384,
"learning_rate": 2.1187162756692057e-05,
"loss": 0.7393,
"step": 308
},
{
"epoch": 0.6219806763285024,
"grad_norm": 1.2004282474517822,
"learning_rate": 2.09904528841284e-05,
"loss": 0.7522,
"step": 309
},
{
"epoch": 0.6239935587761675,
"grad_norm": 1.1190348863601685,
"learning_rate": 2.0794223943846917e-05,
"loss": 0.7141,
"step": 310
},
{
"epoch": 0.6260064412238325,
"grad_norm": 1.2460802793502808,
"learning_rate": 2.059848413537369e-05,
"loss": 0.818,
"step": 311
},
{
"epoch": 0.6280193236714976,
"grad_norm": 1.1238231658935547,
"learning_rate": 2.040324163779623e-05,
"loss": 0.7505,
"step": 312
},
{
"epoch": 0.6300322061191627,
"grad_norm": 1.264402985572815,
"learning_rate": 2.020850460942162e-05,
"loss": 0.7544,
"step": 313
},
{
"epoch": 0.6320450885668277,
"grad_norm": 1.197068214416504,
"learning_rate": 2.0014281187435673e-05,
"loss": 0.751,
"step": 314
},
{
"epoch": 0.6340579710144928,
"grad_norm": 1.1713694334030151,
"learning_rate": 1.9820579487562915e-05,
"loss": 0.7245,
"step": 315
},
{
"epoch": 0.6360708534621579,
"grad_norm": 1.2123608589172363,
"learning_rate": 1.9627407603727402e-05,
"loss": 0.7627,
"step": 316
},
{
"epoch": 0.6380837359098228,
"grad_norm": 1.1857858896255493,
"learning_rate": 1.9434773607714608e-05,
"loss": 0.7352,
"step": 317
},
{
"epoch": 0.6400966183574879,
"grad_norm": 1.1570547819137573,
"learning_rate": 1.9242685548834033e-05,
"loss": 0.7537,
"step": 318
},
{
"epoch": 0.6421095008051529,
"grad_norm": 1.2034544944763184,
"learning_rate": 1.9051151453582976e-05,
"loss": 0.7414,
"step": 319
},
{
"epoch": 0.644122383252818,
"grad_norm": 1.1642334461212158,
"learning_rate": 1.8860179325311052e-05,
"loss": 0.7448,
"step": 320
},
{
"epoch": 0.6461352657004831,
"grad_norm": 1.235265851020813,
"learning_rate": 1.866977714388581e-05,
"loss": 0.773,
"step": 321
},
{
"epoch": 0.6481481481481481,
"grad_norm": 1.2570306062698364,
"learning_rate": 1.847995286535927e-05,
"loss": 0.7205,
"step": 322
},
{
"epoch": 0.6501610305958132,
"grad_norm": 1.201730489730835,
"learning_rate": 1.829071442163547e-05,
"loss": 0.7353,
"step": 323
},
{
"epoch": 0.6521739130434783,
"grad_norm": 1.1657803058624268,
"learning_rate": 1.8102069720139113e-05,
"loss": 0.7206,
"step": 324
},
{
"epoch": 0.6541867954911433,
"grad_norm": 1.0922691822052002,
"learning_rate": 1.7914026643484976e-05,
"loss": 0.7105,
"step": 325
},
{
"epoch": 0.6561996779388084,
"grad_norm": 1.1522175073623657,
"learning_rate": 1.772659304914873e-05,
"loss": 0.7529,
"step": 326
},
{
"epoch": 0.6582125603864735,
"grad_norm": 1.1323693990707397,
"learning_rate": 1.7539776769138468e-05,
"loss": 0.728,
"step": 327
},
{
"epoch": 0.6602254428341385,
"grad_norm": 1.229993224143982,
"learning_rate": 1.7353585609667497e-05,
"loss": 0.7535,
"step": 328
},
{
"epoch": 0.6622383252818036,
"grad_norm": 1.1816473007202148,
"learning_rate": 1.7168027350828144e-05,
"loss": 0.7336,
"step": 329
},
{
"epoch": 0.6642512077294686,
"grad_norm": 1.2471328973770142,
"learning_rate": 1.6983109746266657e-05,
"loss": 0.7856,
"step": 330
},
{
"epoch": 0.6662640901771336,
"grad_norm": 1.1073960065841675,
"learning_rate": 1.6798840522859247e-05,
"loss": 0.6935,
"step": 331
},
{
"epoch": 0.6682769726247987,
"grad_norm": 1.2102614641189575,
"learning_rate": 1.6615227380389165e-05,
"loss": 0.7561,
"step": 332
},
{
"epoch": 0.6702898550724637,
"grad_norm": 1.3027081489562988,
"learning_rate": 1.6432277991224978e-05,
"loss": 0.7802,
"step": 333
},
{
"epoch": 0.6723027375201288,
"grad_norm": 1.2084347009658813,
"learning_rate": 1.6250000000000005e-05,
"loss": 0.8191,
"step": 334
},
{
"epoch": 0.6743156199677939,
"grad_norm": 1.2484228610992432,
"learning_rate": 1.6068401023292833e-05,
"loss": 0.7389,
"step": 335
},
{
"epoch": 0.6763285024154589,
"grad_norm": 1.2207857370376587,
"learning_rate": 1.5887488649309122e-05,
"loss": 0.7465,
"step": 336
},
{
"epoch": 0.678341384863124,
"grad_norm": 1.1802961826324463,
"learning_rate": 1.5707270437564453e-05,
"loss": 0.7105,
"step": 337
},
{
"epoch": 0.6803542673107891,
"grad_norm": 1.1720234155654907,
"learning_rate": 1.5527753918568504e-05,
"loss": 0.6955,
"step": 338
},
{
"epoch": 0.6823671497584541,
"grad_norm": 1.0980851650238037,
"learning_rate": 1.5348946593510345e-05,
"loss": 0.7273,
"step": 339
},
{
"epoch": 0.6843800322061192,
"grad_norm": 1.2615996599197388,
"learning_rate": 1.5170855933945039e-05,
"loss": 0.7734,
"step": 340
},
{
"epoch": 0.6863929146537843,
"grad_norm": 1.1403189897537231,
"learning_rate": 1.4993489381481403e-05,
"loss": 0.7184,
"step": 341
},
{
"epoch": 0.6884057971014492,
"grad_norm": 1.2819575071334839,
"learning_rate": 1.481685434747106e-05,
"loss": 0.832,
"step": 342
},
{
"epoch": 0.6904186795491143,
"grad_norm": 1.1605795621871948,
"learning_rate": 1.4640958212698804e-05,
"loss": 0.7517,
"step": 343
},
{
"epoch": 0.6924315619967794,
"grad_norm": 1.1168081760406494,
"learning_rate": 1.4465808327074102e-05,
"loss": 0.6931,
"step": 344
},
{
"epoch": 0.6944444444444444,
"grad_norm": 1.167962670326233,
"learning_rate": 1.4291412009324043e-05,
"loss": 0.6917,
"step": 345
},
{
"epoch": 0.6964573268921095,
"grad_norm": 1.1960166692733765,
"learning_rate": 1.41177765466875e-05,
"loss": 0.7653,
"step": 346
},
{
"epoch": 0.6984702093397746,
"grad_norm": 1.1906245946884155,
"learning_rate": 1.3944909194610604e-05,
"loss": 0.7477,
"step": 347
},
{
"epoch": 0.7004830917874396,
"grad_norm": 1.2501006126403809,
"learning_rate": 1.3772817176443637e-05,
"loss": 0.8167,
"step": 348
},
{
"epoch": 0.7024959742351047,
"grad_norm": 1.1363681554794312,
"learning_rate": 1.360150768313913e-05,
"loss": 0.7148,
"step": 349
},
{
"epoch": 0.7045088566827697,
"grad_norm": 1.164594292640686,
"learning_rate": 1.343098787295142e-05,
"loss": 0.761,
"step": 350
}
],
"logging_steps": 1,
"max_steps": 496,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.114526806679224e+17,
"train_batch_size": 6,
"trial_name": null,
"trial_params": null
}