xlm-roberta-base-msmarco / trainer_state.json
michaeldinzinger's picture
Add model
9d8b836
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 30.0,
"eval_steps": 0,
"global_step": 235740,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06362942224484602,
"grad_norm": 1662.35009765625,
"learning_rate": 4.86e-07,
"loss": 92.5416,
"step": 500
},
{
"epoch": 0.12725884448969205,
"grad_norm": 288.2401428222656,
"learning_rate": 9.86e-07,
"loss": 20.6659,
"step": 1000
},
{
"epoch": 0.19088826673453804,
"grad_norm": 56.13795852661133,
"learning_rate": 1.4860000000000003e-06,
"loss": 14.7631,
"step": 1500
},
{
"epoch": 0.2545176889793841,
"grad_norm": 102.28019714355469,
"learning_rate": 1.986e-06,
"loss": 14.3025,
"step": 2000
},
{
"epoch": 0.31814711122423006,
"grad_norm": 155.62403869628906,
"learning_rate": 2.486e-06,
"loss": 13.5257,
"step": 2500
},
{
"epoch": 0.3817765334690761,
"grad_norm": 210.75811767578125,
"learning_rate": 2.986e-06,
"loss": 12.8666,
"step": 3000
},
{
"epoch": 0.4454059557139221,
"grad_norm": 256.039306640625,
"learning_rate": 3.4860000000000006e-06,
"loss": 12.397,
"step": 3500
},
{
"epoch": 0.5090353779587682,
"grad_norm": 227.79017639160156,
"learning_rate": 3.9860000000000005e-06,
"loss": 12.2718,
"step": 4000
},
{
"epoch": 0.5726648002036141,
"grad_norm": 307.928955078125,
"learning_rate": 4.486000000000001e-06,
"loss": 11.539,
"step": 4500
},
{
"epoch": 0.6362942224484601,
"grad_norm": 199.85580444335938,
"learning_rate": 4.986e-06,
"loss": 11.1145,
"step": 5000
},
{
"epoch": 0.6999236446933061,
"grad_norm": 236.899169921875,
"learning_rate": 5.4860000000000005e-06,
"loss": 11.1232,
"step": 5500
},
{
"epoch": 0.7635530669381522,
"grad_norm": 265.123046875,
"learning_rate": 5.986000000000001e-06,
"loss": 10.6021,
"step": 6000
},
{
"epoch": 0.8271824891829982,
"grad_norm": 254.1043701171875,
"learning_rate": 6.486e-06,
"loss": 10.4115,
"step": 6500
},
{
"epoch": 0.8908119114278442,
"grad_norm": 172.3489990234375,
"learning_rate": 6.9860000000000005e-06,
"loss": 10.4529,
"step": 7000
},
{
"epoch": 0.9544413336726902,
"grad_norm": 374.72003173828125,
"learning_rate": 7.486000000000001e-06,
"loss": 10.1329,
"step": 7500
},
{
"epoch": 1.0180707559175364,
"grad_norm": 320.3682556152344,
"learning_rate": 7.985e-06,
"loss": 10.1367,
"step": 8000
},
{
"epoch": 1.0817001781623823,
"grad_norm": 297.0594787597656,
"learning_rate": 8.485000000000001e-06,
"loss": 9.5914,
"step": 8500
},
{
"epoch": 1.1453296004072282,
"grad_norm": 266.2686767578125,
"learning_rate": 8.985000000000001e-06,
"loss": 9.2799,
"step": 9000
},
{
"epoch": 1.2089590226520743,
"grad_norm": 168.0514373779297,
"learning_rate": 9.485000000000002e-06,
"loss": 9.266,
"step": 9500
},
{
"epoch": 1.2725884448969205,
"grad_norm": 213.7965545654297,
"learning_rate": 9.985000000000002e-06,
"loss": 9.1661,
"step": 10000
},
{
"epoch": 1.3362178671417664,
"grad_norm": 189.05682373046875,
"learning_rate": 9.978515105874015e-06,
"loss": 8.954,
"step": 10500
},
{
"epoch": 1.3998472893866123,
"grad_norm": 230.05084228515625,
"learning_rate": 9.956365730486402e-06,
"loss": 8.9562,
"step": 11000
},
{
"epoch": 1.4634767116314584,
"grad_norm": 314.4221496582031,
"learning_rate": 9.934304952600337e-06,
"loss": 9.4717,
"step": 11500
},
{
"epoch": 1.5271061338763046,
"grad_norm": 190.9048614501953,
"learning_rate": 9.912155577212723e-06,
"loss": 8.6758,
"step": 12000
},
{
"epoch": 1.5907355561211505,
"grad_norm": 3140.1875,
"learning_rate": 9.89000620182511e-06,
"loss": 8.87,
"step": 12500
},
{
"epoch": 1.6543649783659964,
"grad_norm": 396.64117431640625,
"learning_rate": 9.867856826437496e-06,
"loss": 8.5826,
"step": 13000
},
{
"epoch": 1.7179944006108423,
"grad_norm": 171.70077514648438,
"learning_rate": 9.845707451049881e-06,
"loss": 8.4827,
"step": 13500
},
{
"epoch": 1.7816238228556884,
"grad_norm": 269.8551940917969,
"learning_rate": 9.823558075662267e-06,
"loss": 8.5306,
"step": 14000
},
{
"epoch": 1.8452532451005346,
"grad_norm": 255.013671875,
"learning_rate": 9.801408700274653e-06,
"loss": 8.182,
"step": 14500
},
{
"epoch": 1.9088826673453805,
"grad_norm": 194.22486877441406,
"learning_rate": 9.77925932488704e-06,
"loss": 8.3592,
"step": 15000
},
{
"epoch": 1.9725120895902264,
"grad_norm": 149.85800170898438,
"learning_rate": 9.757109949499426e-06,
"loss": 8.3879,
"step": 15500
},
{
"epoch": 2.0361415118350727,
"grad_norm": 156.6005401611328,
"learning_rate": 9.735004872862585e-06,
"loss": 7.4399,
"step": 16000
},
{
"epoch": 2.0997709340799187,
"grad_norm": 286.58648681640625,
"learning_rate": 9.712855497474972e-06,
"loss": 7.0406,
"step": 16500
},
{
"epoch": 2.1634003563247646,
"grad_norm": 242.3479461669922,
"learning_rate": 9.690706122087358e-06,
"loss": 6.89,
"step": 17000
},
{
"epoch": 2.2270297785696105,
"grad_norm": 180.5225372314453,
"learning_rate": 9.668556746699744e-06,
"loss": 6.8651,
"step": 17500
},
{
"epoch": 2.2906592008144564,
"grad_norm": 223.84552001953125,
"learning_rate": 9.64640737131213e-06,
"loss": 6.8461,
"step": 18000
},
{
"epoch": 2.3542886230593028,
"grad_norm": 233.3303680419922,
"learning_rate": 9.624257995924515e-06,
"loss": 6.7663,
"step": 18500
},
{
"epoch": 2.4179180453041487,
"grad_norm": 237.0810546875,
"learning_rate": 9.602108620536902e-06,
"loss": 6.9313,
"step": 19000
},
{
"epoch": 2.4815474675489946,
"grad_norm": 176.5728302001953,
"learning_rate": 9.579959245149288e-06,
"loss": 6.9688,
"step": 19500
},
{
"epoch": 2.545176889793841,
"grad_norm": 184.43077087402344,
"learning_rate": 9.557809869761674e-06,
"loss": 6.7821,
"step": 20000
},
{
"epoch": 2.608806312038687,
"grad_norm": 182.1748809814453,
"learning_rate": 9.535660494374059e-06,
"loss": 6.9468,
"step": 20500
},
{
"epoch": 2.6724357342835328,
"grad_norm": 232.06759643554688,
"learning_rate": 9.51355541773722e-06,
"loss": 6.731,
"step": 21000
},
{
"epoch": 2.7360651565283787,
"grad_norm": 169.12734985351562,
"learning_rate": 9.491406042349606e-06,
"loss": 6.649,
"step": 21500
},
{
"epoch": 2.7996945787732246,
"grad_norm": 153.9056854248047,
"learning_rate": 9.469256666961992e-06,
"loss": 6.7055,
"step": 22000
},
{
"epoch": 2.8633240010180705,
"grad_norm": 252.30517578125,
"learning_rate": 9.447107291574379e-06,
"loss": 6.7744,
"step": 22500
},
{
"epoch": 2.926953423262917,
"grad_norm": 182.51229858398438,
"learning_rate": 9.424957916186765e-06,
"loss": 6.9481,
"step": 23000
},
{
"epoch": 2.9905828455077628,
"grad_norm": 213.7582244873047,
"learning_rate": 9.40280854079915e-06,
"loss": 6.5967,
"step": 23500
},
{
"epoch": 3.0542122677526087,
"grad_norm": 187.1132049560547,
"learning_rate": 9.380659165411536e-06,
"loss": 5.7351,
"step": 24000
},
{
"epoch": 3.117841689997455,
"grad_norm": 157.81378173828125,
"learning_rate": 9.358509790023921e-06,
"loss": 5.4125,
"step": 24500
},
{
"epoch": 3.181471112242301,
"grad_norm": 448.2672424316406,
"learning_rate": 9.336360414636309e-06,
"loss": 5.4095,
"step": 25000
},
{
"epoch": 3.245100534487147,
"grad_norm": 170.9069061279297,
"learning_rate": 9.314211039248694e-06,
"loss": 5.4253,
"step": 25500
},
{
"epoch": 3.3087299567319928,
"grad_norm": 186.37034606933594,
"learning_rate": 9.29206166386108e-06,
"loss": 5.3774,
"step": 26000
},
{
"epoch": 3.3723593789768387,
"grad_norm": 134.44960021972656,
"learning_rate": 9.269912288473466e-06,
"loss": 5.5277,
"step": 26500
},
{
"epoch": 3.435988801221685,
"grad_norm": 268.1274108886719,
"learning_rate": 9.247807211836627e-06,
"loss": 5.4516,
"step": 27000
},
{
"epoch": 3.499618223466531,
"grad_norm": 248.0684814453125,
"learning_rate": 9.225657836449013e-06,
"loss": 5.322,
"step": 27500
},
{
"epoch": 3.563247645711377,
"grad_norm": 214.72317504882812,
"learning_rate": 9.203508461061398e-06,
"loss": 5.5531,
"step": 28000
},
{
"epoch": 3.626877067956223,
"grad_norm": 153.9894256591797,
"learning_rate": 9.181359085673784e-06,
"loss": 5.5238,
"step": 28500
},
{
"epoch": 3.690506490201069,
"grad_norm": 174.88331604003906,
"learning_rate": 9.159209710286171e-06,
"loss": 5.5992,
"step": 29000
},
{
"epoch": 3.754135912445915,
"grad_norm": 301.410888671875,
"learning_rate": 9.137104633649332e-06,
"loss": 5.5351,
"step": 29500
},
{
"epoch": 3.817765334690761,
"grad_norm": 201.53282165527344,
"learning_rate": 9.114955258261718e-06,
"loss": 5.3985,
"step": 30000
},
{
"epoch": 3.881394756935607,
"grad_norm": 212.6214141845703,
"learning_rate": 9.092805882874104e-06,
"loss": 5.4313,
"step": 30500
},
{
"epoch": 3.945024179180453,
"grad_norm": 177.44863891601562,
"learning_rate": 9.07065650748649e-06,
"loss": 5.4173,
"step": 31000
},
{
"epoch": 4.008653601425299,
"grad_norm": 160.0504150390625,
"learning_rate": 9.04855143084965e-06,
"loss": 5.2333,
"step": 31500
},
{
"epoch": 4.0722830236701455,
"grad_norm": 150.31857299804688,
"learning_rate": 9.026446354212812e-06,
"loss": 4.3352,
"step": 32000
},
{
"epoch": 4.135912445914991,
"grad_norm": 124.97169494628906,
"learning_rate": 9.004296978825197e-06,
"loss": 4.3442,
"step": 32500
},
{
"epoch": 4.199541868159837,
"grad_norm": 215.25157165527344,
"learning_rate": 8.982147603437585e-06,
"loss": 4.3288,
"step": 33000
},
{
"epoch": 4.263171290404683,
"grad_norm": 148.4134521484375,
"learning_rate": 8.95999822804997e-06,
"loss": 4.367,
"step": 33500
},
{
"epoch": 4.326800712649529,
"grad_norm": 204.40850830078125,
"learning_rate": 8.93789315141313e-06,
"loss": 4.4607,
"step": 34000
},
{
"epoch": 4.390430134894375,
"grad_norm": 164.64273071289062,
"learning_rate": 8.915743776025517e-06,
"loss": 4.4461,
"step": 34500
},
{
"epoch": 4.454059557139221,
"grad_norm": 204.80953979492188,
"learning_rate": 8.893594400637903e-06,
"loss": 4.6218,
"step": 35000
},
{
"epoch": 4.517688979384067,
"grad_norm": 185.70278930664062,
"learning_rate": 8.871445025250289e-06,
"loss": 4.4249,
"step": 35500
},
{
"epoch": 4.581318401628913,
"grad_norm": 202.91989135742188,
"learning_rate": 8.849295649862674e-06,
"loss": 4.4129,
"step": 36000
},
{
"epoch": 4.64494782387376,
"grad_norm": 164.02198791503906,
"learning_rate": 8.82714627447506e-06,
"loss": 4.4065,
"step": 36500
},
{
"epoch": 4.7085772461186055,
"grad_norm": 155.7901153564453,
"learning_rate": 8.804996899087447e-06,
"loss": 4.5452,
"step": 37000
},
{
"epoch": 4.772206668363451,
"grad_norm": 194.26280212402344,
"learning_rate": 8.782847523699833e-06,
"loss": 4.5411,
"step": 37500
},
{
"epoch": 4.835836090608297,
"grad_norm": 168.18798828125,
"learning_rate": 8.760698148312218e-06,
"loss": 4.5423,
"step": 38000
},
{
"epoch": 4.899465512853143,
"grad_norm": 136.41905212402344,
"learning_rate": 8.738548772924604e-06,
"loss": 4.4942,
"step": 38500
},
{
"epoch": 4.963094935097989,
"grad_norm": 141.8522491455078,
"learning_rate": 8.71639939753699e-06,
"loss": 4.5332,
"step": 39000
},
{
"epoch": 5.026724357342835,
"grad_norm": 149.42271423339844,
"learning_rate": 8.694250022149377e-06,
"loss": 4.0759,
"step": 39500
},
{
"epoch": 5.090353779587681,
"grad_norm": 139.2994842529297,
"learning_rate": 8.672100646761763e-06,
"loss": 3.6274,
"step": 40000
},
{
"epoch": 5.153983201832528,
"grad_norm": 140.65269470214844,
"learning_rate": 8.649951271374148e-06,
"loss": 3.6795,
"step": 40500
},
{
"epoch": 5.217612624077374,
"grad_norm": 139.22752380371094,
"learning_rate": 8.627801895986534e-06,
"loss": 3.6741,
"step": 41000
},
{
"epoch": 5.28124204632222,
"grad_norm": 93.71381378173828,
"learning_rate": 8.60565252059892e-06,
"loss": 3.7396,
"step": 41500
},
{
"epoch": 5.3448714685670655,
"grad_norm": 118.81936645507812,
"learning_rate": 8.583503145211307e-06,
"loss": 3.6839,
"step": 42000
},
{
"epoch": 5.408500890811911,
"grad_norm": 143.53829956054688,
"learning_rate": 8.561353769823692e-06,
"loss": 3.732,
"step": 42500
},
{
"epoch": 5.472130313056757,
"grad_norm": 152.01527404785156,
"learning_rate": 8.539248693186852e-06,
"loss": 3.6557,
"step": 43000
},
{
"epoch": 5.535759735301603,
"grad_norm": 159.16392517089844,
"learning_rate": 8.517143616550015e-06,
"loss": 3.6925,
"step": 43500
},
{
"epoch": 5.599389157546449,
"grad_norm": 143.2123260498047,
"learning_rate": 8.4949942411624e-06,
"loss": 3.7149,
"step": 44000
},
{
"epoch": 5.663018579791295,
"grad_norm": 136.5101318359375,
"learning_rate": 8.472844865774786e-06,
"loss": 3.6744,
"step": 44500
},
{
"epoch": 5.726648002036142,
"grad_norm": 156.95541381835938,
"learning_rate": 8.450695490387172e-06,
"loss": 3.7669,
"step": 45000
},
{
"epoch": 5.790277424280988,
"grad_norm": 137.13330078125,
"learning_rate": 8.428546114999557e-06,
"loss": 3.651,
"step": 45500
},
{
"epoch": 5.853906846525834,
"grad_norm": 149.19625854492188,
"learning_rate": 8.406396739611945e-06,
"loss": 3.721,
"step": 46000
},
{
"epoch": 5.91753626877068,
"grad_norm": 193.83432006835938,
"learning_rate": 8.384291662975104e-06,
"loss": 3.7012,
"step": 46500
},
{
"epoch": 5.9811656910155255,
"grad_norm": 149.3867950439453,
"learning_rate": 8.362186586338266e-06,
"loss": 3.7294,
"step": 47000
},
{
"epoch": 6.0447951132603714,
"grad_norm": 144.5869140625,
"learning_rate": 8.340037210950653e-06,
"loss": 3.2432,
"step": 47500
},
{
"epoch": 6.108424535505217,
"grad_norm": 138.15234375,
"learning_rate": 8.317887835563039e-06,
"loss": 3.0295,
"step": 48000
},
{
"epoch": 6.172053957750063,
"grad_norm": 544.6531372070312,
"learning_rate": 8.295738460175424e-06,
"loss": 3.0364,
"step": 48500
},
{
"epoch": 6.23568337999491,
"grad_norm": 124.35468292236328,
"learning_rate": 8.273633383538585e-06,
"loss": 3.0687,
"step": 49000
},
{
"epoch": 6.299312802239756,
"grad_norm": 93.38568878173828,
"learning_rate": 8.251484008150971e-06,
"loss": 3.064,
"step": 49500
},
{
"epoch": 6.362942224484602,
"grad_norm": 192.03231811523438,
"learning_rate": 8.229334632763357e-06,
"loss": 3.112,
"step": 50000
},
{
"epoch": 6.426571646729448,
"grad_norm": 107.92765808105469,
"learning_rate": 8.207185257375742e-06,
"loss": 3.1438,
"step": 50500
},
{
"epoch": 6.490201068974294,
"grad_norm": 124.23885345458984,
"learning_rate": 8.185080180738904e-06,
"loss": 3.0733,
"step": 51000
},
{
"epoch": 6.55383049121914,
"grad_norm": 154.87612915039062,
"learning_rate": 8.162930805351291e-06,
"loss": 3.1719,
"step": 51500
},
{
"epoch": 6.6174599134639855,
"grad_norm": 134.2186737060547,
"learning_rate": 8.140781429963675e-06,
"loss": 3.1355,
"step": 52000
},
{
"epoch": 6.6810893357088315,
"grad_norm": 173.08433532714844,
"learning_rate": 8.11863205457606e-06,
"loss": 3.1612,
"step": 52500
},
{
"epoch": 6.744718757953677,
"grad_norm": 179.25296020507812,
"learning_rate": 8.096482679188448e-06,
"loss": 3.1938,
"step": 53000
},
{
"epoch": 6.808348180198524,
"grad_norm": 138.08518981933594,
"learning_rate": 8.074333303800833e-06,
"loss": 3.1375,
"step": 53500
},
{
"epoch": 6.87197760244337,
"grad_norm": 106.96342468261719,
"learning_rate": 8.052183928413219e-06,
"loss": 3.1969,
"step": 54000
},
{
"epoch": 6.935607024688216,
"grad_norm": 127.7270278930664,
"learning_rate": 8.030034553025605e-06,
"loss": 3.2214,
"step": 54500
},
{
"epoch": 6.999236446933062,
"grad_norm": 151.88905334472656,
"learning_rate": 8.007885177637992e-06,
"loss": 3.1364,
"step": 55000
},
{
"epoch": 7.062865869177908,
"grad_norm": 146.13461303710938,
"learning_rate": 7.985735802250378e-06,
"loss": 2.63,
"step": 55500
},
{
"epoch": 7.126495291422754,
"grad_norm": 158.6125030517578,
"learning_rate": 7.963586426862763e-06,
"loss": 2.5451,
"step": 56000
},
{
"epoch": 7.1901247136676,
"grad_norm": 136.17828369140625,
"learning_rate": 7.941481350225924e-06,
"loss": 2.644,
"step": 56500
},
{
"epoch": 7.2537541359124456,
"grad_norm": 183.11447143554688,
"learning_rate": 7.91933197483831e-06,
"loss": 2.6482,
"step": 57000
},
{
"epoch": 7.317383558157292,
"grad_norm": 125.30079650878906,
"learning_rate": 7.897182599450696e-06,
"loss": 2.6017,
"step": 57500
},
{
"epoch": 7.381012980402138,
"grad_norm": 104.10094451904297,
"learning_rate": 7.875033224063083e-06,
"loss": 2.6626,
"step": 58000
},
{
"epoch": 7.444642402646984,
"grad_norm": 153.14060974121094,
"learning_rate": 7.852883848675467e-06,
"loss": 2.6698,
"step": 58500
},
{
"epoch": 7.50827182489183,
"grad_norm": 80.38119506835938,
"learning_rate": 7.830734473287854e-06,
"loss": 2.6595,
"step": 59000
},
{
"epoch": 7.571901247136676,
"grad_norm": 139.31524658203125,
"learning_rate": 7.80858509790024e-06,
"loss": 2.6683,
"step": 59500
},
{
"epoch": 7.635530669381522,
"grad_norm": 135.78240966796875,
"learning_rate": 7.786480021263401e-06,
"loss": 2.7187,
"step": 60000
},
{
"epoch": 7.699160091626368,
"grad_norm": 109.59832000732422,
"learning_rate": 7.764330645875787e-06,
"loss": 2.6213,
"step": 60500
},
{
"epoch": 7.762789513871214,
"grad_norm": 143.305908203125,
"learning_rate": 7.742181270488172e-06,
"loss": 2.7119,
"step": 61000
},
{
"epoch": 7.82641893611606,
"grad_norm": 147.27064514160156,
"learning_rate": 7.72003189510056e-06,
"loss": 2.739,
"step": 61500
},
{
"epoch": 7.8900483583609065,
"grad_norm": 109.4032211303711,
"learning_rate": 7.697882519712945e-06,
"loss": 2.686,
"step": 62000
},
{
"epoch": 7.953677780605752,
"grad_norm": 111.08818054199219,
"learning_rate": 7.675733144325331e-06,
"loss": 2.7295,
"step": 62500
},
{
"epoch": 8.017307202850597,
"grad_norm": 80.8994369506836,
"learning_rate": 7.653583768937717e-06,
"loss": 2.6062,
"step": 63000
},
{
"epoch": 8.080936625095443,
"grad_norm": 132.42283630371094,
"learning_rate": 7.631434393550102e-06,
"loss": 2.2272,
"step": 63500
},
{
"epoch": 8.144566047340291,
"grad_norm": 105.58837127685547,
"learning_rate": 7.6093293169132635e-06,
"loss": 2.2692,
"step": 64000
},
{
"epoch": 8.208195469585137,
"grad_norm": 165.8797149658203,
"learning_rate": 7.58717994152565e-06,
"loss": 2.3135,
"step": 64500
},
{
"epoch": 8.271824891829983,
"grad_norm": 103.73261260986328,
"learning_rate": 7.5650305661380356e-06,
"loss": 2.2546,
"step": 65000
},
{
"epoch": 8.335454314074829,
"grad_norm": 100.5468521118164,
"learning_rate": 7.542881190750422e-06,
"loss": 2.2882,
"step": 65500
},
{
"epoch": 8.399083736319675,
"grad_norm": 124.30194854736328,
"learning_rate": 7.520731815362808e-06,
"loss": 2.2749,
"step": 66000
},
{
"epoch": 8.46271315856452,
"grad_norm": 124.07736206054688,
"learning_rate": 7.498582439975194e-06,
"loss": 2.363,
"step": 66500
},
{
"epoch": 8.526342580809366,
"grad_norm": 110.9386978149414,
"learning_rate": 7.47643306458758e-06,
"loss": 2.2923,
"step": 67000
},
{
"epoch": 8.589972003054212,
"grad_norm": 129.3117218017578,
"learning_rate": 7.4542836891999645e-06,
"loss": 2.3275,
"step": 67500
},
{
"epoch": 8.653601425299058,
"grad_norm": 111.8931884765625,
"learning_rate": 7.432134313812351e-06,
"loss": 2.3738,
"step": 68000
},
{
"epoch": 8.717230847543904,
"grad_norm": 118.7526626586914,
"learning_rate": 7.409984938424737e-06,
"loss": 2.3416,
"step": 68500
},
{
"epoch": 8.78086026978875,
"grad_norm": 149.440673828125,
"learning_rate": 7.387835563037123e-06,
"loss": 2.3851,
"step": 69000
},
{
"epoch": 8.844489692033596,
"grad_norm": 122.81755828857422,
"learning_rate": 7.365730486400284e-06,
"loss": 2.3356,
"step": 69500
},
{
"epoch": 8.908119114278442,
"grad_norm": 132.1360626220703,
"learning_rate": 7.34358111101267e-06,
"loss": 2.3598,
"step": 70000
},
{
"epoch": 8.971748536523288,
"grad_norm": 125.38104248046875,
"learning_rate": 7.3214317356250565e-06,
"loss": 2.4272,
"step": 70500
},
{
"epoch": 9.035377958768134,
"grad_norm": 94.84292602539062,
"learning_rate": 7.299326658988217e-06,
"loss": 2.141,
"step": 71000
},
{
"epoch": 9.09900738101298,
"grad_norm": 108.36376190185547,
"learning_rate": 7.2771772836006025e-06,
"loss": 2.001,
"step": 71500
},
{
"epoch": 9.162636803257826,
"grad_norm": 120.51274108886719,
"learning_rate": 7.255027908212989e-06,
"loss": 2.014,
"step": 72000
},
{
"epoch": 9.226266225502673,
"grad_norm": 76.73661041259766,
"learning_rate": 7.232878532825375e-06,
"loss": 1.9826,
"step": 72500
},
{
"epoch": 9.28989564774752,
"grad_norm": 93.48287200927734,
"learning_rate": 7.210729157437761e-06,
"loss": 1.995,
"step": 73000
},
{
"epoch": 9.353525069992365,
"grad_norm": 87.56092071533203,
"learning_rate": 7.188579782050147e-06,
"loss": 2.0097,
"step": 73500
},
{
"epoch": 9.417154492237211,
"grad_norm": 128.68373107910156,
"learning_rate": 7.166430406662532e-06,
"loss": 2.0412,
"step": 74000
},
{
"epoch": 9.480783914482057,
"grad_norm": 101.52668762207031,
"learning_rate": 7.144281031274919e-06,
"loss": 2.0144,
"step": 74500
},
{
"epoch": 9.544413336726903,
"grad_norm": 90.50218963623047,
"learning_rate": 7.12217595463808e-06,
"loss": 2.0653,
"step": 75000
},
{
"epoch": 9.608042758971749,
"grad_norm": 113.8707046508789,
"learning_rate": 7.100026579250465e-06,
"loss": 2.022,
"step": 75500
},
{
"epoch": 9.671672181216595,
"grad_norm": 78.54847717285156,
"learning_rate": 7.077921502613627e-06,
"loss": 2.0327,
"step": 76000
},
{
"epoch": 9.73530160346144,
"grad_norm": 131.4427947998047,
"learning_rate": 7.055772127226013e-06,
"loss": 2.0596,
"step": 76500
},
{
"epoch": 9.798931025706286,
"grad_norm": 120.61900329589844,
"learning_rate": 7.033667050589174e-06,
"loss": 2.0761,
"step": 77000
},
{
"epoch": 9.862560447951132,
"grad_norm": 84.29814147949219,
"learning_rate": 7.01151767520156e-06,
"loss": 2.1245,
"step": 77500
},
{
"epoch": 9.926189870195978,
"grad_norm": 91.78532409667969,
"learning_rate": 6.989368299813946e-06,
"loss": 2.1062,
"step": 78000
},
{
"epoch": 9.989819292440824,
"grad_norm": 111.85667419433594,
"learning_rate": 6.9672189244263324e-06,
"loss": 2.1186,
"step": 78500
},
{
"epoch": 10.05344871468567,
"grad_norm": 97.98519897460938,
"learning_rate": 6.945113847789493e-06,
"loss": 1.8283,
"step": 79000
},
{
"epoch": 10.117078136930516,
"grad_norm": 80.28434753417969,
"learning_rate": 6.9229644724018785e-06,
"loss": 1.7627,
"step": 79500
},
{
"epoch": 10.180707559175362,
"grad_norm": 99.89539337158203,
"learning_rate": 6.900859395765041e-06,
"loss": 1.7775,
"step": 80000
},
{
"epoch": 10.244336981420208,
"grad_norm": 87.49510955810547,
"learning_rate": 6.878710020377426e-06,
"loss": 1.7865,
"step": 80500
},
{
"epoch": 10.307966403665056,
"grad_norm": 87.29383850097656,
"learning_rate": 6.856560644989811e-06,
"loss": 1.8018,
"step": 81000
},
{
"epoch": 10.371595825909901,
"grad_norm": 88.82074737548828,
"learning_rate": 6.834411269602198e-06,
"loss": 1.7851,
"step": 81500
},
{
"epoch": 10.435225248154747,
"grad_norm": 90.42290496826172,
"learning_rate": 6.812261894214583e-06,
"loss": 1.8085,
"step": 82000
},
{
"epoch": 10.498854670399593,
"grad_norm": 85.89569091796875,
"learning_rate": 6.7901125188269704e-06,
"loss": 1.8293,
"step": 82500
},
{
"epoch": 10.56248409264444,
"grad_norm": 89.20499420166016,
"learning_rate": 6.767963143439355e-06,
"loss": 1.8549,
"step": 83000
},
{
"epoch": 10.626113514889285,
"grad_norm": 193.05775451660156,
"learning_rate": 6.745813768051741e-06,
"loss": 1.8531,
"step": 83500
},
{
"epoch": 10.689742937134131,
"grad_norm": 106.58789825439453,
"learning_rate": 6.723664392664127e-06,
"loss": 1.8538,
"step": 84000
},
{
"epoch": 10.753372359378977,
"grad_norm": 136.8468780517578,
"learning_rate": 6.701515017276513e-06,
"loss": 1.8814,
"step": 84500
},
{
"epoch": 10.817001781623823,
"grad_norm": 128.12271118164062,
"learning_rate": 6.679365641888899e-06,
"loss": 1.8576,
"step": 85000
},
{
"epoch": 10.880631203868669,
"grad_norm": 70.90370178222656,
"learning_rate": 6.657216266501285e-06,
"loss": 1.8516,
"step": 85500
},
{
"epoch": 10.944260626113515,
"grad_norm": 77.27445220947266,
"learning_rate": 6.635066891113671e-06,
"loss": 1.8555,
"step": 86000
},
{
"epoch": 11.00789004835836,
"grad_norm": 108.38621520996094,
"learning_rate": 6.612917515726057e-06,
"loss": 1.8631,
"step": 86500
},
{
"epoch": 11.071519470603207,
"grad_norm": 145.12940979003906,
"learning_rate": 6.590768140338443e-06,
"loss": 1.6189,
"step": 87000
},
{
"epoch": 11.135148892848052,
"grad_norm": 115.5062484741211,
"learning_rate": 6.568618764950829e-06,
"loss": 1.6143,
"step": 87500
},
{
"epoch": 11.198778315092898,
"grad_norm": 71.71438598632812,
"learning_rate": 6.546469389563215e-06,
"loss": 1.6246,
"step": 88000
},
{
"epoch": 11.262407737337744,
"grad_norm": 89.9764633178711,
"learning_rate": 6.5243200141756004e-06,
"loss": 1.5997,
"step": 88500
},
{
"epoch": 11.32603715958259,
"grad_norm": 80.51982879638672,
"learning_rate": 6.502170638787987e-06,
"loss": 1.646,
"step": 89000
},
{
"epoch": 11.389666581827438,
"grad_norm": 87.14283752441406,
"learning_rate": 6.4800212634003725e-06,
"loss": 1.6323,
"step": 89500
},
{
"epoch": 11.453296004072284,
"grad_norm": 76.05656433105469,
"learning_rate": 6.457871888012759e-06,
"loss": 1.6623,
"step": 90000
},
{
"epoch": 11.51692542631713,
"grad_norm": 84.08787536621094,
"learning_rate": 6.435722512625145e-06,
"loss": 1.6544,
"step": 90500
},
{
"epoch": 11.580554848561976,
"grad_norm": 113.19395446777344,
"learning_rate": 6.413573137237531e-06,
"loss": 1.6671,
"step": 91000
},
{
"epoch": 11.644184270806822,
"grad_norm": 92.68965911865234,
"learning_rate": 6.391423761849917e-06,
"loss": 1.6742,
"step": 91500
},
{
"epoch": 11.707813693051667,
"grad_norm": 116.95278930664062,
"learning_rate": 6.369274386462302e-06,
"loss": 1.6409,
"step": 92000
},
{
"epoch": 11.771443115296513,
"grad_norm": 77.6058120727539,
"learning_rate": 6.347213608576238e-06,
"loss": 1.6504,
"step": 92500
},
{
"epoch": 11.83507253754136,
"grad_norm": 74.96102142333984,
"learning_rate": 6.3251085319394e-06,
"loss": 1.6791,
"step": 93000
},
{
"epoch": 11.898701959786205,
"grad_norm": 95.83757781982422,
"learning_rate": 6.302959156551785e-06,
"loss": 1.6923,
"step": 93500
},
{
"epoch": 11.962331382031051,
"grad_norm": 114.55757141113281,
"learning_rate": 6.280809781164172e-06,
"loss": 1.697,
"step": 94000
},
{
"epoch": 12.025960804275897,
"grad_norm": 59.73118591308594,
"learning_rate": 6.258660405776557e-06,
"loss": 1.6136,
"step": 94500
},
{
"epoch": 12.089590226520743,
"grad_norm": 86.23199462890625,
"learning_rate": 6.236511030388943e-06,
"loss": 1.4437,
"step": 95000
},
{
"epoch": 12.153219648765589,
"grad_norm": 71.51868438720703,
"learning_rate": 6.2143616550013295e-06,
"loss": 1.49,
"step": 95500
},
{
"epoch": 12.216849071010435,
"grad_norm": 96.19779205322266,
"learning_rate": 6.192212279613715e-06,
"loss": 1.4567,
"step": 96000
},
{
"epoch": 12.28047849325528,
"grad_norm": 79.43608093261719,
"learning_rate": 6.170062904226102e-06,
"loss": 1.5007,
"step": 96500
},
{
"epoch": 12.344107915500127,
"grad_norm": 79.2935791015625,
"learning_rate": 6.147913528838487e-06,
"loss": 1.4826,
"step": 97000
},
{
"epoch": 12.407737337744972,
"grad_norm": 144.53054809570312,
"learning_rate": 6.125764153450873e-06,
"loss": 1.4668,
"step": 97500
},
{
"epoch": 12.47136675998982,
"grad_norm": 105.31471252441406,
"learning_rate": 6.103659076814035e-06,
"loss": 1.5009,
"step": 98000
},
{
"epoch": 12.534996182234666,
"grad_norm": 79.45948028564453,
"learning_rate": 6.08150970142642e-06,
"loss": 1.5008,
"step": 98500
},
{
"epoch": 12.598625604479512,
"grad_norm": 100.81867218017578,
"learning_rate": 6.059360326038807e-06,
"loss": 1.5336,
"step": 99000
},
{
"epoch": 12.662255026724358,
"grad_norm": 94.66363525390625,
"learning_rate": 6.037210950651192e-06,
"loss": 1.5057,
"step": 99500
},
{
"epoch": 12.725884448969204,
"grad_norm": 73.030517578125,
"learning_rate": 6.0150615752635775e-06,
"loss": 1.5081,
"step": 100000
},
{
"epoch": 12.78951387121405,
"grad_norm": 67.0549545288086,
"learning_rate": 5.99295649862674e-06,
"loss": 1.5402,
"step": 100500
},
{
"epoch": 12.853143293458896,
"grad_norm": 91.37773895263672,
"learning_rate": 5.970807123239125e-06,
"loss": 1.5519,
"step": 101000
},
{
"epoch": 12.916772715703742,
"grad_norm": 87.36595153808594,
"learning_rate": 5.948657747851511e-06,
"loss": 1.5171,
"step": 101500
},
{
"epoch": 12.980402137948587,
"grad_norm": 82.45221710205078,
"learning_rate": 5.926508372463897e-06,
"loss": 1.5249,
"step": 102000
},
{
"epoch": 13.044031560193433,
"grad_norm": 67.87359619140625,
"learning_rate": 5.904358997076283e-06,
"loss": 1.4117,
"step": 102500
},
{
"epoch": 13.10766098243828,
"grad_norm": 77.75003814697266,
"learning_rate": 5.882209621688669e-06,
"loss": 1.3524,
"step": 103000
},
{
"epoch": 13.171290404683125,
"grad_norm": 103.19142150878906,
"learning_rate": 5.860060246301055e-06,
"loss": 1.3564,
"step": 103500
},
{
"epoch": 13.234919826927971,
"grad_norm": 82.8349380493164,
"learning_rate": 5.837999468414991e-06,
"loss": 1.3483,
"step": 104000
},
{
"epoch": 13.298549249172817,
"grad_norm": 83.94813537597656,
"learning_rate": 5.815850093027378e-06,
"loss": 1.386,
"step": 104500
},
{
"epoch": 13.362178671417663,
"grad_norm": 80.00110626220703,
"learning_rate": 5.793700717639763e-06,
"loss": 1.3723,
"step": 105000
},
{
"epoch": 13.425808093662509,
"grad_norm": 79.54706573486328,
"learning_rate": 5.771551342252149e-06,
"loss": 1.3933,
"step": 105500
},
{
"epoch": 13.489437515907355,
"grad_norm": 118.33966827392578,
"learning_rate": 5.749401966864535e-06,
"loss": 1.3672,
"step": 106000
},
{
"epoch": 13.553066938152202,
"grad_norm": 148.68141174316406,
"learning_rate": 5.727252591476921e-06,
"loss": 1.3796,
"step": 106500
},
{
"epoch": 13.616696360397048,
"grad_norm": 81.23079681396484,
"learning_rate": 5.705103216089307e-06,
"loss": 1.3637,
"step": 107000
},
{
"epoch": 13.680325782641894,
"grad_norm": 118.37026977539062,
"learning_rate": 5.682953840701693e-06,
"loss": 1.4061,
"step": 107500
},
{
"epoch": 13.74395520488674,
"grad_norm": 87.67139434814453,
"learning_rate": 5.660804465314078e-06,
"loss": 1.3897,
"step": 108000
},
{
"epoch": 13.807584627131586,
"grad_norm": 76.84065246582031,
"learning_rate": 5.638655089926465e-06,
"loss": 1.4342,
"step": 108500
},
{
"epoch": 13.871214049376432,
"grad_norm": 83.0779037475586,
"learning_rate": 5.61650571453885e-06,
"loss": 1.3821,
"step": 109000
},
{
"epoch": 13.934843471621278,
"grad_norm": 63.323001861572266,
"learning_rate": 5.594400637902012e-06,
"loss": 1.411,
"step": 109500
},
{
"epoch": 13.998472893866124,
"grad_norm": 75.757080078125,
"learning_rate": 5.572295561265173e-06,
"loss": 1.4214,
"step": 110000
},
{
"epoch": 14.06210231611097,
"grad_norm": 47.76633071899414,
"learning_rate": 5.550146185877559e-06,
"loss": 1.2551,
"step": 110500
},
{
"epoch": 14.125731738355816,
"grad_norm": 67.52932739257812,
"learning_rate": 5.528041109240719e-06,
"loss": 1.2366,
"step": 111000
},
{
"epoch": 14.189361160600662,
"grad_norm": 77.91776275634766,
"learning_rate": 5.505891733853106e-06,
"loss": 1.2553,
"step": 111500
},
{
"epoch": 14.252990582845507,
"grad_norm": 74.56119537353516,
"learning_rate": 5.4837423584654914e-06,
"loss": 1.2553,
"step": 112000
},
{
"epoch": 14.316620005090353,
"grad_norm": 70.80554962158203,
"learning_rate": 5.461592983077878e-06,
"loss": 1.2624,
"step": 112500
},
{
"epoch": 14.3802494273352,
"grad_norm": 72.7087631225586,
"learning_rate": 5.4394436076902635e-06,
"loss": 1.2771,
"step": 113000
},
{
"epoch": 14.443878849580045,
"grad_norm": 81.98471069335938,
"learning_rate": 5.41729423230265e-06,
"loss": 1.2744,
"step": 113500
},
{
"epoch": 14.507508271824891,
"grad_norm": 71.72978973388672,
"learning_rate": 5.395189155665811e-06,
"loss": 1.2616,
"step": 114000
},
{
"epoch": 14.571137694069737,
"grad_norm": 73.07415771484375,
"learning_rate": 5.373039780278196e-06,
"loss": 1.2744,
"step": 114500
},
{
"epoch": 14.634767116314585,
"grad_norm": 46.78715133666992,
"learning_rate": 5.350890404890583e-06,
"loss": 1.2705,
"step": 115000
},
{
"epoch": 14.69839653855943,
"grad_norm": 80.48126220703125,
"learning_rate": 5.328741029502968e-06,
"loss": 1.3005,
"step": 115500
},
{
"epoch": 14.762025960804277,
"grad_norm": 78.11446380615234,
"learning_rate": 5.306591654115354e-06,
"loss": 1.3013,
"step": 116000
},
{
"epoch": 14.825655383049122,
"grad_norm": 113.7435302734375,
"learning_rate": 5.28444227872774e-06,
"loss": 1.298,
"step": 116500
},
{
"epoch": 14.889284805293968,
"grad_norm": 58.536346435546875,
"learning_rate": 5.262292903340126e-06,
"loss": 1.2972,
"step": 117000
},
{
"epoch": 14.952914227538814,
"grad_norm": 85.87594604492188,
"learning_rate": 5.240143527952512e-06,
"loss": 1.277,
"step": 117500
},
{
"epoch": 15.01654364978366,
"grad_norm": 61.39375305175781,
"learning_rate": 5.217994152564898e-06,
"loss": 1.2718,
"step": 118000
},
{
"epoch": 15.080173072028506,
"grad_norm": 64.70631408691406,
"learning_rate": 5.1958447771772836e-06,
"loss": 1.1697,
"step": 118500
},
{
"epoch": 15.143802494273352,
"grad_norm": 81.51799774169922,
"learning_rate": 5.17369540178967e-06,
"loss": 1.1819,
"step": 119000
},
{
"epoch": 15.207431916518198,
"grad_norm": 81.38251495361328,
"learning_rate": 5.151546026402056e-06,
"loss": 1.1916,
"step": 119500
},
{
"epoch": 15.271061338763044,
"grad_norm": 87.31340789794922,
"learning_rate": 5.129396651014442e-06,
"loss": 1.1829,
"step": 120000
},
{
"epoch": 15.33469076100789,
"grad_norm": 67.25629425048828,
"learning_rate": 5.107247275626828e-06,
"loss": 1.1632,
"step": 120500
},
{
"epoch": 15.398320183252736,
"grad_norm": 56.04712677001953,
"learning_rate": 5.085097900239213e-06,
"loss": 1.1809,
"step": 121000
},
{
"epoch": 15.461949605497582,
"grad_norm": 66.33815002441406,
"learning_rate": 5.0629928236023755e-06,
"loss": 1.1913,
"step": 121500
},
{
"epoch": 15.525579027742427,
"grad_norm": 69.98699951171875,
"learning_rate": 5.04084344821476e-06,
"loss": 1.1916,
"step": 122000
},
{
"epoch": 15.589208449987273,
"grad_norm": 70.65410614013672,
"learning_rate": 5.018694072827147e-06,
"loss": 1.1969,
"step": 122500
},
{
"epoch": 15.65283787223212,
"grad_norm": 68.66796875,
"learning_rate": 4.996544697439532e-06,
"loss": 1.1929,
"step": 123000
},
{
"epoch": 15.716467294476967,
"grad_norm": 68.35984802246094,
"learning_rate": 4.974439620802694e-06,
"loss": 1.2086,
"step": 123500
},
{
"epoch": 15.780096716721813,
"grad_norm": 64.63552856445312,
"learning_rate": 4.952290245415079e-06,
"loss": 1.1864,
"step": 124000
},
{
"epoch": 15.843726138966659,
"grad_norm": 59.172645568847656,
"learning_rate": 4.930140870027466e-06,
"loss": 1.2068,
"step": 124500
},
{
"epoch": 15.907355561211505,
"grad_norm": 64.2562255859375,
"learning_rate": 4.907991494639851e-06,
"loss": 1.2253,
"step": 125000
},
{
"epoch": 15.97098498345635,
"grad_norm": 61.80392837524414,
"learning_rate": 4.885842119252238e-06,
"loss": 1.1963,
"step": 125500
},
{
"epoch": 16.034614405701195,
"grad_norm": 86.79552459716797,
"learning_rate": 4.8636927438646234e-06,
"loss": 1.1585,
"step": 126000
},
{
"epoch": 16.098243827946042,
"grad_norm": 81.79373931884766,
"learning_rate": 4.841543368477009e-06,
"loss": 1.0834,
"step": 126500
},
{
"epoch": 16.161873250190887,
"grad_norm": 60.24835205078125,
"learning_rate": 4.8193939930893955e-06,
"loss": 1.0937,
"step": 127000
},
{
"epoch": 16.225502672435734,
"grad_norm": 74.93160247802734,
"learning_rate": 4.797244617701781e-06,
"loss": 1.0995,
"step": 127500
},
{
"epoch": 16.289132094680582,
"grad_norm": 75.08971405029297,
"learning_rate": 4.775095242314168e-06,
"loss": 1.0787,
"step": 128000
},
{
"epoch": 16.352761516925426,
"grad_norm": 66.41687774658203,
"learning_rate": 4.752990165677328e-06,
"loss": 1.1217,
"step": 128500
},
{
"epoch": 16.416390939170274,
"grad_norm": 68.62983703613281,
"learning_rate": 4.730840790289714e-06,
"loss": 1.1185,
"step": 129000
},
{
"epoch": 16.480020361415118,
"grad_norm": 67.19387817382812,
"learning_rate": 4.7086914149021e-06,
"loss": 1.1203,
"step": 129500
},
{
"epoch": 16.543649783659966,
"grad_norm": 84.18933868408203,
"learning_rate": 4.686542039514486e-06,
"loss": 1.1201,
"step": 130000
},
{
"epoch": 16.60727920590481,
"grad_norm": 56.41159439086914,
"learning_rate": 4.664392664126872e-06,
"loss": 1.125,
"step": 130500
},
{
"epoch": 16.670908628149657,
"grad_norm": 90.81446075439453,
"learning_rate": 4.642376184991584e-06,
"loss": 1.1214,
"step": 131000
},
{
"epoch": 16.7345380503945,
"grad_norm": 66.80113220214844,
"learning_rate": 4.62022680960397e-06,
"loss": 1.1228,
"step": 131500
},
{
"epoch": 16.79816747263935,
"grad_norm": 68.8161849975586,
"learning_rate": 4.598077434216355e-06,
"loss": 1.1381,
"step": 132000
},
{
"epoch": 16.861796894884193,
"grad_norm": 80.11527252197266,
"learning_rate": 4.575928058828742e-06,
"loss": 1.1414,
"step": 132500
},
{
"epoch": 16.92542631712904,
"grad_norm": 64.7822036743164,
"learning_rate": 4.553778683441127e-06,
"loss": 1.123,
"step": 133000
},
{
"epoch": 16.989055739373885,
"grad_norm": 65.32453918457031,
"learning_rate": 4.531629308053514e-06,
"loss": 1.1003,
"step": 133500
},
{
"epoch": 17.052685161618733,
"grad_norm": 91.62205505371094,
"learning_rate": 4.5094799326658994e-06,
"loss": 1.0447,
"step": 134000
},
{
"epoch": 17.116314583863577,
"grad_norm": 49.810699462890625,
"learning_rate": 4.487330557278285e-06,
"loss": 1.036,
"step": 134500
},
{
"epoch": 17.179944006108425,
"grad_norm": 64.78093719482422,
"learning_rate": 4.465181181890671e-06,
"loss": 1.0264,
"step": 135000
},
{
"epoch": 17.24357342835327,
"grad_norm": 61.86587905883789,
"learning_rate": 4.443031806503057e-06,
"loss": 1.0375,
"step": 135500
},
{
"epoch": 17.307202850598117,
"grad_norm": 57.83167266845703,
"learning_rate": 4.420882431115443e-06,
"loss": 1.0509,
"step": 136000
},
{
"epoch": 17.370832272842964,
"grad_norm": 81.06472778320312,
"learning_rate": 4.398733055727829e-06,
"loss": 1.0452,
"step": 136500
},
{
"epoch": 17.43446169508781,
"grad_norm": 77.34078979492188,
"learning_rate": 4.376583680340215e-06,
"loss": 1.0519,
"step": 137000
},
{
"epoch": 17.498091117332656,
"grad_norm": 75.93341064453125,
"learning_rate": 4.3544343049526005e-06,
"loss": 1.0498,
"step": 137500
},
{
"epoch": 17.5617205395775,
"grad_norm": 56.93536376953125,
"learning_rate": 4.332284929564987e-06,
"loss": 1.0514,
"step": 138000
},
{
"epoch": 17.625349961822348,
"grad_norm": 63.56499481201172,
"learning_rate": 4.310179852928148e-06,
"loss": 1.054,
"step": 138500
},
{
"epoch": 17.688979384067192,
"grad_norm": 71.97218322753906,
"learning_rate": 4.288030477540534e-06,
"loss": 1.0457,
"step": 139000
},
{
"epoch": 17.75260880631204,
"grad_norm": 63.93644332885742,
"learning_rate": 4.265925400903695e-06,
"loss": 1.0582,
"step": 139500
},
{
"epoch": 17.816238228556884,
"grad_norm": 60.03602981567383,
"learning_rate": 4.243776025516081e-06,
"loss": 1.0566,
"step": 140000
},
{
"epoch": 17.87986765080173,
"grad_norm": 66.63105010986328,
"learning_rate": 4.221626650128467e-06,
"loss": 1.0644,
"step": 140500
},
{
"epoch": 17.943497073046576,
"grad_norm": 66.42560577392578,
"learning_rate": 4.199477274740853e-06,
"loss": 1.0579,
"step": 141000
},
{
"epoch": 18.007126495291423,
"grad_norm": 58.22215270996094,
"learning_rate": 4.1773278993532385e-06,
"loss": 1.0647,
"step": 141500
},
{
"epoch": 18.070755917536268,
"grad_norm": 63.40778350830078,
"learning_rate": 4.155178523965624e-06,
"loss": 0.9704,
"step": 142000
},
{
"epoch": 18.134385339781115,
"grad_norm": 67.59272003173828,
"learning_rate": 4.1330291485780105e-06,
"loss": 0.9787,
"step": 142500
},
{
"epoch": 18.19801476202596,
"grad_norm": 58.86367416381836,
"learning_rate": 4.110879773190396e-06,
"loss": 0.9875,
"step": 143000
},
{
"epoch": 18.261644184270807,
"grad_norm": 72.68678283691406,
"learning_rate": 4.088730397802782e-06,
"loss": 0.987,
"step": 143500
},
{
"epoch": 18.32527360651565,
"grad_norm": 69.95580291748047,
"learning_rate": 4.066581022415168e-06,
"loss": 0.9834,
"step": 144000
},
{
"epoch": 18.3889030287605,
"grad_norm": 63.809104919433594,
"learning_rate": 4.044431647027554e-06,
"loss": 0.999,
"step": 144500
},
{
"epoch": 18.452532451005347,
"grad_norm": 76.64576721191406,
"learning_rate": 4.02228227163994e-06,
"loss": 0.9872,
"step": 145000
},
{
"epoch": 18.51616187325019,
"grad_norm": 54.77001953125,
"learning_rate": 4.000177195003101e-06,
"loss": 0.9851,
"step": 145500
},
{
"epoch": 18.57979129549504,
"grad_norm": 67.22696685791016,
"learning_rate": 3.978027819615487e-06,
"loss": 0.9986,
"step": 146000
},
{
"epoch": 18.643420717739883,
"grad_norm": 69.88746643066406,
"learning_rate": 3.955878444227873e-06,
"loss": 0.9853,
"step": 146500
},
{
"epoch": 18.70705013998473,
"grad_norm": 66.42214965820312,
"learning_rate": 3.933729068840259e-06,
"loss": 0.9973,
"step": 147000
},
{
"epoch": 18.770679562229574,
"grad_norm": 75.5511245727539,
"learning_rate": 3.9116682909541955e-06,
"loss": 0.988,
"step": 147500
},
{
"epoch": 18.834308984474422,
"grad_norm": 73.2605209350586,
"learning_rate": 3.889518915566581e-06,
"loss": 0.999,
"step": 148000
},
{
"epoch": 18.897938406719266,
"grad_norm": 63.08274841308594,
"learning_rate": 3.8673695401789675e-06,
"loss": 0.9899,
"step": 148500
},
{
"epoch": 18.961567828964114,
"grad_norm": 98.51166534423828,
"learning_rate": 3.845220164791353e-06,
"loss": 1.0053,
"step": 149000
},
{
"epoch": 19.025197251208958,
"grad_norm": 67.6368408203125,
"learning_rate": 3.823070789403739e-06,
"loss": 0.9802,
"step": 149500
},
{
"epoch": 19.088826673453806,
"grad_norm": 71.1702880859375,
"learning_rate": 3.800921414016125e-06,
"loss": 0.9301,
"step": 150000
},
{
"epoch": 19.15245609569865,
"grad_norm": 74.88888549804688,
"learning_rate": 3.778772038628511e-06,
"loss": 0.9295,
"step": 150500
},
{
"epoch": 19.216085517943498,
"grad_norm": 49.797691345214844,
"learning_rate": 3.756622663240897e-06,
"loss": 0.9334,
"step": 151000
},
{
"epoch": 19.27971494018834,
"grad_norm": 49.12934875488281,
"learning_rate": 3.734473287853283e-06,
"loss": 0.9503,
"step": 151500
},
{
"epoch": 19.34334436243319,
"grad_norm": 47.530452728271484,
"learning_rate": 3.712323912465669e-06,
"loss": 0.9161,
"step": 152000
},
{
"epoch": 19.406973784678033,
"grad_norm": 69.1083984375,
"learning_rate": 3.6901745370780546e-06,
"loss": 0.9433,
"step": 152500
},
{
"epoch": 19.47060320692288,
"grad_norm": 62.554718017578125,
"learning_rate": 3.6680251616904407e-06,
"loss": 0.9376,
"step": 153000
},
{
"epoch": 19.53423262916773,
"grad_norm": 55.151100158691406,
"learning_rate": 3.645920085053602e-06,
"loss": 0.9274,
"step": 153500
},
{
"epoch": 19.597862051412573,
"grad_norm": 60.6050910949707,
"learning_rate": 3.623770709665988e-06,
"loss": 0.9414,
"step": 154000
},
{
"epoch": 19.66149147365742,
"grad_norm": 55.62131118774414,
"learning_rate": 3.6016213342783736e-06,
"loss": 0.94,
"step": 154500
},
{
"epoch": 19.725120895902265,
"grad_norm": 59.69659423828125,
"learning_rate": 3.5794719588907597e-06,
"loss": 0.9344,
"step": 155000
},
{
"epoch": 19.788750318147112,
"grad_norm": 46.444984436035156,
"learning_rate": 3.557366882253921e-06,
"loss": 0.9464,
"step": 155500
},
{
"epoch": 19.852379740391957,
"grad_norm": 63.4849739074707,
"learning_rate": 3.535217506866307e-06,
"loss": 0.9583,
"step": 156000
},
{
"epoch": 19.916009162636804,
"grad_norm": 69.28148651123047,
"learning_rate": 3.5130681314786926e-06,
"loss": 0.953,
"step": 156500
},
{
"epoch": 19.97963858488165,
"grad_norm": 127.65802764892578,
"learning_rate": 3.4909187560910782e-06,
"loss": 0.9481,
"step": 157000
},
{
"epoch": 20.043268007126496,
"grad_norm": 64.03028106689453,
"learning_rate": 3.46881367945424e-06,
"loss": 0.8982,
"step": 157500
},
{
"epoch": 20.10689742937134,
"grad_norm": 68.30170440673828,
"learning_rate": 3.446664304066625e-06,
"loss": 0.8974,
"step": 158000
},
{
"epoch": 20.170526851616188,
"grad_norm": 44.01250457763672,
"learning_rate": 3.424514928679011e-06,
"loss": 0.9022,
"step": 158500
},
{
"epoch": 20.234156273861032,
"grad_norm": 65.26950073242188,
"learning_rate": 3.4023655532913972e-06,
"loss": 0.8923,
"step": 159000
},
{
"epoch": 20.29778569610588,
"grad_norm": 46.552730560302734,
"learning_rate": 3.380260476654559e-06,
"loss": 0.8935,
"step": 159500
},
{
"epoch": 20.361415118350724,
"grad_norm": 59.73283767700195,
"learning_rate": 3.358111101266944e-06,
"loss": 0.8917,
"step": 160000
},
{
"epoch": 20.42504454059557,
"grad_norm": 84.19660186767578,
"learning_rate": 3.33596172587933e-06,
"loss": 0.9021,
"step": 160500
},
{
"epoch": 20.488673962840416,
"grad_norm": 48.705833435058594,
"learning_rate": 3.3138123504917162e-06,
"loss": 0.8978,
"step": 161000
},
{
"epoch": 20.552303385085263,
"grad_norm": 44.999656677246094,
"learning_rate": 3.2916629751041023e-06,
"loss": 0.9078,
"step": 161500
},
{
"epoch": 20.61593280733011,
"grad_norm": 62.21163558959961,
"learning_rate": 3.2695135997164883e-06,
"loss": 0.903,
"step": 162000
},
{
"epoch": 20.679562229574955,
"grad_norm": 61.40314483642578,
"learning_rate": 3.247408523079649e-06,
"loss": 0.8989,
"step": 162500
},
{
"epoch": 20.743191651819803,
"grad_norm": 55.93895721435547,
"learning_rate": 3.2252591476920352e-06,
"loss": 0.9023,
"step": 163000
},
{
"epoch": 20.806821074064647,
"grad_norm": 64.3861312866211,
"learning_rate": 3.2031097723044213e-06,
"loss": 0.8918,
"step": 163500
},
{
"epoch": 20.870450496309495,
"grad_norm": 92.62686157226562,
"learning_rate": 3.1809603969168073e-06,
"loss": 0.8968,
"step": 164000
},
{
"epoch": 20.93407991855434,
"grad_norm": 58.37923049926758,
"learning_rate": 3.1588110215291934e-06,
"loss": 0.8977,
"step": 164500
},
{
"epoch": 20.997709340799187,
"grad_norm": 49.36125564575195,
"learning_rate": 3.136661646141579e-06,
"loss": 0.9035,
"step": 165000
},
{
"epoch": 21.06133876304403,
"grad_norm": 69.00907135009766,
"learning_rate": 3.114512270753965e-06,
"loss": 0.8347,
"step": 165500
},
{
"epoch": 21.12496818528888,
"grad_norm": 56.581600189208984,
"learning_rate": 3.0924071941171263e-06,
"loss": 0.8415,
"step": 166000
},
{
"epoch": 21.188597607533723,
"grad_norm": 56.39949417114258,
"learning_rate": 3.0702578187295124e-06,
"loss": 0.8472,
"step": 166500
},
{
"epoch": 21.25222702977857,
"grad_norm": 58.36819839477539,
"learning_rate": 3.048108443341898e-06,
"loss": 0.8663,
"step": 167000
},
{
"epoch": 21.315856452023414,
"grad_norm": 59.97529602050781,
"learning_rate": 3.025959067954284e-06,
"loss": 0.8633,
"step": 167500
},
{
"epoch": 21.379485874268262,
"grad_norm": 52.96846008300781,
"learning_rate": 3.00380969256667e-06,
"loss": 0.8569,
"step": 168000
},
{
"epoch": 21.443115296513106,
"grad_norm": 52.254085540771484,
"learning_rate": 2.981660317179056e-06,
"loss": 0.8529,
"step": 168500
},
{
"epoch": 21.506744718757954,
"grad_norm": 80.7918472290039,
"learning_rate": 2.959555240542217e-06,
"loss": 0.8485,
"step": 169000
},
{
"epoch": 21.570374141002798,
"grad_norm": 59.65958023071289,
"learning_rate": 2.9374058651546026e-06,
"loss": 0.8759,
"step": 169500
},
{
"epoch": 21.634003563247646,
"grad_norm": 48.33919906616211,
"learning_rate": 2.9152564897669886e-06,
"loss": 0.8667,
"step": 170000
},
{
"epoch": 21.697632985492493,
"grad_norm": 68.83987426757812,
"learning_rate": 2.8931071143793747e-06,
"loss": 0.8615,
"step": 170500
},
{
"epoch": 21.761262407737338,
"grad_norm": 42.605552673339844,
"learning_rate": 2.8709577389917607e-06,
"loss": 0.8623,
"step": 171000
},
{
"epoch": 21.824891829982185,
"grad_norm": 57.37046432495117,
"learning_rate": 2.8488083636041464e-06,
"loss": 0.8613,
"step": 171500
},
{
"epoch": 21.88852125222703,
"grad_norm": 66.89559173583984,
"learning_rate": 2.8266589882165324e-06,
"loss": 0.8515,
"step": 172000
},
{
"epoch": 21.952150674471877,
"grad_norm": 53.939571380615234,
"learning_rate": 2.8045096128289184e-06,
"loss": 0.8615,
"step": 172500
},
{
"epoch": 22.01578009671672,
"grad_norm": 61.67373275756836,
"learning_rate": 2.7824045361920797e-06,
"loss": 0.8457,
"step": 173000
},
{
"epoch": 22.07940951896157,
"grad_norm": 71.31520080566406,
"learning_rate": 2.7602551608044653e-06,
"loss": 0.8106,
"step": 173500
},
{
"epoch": 22.143038941206413,
"grad_norm": 44.70698165893555,
"learning_rate": 2.7381057854168514e-06,
"loss": 0.8109,
"step": 174000
},
{
"epoch": 22.20666836345126,
"grad_norm": 43.95622253417969,
"learning_rate": 2.7159564100292374e-06,
"loss": 0.8108,
"step": 174500
},
{
"epoch": 22.270297785696105,
"grad_norm": 55.156822204589844,
"learning_rate": 2.6938513333923987e-06,
"loss": 0.8197,
"step": 175000
},
{
"epoch": 22.333927207940953,
"grad_norm": 85.59542846679688,
"learning_rate": 2.6717019580047843e-06,
"loss": 0.8165,
"step": 175500
},
{
"epoch": 22.397556630185797,
"grad_norm": 65.07913208007812,
"learning_rate": 2.6495525826171704e-06,
"loss": 0.8289,
"step": 176000
},
{
"epoch": 22.461186052430644,
"grad_norm": 65.89120483398438,
"learning_rate": 2.6274032072295564e-06,
"loss": 0.8288,
"step": 176500
},
{
"epoch": 22.52481547467549,
"grad_norm": 55.914939880371094,
"learning_rate": 2.6052981305927177e-06,
"loss": 0.8145,
"step": 177000
},
{
"epoch": 22.588444896920336,
"grad_norm": 80.44625854492188,
"learning_rate": 2.5831487552051033e-06,
"loss": 0.8249,
"step": 177500
},
{
"epoch": 22.65207431916518,
"grad_norm": 65.78691101074219,
"learning_rate": 2.5609993798174894e-06,
"loss": 0.8218,
"step": 178000
},
{
"epoch": 22.715703741410028,
"grad_norm": 41.24105453491211,
"learning_rate": 2.5388500044298754e-06,
"loss": 0.8284,
"step": 178500
},
{
"epoch": 22.779333163654876,
"grad_norm": 64.46809387207031,
"learning_rate": 2.5167892265438115e-06,
"loss": 0.833,
"step": 179000
},
{
"epoch": 22.84296258589972,
"grad_norm": 56.47655487060547,
"learning_rate": 2.4946398511561976e-06,
"loss": 0.8176,
"step": 179500
},
{
"epoch": 22.906592008144568,
"grad_norm": 71.83133697509766,
"learning_rate": 2.4724904757685836e-06,
"loss": 0.8431,
"step": 180000
},
{
"epoch": 22.97022143038941,
"grad_norm": 53.66551971435547,
"learning_rate": 2.450385399131745e-06,
"loss": 0.8234,
"step": 180500
},
{
"epoch": 23.03385085263426,
"grad_norm": 78.90325927734375,
"learning_rate": 2.4282360237441305e-06,
"loss": 0.7998,
"step": 181000
},
{
"epoch": 23.097480274879103,
"grad_norm": 64.31370544433594,
"learning_rate": 2.4060866483565166e-06,
"loss": 0.7821,
"step": 181500
},
{
"epoch": 23.16110969712395,
"grad_norm": 48.68030548095703,
"learning_rate": 2.3839372729689026e-06,
"loss": 0.7914,
"step": 182000
},
{
"epoch": 23.224739119368795,
"grad_norm": 52.06983184814453,
"learning_rate": 2.3617878975812882e-06,
"loss": 0.7851,
"step": 182500
},
{
"epoch": 23.288368541613643,
"grad_norm": 50.310157775878906,
"learning_rate": 2.3396385221936743e-06,
"loss": 0.7797,
"step": 183000
},
{
"epoch": 23.351997963858487,
"grad_norm": 52.41871643066406,
"learning_rate": 2.3174891468060603e-06,
"loss": 0.7931,
"step": 183500
},
{
"epoch": 23.415627386103335,
"grad_norm": 88.78260040283203,
"learning_rate": 2.295339771418446e-06,
"loss": 0.7912,
"step": 184000
},
{
"epoch": 23.47925680834818,
"grad_norm": 62.528663635253906,
"learning_rate": 2.273190396030832e-06,
"loss": 0.7876,
"step": 184500
},
{
"epoch": 23.542886230593027,
"grad_norm": 46.27097702026367,
"learning_rate": 2.251041020643218e-06,
"loss": 0.7954,
"step": 185000
},
{
"epoch": 23.60651565283787,
"grad_norm": 50.20694351196289,
"learning_rate": 2.228891645255604e-06,
"loss": 0.7946,
"step": 185500
},
{
"epoch": 23.67014507508272,
"grad_norm": 56.892765045166016,
"learning_rate": 2.20674226986799e-06,
"loss": 0.7782,
"step": 186000
},
{
"epoch": 23.733774497327563,
"grad_norm": 41.52644729614258,
"learning_rate": 2.184637193231151e-06,
"loss": 0.7952,
"step": 186500
},
{
"epoch": 23.79740391957241,
"grad_norm": 58.025516510009766,
"learning_rate": 2.162487817843537e-06,
"loss": 0.8015,
"step": 187000
},
{
"epoch": 23.861033341817258,
"grad_norm": 48.62569046020508,
"learning_rate": 2.140338442455923e-06,
"loss": 0.7977,
"step": 187500
},
{
"epoch": 23.924662764062102,
"grad_norm": 46.91473388671875,
"learning_rate": 2.1181890670683087e-06,
"loss": 0.7875,
"step": 188000
},
{
"epoch": 23.98829218630695,
"grad_norm": 52.42847442626953,
"learning_rate": 2.09608399043147e-06,
"loss": 0.7935,
"step": 188500
},
{
"epoch": 24.051921608551794,
"grad_norm": 76.6783676147461,
"learning_rate": 2.073934615043856e-06,
"loss": 0.7617,
"step": 189000
},
{
"epoch": 24.11555103079664,
"grad_norm": 67.17424011230469,
"learning_rate": 2.0517852396562417e-06,
"loss": 0.7625,
"step": 189500
},
{
"epoch": 24.179180453041486,
"grad_norm": 50.021053314208984,
"learning_rate": 2.0296358642686277e-06,
"loss": 0.7514,
"step": 190000
},
{
"epoch": 24.242809875286333,
"grad_norm": 53.048465728759766,
"learning_rate": 2.0074864888810137e-06,
"loss": 0.7662,
"step": 190500
},
{
"epoch": 24.306439297531178,
"grad_norm": 67.73706817626953,
"learning_rate": 1.9854257109949503e-06,
"loss": 0.7692,
"step": 191000
},
{
"epoch": 24.370068719776025,
"grad_norm": 57.47793960571289,
"learning_rate": 1.9632763356073363e-06,
"loss": 0.7733,
"step": 191500
},
{
"epoch": 24.43369814202087,
"grad_norm": 59.039405822753906,
"learning_rate": 1.941126960219722e-06,
"loss": 0.7561,
"step": 192000
},
{
"epoch": 24.497327564265717,
"grad_norm": 46.10505676269531,
"learning_rate": 1.918977584832108e-06,
"loss": 0.7577,
"step": 192500
},
{
"epoch": 24.56095698651056,
"grad_norm": 85.20184326171875,
"learning_rate": 1.8968282094444936e-06,
"loss": 0.7687,
"step": 193000
},
{
"epoch": 24.62458640875541,
"grad_norm": 53.42023849487305,
"learning_rate": 1.8746788340568796e-06,
"loss": 0.7647,
"step": 193500
},
{
"epoch": 24.688215831000253,
"grad_norm": 63.070919036865234,
"learning_rate": 1.852573757420041e-06,
"loss": 0.7717,
"step": 194000
},
{
"epoch": 24.7518452532451,
"grad_norm": 59.02709197998047,
"learning_rate": 1.830424382032427e-06,
"loss": 0.761,
"step": 194500
},
{
"epoch": 24.815474675489945,
"grad_norm": 47.43505859375,
"learning_rate": 1.8082750066448126e-06,
"loss": 0.7661,
"step": 195000
},
{
"epoch": 24.879104097734793,
"grad_norm": 79.37848663330078,
"learning_rate": 1.7861256312571986e-06,
"loss": 0.7446,
"step": 195500
},
{
"epoch": 24.94273351997964,
"grad_norm": 51.29045104980469,
"learning_rate": 1.7639762558695847e-06,
"loss": 0.7659,
"step": 196000
},
{
"epoch": 25.006362942224484,
"grad_norm": 43.27066421508789,
"learning_rate": 1.7418711792327458e-06,
"loss": 0.7559,
"step": 196500
},
{
"epoch": 25.069992364469332,
"grad_norm": 45.82556915283203,
"learning_rate": 1.7197218038451316e-06,
"loss": 0.7183,
"step": 197000
},
{
"epoch": 25.133621786714176,
"grad_norm": 61.48518753051758,
"learning_rate": 1.6975724284575176e-06,
"loss": 0.7399,
"step": 197500
},
{
"epoch": 25.197251208959024,
"grad_norm": 56.30770492553711,
"learning_rate": 1.6754230530699037e-06,
"loss": 0.7308,
"step": 198000
},
{
"epoch": 25.260880631203868,
"grad_norm": 77.96941375732422,
"learning_rate": 1.6532736776822895e-06,
"loss": 0.733,
"step": 198500
},
{
"epoch": 25.324510053448716,
"grad_norm": 75.03907775878906,
"learning_rate": 1.6311243022946753e-06,
"loss": 0.746,
"step": 199000
},
{
"epoch": 25.38813947569356,
"grad_norm": 49.624366760253906,
"learning_rate": 1.6089749269070614e-06,
"loss": 0.7274,
"step": 199500
},
{
"epoch": 25.451768897938408,
"grad_norm": 54.31991195678711,
"learning_rate": 1.5868255515194472e-06,
"loss": 0.7358,
"step": 200000
},
{
"epoch": 25.51539832018325,
"grad_norm": 57.31879425048828,
"learning_rate": 1.5646761761318333e-06,
"loss": 0.7468,
"step": 200500
},
{
"epoch": 25.5790277424281,
"grad_norm": 51.115596771240234,
"learning_rate": 1.5425710994949943e-06,
"loss": 0.734,
"step": 201000
},
{
"epoch": 25.642657164672944,
"grad_norm": 68.8400650024414,
"learning_rate": 1.5204660228581556e-06,
"loss": 0.7493,
"step": 201500
},
{
"epoch": 25.70628658691779,
"grad_norm": 40.318153381347656,
"learning_rate": 1.4983166474705415e-06,
"loss": 0.7263,
"step": 202000
},
{
"epoch": 25.769916009162635,
"grad_norm": 63.84051513671875,
"learning_rate": 1.4761672720829273e-06,
"loss": 0.7355,
"step": 202500
},
{
"epoch": 25.833545431407483,
"grad_norm": 61.53810501098633,
"learning_rate": 1.4540178966953133e-06,
"loss": 0.745,
"step": 203000
},
{
"epoch": 25.897174853652327,
"grad_norm": 51.513187408447266,
"learning_rate": 1.4318685213076994e-06,
"loss": 0.7301,
"step": 203500
},
{
"epoch": 25.960804275897175,
"grad_norm": 65.9397201538086,
"learning_rate": 1.4097191459200852e-06,
"loss": 0.7457,
"step": 204000
},
{
"epoch": 26.024433698142023,
"grad_norm": 59.864540100097656,
"learning_rate": 1.3875697705324713e-06,
"loss": 0.7072,
"step": 204500
},
{
"epoch": 26.088063120386867,
"grad_norm": 52.43559646606445,
"learning_rate": 1.3654203951448569e-06,
"loss": 0.7212,
"step": 205000
},
{
"epoch": 26.151692542631714,
"grad_norm": 45.977447509765625,
"learning_rate": 1.343315318508018e-06,
"loss": 0.7186,
"step": 205500
},
{
"epoch": 26.21532196487656,
"grad_norm": 48.874996185302734,
"learning_rate": 1.321165943120404e-06,
"loss": 0.7225,
"step": 206000
},
{
"epoch": 26.278951387121406,
"grad_norm": 57.50956344604492,
"learning_rate": 1.29901656773279e-06,
"loss": 0.7065,
"step": 206500
},
{
"epoch": 26.34258080936625,
"grad_norm": 64.73326110839844,
"learning_rate": 1.2768671923451759e-06,
"loss": 0.7153,
"step": 207000
},
{
"epoch": 26.406210231611098,
"grad_norm": 53.96969223022461,
"learning_rate": 1.254762115708337e-06,
"loss": 0.72,
"step": 207500
},
{
"epoch": 26.469839653855942,
"grad_norm": 56.118255615234375,
"learning_rate": 1.232612740320723e-06,
"loss": 0.7074,
"step": 208000
},
{
"epoch": 26.53346907610079,
"grad_norm": 57.4562873840332,
"learning_rate": 1.2104633649331088e-06,
"loss": 0.7117,
"step": 208500
},
{
"epoch": 26.597098498345634,
"grad_norm": 60.367919921875,
"learning_rate": 1.1883139895454949e-06,
"loss": 0.7206,
"step": 209000
},
{
"epoch": 26.66072792059048,
"grad_norm": 55.18882369995117,
"learning_rate": 1.166164614157881e-06,
"loss": 0.7132,
"step": 209500
},
{
"epoch": 26.724357342835326,
"grad_norm": 48.3643798828125,
"learning_rate": 1.144059537521042e-06,
"loss": 0.7199,
"step": 210000
},
{
"epoch": 26.787986765080174,
"grad_norm": 50.825225830078125,
"learning_rate": 1.1219101621334278e-06,
"loss": 0.7102,
"step": 210500
},
{
"epoch": 26.851616187325018,
"grad_norm": 36.502899169921875,
"learning_rate": 1.0997607867458139e-06,
"loss": 0.7155,
"step": 211000
},
{
"epoch": 26.915245609569865,
"grad_norm": 58.10041809082031,
"learning_rate": 1.0776114113581997e-06,
"loss": 0.7057,
"step": 211500
},
{
"epoch": 26.97887503181471,
"grad_norm": 41.11175537109375,
"learning_rate": 1.055506334721361e-06,
"loss": 0.7191,
"step": 212000
},
{
"epoch": 27.042504454059557,
"grad_norm": 56.8629150390625,
"learning_rate": 1.0333569593337468e-06,
"loss": 0.6942,
"step": 212500
},
{
"epoch": 27.106133876304405,
"grad_norm": 43.03855514526367,
"learning_rate": 1.011251882696908e-06,
"loss": 0.6924,
"step": 213000
},
{
"epoch": 27.16976329854925,
"grad_norm": 41.03914260864258,
"learning_rate": 9.89102507309294e-07,
"loss": 0.7025,
"step": 213500
},
{
"epoch": 27.233392720794097,
"grad_norm": 44.40423583984375,
"learning_rate": 9.6695313192168e-07,
"loss": 0.6911,
"step": 214000
},
{
"epoch": 27.29702214303894,
"grad_norm": 48.28982925415039,
"learning_rate": 9.448037565340658e-07,
"loss": 0.6955,
"step": 214500
},
{
"epoch": 27.36065156528379,
"grad_norm": 58.85805130004883,
"learning_rate": 9.226543811464518e-07,
"loss": 0.6875,
"step": 215000
},
{
"epoch": 27.424280987528633,
"grad_norm": 58.64131164550781,
"learning_rate": 9.005050057588377e-07,
"loss": 0.698,
"step": 215500
},
{
"epoch": 27.48791040977348,
"grad_norm": 54.10153579711914,
"learning_rate": 8.783999291219989e-07,
"loss": 0.7054,
"step": 216000
},
{
"epoch": 27.551539832018324,
"grad_norm": 37.60294723510742,
"learning_rate": 8.562505537343847e-07,
"loss": 0.6968,
"step": 216500
},
{
"epoch": 27.615169254263172,
"grad_norm": 46.13175964355469,
"learning_rate": 8.341011783467707e-07,
"loss": 0.7044,
"step": 217000
},
{
"epoch": 27.678798676508016,
"grad_norm": 49.83407211303711,
"learning_rate": 8.119518029591567e-07,
"loss": 0.6946,
"step": 217500
},
{
"epoch": 27.742428098752864,
"grad_norm": 62.65508270263672,
"learning_rate": 7.898024275715425e-07,
"loss": 0.6865,
"step": 218000
},
{
"epoch": 27.806057520997708,
"grad_norm": 64.78981018066406,
"learning_rate": 7.676530521839285e-07,
"loss": 0.6974,
"step": 218500
},
{
"epoch": 27.869686943242556,
"grad_norm": 55.65605926513672,
"learning_rate": 7.455479755470895e-07,
"loss": 0.698,
"step": 219000
},
{
"epoch": 27.9333163654874,
"grad_norm": 51.40291976928711,
"learning_rate": 7.233986001594756e-07,
"loss": 0.6943,
"step": 219500
},
{
"epoch": 27.996945787732248,
"grad_norm": 52.821475982666016,
"learning_rate": 7.012492247718615e-07,
"loss": 0.6985,
"step": 220000
},
{
"epoch": 28.06057520997709,
"grad_norm": 105.65634155273438,
"learning_rate": 6.790998493842474e-07,
"loss": 0.6785,
"step": 220500
},
{
"epoch": 28.12420463222194,
"grad_norm": 66.97595977783203,
"learning_rate": 6.569504739966333e-07,
"loss": 0.6842,
"step": 221000
},
{
"epoch": 28.187834054466787,
"grad_norm": 77.8376693725586,
"learning_rate": 6.348010986090193e-07,
"loss": 0.6832,
"step": 221500
},
{
"epoch": 28.25146347671163,
"grad_norm": 68.83918762207031,
"learning_rate": 6.126517232214052e-07,
"loss": 0.6863,
"step": 222000
},
{
"epoch": 28.31509289895648,
"grad_norm": 49.16581344604492,
"learning_rate": 5.905023478337911e-07,
"loss": 0.6806,
"step": 222500
},
{
"epoch": 28.378722321201323,
"grad_norm": 58.93035888671875,
"learning_rate": 5.683972711969523e-07,
"loss": 0.6897,
"step": 223000
},
{
"epoch": 28.44235174344617,
"grad_norm": 57.476531982421875,
"learning_rate": 5.462478958093382e-07,
"loss": 0.6975,
"step": 223500
},
{
"epoch": 28.505981165691015,
"grad_norm": 56.7477912902832,
"learning_rate": 5.240985204217242e-07,
"loss": 0.6802,
"step": 224000
},
{
"epoch": 28.569610587935863,
"grad_norm": 45.01617431640625,
"learning_rate": 5.0194914503411e-07,
"loss": 0.6836,
"step": 224500
},
{
"epoch": 28.633240010180707,
"grad_norm": 49.77652359008789,
"learning_rate": 4.79799769646496e-07,
"loss": 0.6849,
"step": 225000
},
{
"epoch": 28.696869432425554,
"grad_norm": 52.57892990112305,
"learning_rate": 4.57650394258882e-07,
"loss": 0.6781,
"step": 225500
},
{
"epoch": 28.7604988546704,
"grad_norm": 64.97437286376953,
"learning_rate": 4.3550101887126787e-07,
"loss": 0.6761,
"step": 226000
},
{
"epoch": 28.824128276915246,
"grad_norm": 52.035160064697266,
"learning_rate": 4.133516434836538e-07,
"loss": 0.6762,
"step": 226500
},
{
"epoch": 28.88775769916009,
"grad_norm": 57.393035888671875,
"learning_rate": 3.912022680960397e-07,
"loss": 0.6781,
"step": 227000
},
{
"epoch": 28.951387121404938,
"grad_norm": 49.78774642944336,
"learning_rate": 3.691414902099761e-07,
"loss": 0.682,
"step": 227500
},
{
"epoch": 29.015016543649782,
"grad_norm": 47.4661750793457,
"learning_rate": 3.4699211482236206e-07,
"loss": 0.6742,
"step": 228000
},
{
"epoch": 29.07864596589463,
"grad_norm": 69.56925964355469,
"learning_rate": 3.248870381855232e-07,
"loss": 0.6595,
"step": 228500
},
{
"epoch": 29.142275388139474,
"grad_norm": 49.844520568847656,
"learning_rate": 3.027376627979091e-07,
"loss": 0.683,
"step": 229000
},
{
"epoch": 29.20590481038432,
"grad_norm": 58.6362419128418,
"learning_rate": 2.8058828741029506e-07,
"loss": 0.6721,
"step": 229500
},
{
"epoch": 29.26953423262917,
"grad_norm": 44.214717864990234,
"learning_rate": 2.5843891202268095e-07,
"loss": 0.669,
"step": 230000
},
{
"epoch": 29.333163654874014,
"grad_norm": 50.08256530761719,
"learning_rate": 2.3628953663506691e-07,
"loss": 0.683,
"step": 230500
},
{
"epoch": 29.39679307711886,
"grad_norm": 51.15972900390625,
"learning_rate": 2.1414016124745283e-07,
"loss": 0.6652,
"step": 231000
},
{
"epoch": 29.460422499363705,
"grad_norm": 47.7255859375,
"learning_rate": 1.92035084610614e-07,
"loss": 0.671,
"step": 231500
},
{
"epoch": 29.524051921608553,
"grad_norm": 45.42967987060547,
"learning_rate": 1.6988570922299992e-07,
"loss": 0.6662,
"step": 232000
},
{
"epoch": 29.587681343853397,
"grad_norm": 47.5881462097168,
"learning_rate": 1.4773633383538586e-07,
"loss": 0.6665,
"step": 232500
},
{
"epoch": 29.651310766098245,
"grad_norm": 71.63655090332031,
"learning_rate": 1.2558695844777177e-07,
"loss": 0.6718,
"step": 233000
},
{
"epoch": 29.71494018834309,
"grad_norm": 45.697998046875,
"learning_rate": 1.0343758306015771e-07,
"loss": 0.6657,
"step": 233500
},
{
"epoch": 29.778569610587937,
"grad_norm": 58.17982864379883,
"learning_rate": 8.128820767254363e-08,
"loss": 0.6677,
"step": 234000
},
{
"epoch": 29.84219903283278,
"grad_norm": 46.64686965942383,
"learning_rate": 5.9138832284929565e-08,
"loss": 0.6732,
"step": 234500
},
{
"epoch": 29.90582845507763,
"grad_norm": 52.96521759033203,
"learning_rate": 3.69894568973155e-08,
"loss": 0.6687,
"step": 235000
},
{
"epoch": 29.969457877322473,
"grad_norm": 44.063079833984375,
"learning_rate": 1.4840081509701428e-08,
"loss": 0.6732,
"step": 235500
}
],
"logging_steps": 500,
"max_steps": 235740,
"num_input_tokens_seen": 0,
"num_train_epochs": 30,
"save_steps": 10000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}