Files
out2/last-checkpoint/trainer_state.json

6041 lines
145 KiB
JSON
Raw Permalink Normal View History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.09007874015748031,
"eval_steps": 2858,
"global_step": 1716,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00010498687664041995,
"grad_norm": 10.849783897399902,
"learning_rate": 8.421052631578948e-06,
"loss": 11.336052894592285,
"step": 2
},
{
"epoch": 0.0002099737532808399,
"grad_norm": 4.206523895263672,
"learning_rate": 2.5263157894736845e-05,
"loss": 10.710294723510742,
"step": 4
},
{
"epoch": 0.00031496062992125983,
"grad_norm": 2.95147705078125,
"learning_rate": 4.210526315789474e-05,
"loss": 10.311192512512207,
"step": 6
},
{
"epoch": 0.0004199475065616798,
"grad_norm": 7.974979400634766,
"learning_rate": 5.894736842105263e-05,
"loss": 9.713238716125488,
"step": 8
},
{
"epoch": 0.0005249343832020997,
"grad_norm": 2.7956748008728027,
"learning_rate": 7.578947368421054e-05,
"loss": 9.508157730102539,
"step": 10
},
{
"epoch": 0.0006299212598425197,
"grad_norm": 11.139887809753418,
"learning_rate": 9.263157894736843e-05,
"loss": 9.507661819458008,
"step": 12
},
{
"epoch": 0.0007349081364829396,
"grad_norm": 4.121689796447754,
"learning_rate": 0.00010947368421052633,
"loss": 9.094792366027832,
"step": 14
},
{
"epoch": 0.0008398950131233596,
"grad_norm": 11.641839027404785,
"learning_rate": 0.0001263157894736842,
"loss": 8.865646362304688,
"step": 16
},
{
"epoch": 0.0009448818897637795,
"grad_norm": 3.2739551067352295,
"learning_rate": 0.0001431578947368421,
"loss": 8.6943998336792,
"step": 18
},
{
"epoch": 0.0010498687664041995,
"grad_norm": 3.3511805534362793,
"learning_rate": 0.00016,
"loss": 8.40627670288086,
"step": 20
},
{
"epoch": 0.0011548556430446195,
"grad_norm": 3.8193061351776123,
"learning_rate": 0.0001768421052631579,
"loss": 8.06525707244873,
"step": 22
},
{
"epoch": 0.0012598425196850393,
"grad_norm": 2.8360342979431152,
"learning_rate": 0.0001936842105263158,
"loss": 8.069121360778809,
"step": 24
},
{
"epoch": 0.0013648293963254593,
"grad_norm": 2.07961368560791,
"learning_rate": 0.0002105263157894737,
"loss": 7.9217634201049805,
"step": 26
},
{
"epoch": 0.0014698162729658792,
"grad_norm": 1.3632010221481323,
"learning_rate": 0.0002273684210526316,
"loss": 7.819206714630127,
"step": 28
},
{
"epoch": 0.0015748031496062992,
"grad_norm": 2.2996950149536133,
"learning_rate": 0.0002442105263157895,
"loss": 7.806654453277588,
"step": 30
},
{
"epoch": 0.0016797900262467192,
"grad_norm": 0.5869771242141724,
"learning_rate": 0.0002610526315789474,
"loss": 7.715257167816162,
"step": 32
},
{
"epoch": 0.001784776902887139,
"grad_norm": 0.8440877795219421,
"learning_rate": 0.0002778947368421053,
"loss": 7.586756229400635,
"step": 34
},
{
"epoch": 0.001889763779527559,
"grad_norm": 0.774182140827179,
"learning_rate": 0.00029473684210526316,
"loss": 7.62679386138916,
"step": 36
},
{
"epoch": 0.001994750656167979,
"grad_norm": 0.5010451078414917,
"learning_rate": 0.00031157894736842103,
"loss": 7.545993328094482,
"step": 38
},
{
"epoch": 0.002099737532808399,
"grad_norm": 0.6951680183410645,
"learning_rate": 0.00032842105263157896,
"loss": 7.461381912231445,
"step": 40
},
{
"epoch": 0.002204724409448819,
"grad_norm": 0.8257125020027161,
"learning_rate": 0.00034526315789473684,
"loss": 7.4312357902526855,
"step": 42
},
{
"epoch": 0.002309711286089239,
"grad_norm": 0.6842756271362305,
"learning_rate": 0.00036210526315789477,
"loss": 7.449553489685059,
"step": 44
},
{
"epoch": 0.0024146981627296586,
"grad_norm": 0.7420353293418884,
"learning_rate": 0.00037894736842105265,
"loss": 7.360008239746094,
"step": 46
},
{
"epoch": 0.0025196850393700786,
"grad_norm": 0.5558741688728333,
"learning_rate": 0.0003957894736842105,
"loss": 7.450737953186035,
"step": 48
},
{
"epoch": 0.0026246719160104987,
"grad_norm": 1.2673524618148804,
"learning_rate": 0.00041263157894736845,
"loss": 7.304603576660156,
"step": 50
},
{
"epoch": 0.0027296587926509187,
"grad_norm": 1.1506381034851074,
"learning_rate": 0.00042947368421052633,
"loss": 7.373305797576904,
"step": 52
},
{
"epoch": 0.0028346456692913387,
"grad_norm": 1.34714937210083,
"learning_rate": 0.0004463157894736842,
"loss": 7.287379264831543,
"step": 54
},
{
"epoch": 0.0029396325459317583,
"grad_norm": 1.8458038568496704,
"learning_rate": 0.00046315789473684214,
"loss": 7.345888137817383,
"step": 56
},
{
"epoch": 0.0030446194225721783,
"grad_norm": 1.229347825050354,
"learning_rate": 0.00048,
"loss": 7.267388343811035,
"step": 58
},
{
"epoch": 0.0031496062992125984,
"grad_norm": 1.0520741939544678,
"learning_rate": 0.0004968421052631579,
"loss": 7.2191925048828125,
"step": 60
},
{
"epoch": 0.0032545931758530184,
"grad_norm": 1.0573132038116455,
"learning_rate": 0.0005136842105263158,
"loss": 7.139622211456299,
"step": 62
},
{
"epoch": 0.0033595800524934384,
"grad_norm": 0.7959205508232117,
"learning_rate": 0.0005305263157894737,
"loss": 7.1705827713012695,
"step": 64
},
{
"epoch": 0.0034645669291338585,
"grad_norm": 1.0648680925369263,
"learning_rate": 0.0005473684210526316,
"loss": 7.059314727783203,
"step": 66
},
{
"epoch": 0.003569553805774278,
"grad_norm": 1.2019802331924438,
"learning_rate": 0.0005642105263157894,
"loss": 7.1090087890625,
"step": 68
},
{
"epoch": 0.003674540682414698,
"grad_norm": 0.6939458250999451,
"learning_rate": 0.0005810526315789474,
"loss": 7.071786880493164,
"step": 70
},
{
"epoch": 0.003779527559055118,
"grad_norm": 0.5002018213272095,
"learning_rate": 0.0005978947368421053,
"loss": 7.020046234130859,
"step": 72
},
{
"epoch": 0.003884514435695538,
"grad_norm": 0.5465899109840393,
"learning_rate": 0.0006147368421052632,
"loss": 6.96237325668335,
"step": 74
},
{
"epoch": 0.003989501312335958,
"grad_norm": 0.9754618406295776,
"learning_rate": 0.0006315789473684211,
"loss": 6.940667152404785,
"step": 76
},
{
"epoch": 0.004094488188976378,
"grad_norm": 1.0599706172943115,
"learning_rate": 0.0006484210526315789,
"loss": 6.961879730224609,
"step": 78
},
{
"epoch": 0.004199475065616798,
"grad_norm": 0.9335948824882507,
"learning_rate": 0.0006652631578947369,
"loss": 6.944250106811523,
"step": 80
},
{
"epoch": 0.0043044619422572174,
"grad_norm": 0.9988331198692322,
"learning_rate": 0.0006821052631578948,
"loss": 6.911154747009277,
"step": 82
},
{
"epoch": 0.004409448818897638,
"grad_norm": 0.8610116243362427,
"learning_rate": 0.0006989473684210527,
"loss": 6.893559455871582,
"step": 84
},
{
"epoch": 0.0045144356955380575,
"grad_norm": 0.7761997580528259,
"learning_rate": 0.0007157894736842105,
"loss": 6.926453590393066,
"step": 86
},
{
"epoch": 0.004619422572178478,
"grad_norm": 0.825920045375824,
"learning_rate": 0.0007326315789473684,
"loss": 6.813850402832031,
"step": 88
},
{
"epoch": 0.004724409448818898,
"grad_norm": 0.8140450119972229,
"learning_rate": 0.0007494736842105264,
"loss": 6.821445941925049,
"step": 90
},
{
"epoch": 0.004829396325459317,
"grad_norm": 0.5451359748840332,
"learning_rate": 0.0007663157894736842,
"loss": 6.663788795471191,
"step": 92
},
{
"epoch": 0.004934383202099738,
"grad_norm": 0.4969961941242218,
"learning_rate": 0.0007831578947368422,
"loss": 6.7580647468566895,
"step": 94
},
{
"epoch": 0.005039370078740157,
"grad_norm": 0.5622134804725647,
"learning_rate": 0.0008,
"loss": 6.753166198730469,
"step": 96
},
{
"epoch": 0.005144356955380578,
"grad_norm": 0.45332568883895874,
"learning_rate": 0.0008,
"loss": 6.61945104598999,
"step": 98
},
{
"epoch": 0.005249343832020997,
"grad_norm": 0.6089130640029907,
"learning_rate": 0.0008,
"loss": 6.531531810760498,
"step": 100
},
{
"epoch": 0.005354330708661417,
"grad_norm": 1.5867327451705933,
"learning_rate": 0.0008,
"loss": 6.609947204589844,
"step": 102
},
{
"epoch": 0.005459317585301837,
"grad_norm": 0.8609986901283264,
"learning_rate": 0.0008,
"loss": 6.586551189422607,
"step": 104
},
{
"epoch": 0.005564304461942257,
"grad_norm": 0.682275116443634,
"learning_rate": 0.0008,
"loss": 6.591581344604492,
"step": 106
},
{
"epoch": 0.005669291338582677,
"grad_norm": 0.8488819003105164,
"learning_rate": 0.0008,
"loss": 6.605495452880859,
"step": 108
},
{
"epoch": 0.005774278215223097,
"grad_norm": 0.8200653195381165,
"learning_rate": 0.0008,
"loss": 6.560756206512451,
"step": 110
},
{
"epoch": 0.005879265091863517,
"grad_norm": 0.859346330165863,
"learning_rate": 0.0008,
"loss": 6.440073490142822,
"step": 112
},
{
"epoch": 0.005984251968503937,
"grad_norm": 1.1621174812316895,
"learning_rate": 0.0008,
"loss": 6.41163444519043,
"step": 114
},
{
"epoch": 0.006089238845144357,
"grad_norm": 0.5757318735122681,
"learning_rate": 0.0008,
"loss": 6.400125503540039,
"step": 116
},
{
"epoch": 0.006194225721784777,
"grad_norm": 0.5290873050689697,
"learning_rate": 0.0008,
"loss": 6.3030877113342285,
"step": 118
},
{
"epoch": 0.006299212598425197,
"grad_norm": 1.0253428220748901,
"learning_rate": 0.0008,
"loss": 6.3230977058410645,
"step": 120
},
{
"epoch": 0.006404199475065617,
"grad_norm": 0.6795729398727417,
"learning_rate": 0.0008,
"loss": 6.3237199783325195,
"step": 122
},
{
"epoch": 0.006509186351706037,
"grad_norm": 0.861482560634613,
"learning_rate": 0.0008,
"loss": 6.25187873840332,
"step": 124
},
{
"epoch": 0.006614173228346456,
"grad_norm": 0.7200944423675537,
"learning_rate": 0.0008,
"loss": 6.1981401443481445,
"step": 126
},
{
"epoch": 0.006719160104986877,
"grad_norm": 0.6993811726570129,
"learning_rate": 0.0008,
"loss": 6.191583633422852,
"step": 128
},
{
"epoch": 0.0068241469816272965,
"grad_norm": 0.4931415915489197,
"learning_rate": 0.0008,
"loss": 6.107348442077637,
"step": 130
},
{
"epoch": 0.006929133858267717,
"grad_norm": 0.3714856803417206,
"learning_rate": 0.0008,
"loss": 6.135107040405273,
"step": 132
},
{
"epoch": 0.0070341207349081366,
"grad_norm": 0.4941980242729187,
"learning_rate": 0.0008,
"loss": 6.1131463050842285,
"step": 134
},
{
"epoch": 0.007139107611548556,
"grad_norm": 0.5307848453521729,
"learning_rate": 0.0008,
"loss": 6.129576683044434,
"step": 136
},
{
"epoch": 0.007244094488188977,
"grad_norm": 0.4134950041770935,
"learning_rate": 0.0008,
"loss": 6.058399200439453,
"step": 138
},
{
"epoch": 0.007349081364829396,
"grad_norm": 0.5328584313392639,
"learning_rate": 0.0008,
"loss": 6.038764476776123,
"step": 140
},
{
"epoch": 0.007454068241469817,
"grad_norm": 1.15119469165802,
"learning_rate": 0.0008,
"loss": 5.919521808624268,
"step": 142
},
{
"epoch": 0.007559055118110236,
"grad_norm": 0.6950765252113342,
"learning_rate": 0.0008,
"loss": 5.90153694152832,
"step": 144
},
{
"epoch": 0.007664041994750656,
"grad_norm": 0.607292115688324,
"learning_rate": 0.0008,
"loss": 5.805788993835449,
"step": 146
},
{
"epoch": 0.007769028871391076,
"grad_norm": 0.8245534896850586,
"learning_rate": 0.0008,
"loss": 5.942452907562256,
"step": 148
},
{
"epoch": 0.007874015748031496,
"grad_norm": 0.643883228302002,
"learning_rate": 0.0008,
"loss": 5.859640598297119,
"step": 150
},
{
"epoch": 0.007979002624671916,
"grad_norm": 0.6031001806259155,
"learning_rate": 0.0008,
"loss": 5.771254539489746,
"step": 152
},
{
"epoch": 0.008083989501312335,
"grad_norm": 0.3471139967441559,
"learning_rate": 0.0008,
"loss": 5.825682163238525,
"step": 154
},
{
"epoch": 0.008188976377952756,
"grad_norm": 0.35251903533935547,
"learning_rate": 0.0008,
"loss": 5.824915885925293,
"step": 156
},
{
"epoch": 0.008293963254593176,
"grad_norm": 0.5420740842819214,
"learning_rate": 0.0008,
"loss": 5.735776424407959,
"step": 158
},
{
"epoch": 0.008398950131233596,
"grad_norm": 0.5785290002822876,
"learning_rate": 0.0008,
"loss": 5.71408748626709,
"step": 160
},
{
"epoch": 0.008503937007874015,
"grad_norm": 0.5503653287887573,
"learning_rate": 0.0008,
"loss": 5.681863784790039,
"step": 162
},
{
"epoch": 0.008608923884514435,
"grad_norm": 0.38715237379074097,
"learning_rate": 0.0008,
"loss": 5.627864360809326,
"step": 164
},
{
"epoch": 0.008713910761154856,
"grad_norm": 0.47762763500213623,
"learning_rate": 0.0008,
"loss": 5.623003959655762,
"step": 166
},
{
"epoch": 0.008818897637795276,
"grad_norm": 0.7163979411125183,
"learning_rate": 0.0008,
"loss": 5.694301128387451,
"step": 168
},
{
"epoch": 0.008923884514435695,
"grad_norm": 0.5806844830513,
"learning_rate": 0.0008,
"loss": 5.556089878082275,
"step": 170
},
{
"epoch": 0.009028871391076115,
"grad_norm": 0.39758580923080444,
"learning_rate": 0.0008,
"loss": 5.631988048553467,
"step": 172
},
{
"epoch": 0.009133858267716535,
"grad_norm": 0.4177590012550354,
"learning_rate": 0.0008,
"loss": 5.465466022491455,
"step": 174
},
{
"epoch": 0.009238845144356956,
"grad_norm": 0.3706369400024414,
"learning_rate": 0.0008,
"loss": 5.473786354064941,
"step": 176
},
{
"epoch": 0.009343832020997376,
"grad_norm": 0.3802669942378998,
"learning_rate": 0.0008,
"loss": 5.476729393005371,
"step": 178
},
{
"epoch": 0.009448818897637795,
"grad_norm": 0.44668325781822205,
"learning_rate": 0.0008,
"loss": 5.477040767669678,
"step": 180
},
{
"epoch": 0.009553805774278215,
"grad_norm": 0.2561449408531189,
"learning_rate": 0.0008,
"loss": 5.360054016113281,
"step": 182
},
{
"epoch": 0.009658792650918634,
"grad_norm": 0.3362152874469757,
"learning_rate": 0.0008,
"loss": 5.358182907104492,
"step": 184
},
{
"epoch": 0.009763779527559056,
"grad_norm": 0.2856195569038391,
"learning_rate": 0.0008,
"loss": 5.342494010925293,
"step": 186
},
{
"epoch": 0.009868766404199475,
"grad_norm": 0.5502752661705017,
"learning_rate": 0.0008,
"loss": 5.342869758605957,
"step": 188
},
{
"epoch": 0.009973753280839895,
"grad_norm": 0.7680650353431702,
"learning_rate": 0.0008,
"loss": 5.356422424316406,
"step": 190
},
{
"epoch": 0.010078740157480314,
"grad_norm": 0.5406929850578308,
"learning_rate": 0.0008,
"loss": 5.300556182861328,
"step": 192
},
{
"epoch": 0.010183727034120734,
"grad_norm": 0.3668650984764099,
"learning_rate": 0.0008,
"loss": 5.367114067077637,
"step": 194
},
{
"epoch": 0.010288713910761155,
"grad_norm": 0.4027565121650696,
"learning_rate": 0.0008,
"loss": 5.251592636108398,
"step": 196
},
{
"epoch": 0.010393700787401575,
"grad_norm": 0.40343940258026123,
"learning_rate": 0.0008,
"loss": 5.276173114776611,
"step": 198
},
{
"epoch": 0.010498687664041995,
"grad_norm": 0.4856398105621338,
"learning_rate": 0.0008,
"loss": 5.210047245025635,
"step": 200
},
{
"epoch": 0.010603674540682414,
"grad_norm": 0.26983195543289185,
"learning_rate": 0.0008,
"loss": 5.17520809173584,
"step": 202
},
{
"epoch": 0.010708661417322834,
"grad_norm": 0.25971466302871704,
"learning_rate": 0.0008,
"loss": 5.155277252197266,
"step": 204
},
{
"epoch": 0.010813648293963255,
"grad_norm": 0.2467920333147049,
"learning_rate": 0.0008,
"loss": 5.207974910736084,
"step": 206
},
{
"epoch": 0.010918635170603675,
"grad_norm": 0.27808240056037903,
"learning_rate": 0.0008,
"loss": 5.16036319732666,
"step": 208
},
{
"epoch": 0.011023622047244094,
"grad_norm": 0.287492960691452,
"learning_rate": 0.0008,
"loss": 5.079829692840576,
"step": 210
},
{
"epoch": 0.011128608923884514,
"grad_norm": 0.25132930278778076,
"learning_rate": 0.0008,
"loss": 5.055511474609375,
"step": 212
},
{
"epoch": 0.011233595800524934,
"grad_norm": 0.44570592045783997,
"learning_rate": 0.0008,
"loss": 5.137527942657471,
"step": 214
},
{
"epoch": 0.011338582677165355,
"grad_norm": 0.5238414406776428,
"learning_rate": 0.0008,
"loss": 5.096850872039795,
"step": 216
},
{
"epoch": 0.011443569553805774,
"grad_norm": 0.46957311034202576,
"learning_rate": 0.0008,
"loss": 5.067659378051758,
"step": 218
},
{
"epoch": 0.011548556430446194,
"grad_norm": 0.535942792892456,
"learning_rate": 0.0008,
"loss": 5.147111415863037,
"step": 220
},
{
"epoch": 0.011653543307086614,
"grad_norm": 0.4777580797672272,
"learning_rate": 0.0008,
"loss": 5.075133800506592,
"step": 222
},
{
"epoch": 0.011758530183727033,
"grad_norm": 0.31084227561950684,
"learning_rate": 0.0008,
"loss": 5.079253673553467,
"step": 224
},
{
"epoch": 0.011863517060367455,
"grad_norm": 0.2853791117668152,
"learning_rate": 0.0008,
"loss": 4.923807144165039,
"step": 226
},
{
"epoch": 0.011968503937007874,
"grad_norm": 0.2706334590911865,
"learning_rate": 0.0008,
"loss": 4.94926118850708,
"step": 228
},
{
"epoch": 0.012073490813648294,
"grad_norm": 0.2381977140903473,
"learning_rate": 0.0008,
"loss": 4.920800685882568,
"step": 230
},
{
"epoch": 0.012178477690288713,
"grad_norm": 0.21651628613471985,
"learning_rate": 0.0008,
"loss": 4.997503757476807,
"step": 232
},
{
"epoch": 0.012283464566929133,
"grad_norm": 0.28761589527130127,
"learning_rate": 0.0008,
"loss": 4.905304431915283,
"step": 234
},
{
"epoch": 0.012388451443569554,
"grad_norm": 0.3810858130455017,
"learning_rate": 0.0008,
"loss": 4.907279968261719,
"step": 236
},
{
"epoch": 0.012493438320209974,
"grad_norm": 0.6002088189125061,
"learning_rate": 0.0008,
"loss": 4.840156555175781,
"step": 238
},
{
"epoch": 0.012598425196850394,
"grad_norm": 0.42039456963539124,
"learning_rate": 0.0008,
"loss": 4.886885643005371,
"step": 240
},
{
"epoch": 0.012703412073490813,
"grad_norm": 0.42322126030921936,
"learning_rate": 0.0008,
"loss": 4.822059631347656,
"step": 242
},
{
"epoch": 0.012808398950131234,
"grad_norm": 0.33545973896980286,
"learning_rate": 0.0008,
"loss": 4.766934871673584,
"step": 244
},
{
"epoch": 0.012913385826771654,
"grad_norm": 0.35304394364356995,
"learning_rate": 0.0008,
"loss": 4.7689738273620605,
"step": 246
},
{
"epoch": 0.013018372703412074,
"grad_norm": 0.3135300278663635,
"learning_rate": 0.0008,
"loss": 4.7434821128845215,
"step": 248
},
{
"epoch": 0.013123359580052493,
"grad_norm": 0.2875298857688904,
"learning_rate": 0.0008,
"loss": 4.7837395668029785,
"step": 250
},
{
"epoch": 0.013228346456692913,
"grad_norm": 0.34506675601005554,
"learning_rate": 0.0008,
"loss": 4.787559509277344,
"step": 252
},
{
"epoch": 0.013333333333333334,
"grad_norm": 0.3315136730670929,
"learning_rate": 0.0008,
"loss": 4.751657962799072,
"step": 254
},
{
"epoch": 0.013438320209973754,
"grad_norm": 0.3462645709514618,
"learning_rate": 0.0008,
"loss": 4.821771621704102,
"step": 256
},
{
"epoch": 0.013543307086614173,
"grad_norm": 0.24309296905994415,
"learning_rate": 0.0008,
"loss": 4.689890384674072,
"step": 258
},
{
"epoch": 0.013648293963254593,
"grad_norm": 0.4050637185573578,
"learning_rate": 0.0008,
"loss": 4.697262287139893,
"step": 260
},
{
"epoch": 0.013753280839895013,
"grad_norm": 0.4226019084453583,
"learning_rate": 0.0008,
"loss": 4.713808059692383,
"step": 262
},
{
"epoch": 0.013858267716535434,
"grad_norm": 0.4319268763065338,
"learning_rate": 0.0008,
"loss": 4.579202651977539,
"step": 264
},
{
"epoch": 0.013963254593175854,
"grad_norm": 0.3217737078666687,
"learning_rate": 0.0008,
"loss": 4.692221641540527,
"step": 266
},
{
"epoch": 0.014068241469816273,
"grad_norm": 0.30460724234580994,
"learning_rate": 0.0008,
"loss": 4.656576156616211,
"step": 268
},
{
"epoch": 0.014173228346456693,
"grad_norm": 0.25518161058425903,
"learning_rate": 0.0008,
"loss": 4.592221260070801,
"step": 270
},
{
"epoch": 0.014278215223097112,
"grad_norm": 0.24282623827457428,
"learning_rate": 0.0008,
"loss": 4.648724555969238,
"step": 272
},
{
"epoch": 0.014383202099737534,
"grad_norm": 0.39138299226760864,
"learning_rate": 0.0008,
"loss": 4.606783866882324,
"step": 274
},
{
"epoch": 0.014488188976377953,
"grad_norm": 0.32089442014694214,
"learning_rate": 0.0008,
"loss": 4.516218662261963,
"step": 276
},
{
"epoch": 0.014593175853018373,
"grad_norm": 0.3266720473766327,
"learning_rate": 0.0008,
"loss": 4.552274227142334,
"step": 278
},
{
"epoch": 0.014698162729658792,
"grad_norm": 0.27863070368766785,
"learning_rate": 0.0008,
"loss": 4.488729476928711,
"step": 280
},
{
"epoch": 0.014803149606299212,
"grad_norm": 0.28705859184265137,
"learning_rate": 0.0008,
"loss": 4.477656364440918,
"step": 282
},
{
"epoch": 0.014908136482939633,
"grad_norm": 0.33214113116264343,
"learning_rate": 0.0008,
"loss": 4.430954456329346,
"step": 284
},
{
"epoch": 0.015013123359580053,
"grad_norm": 0.3688258230686188,
"learning_rate": 0.0008,
"loss": 4.452303886413574,
"step": 286
},
{
"epoch": 0.015118110236220473,
"grad_norm": 0.36506983637809753,
"learning_rate": 0.0008,
"loss": 4.543822288513184,
"step": 288
},
{
"epoch": 0.015223097112860892,
"grad_norm": 0.3670697808265686,
"learning_rate": 0.0008,
"loss": 4.436527252197266,
"step": 290
},
{
"epoch": 0.015328083989501312,
"grad_norm": 0.2648005187511444,
"learning_rate": 0.0008,
"loss": 4.4850335121154785,
"step": 292
},
{
"epoch": 0.015433070866141733,
"grad_norm": 0.22264482080936432,
"learning_rate": 0.0008,
"loss": 4.484733581542969,
"step": 294
},
{
"epoch": 0.015538057742782153,
"grad_norm": 0.2611202895641327,
"learning_rate": 0.0008,
"loss": 4.408095836639404,
"step": 296
},
{
"epoch": 0.01564304461942257,
"grad_norm": 0.2882183790206909,
"learning_rate": 0.0008,
"loss": 4.459738731384277,
"step": 298
},
{
"epoch": 0.015748031496062992,
"grad_norm": 0.28506702184677124,
"learning_rate": 0.0008,
"loss": 4.3531670570373535,
"step": 300
},
{
"epoch": 0.015853018372703413,
"grad_norm": 0.2589276432991028,
"learning_rate": 0.0008,
"loss": 4.410321235656738,
"step": 302
},
{
"epoch": 0.01595800524934383,
"grad_norm": 0.2526051104068756,
"learning_rate": 0.0008,
"loss": 4.283108711242676,
"step": 304
},
{
"epoch": 0.016062992125984252,
"grad_norm": 0.37200987339019775,
"learning_rate": 0.0008,
"loss": 4.3569817543029785,
"step": 306
},
{
"epoch": 0.01616797900262467,
"grad_norm": 0.307287335395813,
"learning_rate": 0.0008,
"loss": 4.438014507293701,
"step": 308
},
{
"epoch": 0.01627296587926509,
"grad_norm": 0.36766815185546875,
"learning_rate": 0.0008,
"loss": 4.295423984527588,
"step": 310
},
{
"epoch": 0.016377952755905513,
"grad_norm": 0.31193122267723083,
"learning_rate": 0.0008,
"loss": 4.333798885345459,
"step": 312
},
{
"epoch": 0.01648293963254593,
"grad_norm": 0.31765303015708923,
"learning_rate": 0.0008,
"loss": 4.16727352142334,
"step": 314
},
{
"epoch": 0.016587926509186352,
"grad_norm": 0.21497637033462524,
"learning_rate": 0.0008,
"loss": 4.2583441734313965,
"step": 316
},
{
"epoch": 0.01669291338582677,
"grad_norm": 0.26689282059669495,
"learning_rate": 0.0008,
"loss": 4.223230361938477,
"step": 318
},
{
"epoch": 0.01679790026246719,
"grad_norm": 0.27385199069976807,
"learning_rate": 0.0008,
"loss": 4.208255767822266,
"step": 320
},
{
"epoch": 0.016902887139107613,
"grad_norm": 0.2642309367656708,
"learning_rate": 0.0008,
"loss": 4.289506435394287,
"step": 322
},
{
"epoch": 0.01700787401574803,
"grad_norm": 0.2722127437591553,
"learning_rate": 0.0008,
"loss": 4.300339221954346,
"step": 324
},
{
"epoch": 0.017112860892388452,
"grad_norm": 0.38802817463874817,
"learning_rate": 0.0008,
"loss": 4.228229999542236,
"step": 326
},
{
"epoch": 0.01721784776902887,
"grad_norm": 0.2825157642364502,
"learning_rate": 0.0008,
"loss": 4.32781982421875,
"step": 328
},
{
"epoch": 0.01732283464566929,
"grad_norm": 0.3203144669532776,
"learning_rate": 0.0008,
"loss": 4.10207462310791,
"step": 330
},
{
"epoch": 0.017427821522309712,
"grad_norm": 0.2983134090900421,
"learning_rate": 0.0008,
"loss": 4.20668888092041,
"step": 332
},
{
"epoch": 0.01753280839895013,
"grad_norm": 0.33699917793273926,
"learning_rate": 0.0008,
"loss": 4.1426262855529785,
"step": 334
},
{
"epoch": 0.01763779527559055,
"grad_norm": 0.3318274915218353,
"learning_rate": 0.0008,
"loss": 4.161504745483398,
"step": 336
},
{
"epoch": 0.01774278215223097,
"grad_norm": 0.2278800904750824,
"learning_rate": 0.0008,
"loss": 3.990349292755127,
"step": 338
},
{
"epoch": 0.01784776902887139,
"grad_norm": 0.2122919112443924,
"learning_rate": 0.0008,
"loss": 4.127922534942627,
"step": 340
},
{
"epoch": 0.017952755905511812,
"grad_norm": 0.24514071643352509,
"learning_rate": 0.0008,
"loss": 4.193850994110107,
"step": 342
},
{
"epoch": 0.01805774278215223,
"grad_norm": 0.28716644644737244,
"learning_rate": 0.0008,
"loss": 4.070234298706055,
"step": 344
},
{
"epoch": 0.01816272965879265,
"grad_norm": 0.25690266489982605,
"learning_rate": 0.0008,
"loss": 3.966444730758667,
"step": 346
},
{
"epoch": 0.01826771653543307,
"grad_norm": 0.2349938452243805,
"learning_rate": 0.0008,
"loss": 3.9333581924438477,
"step": 348
},
{
"epoch": 0.01837270341207349,
"grad_norm": 0.20146915316581726,
"learning_rate": 0.0008,
"loss": 3.953355550765991,
"step": 350
},
{
"epoch": 0.018477690288713912,
"grad_norm": 0.1961042433977127,
"learning_rate": 0.0008,
"loss": 3.973087787628174,
"step": 352
},
{
"epoch": 0.01858267716535433,
"grad_norm": 0.2598169445991516,
"learning_rate": 0.0008,
"loss": 4.002113342285156,
"step": 354
},
{
"epoch": 0.01868766404199475,
"grad_norm": 0.22022010385990143,
"learning_rate": 0.0008,
"loss": 3.9722490310668945,
"step": 356
},
{
"epoch": 0.01879265091863517,
"grad_norm": 0.212201327085495,
"learning_rate": 0.0008,
"loss": 3.8929874897003174,
"step": 358
},
{
"epoch": 0.01889763779527559,
"grad_norm": 0.1991279572248459,
"learning_rate": 0.0008,
"loss": 3.894895076751709,
"step": 360
},
{
"epoch": 0.01900262467191601,
"grad_norm": 0.24566085636615753,
"learning_rate": 0.0008,
"loss": 3.8610589504241943,
"step": 362
},
{
"epoch": 0.01910761154855643,
"grad_norm": 0.2806271016597748,
"learning_rate": 0.0008,
"loss": 3.861912488937378,
"step": 364
},
{
"epoch": 0.01921259842519685,
"grad_norm": 0.2231629341840744,
"learning_rate": 0.0008,
"loss": 3.8544185161590576,
"step": 366
},
{
"epoch": 0.01931758530183727,
"grad_norm": 0.26531746983528137,
"learning_rate": 0.0008,
"loss": 3.8621199131011963,
"step": 368
},
{
"epoch": 0.01942257217847769,
"grad_norm": 0.3318291902542114,
"learning_rate": 0.0008,
"loss": 3.902070999145508,
"step": 370
},
{
"epoch": 0.01952755905511811,
"grad_norm": 0.23807932436466217,
"learning_rate": 0.0008,
"loss": 3.86655855178833,
"step": 372
},
{
"epoch": 0.01963254593175853,
"grad_norm": 0.215584397315979,
"learning_rate": 0.0008,
"loss": 3.773761510848999,
"step": 374
},
{
"epoch": 0.01973753280839895,
"grad_norm": 0.289485901594162,
"learning_rate": 0.0008,
"loss": 3.8897311687469482,
"step": 376
},
{
"epoch": 0.01984251968503937,
"grad_norm": 0.2350815236568451,
"learning_rate": 0.0008,
"loss": 3.787693738937378,
"step": 378
},
{
"epoch": 0.01994750656167979,
"grad_norm": 0.2330552637577057,
"learning_rate": 0.0008,
"loss": 3.7755932807922363,
"step": 380
},
{
"epoch": 0.02005249343832021,
"grad_norm": 0.2246251106262207,
"learning_rate": 0.0008,
"loss": 3.839930772781372,
"step": 382
},
{
"epoch": 0.02015748031496063,
"grad_norm": 0.23261497914791107,
"learning_rate": 0.0008,
"loss": 3.72586727142334,
"step": 384
},
{
"epoch": 0.02026246719160105,
"grad_norm": 0.24750104546546936,
"learning_rate": 0.0008,
"loss": 3.893145799636841,
"step": 386
},
{
"epoch": 0.020367454068241468,
"grad_norm": 0.22430314123630524,
"learning_rate": 0.0008,
"loss": 3.725208282470703,
"step": 388
},
{
"epoch": 0.02047244094488189,
"grad_norm": 0.20470485091209412,
"learning_rate": 0.0008,
"loss": 3.727203845977783,
"step": 390
},
{
"epoch": 0.02057742782152231,
"grad_norm": 0.1713440865278244,
"learning_rate": 0.0008,
"loss": 3.722830295562744,
"step": 392
},
{
"epoch": 0.02068241469816273,
"grad_norm": 0.17870037257671356,
"learning_rate": 0.0008,
"loss": 3.6994686126708984,
"step": 394
},
{
"epoch": 0.02078740157480315,
"grad_norm": 0.16635218262672424,
"learning_rate": 0.0008,
"loss": 3.628350257873535,
"step": 396
},
{
"epoch": 0.020892388451443568,
"grad_norm": 0.16065655648708344,
"learning_rate": 0.0008,
"loss": 3.696190357208252,
"step": 398
},
{
"epoch": 0.02099737532808399,
"grad_norm": 0.1648516058921814,
"learning_rate": 0.0008,
"loss": 3.7218990325927734,
"step": 400
},
{
"epoch": 0.02110236220472441,
"grad_norm": 0.2350551337003708,
"learning_rate": 0.0008,
"loss": 3.6114625930786133,
"step": 402
},
{
"epoch": 0.02120734908136483,
"grad_norm": 0.21156081557273865,
"learning_rate": 0.0008,
"loss": 3.6270546913146973,
"step": 404
},
{
"epoch": 0.02131233595800525,
"grad_norm": 0.2242772877216339,
"learning_rate": 0.0008,
"loss": 3.6559674739837646,
"step": 406
},
{
"epoch": 0.021417322834645668,
"grad_norm": 0.20296809077262878,
"learning_rate": 0.0008,
"loss": 3.6351869106292725,
"step": 408
},
{
"epoch": 0.02152230971128609,
"grad_norm": 0.21024516224861145,
"learning_rate": 0.0008,
"loss": 3.7134218215942383,
"step": 410
},
{
"epoch": 0.02162729658792651,
"grad_norm": 0.2657431662082672,
"learning_rate": 0.0008,
"loss": 3.675140619277954,
"step": 412
},
{
"epoch": 0.021732283464566928,
"grad_norm": 0.22600969672203064,
"learning_rate": 0.0008,
"loss": 3.6230013370513916,
"step": 414
},
{
"epoch": 0.02183727034120735,
"grad_norm": 0.22580362856388092,
"learning_rate": 0.0008,
"loss": 3.633514881134033,
"step": 416
},
{
"epoch": 0.021942257217847767,
"grad_norm": 0.20401369035243988,
"learning_rate": 0.0008,
"loss": 3.5863749980926514,
"step": 418
},
{
"epoch": 0.02204724409448819,
"grad_norm": 0.19097885489463806,
"learning_rate": 0.0008,
"loss": 3.570152521133423,
"step": 420
},
{
"epoch": 0.02215223097112861,
"grad_norm": 0.16916649043560028,
"learning_rate": 0.0008,
"loss": 3.571899175643921,
"step": 422
},
{
"epoch": 0.022257217847769028,
"grad_norm": 0.15503089129924774,
"learning_rate": 0.0008,
"loss": 3.648607015609741,
"step": 424
},
{
"epoch": 0.02236220472440945,
"grad_norm": 0.18933242559432983,
"learning_rate": 0.0008,
"loss": 3.6147239208221436,
"step": 426
},
{
"epoch": 0.022467191601049867,
"grad_norm": 0.1814320683479309,
"learning_rate": 0.0008,
"loss": 3.5678610801696777,
"step": 428
},
{
"epoch": 0.02257217847769029,
"grad_norm": 0.15981845557689667,
"learning_rate": 0.0008,
"loss": 3.4891350269317627,
"step": 430
},
{
"epoch": 0.02267716535433071,
"grad_norm": 0.1672240048646927,
"learning_rate": 0.0008,
"loss": 3.5254311561584473,
"step": 432
},
{
"epoch": 0.022782152230971128,
"grad_norm": 0.17923741042613983,
"learning_rate": 0.0008,
"loss": 3.4941389560699463,
"step": 434
},
{
"epoch": 0.02288713910761155,
"grad_norm": 0.20545029640197754,
"learning_rate": 0.0008,
"loss": 3.4603352546691895,
"step": 436
},
{
"epoch": 0.022992125984251967,
"grad_norm": 0.21872857213020325,
"learning_rate": 0.0008,
"loss": 3.4523208141326904,
"step": 438
},
{
"epoch": 0.023097112860892388,
"grad_norm": 0.17705431580543518,
"learning_rate": 0.0008,
"loss": 3.443699598312378,
"step": 440
},
{
"epoch": 0.02320209973753281,
"grad_norm": 0.14959222078323364,
"learning_rate": 0.0008,
"loss": 3.557424545288086,
"step": 442
},
{
"epoch": 0.023307086614173227,
"grad_norm": 0.1745806336402893,
"learning_rate": 0.0008,
"loss": 3.4890198707580566,
"step": 444
},
{
"epoch": 0.02341207349081365,
"grad_norm": 0.18317265808582306,
"learning_rate": 0.0008,
"loss": 3.5291688442230225,
"step": 446
},
{
"epoch": 0.023517060367454067,
"grad_norm": 0.1765255481004715,
"learning_rate": 0.0008,
"loss": 3.471801280975342,
"step": 448
},
{
"epoch": 0.023622047244094488,
"grad_norm": 0.1791754961013794,
"learning_rate": 0.0008,
"loss": 3.4235143661499023,
"step": 450
},
{
"epoch": 0.02372703412073491,
"grad_norm": 0.16694314777851105,
"learning_rate": 0.0008,
"loss": 3.5024945735931396,
"step": 452
},
{
"epoch": 0.023832020997375327,
"grad_norm": 0.20423193275928497,
"learning_rate": 0.0008,
"loss": 3.4986155033111572,
"step": 454
},
{
"epoch": 0.02393700787401575,
"grad_norm": 0.21046102046966553,
"learning_rate": 0.0008,
"loss": 3.5056910514831543,
"step": 456
},
{
"epoch": 0.024041994750656166,
"grad_norm": 0.18477864563465118,
"learning_rate": 0.0008,
"loss": 3.424469470977783,
"step": 458
},
{
"epoch": 0.024146981627296588,
"grad_norm": 0.17082113027572632,
"learning_rate": 0.0008,
"loss": 3.47847056388855,
"step": 460
},
{
"epoch": 0.02425196850393701,
"grad_norm": 0.17604340612888336,
"learning_rate": 0.0008,
"loss": 3.425982713699341,
"step": 462
},
{
"epoch": 0.024356955380577427,
"grad_norm": 0.16897740960121155,
"learning_rate": 0.0008,
"loss": 3.4730064868927,
"step": 464
},
{
"epoch": 0.024461942257217848,
"grad_norm": 0.1673053652048111,
"learning_rate": 0.0008,
"loss": 3.432903289794922,
"step": 466
},
{
"epoch": 0.024566929133858266,
"grad_norm": 0.17199593782424927,
"learning_rate": 0.0008,
"loss": 3.5054171085357666,
"step": 468
},
{
"epoch": 0.024671916010498687,
"grad_norm": 0.19890399277210236,
"learning_rate": 0.0008,
"loss": 3.4409797191619873,
"step": 470
},
{
"epoch": 0.02477690288713911,
"grad_norm": 0.19607073068618774,
"learning_rate": 0.0008,
"loss": 3.3515682220458984,
"step": 472
},
{
"epoch": 0.024881889763779527,
"grad_norm": 0.16958890855312347,
"learning_rate": 0.0008,
"loss": 3.420071840286255,
"step": 474
},
{
"epoch": 0.024986876640419948,
"grad_norm": 0.1964447945356369,
"learning_rate": 0.0008,
"loss": 3.526289224624634,
"step": 476
},
{
"epoch": 0.02509186351706037,
"grad_norm": 0.1786402314901352,
"learning_rate": 0.0008,
"loss": 3.440227746963501,
"step": 478
},
{
"epoch": 0.025196850393700787,
"grad_norm": 0.16233603656291962,
"learning_rate": 0.0008,
"loss": 3.317654609680176,
"step": 480
},
{
"epoch": 0.02530183727034121,
"grad_norm": 0.18433336913585663,
"learning_rate": 0.0008,
"loss": 3.444368839263916,
"step": 482
},
{
"epoch": 0.025406824146981626,
"grad_norm": 0.16506624221801758,
"learning_rate": 0.0008,
"loss": 3.4707281589508057,
"step": 484
},
{
"epoch": 0.025511811023622048,
"grad_norm": 0.1551865041255951,
"learning_rate": 0.0008,
"loss": 3.3682827949523926,
"step": 486
},
{
"epoch": 0.02561679790026247,
"grad_norm": 0.14763277769088745,
"learning_rate": 0.0008,
"loss": 3.325780153274536,
"step": 488
},
{
"epoch": 0.025721784776902887,
"grad_norm": 0.1381286233663559,
"learning_rate": 0.0008,
"loss": 3.426196813583374,
"step": 490
},
{
"epoch": 0.025826771653543308,
"grad_norm": 0.15651266276836395,
"learning_rate": 0.0008,
"loss": 3.38508677482605,
"step": 492
},
{
"epoch": 0.025931758530183726,
"grad_norm": 0.16916270554065704,
"learning_rate": 0.0008,
"loss": 3.394261598587036,
"step": 494
},
{
"epoch": 0.026036745406824147,
"grad_norm": 0.16897031664848328,
"learning_rate": 0.0008,
"loss": 3.278876543045044,
"step": 496
},
{
"epoch": 0.02614173228346457,
"grad_norm": 0.16116946935653687,
"learning_rate": 0.0008,
"loss": 3.3523120880126953,
"step": 498
},
{
"epoch": 0.026246719160104987,
"grad_norm": 0.17504142224788666,
"learning_rate": 0.0008,
"loss": 3.3894450664520264,
"step": 500
},
{
"epoch": 0.026351706036745408,
"grad_norm": 0.17068205773830414,
"learning_rate": 0.0008,
"loss": 3.4036076068878174,
"step": 502
},
{
"epoch": 0.026456692913385826,
"grad_norm": 0.1658509224653244,
"learning_rate": 0.0008,
"loss": 3.378098487854004,
"step": 504
},
{
"epoch": 0.026561679790026247,
"grad_norm": 0.1450873762369156,
"learning_rate": 0.0008,
"loss": 3.304023265838623,
"step": 506
},
{
"epoch": 0.02666666666666667,
"grad_norm": 0.18289312720298767,
"learning_rate": 0.0008,
"loss": 3.288076639175415,
"step": 508
},
{
"epoch": 0.026771653543307086,
"grad_norm": 0.1541556864976883,
"learning_rate": 0.0008,
"loss": 3.304835081100464,
"step": 510
},
{
"epoch": 0.026876640419947508,
"grad_norm": 0.16644538938999176,
"learning_rate": 0.0008,
"loss": 3.2379486560821533,
"step": 512
},
{
"epoch": 0.026981627296587925,
"grad_norm": 0.19644027948379517,
"learning_rate": 0.0008,
"loss": 3.3676295280456543,
"step": 514
},
{
"epoch": 0.027086614173228347,
"grad_norm": 0.20000602304935455,
"learning_rate": 0.0008,
"loss": 3.255898952484131,
"step": 516
},
{
"epoch": 0.027191601049868768,
"grad_norm": 0.17630483210086823,
"learning_rate": 0.0008,
"loss": 3.2831783294677734,
"step": 518
},
{
"epoch": 0.027296587926509186,
"grad_norm": 0.16653336584568024,
"learning_rate": 0.0008,
"loss": 3.388322591781616,
"step": 520
},
{
"epoch": 0.027401574803149607,
"grad_norm": 0.15305423736572266,
"learning_rate": 0.0008,
"loss": 3.3861708641052246,
"step": 522
},
{
"epoch": 0.027506561679790025,
"grad_norm": 0.15171492099761963,
"learning_rate": 0.0008,
"loss": 3.336448907852173,
"step": 524
},
{
"epoch": 0.027611548556430447,
"grad_norm": 0.17332474887371063,
"learning_rate": 0.0008,
"loss": 3.248317003250122,
"step": 526
},
{
"epoch": 0.027716535433070868,
"grad_norm": 0.14799350500106812,
"learning_rate": 0.0008,
"loss": 3.3303961753845215,
"step": 528
},
{
"epoch": 0.027821522309711286,
"grad_norm": 0.14763560891151428,
"learning_rate": 0.0008,
"loss": 3.3051490783691406,
"step": 530
},
{
"epoch": 0.027926509186351707,
"grad_norm": 0.1350218653678894,
"learning_rate": 0.0008,
"loss": 3.3351500034332275,
"step": 532
},
{
"epoch": 0.028031496062992125,
"grad_norm": 0.14229005575180054,
"learning_rate": 0.0008,
"loss": 3.2528343200683594,
"step": 534
},
{
"epoch": 0.028136482939632546,
"grad_norm": 0.14102040231227875,
"learning_rate": 0.0008,
"loss": 3.204890012741089,
"step": 536
},
{
"epoch": 0.028241469816272968,
"grad_norm": 0.14591607451438904,
"learning_rate": 0.0008,
"loss": 3.367074966430664,
"step": 538
},
{
"epoch": 0.028346456692913385,
"grad_norm": 0.16307151317596436,
"learning_rate": 0.0008,
"loss": 3.236833333969116,
"step": 540
},
{
"epoch": 0.028451443569553807,
"grad_norm": 0.1497374176979065,
"learning_rate": 0.0008,
"loss": 3.206105947494507,
"step": 542
},
{
"epoch": 0.028556430446194225,
"grad_norm": 0.1525629311800003,
"learning_rate": 0.0008,
"loss": 3.3076024055480957,
"step": 544
},
{
"epoch": 0.028661417322834646,
"grad_norm": 0.1597941815853119,
"learning_rate": 0.0008,
"loss": 3.287429094314575,
"step": 546
},
{
"epoch": 0.028766404199475067,
"grad_norm": 0.16407884657382965,
"learning_rate": 0.0008,
"loss": 3.329230785369873,
"step": 548
},
{
"epoch": 0.028871391076115485,
"grad_norm": 0.18955646455287933,
"learning_rate": 0.0008,
"loss": 3.29620099067688,
"step": 550
},
{
"epoch": 0.028976377952755906,
"grad_norm": 0.13810871541500092,
"learning_rate": 0.0008,
"loss": 3.22092604637146,
"step": 552
},
{
"epoch": 0.029081364829396324,
"grad_norm": 0.14122328162193298,
"learning_rate": 0.0008,
"loss": 3.2574150562286377,
"step": 554
},
{
"epoch": 0.029186351706036746,
"grad_norm": 0.17227867245674133,
"learning_rate": 0.0008,
"loss": 3.2021737098693848,
"step": 556
},
{
"epoch": 0.029291338582677167,
"grad_norm": 0.13745535910129547,
"learning_rate": 0.0008,
"loss": 3.2652475833892822,
"step": 558
},
{
"epoch": 0.029396325459317585,
"grad_norm": 0.14315351843833923,
"learning_rate": 0.0008,
"loss": 3.3042309284210205,
"step": 560
},
{
"epoch": 0.029501312335958006,
"grad_norm": 0.1505221426486969,
"learning_rate": 0.0008,
"loss": 3.1302292346954346,
"step": 562
},
{
"epoch": 0.029606299212598424,
"grad_norm": 0.15946339070796967,
"learning_rate": 0.0008,
"loss": 3.2585742473602295,
"step": 564
},
{
"epoch": 0.029711286089238845,
"grad_norm": 0.17035390436649323,
"learning_rate": 0.0008,
"loss": 3.200352191925049,
"step": 566
},
{
"epoch": 0.029816272965879267,
"grad_norm": 0.14264027774333954,
"learning_rate": 0.0008,
"loss": 3.1434473991394043,
"step": 568
},
{
"epoch": 0.029921259842519685,
"grad_norm": 0.14433781802654266,
"learning_rate": 0.0008,
"loss": 3.141904592514038,
"step": 570
},
{
"epoch": 0.030026246719160106,
"grad_norm": 0.13526467978954315,
"learning_rate": 0.0008,
"loss": 3.0416038036346436,
"step": 572
},
{
"epoch": 0.030131233595800524,
"grad_norm": 0.13533855974674225,
"learning_rate": 0.0008,
"loss": 3.1272072792053223,
"step": 574
},
{
"epoch": 0.030236220472440945,
"grad_norm": 0.15500874817371368,
"learning_rate": 0.0008,
"loss": 3.2618722915649414,
"step": 576
},
{
"epoch": 0.030341207349081366,
"grad_norm": 0.17267724871635437,
"learning_rate": 0.0008,
"loss": 3.2308037281036377,
"step": 578
},
{
"epoch": 0.030446194225721784,
"grad_norm": 0.1582280397415161,
"learning_rate": 0.0008,
"loss": 3.23921537399292,
"step": 580
},
{
"epoch": 0.030551181102362206,
"grad_norm": 0.13486045598983765,
"learning_rate": 0.0008,
"loss": 3.1242129802703857,
"step": 582
},
{
"epoch": 0.030656167979002624,
"grad_norm": 0.1379910260438919,
"learning_rate": 0.0008,
"loss": 3.177032470703125,
"step": 584
},
{
"epoch": 0.030761154855643045,
"grad_norm": 0.14302867650985718,
"learning_rate": 0.0008,
"loss": 3.2286078929901123,
"step": 586
},
{
"epoch": 0.030866141732283466,
"grad_norm": 0.1382298469543457,
"learning_rate": 0.0008,
"loss": 3.222778797149658,
"step": 588
},
{
"epoch": 0.030971128608923884,
"grad_norm": 0.15394456684589386,
"learning_rate": 0.0008,
"loss": 3.2219724655151367,
"step": 590
},
{
"epoch": 0.031076115485564305,
"grad_norm": 0.13939788937568665,
"learning_rate": 0.0008,
"loss": 3.1774375438690186,
"step": 592
},
{
"epoch": 0.031181102362204723,
"grad_norm": 0.1534331738948822,
"learning_rate": 0.0008,
"loss": 3.174874782562256,
"step": 594
},
{
"epoch": 0.03128608923884514,
"grad_norm": 0.1796104907989502,
"learning_rate": 0.0008,
"loss": 3.226047992706299,
"step": 596
},
{
"epoch": 0.03139107611548556,
"grad_norm": 0.13423976302146912,
"learning_rate": 0.0008,
"loss": 3.154773473739624,
"step": 598
},
{
"epoch": 0.031496062992125984,
"grad_norm": 0.14498203992843628,
"learning_rate": 0.0008,
"loss": 3.2181460857391357,
"step": 600
},
{
"epoch": 0.031601049868766405,
"grad_norm": 0.14076939225196838,
"learning_rate": 0.0008,
"loss": 3.1480512619018555,
"step": 602
},
{
"epoch": 0.031706036745406826,
"grad_norm": 0.14199046790599823,
"learning_rate": 0.0008,
"loss": 3.1948139667510986,
"step": 604
},
{
"epoch": 0.03181102362204724,
"grad_norm": 0.1405128389596939,
"learning_rate": 0.0008,
"loss": 3.1463754177093506,
"step": 606
},
{
"epoch": 0.03191601049868766,
"grad_norm": 0.13525350391864777,
"learning_rate": 0.0008,
"loss": 3.1250717639923096,
"step": 608
},
{
"epoch": 0.032020997375328084,
"grad_norm": 0.14196738600730896,
"learning_rate": 0.0008,
"loss": 3.2256250381469727,
"step": 610
},
{
"epoch": 0.032125984251968505,
"grad_norm": 0.1674332171678543,
"learning_rate": 0.0008,
"loss": 3.189035177230835,
"step": 612
},
{
"epoch": 0.032230971128608926,
"grad_norm": 0.19794052839279175,
"learning_rate": 0.0008,
"loss": 3.231616258621216,
"step": 614
},
{
"epoch": 0.03233595800524934,
"grad_norm": 0.1598575860261917,
"learning_rate": 0.0008,
"loss": 3.1828837394714355,
"step": 616
},
{
"epoch": 0.03244094488188976,
"grad_norm": 0.14745914936065674,
"learning_rate": 0.0008,
"loss": 3.1849329471588135,
"step": 618
},
{
"epoch": 0.03254593175853018,
"grad_norm": 0.3145313858985901,
"learning_rate": 0.0008,
"loss": 3.165916681289673,
"step": 620
},
{
"epoch": 0.032650918635170605,
"grad_norm": 0.26110589504241943,
"learning_rate": 0.0008,
"loss": 3.1651082038879395,
"step": 622
},
{
"epoch": 0.032755905511811026,
"grad_norm": 0.22751542925834656,
"learning_rate": 0.0008,
"loss": 3.210188627243042,
"step": 624
},
{
"epoch": 0.03286089238845144,
"grad_norm": 0.18317535519599915,
"learning_rate": 0.0008,
"loss": 3.2566449642181396,
"step": 626
},
{
"epoch": 0.03296587926509186,
"grad_norm": 0.15907306969165802,
"learning_rate": 0.0008,
"loss": 3.1539463996887207,
"step": 628
},
{
"epoch": 0.03307086614173228,
"grad_norm": 0.15025147795677185,
"learning_rate": 0.0008,
"loss": 3.142364740371704,
"step": 630
},
{
"epoch": 0.033175853018372704,
"grad_norm": 0.1286715716123581,
"learning_rate": 0.0008,
"loss": 3.1074650287628174,
"step": 632
},
{
"epoch": 0.033280839895013126,
"grad_norm": 0.12226458638906479,
"learning_rate": 0.0008,
"loss": 3.0952885150909424,
"step": 634
},
{
"epoch": 0.03338582677165354,
"grad_norm": 0.13879609107971191,
"learning_rate": 0.0008,
"loss": 3.1514804363250732,
"step": 636
},
{
"epoch": 0.03349081364829396,
"grad_norm": 0.12534929811954498,
"learning_rate": 0.0008,
"loss": 3.139106035232544,
"step": 638
},
{
"epoch": 0.03359580052493438,
"grad_norm": 0.12349742650985718,
"learning_rate": 0.0008,
"loss": 3.105691909790039,
"step": 640
},
{
"epoch": 0.033700787401574804,
"grad_norm": 0.12220428138971329,
"learning_rate": 0.0008,
"loss": 3.1019020080566406,
"step": 642
},
{
"epoch": 0.033805774278215225,
"grad_norm": 0.1326756477355957,
"learning_rate": 0.0008,
"loss": 3.1477456092834473,
"step": 644
},
{
"epoch": 0.03391076115485564,
"grad_norm": 0.13377100229263306,
"learning_rate": 0.0008,
"loss": 3.0433576107025146,
"step": 646
},
{
"epoch": 0.03401574803149606,
"grad_norm": 0.12178801745176315,
"learning_rate": 0.0008,
"loss": 3.07883620262146,
"step": 648
},
{
"epoch": 0.03412073490813648,
"grad_norm": 0.13815799355506897,
"learning_rate": 0.0008,
"loss": 3.0264294147491455,
"step": 650
},
{
"epoch": 0.034225721784776904,
"grad_norm": 0.1332225501537323,
"learning_rate": 0.0008,
"loss": 3.1015422344207764,
"step": 652
},
{
"epoch": 0.034330708661417325,
"grad_norm": 0.12200571596622467,
"learning_rate": 0.0008,
"loss": 3.0805413722991943,
"step": 654
},
{
"epoch": 0.03443569553805774,
"grad_norm": 0.1238102912902832,
"learning_rate": 0.0008,
"loss": 3.0576930046081543,
"step": 656
},
{
"epoch": 0.03454068241469816,
"grad_norm": 0.1291918158531189,
"learning_rate": 0.0008,
"loss": 3.13897967338562,
"step": 658
},
{
"epoch": 0.03464566929133858,
"grad_norm": 0.13744677603244781,
"learning_rate": 0.0008,
"loss": 3.164642333984375,
"step": 660
},
{
"epoch": 0.034750656167979004,
"grad_norm": 0.12718631327152252,
"learning_rate": 0.0008,
"loss": 3.0951108932495117,
"step": 662
},
{
"epoch": 0.034855643044619425,
"grad_norm": 0.12068125605583191,
"learning_rate": 0.0008,
"loss": 3.0444083213806152,
"step": 664
},
{
"epoch": 0.03496062992125984,
"grad_norm": 0.13728944957256317,
"learning_rate": 0.0008,
"loss": 3.0462770462036133,
"step": 666
},
{
"epoch": 0.03506561679790026,
"grad_norm": 0.1373009830713272,
"learning_rate": 0.0008,
"loss": 3.086789131164551,
"step": 668
},
{
"epoch": 0.03517060367454068,
"grad_norm": 0.12281421571969986,
"learning_rate": 0.0008,
"loss": 3.0893633365631104,
"step": 670
},
{
"epoch": 0.0352755905511811,
"grad_norm": 0.13015969097614288,
"learning_rate": 0.0008,
"loss": 3.0368361473083496,
"step": 672
},
{
"epoch": 0.035380577427821525,
"grad_norm": 0.13312262296676636,
"learning_rate": 0.0008,
"loss": 3.122968912124634,
"step": 674
},
{
"epoch": 0.03548556430446194,
"grad_norm": 0.13073506951332092,
"learning_rate": 0.0008,
"loss": 3.062354326248169,
"step": 676
},
{
"epoch": 0.03559055118110236,
"grad_norm": 0.119827501475811,
"learning_rate": 0.0008,
"loss": 3.1293904781341553,
"step": 678
},
{
"epoch": 0.03569553805774278,
"grad_norm": 0.1357945054769516,
"learning_rate": 0.0008,
"loss": 2.9812240600585938,
"step": 680
},
{
"epoch": 0.0358005249343832,
"grad_norm": 0.1311289370059967,
"learning_rate": 0.0008,
"loss": 2.966649293899536,
"step": 682
},
{
"epoch": 0.035905511811023624,
"grad_norm": 0.12661199271678925,
"learning_rate": 0.0008,
"loss": 3.031751871109009,
"step": 684
},
{
"epoch": 0.03601049868766404,
"grad_norm": 0.14154307544231415,
"learning_rate": 0.0008,
"loss": 3.155766248703003,
"step": 686
},
{
"epoch": 0.03611548556430446,
"grad_norm": 0.13769333064556122,
"learning_rate": 0.0008,
"loss": 3.064086675643921,
"step": 688
},
{
"epoch": 0.03622047244094488,
"grad_norm": 0.145602285861969,
"learning_rate": 0.0008,
"loss": 3.0761966705322266,
"step": 690
},
{
"epoch": 0.0363254593175853,
"grad_norm": 0.12669020891189575,
"learning_rate": 0.0008,
"loss": 3.097874164581299,
"step": 692
},
{
"epoch": 0.036430446194225724,
"grad_norm": 0.13513895869255066,
"learning_rate": 0.0008,
"loss": 3.0714070796966553,
"step": 694
},
{
"epoch": 0.03653543307086614,
"grad_norm": 0.13587389886379242,
"learning_rate": 0.0008,
"loss": 3.172131299972534,
"step": 696
},
{
"epoch": 0.03664041994750656,
"grad_norm": 0.130451962351799,
"learning_rate": 0.0008,
"loss": 3.069667100906372,
"step": 698
},
{
"epoch": 0.03674540682414698,
"grad_norm": 0.12922164797782898,
"learning_rate": 0.0008,
"loss": 3.0901424884796143,
"step": 700
},
{
"epoch": 0.0368503937007874,
"grad_norm": 0.12978655099868774,
"learning_rate": 0.0008,
"loss": 3.049433708190918,
"step": 702
},
{
"epoch": 0.036955380577427824,
"grad_norm": 0.12508027255535126,
"learning_rate": 0.0008,
"loss": 3.00188946723938,
"step": 704
},
{
"epoch": 0.03706036745406824,
"grad_norm": 0.11734891682863235,
"learning_rate": 0.0008,
"loss": 2.9634389877319336,
"step": 706
},
{
"epoch": 0.03716535433070866,
"grad_norm": 0.12137921899557114,
"learning_rate": 0.0008,
"loss": 2.999195098876953,
"step": 708
},
{
"epoch": 0.03727034120734908,
"grad_norm": 0.12699182331562042,
"learning_rate": 0.0008,
"loss": 3.018418550491333,
"step": 710
},
{
"epoch": 0.0373753280839895,
"grad_norm": 0.12088700383901596,
"learning_rate": 0.0008,
"loss": 2.9763457775115967,
"step": 712
},
{
"epoch": 0.037480314960629924,
"grad_norm": 0.12237604707479477,
"learning_rate": 0.0008,
"loss": 2.962264060974121,
"step": 714
},
{
"epoch": 0.03758530183727034,
"grad_norm": 0.11808755993843079,
"learning_rate": 0.0008,
"loss": 2.944026470184326,
"step": 716
},
{
"epoch": 0.03769028871391076,
"grad_norm": 0.12789645791053772,
"learning_rate": 0.0008,
"loss": 3.062084913253784,
"step": 718
},
{
"epoch": 0.03779527559055118,
"grad_norm": 0.12254694849252701,
"learning_rate": 0.0008,
"loss": 3.042384386062622,
"step": 720
},
{
"epoch": 0.0379002624671916,
"grad_norm": 0.12937159836292267,
"learning_rate": 0.0008,
"loss": 2.950317859649658,
"step": 722
},
{
"epoch": 0.03800524934383202,
"grad_norm": 0.1205861046910286,
"learning_rate": 0.0008,
"loss": 3.043663740158081,
"step": 724
},
{
"epoch": 0.03811023622047244,
"grad_norm": 0.12075173109769821,
"learning_rate": 0.0008,
"loss": 3.061645269393921,
"step": 726
},
{
"epoch": 0.03821522309711286,
"grad_norm": 0.14968499541282654,
"learning_rate": 0.0008,
"loss": 3.0783021450042725,
"step": 728
},
{
"epoch": 0.03832020997375328,
"grad_norm": 0.1275404989719391,
"learning_rate": 0.0008,
"loss": 3.0341646671295166,
"step": 730
},
{
"epoch": 0.0384251968503937,
"grad_norm": 0.12180853635072708,
"learning_rate": 0.0008,
"loss": 3.0402371883392334,
"step": 732
},
{
"epoch": 0.03853018372703412,
"grad_norm": 0.12133266776800156,
"learning_rate": 0.0008,
"loss": 3.0349020957946777,
"step": 734
},
{
"epoch": 0.03863517060367454,
"grad_norm": 0.14342333376407623,
"learning_rate": 0.0008,
"loss": 2.9737958908081055,
"step": 736
},
{
"epoch": 0.03874015748031496,
"grad_norm": 0.12567119300365448,
"learning_rate": 0.0008,
"loss": 2.999332904815674,
"step": 738
},
{
"epoch": 0.03884514435695538,
"grad_norm": 0.11701060831546783,
"learning_rate": 0.0008,
"loss": 2.9920272827148438,
"step": 740
},
{
"epoch": 0.0389501312335958,
"grad_norm": 0.12809567153453827,
"learning_rate": 0.0008,
"loss": 3.047039270401001,
"step": 742
},
{
"epoch": 0.03905511811023622,
"grad_norm": 0.1611979454755783,
"learning_rate": 0.0008,
"loss": 3.0390896797180176,
"step": 744
},
{
"epoch": 0.03916010498687664,
"grad_norm": 0.1428634077310562,
"learning_rate": 0.0008,
"loss": 2.9358737468719482,
"step": 746
},
{
"epoch": 0.03926509186351706,
"grad_norm": 0.12375941872596741,
"learning_rate": 0.0008,
"loss": 3.0470502376556396,
"step": 748
},
{
"epoch": 0.03937007874015748,
"grad_norm": 0.11091126501560211,
"learning_rate": 0.0008,
"loss": 3.005697250366211,
"step": 750
},
{
"epoch": 0.0394750656167979,
"grad_norm": 0.12000731378793716,
"learning_rate": 0.0008,
"loss": 3.0071187019348145,
"step": 752
},
{
"epoch": 0.03958005249343832,
"grad_norm": 0.12539641559123993,
"learning_rate": 0.0008,
"loss": 2.9291770458221436,
"step": 754
},
{
"epoch": 0.03968503937007874,
"grad_norm": 0.1304706335067749,
"learning_rate": 0.0008,
"loss": 2.963855266571045,
"step": 756
},
{
"epoch": 0.03979002624671916,
"grad_norm": 0.11511696130037308,
"learning_rate": 0.0008,
"loss": 3.024789333343506,
"step": 758
},
{
"epoch": 0.03989501312335958,
"grad_norm": 0.1253596395254135,
"learning_rate": 0.0008,
"loss": 2.9894022941589355,
"step": 760
},
{
"epoch": 0.04,
"grad_norm": 0.11755448579788208,
"learning_rate": 0.0008,
"loss": 3.0086042881011963,
"step": 762
},
{
"epoch": 0.04010498687664042,
"grad_norm": 0.12490132451057434,
"learning_rate": 0.0008,
"loss": 3.0274486541748047,
"step": 764
},
{
"epoch": 0.04020997375328084,
"grad_norm": 0.1350909322500229,
"learning_rate": 0.0008,
"loss": 3.023331642150879,
"step": 766
},
{
"epoch": 0.04031496062992126,
"grad_norm": 0.11557217687368393,
"learning_rate": 0.0008,
"loss": 2.934751272201538,
"step": 768
},
{
"epoch": 0.04041994750656168,
"grad_norm": 0.11128373444080353,
"learning_rate": 0.0008,
"loss": 3.004828929901123,
"step": 770
},
{
"epoch": 0.0405249343832021,
"grad_norm": 0.11425162851810455,
"learning_rate": 0.0008,
"loss": 3.0121257305145264,
"step": 772
},
{
"epoch": 0.04062992125984252,
"grad_norm": 0.11489281803369522,
"learning_rate": 0.0008,
"loss": 2.9543981552124023,
"step": 774
},
{
"epoch": 0.040734908136482936,
"grad_norm": 0.11290168762207031,
"learning_rate": 0.0008,
"loss": 2.975158214569092,
"step": 776
},
{
"epoch": 0.04083989501312336,
"grad_norm": 0.11316516250371933,
"learning_rate": 0.0008,
"loss": 3.0863113403320312,
"step": 778
},
{
"epoch": 0.04094488188976378,
"grad_norm": 0.11379840970039368,
"learning_rate": 0.0008,
"loss": 3.0072288513183594,
"step": 780
},
{
"epoch": 0.0410498687664042,
"grad_norm": 0.10820312052965164,
"learning_rate": 0.0008,
"loss": 2.88815975189209,
"step": 782
},
{
"epoch": 0.04115485564304462,
"grad_norm": 0.11447291821241379,
"learning_rate": 0.0008,
"loss": 2.961986541748047,
"step": 784
},
{
"epoch": 0.041259842519685036,
"grad_norm": 0.11523283272981644,
"learning_rate": 0.0008,
"loss": 2.900437116622925,
"step": 786
},
{
"epoch": 0.04136482939632546,
"grad_norm": 0.11368467658758163,
"learning_rate": 0.0008,
"loss": 2.953047752380371,
"step": 788
},
{
"epoch": 0.04146981627296588,
"grad_norm": 0.12399861216545105,
"learning_rate": 0.0008,
"loss": 2.968926191329956,
"step": 790
},
{
"epoch": 0.0415748031496063,
"grad_norm": 0.11375656723976135,
"learning_rate": 0.0008,
"loss": 2.997025966644287,
"step": 792
},
{
"epoch": 0.04167979002624672,
"grad_norm": 0.11646395176649094,
"learning_rate": 0.0008,
"loss": 2.952754497528076,
"step": 794
},
{
"epoch": 0.041784776902887136,
"grad_norm": 0.1193268746137619,
"learning_rate": 0.0008,
"loss": 2.9536261558532715,
"step": 796
},
{
"epoch": 0.04188976377952756,
"grad_norm": 0.1178014799952507,
"learning_rate": 0.0008,
"loss": 2.913003444671631,
"step": 798
},
{
"epoch": 0.04199475065616798,
"grad_norm": 0.11936375498771667,
"learning_rate": 0.0008,
"loss": 3.0284841060638428,
"step": 800
},
{
"epoch": 0.0420997375328084,
"grad_norm": 0.11003916710615158,
"learning_rate": 0.0008,
"loss": 2.9801266193389893,
"step": 802
},
{
"epoch": 0.04220472440944882,
"grad_norm": 0.20111171901226044,
"learning_rate": 0.0008,
"loss": 2.907733201980591,
"step": 804
},
{
"epoch": 0.042309711286089235,
"grad_norm": 0.12075945734977722,
"learning_rate": 0.0008,
"loss": 2.935979127883911,
"step": 806
},
{
"epoch": 0.04241469816272966,
"grad_norm": 0.11057411134243011,
"learning_rate": 0.0008,
"loss": 3.027822732925415,
"step": 808
},
{
"epoch": 0.04251968503937008,
"grad_norm": 0.12909549474716187,
"learning_rate": 0.0008,
"loss": 2.9112420082092285,
"step": 810
},
{
"epoch": 0.0426246719160105,
"grad_norm": 0.11044399440288544,
"learning_rate": 0.0008,
"loss": 2.889822006225586,
"step": 812
},
{
"epoch": 0.04272965879265092,
"grad_norm": 0.13029007613658905,
"learning_rate": 0.0008,
"loss": 3.0270438194274902,
"step": 814
},
{
"epoch": 0.042834645669291335,
"grad_norm": 0.11640318483114243,
"learning_rate": 0.0008,
"loss": 2.9036266803741455,
"step": 816
},
{
"epoch": 0.04293963254593176,
"grad_norm": 0.10894198715686798,
"learning_rate": 0.0008,
"loss": 2.96498966217041,
"step": 818
},
{
"epoch": 0.04304461942257218,
"grad_norm": 0.11847452819347382,
"learning_rate": 0.0008,
"loss": 2.950117349624634,
"step": 820
},
{
"epoch": 0.0431496062992126,
"grad_norm": 0.1125883162021637,
"learning_rate": 0.0008,
"loss": 2.9723289012908936,
"step": 822
},
{
"epoch": 0.04325459317585302,
"grad_norm": 0.11767535656690598,
"learning_rate": 0.0008,
"loss": 3.0090739727020264,
"step": 824
},
{
"epoch": 0.043359580052493435,
"grad_norm": 0.11515145003795624,
"learning_rate": 0.0008,
"loss": 2.8834097385406494,
"step": 826
},
{
"epoch": 0.043464566929133856,
"grad_norm": 0.1153886616230011,
"learning_rate": 0.0008,
"loss": 2.8896758556365967,
"step": 828
},
{
"epoch": 0.04356955380577428,
"grad_norm": 0.12153846025466919,
"learning_rate": 0.0008,
"loss": 3.001197338104248,
"step": 830
},
{
"epoch": 0.0436745406824147,
"grad_norm": 0.11056739836931229,
"learning_rate": 0.0008,
"loss": 2.9580276012420654,
"step": 832
},
{
"epoch": 0.04377952755905512,
"grad_norm": 0.1146998405456543,
"learning_rate": 0.0008,
"loss": 2.832361936569214,
"step": 834
},
{
"epoch": 0.043884514435695535,
"grad_norm": 0.11632180213928223,
"learning_rate": 0.0008,
"loss": 2.967362880706787,
"step": 836
},
{
"epoch": 0.043989501312335956,
"grad_norm": 0.11315326392650604,
"learning_rate": 0.0008,
"loss": 2.9654767513275146,
"step": 838
},
{
"epoch": 0.04409448818897638,
"grad_norm": 0.11123368889093399,
"learning_rate": 0.0008,
"loss": 3.0236129760742188,
"step": 840
},
{
"epoch": 0.0441994750656168,
"grad_norm": 0.11806689202785492,
"learning_rate": 0.0008,
"loss": 3.0052027702331543,
"step": 842
},
{
"epoch": 0.04430446194225722,
"grad_norm": 0.11948549002408981,
"learning_rate": 0.0008,
"loss": 2.7818121910095215,
"step": 844
},
{
"epoch": 0.044409448818897634,
"grad_norm": 0.1147482842206955,
"learning_rate": 0.0008,
"loss": 2.926354169845581,
"step": 846
},
{
"epoch": 0.044514435695538056,
"grad_norm": 0.11350935697555542,
"learning_rate": 0.0008,
"loss": 2.9837636947631836,
"step": 848
},
{
"epoch": 0.04461942257217848,
"grad_norm": 0.11554283648729324,
"learning_rate": 0.0008,
"loss": 2.97532320022583,
"step": 850
},
{
"epoch": 0.0447244094488189,
"grad_norm": 0.1130303218960762,
"learning_rate": 0.0008,
"loss": 2.9679086208343506,
"step": 852
},
{
"epoch": 0.04482939632545932,
"grad_norm": 0.11595270782709122,
"learning_rate": 0.0008,
"loss": 2.9420673847198486,
"step": 854
},
{
"epoch": 0.044934383202099734,
"grad_norm": 0.11009976267814636,
"learning_rate": 0.0008,
"loss": 2.9262118339538574,
"step": 856
},
{
"epoch": 0.045039370078740155,
"grad_norm": 0.10903191566467285,
"learning_rate": 0.0008,
"loss": 2.982046365737915,
"step": 858
},
{
"epoch": 0.04514435695538058,
"grad_norm": 0.1103678047657013,
"learning_rate": 0.0008,
"loss": 2.8575191497802734,
"step": 860
},
{
"epoch": 0.045249343832021,
"grad_norm": 0.10818672180175781,
"learning_rate": 0.0008,
"loss": 2.913555145263672,
"step": 862
},
{
"epoch": 0.04535433070866142,
"grad_norm": 0.1269296556711197,
"learning_rate": 0.0008,
"loss": 2.9361777305603027,
"step": 864
},
{
"epoch": 0.045459317585301834,
"grad_norm": 0.11180418729782104,
"learning_rate": 0.0008,
"loss": 2.856563091278076,
"step": 866
},
{
"epoch": 0.045564304461942255,
"grad_norm": 0.11334341019392014,
"learning_rate": 0.0008,
"loss": 2.9308438301086426,
"step": 868
},
{
"epoch": 0.04566929133858268,
"grad_norm": 0.12519557774066925,
"learning_rate": 0.0008,
"loss": 2.969743251800537,
"step": 870
},
{
"epoch": 0.0457742782152231,
"grad_norm": 0.1138872504234314,
"learning_rate": 0.0008,
"loss": 2.9254794120788574,
"step": 872
},
{
"epoch": 0.04587926509186352,
"grad_norm": 0.11148543655872345,
"learning_rate": 0.0008,
"loss": 2.950900077819824,
"step": 874
},
{
"epoch": 0.045984251968503934,
"grad_norm": 0.10802996158599854,
"learning_rate": 0.0008,
"loss": 2.9233310222625732,
"step": 876
},
{
"epoch": 0.046089238845144355,
"grad_norm": 0.107913538813591,
"learning_rate": 0.0008,
"loss": 2.8875625133514404,
"step": 878
},
{
"epoch": 0.046194225721784776,
"grad_norm": 0.11127500981092453,
"learning_rate": 0.0008,
"loss": 2.9353115558624268,
"step": 880
},
{
"epoch": 0.0462992125984252,
"grad_norm": 0.107363760471344,
"learning_rate": 0.0008,
"loss": 2.862389087677002,
"step": 882
},
{
"epoch": 0.04640419947506562,
"grad_norm": 0.10834158211946487,
"learning_rate": 0.0008,
"loss": 2.8950586318969727,
"step": 884
},
{
"epoch": 0.04650918635170603,
"grad_norm": 0.11008019000291824,
"learning_rate": 0.0008,
"loss": 2.847538709640503,
"step": 886
},
{
"epoch": 0.046614173228346455,
"grad_norm": 0.10486385971307755,
"learning_rate": 0.0008,
"loss": 2.8976285457611084,
"step": 888
},
{
"epoch": 0.046719160104986876,
"grad_norm": 0.10609378665685654,
"learning_rate": 0.0008,
"loss": 2.9052734375,
"step": 890
},
{
"epoch": 0.0468241469816273,
"grad_norm": 0.10781682282686234,
"learning_rate": 0.0008,
"loss": 2.8474717140197754,
"step": 892
},
{
"epoch": 0.04692913385826772,
"grad_norm": 0.11209188401699066,
"learning_rate": 0.0008,
"loss": 2.8896048069000244,
"step": 894
},
{
"epoch": 0.04703412073490813,
"grad_norm": 0.11089079827070236,
"learning_rate": 0.0008,
"loss": 2.906379222869873,
"step": 896
},
{
"epoch": 0.047139107611548554,
"grad_norm": 0.1138719990849495,
"learning_rate": 0.0008,
"loss": 2.9644546508789062,
"step": 898
},
{
"epoch": 0.047244094488188976,
"grad_norm": 0.11188910156488419,
"learning_rate": 0.0008,
"loss": 2.9156696796417236,
"step": 900
},
{
"epoch": 0.0473490813648294,
"grad_norm": 0.10872109234333038,
"learning_rate": 0.0008,
"loss": 2.8037800788879395,
"step": 902
},
{
"epoch": 0.04745406824146982,
"grad_norm": 0.1132812425494194,
"learning_rate": 0.0008,
"loss": 2.88108491897583,
"step": 904
},
{
"epoch": 0.04755905511811023,
"grad_norm": 0.10931621491909027,
"learning_rate": 0.0008,
"loss": 2.823637008666992,
"step": 906
},
{
"epoch": 0.047664041994750654,
"grad_norm": 0.10800245404243469,
"learning_rate": 0.0008,
"loss": 2.8360915184020996,
"step": 908
},
{
"epoch": 0.047769028871391075,
"grad_norm": 0.10993431508541107,
"learning_rate": 0.0008,
"loss": 2.9463419914245605,
"step": 910
},
{
"epoch": 0.0478740157480315,
"grad_norm": 0.11326651275157928,
"learning_rate": 0.0008,
"loss": 2.8706324100494385,
"step": 912
},
{
"epoch": 0.04797900262467192,
"grad_norm": 0.1067848727107048,
"learning_rate": 0.0008,
"loss": 2.8948814868927,
"step": 914
},
{
"epoch": 0.04808398950131233,
"grad_norm": 0.10832501202821732,
"learning_rate": 0.0008,
"loss": 2.8744025230407715,
"step": 916
},
{
"epoch": 0.048188976377952754,
"grad_norm": 0.22046154737472534,
"learning_rate": 0.0008,
"loss": 2.8172924518585205,
"step": 918
},
{
"epoch": 0.048293963254593175,
"grad_norm": 0.10513289272785187,
"learning_rate": 0.0008,
"loss": 2.8799233436584473,
"step": 920
},
{
"epoch": 0.048398950131233597,
"grad_norm": 0.10676917433738708,
"learning_rate": 0.0008,
"loss": 2.8221311569213867,
"step": 922
},
{
"epoch": 0.04850393700787402,
"grad_norm": 0.11604278534650803,
"learning_rate": 0.0008,
"loss": 2.8618123531341553,
"step": 924
},
{
"epoch": 0.04860892388451443,
"grad_norm": 0.31026268005371094,
"learning_rate": 0.0008,
"loss": 2.933411121368408,
"step": 926
},
{
"epoch": 0.048713910761154854,
"grad_norm": 0.11676490306854248,
"learning_rate": 0.0008,
"loss": 2.900099039077759,
"step": 928
},
{
"epoch": 0.048818897637795275,
"grad_norm": 0.10813336074352264,
"learning_rate": 0.0008,
"loss": 2.8783600330352783,
"step": 930
},
{
"epoch": 0.048923884514435696,
"grad_norm": 0.14493827521800995,
"learning_rate": 0.0008,
"loss": 2.8534443378448486,
"step": 932
},
{
"epoch": 0.04902887139107612,
"grad_norm": 0.1146959587931633,
"learning_rate": 0.0008,
"loss": 2.9133646488189697,
"step": 934
},
{
"epoch": 0.04913385826771653,
"grad_norm": 0.11801094561815262,
"learning_rate": 0.0008,
"loss": 2.9639992713928223,
"step": 936
},
{
"epoch": 0.04923884514435695,
"grad_norm": 0.11729086190462112,
"learning_rate": 0.0008,
"loss": 2.9099583625793457,
"step": 938
},
{
"epoch": 0.049343832020997375,
"grad_norm": 0.1108347624540329,
"learning_rate": 0.0008,
"loss": 2.8269410133361816,
"step": 940
},
{
"epoch": 0.049448818897637796,
"grad_norm": 0.107319176197052,
"learning_rate": 0.0008,
"loss": 2.894010066986084,
"step": 942
},
{
"epoch": 0.04955380577427822,
"grad_norm": 0.11818240582942963,
"learning_rate": 0.0008,
"loss": 2.8637502193450928,
"step": 944
},
{
"epoch": 0.04965879265091863,
"grad_norm": 0.10464034974575043,
"learning_rate": 0.0008,
"loss": 2.848630666732788,
"step": 946
},
{
"epoch": 0.04976377952755905,
"grad_norm": 0.110150046646595,
"learning_rate": 0.0008,
"loss": 2.8126089572906494,
"step": 948
},
{
"epoch": 0.049868766404199474,
"grad_norm": 0.11635616421699524,
"learning_rate": 0.0008,
"loss": 2.854870319366455,
"step": 950
},
{
"epoch": 0.049973753280839896,
"grad_norm": 0.10688231140375137,
"learning_rate": 0.0008,
"loss": 2.851635217666626,
"step": 952
},
{
"epoch": 0.05007874015748032,
"grad_norm": 0.10546289384365082,
"learning_rate": 0.0008,
"loss": 2.863751173019409,
"step": 954
},
{
"epoch": 0.05018372703412074,
"grad_norm": 0.10257919877767563,
"learning_rate": 0.0008,
"loss": 2.952653169631958,
"step": 956
},
{
"epoch": 0.05028871391076115,
"grad_norm": 0.10375232249498367,
"learning_rate": 0.0008,
"loss": 2.8090758323669434,
"step": 958
},
{
"epoch": 0.050393700787401574,
"grad_norm": 0.12159629911184311,
"learning_rate": 0.0008,
"loss": 2.9165844917297363,
"step": 960
},
{
"epoch": 0.050498687664041995,
"grad_norm": 0.1033838540315628,
"learning_rate": 0.0008,
"loss": 2.849384069442749,
"step": 962
},
{
"epoch": 0.05060367454068242,
"grad_norm": 0.11069808155298233,
"learning_rate": 0.0008,
"loss": 2.8043620586395264,
"step": 964
},
{
"epoch": 0.05070866141732284,
"grad_norm": 0.12036273628473282,
"learning_rate": 0.0008,
"loss": 2.9057257175445557,
"step": 966
},
{
"epoch": 0.05081364829396325,
"grad_norm": 0.10124826431274414,
"learning_rate": 0.0008,
"loss": 2.830293655395508,
"step": 968
},
{
"epoch": 0.050918635170603674,
"grad_norm": 0.10840156674385071,
"learning_rate": 0.0008,
"loss": 2.892146110534668,
"step": 970
},
{
"epoch": 0.051023622047244095,
"grad_norm": 0.10134908556938171,
"learning_rate": 0.0008,
"loss": 2.7851529121398926,
"step": 972
},
{
"epoch": 0.051128608923884517,
"grad_norm": 0.10375969111919403,
"learning_rate": 0.0008,
"loss": 2.8426032066345215,
"step": 974
},
{
"epoch": 0.05123359580052494,
"grad_norm": 0.10250184684991837,
"learning_rate": 0.0008,
"loss": 2.8460187911987305,
"step": 976
},
{
"epoch": 0.05133858267716535,
"grad_norm": 0.10046141594648361,
"learning_rate": 0.0008,
"loss": 2.790334939956665,
"step": 978
},
{
"epoch": 0.051443569553805774,
"grad_norm": 0.10310408473014832,
"learning_rate": 0.0008,
"loss": 2.8429830074310303,
"step": 980
},
{
"epoch": 0.051548556430446195,
"grad_norm": 0.10038266330957413,
"learning_rate": 0.0008,
"loss": 2.8468050956726074,
"step": 982
},
{
"epoch": 0.051653543307086616,
"grad_norm": 0.11408326029777527,
"learning_rate": 0.0008,
"loss": 2.869588851928711,
"step": 984
},
{
"epoch": 0.05175853018372704,
"grad_norm": 0.10076751559972763,
"learning_rate": 0.0008,
"loss": 2.8215019702911377,
"step": 986
},
{
"epoch": 0.05186351706036745,
"grad_norm": 0.11360592395067215,
"learning_rate": 0.0008,
"loss": 2.8531057834625244,
"step": 988
},
{
"epoch": 0.05196850393700787,
"grad_norm": 0.1087770015001297,
"learning_rate": 0.0008,
"loss": 2.857332706451416,
"step": 990
},
{
"epoch": 0.052073490813648295,
"grad_norm": 0.09793613106012344,
"learning_rate": 0.0008,
"loss": 2.781360626220703,
"step": 992
},
{
"epoch": 0.052178477690288716,
"grad_norm": 0.1005278155207634,
"learning_rate": 0.0008,
"loss": 2.7993361949920654,
"step": 994
},
{
"epoch": 0.05228346456692914,
"grad_norm": 0.10499605536460876,
"learning_rate": 0.0008,
"loss": 2.8021810054779053,
"step": 996
},
{
"epoch": 0.05238845144356955,
"grad_norm": 0.09995300322771072,
"learning_rate": 0.0008,
"loss": 2.8334829807281494,
"step": 998
},
{
"epoch": 0.05249343832020997,
"grad_norm": 0.09899105876684189,
"learning_rate": 0.0008,
"loss": 2.7776875495910645,
"step": 1000
},
{
"epoch": 0.052598425196850394,
"grad_norm": 0.10376624763011932,
"learning_rate": 0.0008,
"loss": 2.8660783767700195,
"step": 1002
},
{
"epoch": 0.052703412073490816,
"grad_norm": 0.10802112519741058,
"learning_rate": 0.0008,
"loss": 2.864668369293213,
"step": 1004
},
{
"epoch": 0.05280839895013124,
"grad_norm": 0.10298653692007065,
"learning_rate": 0.0008,
"loss": 2.800145387649536,
"step": 1006
},
{
"epoch": 0.05291338582677165,
"grad_norm": 0.09753638505935669,
"learning_rate": 0.0008,
"loss": 2.8046822547912598,
"step": 1008
},
{
"epoch": 0.05301837270341207,
"grad_norm": 0.10928277671337128,
"learning_rate": 0.0008,
"loss": 2.8910574913024902,
"step": 1010
},
{
"epoch": 0.053123359580052494,
"grad_norm": 0.10510570555925369,
"learning_rate": 0.0008,
"loss": 2.772444248199463,
"step": 1012
},
{
"epoch": 0.053228346456692915,
"grad_norm": 0.1018993929028511,
"learning_rate": 0.0008,
"loss": 2.821305990219116,
"step": 1014
},
{
"epoch": 0.05333333333333334,
"grad_norm": 0.1073940172791481,
"learning_rate": 0.0008,
"loss": 2.8084757328033447,
"step": 1016
},
{
"epoch": 0.05343832020997375,
"grad_norm": 0.10738760232925415,
"learning_rate": 0.0008,
"loss": 2.780719041824341,
"step": 1018
},
{
"epoch": 0.05354330708661417,
"grad_norm": 0.1023760661482811,
"learning_rate": 0.0008,
"loss": 2.7836318016052246,
"step": 1020
},
{
"epoch": 0.053648293963254594,
"grad_norm": 0.10736978054046631,
"learning_rate": 0.0008,
"loss": 2.846604108810425,
"step": 1022
},
{
"epoch": 0.053753280839895015,
"grad_norm": 0.10393604636192322,
"learning_rate": 0.0008,
"loss": 2.7620151042938232,
"step": 1024
},
{
"epoch": 0.053858267716535436,
"grad_norm": 0.09899700433015823,
"learning_rate": 0.0008,
"loss": 2.773373603820801,
"step": 1026
},
{
"epoch": 0.05396325459317585,
"grad_norm": 0.10414134711027145,
"learning_rate": 0.0008,
"loss": 2.7963967323303223,
"step": 1028
},
{
"epoch": 0.05406824146981627,
"grad_norm": 0.1031123548746109,
"learning_rate": 0.0008,
"loss": 2.845099925994873,
"step": 1030
},
{
"epoch": 0.054173228346456694,
"grad_norm": 0.108132004737854,
"learning_rate": 0.0008,
"loss": 2.8229126930236816,
"step": 1032
},
{
"epoch": 0.054278215223097115,
"grad_norm": 0.11058522760868073,
"learning_rate": 0.0008,
"loss": 2.8594136238098145,
"step": 1034
},
{
"epoch": 0.054383202099737536,
"grad_norm": 0.11115548014640808,
"learning_rate": 0.0008,
"loss": 2.81899094581604,
"step": 1036
},
{
"epoch": 0.05448818897637795,
"grad_norm": 0.1087251603603363,
"learning_rate": 0.0008,
"loss": 2.7584517002105713,
"step": 1038
},
{
"epoch": 0.05459317585301837,
"grad_norm": 0.10288669168949127,
"learning_rate": 0.0008,
"loss": 2.8365824222564697,
"step": 1040
},
{
"epoch": 0.05469816272965879,
"grad_norm": 0.10305164009332657,
"learning_rate": 0.0008,
"loss": 2.8229153156280518,
"step": 1042
},
{
"epoch": 0.054803149606299215,
"grad_norm": 0.1453515738248825,
"learning_rate": 0.0008,
"loss": 2.805276393890381,
"step": 1044
},
{
"epoch": 0.054908136482939636,
"grad_norm": 0.10317279398441315,
"learning_rate": 0.0008,
"loss": 2.756784200668335,
"step": 1046
},
{
"epoch": 0.05501312335958005,
"grad_norm": 0.09912578016519547,
"learning_rate": 0.0008,
"loss": 2.751218318939209,
"step": 1048
},
{
"epoch": 0.05511811023622047,
"grad_norm": 0.10517663508653641,
"learning_rate": 0.0008,
"loss": 2.8035247325897217,
"step": 1050
},
{
"epoch": 0.05522309711286089,
"grad_norm": 0.20114435255527496,
"learning_rate": 0.0008,
"loss": 2.7888002395629883,
"step": 1052
},
{
"epoch": 0.055328083989501314,
"grad_norm": 0.10310180485248566,
"learning_rate": 0.0008,
"loss": 2.881930351257324,
"step": 1054
},
{
"epoch": 0.055433070866141736,
"grad_norm": 0.09550151228904724,
"learning_rate": 0.0008,
"loss": 2.761927604675293,
"step": 1056
},
{
"epoch": 0.05553805774278215,
"grad_norm": 0.10260967165231705,
"learning_rate": 0.0008,
"loss": 2.818103551864624,
"step": 1058
},
{
"epoch": 0.05564304461942257,
"grad_norm": 0.12903259694576263,
"learning_rate": 0.0008,
"loss": 2.814908266067505,
"step": 1060
},
{
"epoch": 0.05574803149606299,
"grad_norm": 0.1667206883430481,
"learning_rate": 0.0008,
"loss": 2.8861734867095947,
"step": 1062
},
{
"epoch": 0.055853018372703414,
"grad_norm": 0.116305872797966,
"learning_rate": 0.0008,
"loss": 2.7723100185394287,
"step": 1064
},
{
"epoch": 0.055958005249343835,
"grad_norm": 0.11162646859884262,
"learning_rate": 0.0008,
"loss": 2.8139381408691406,
"step": 1066
},
{
"epoch": 0.05606299212598425,
"grad_norm": 0.11301624029874802,
"learning_rate": 0.0008,
"loss": 2.7693135738372803,
"step": 1068
},
{
"epoch": 0.05616797900262467,
"grad_norm": 0.09614431113004684,
"learning_rate": 0.0008,
"loss": 2.7754907608032227,
"step": 1070
},
{
"epoch": 0.05627296587926509,
"grad_norm": 0.10846854001283646,
"learning_rate": 0.0008,
"loss": 2.7906415462493896,
"step": 1072
},
{
"epoch": 0.056377952755905514,
"grad_norm": 0.10793575644493103,
"learning_rate": 0.0008,
"loss": 2.7774417400360107,
"step": 1074
},
{
"epoch": 0.056482939632545935,
"grad_norm": 0.10033487528562546,
"learning_rate": 0.0008,
"loss": 2.7576797008514404,
"step": 1076
},
{
"epoch": 0.05658792650918635,
"grad_norm": 0.10204245150089264,
"learning_rate": 0.0008,
"loss": 2.8064651489257812,
"step": 1078
},
{
"epoch": 0.05669291338582677,
"grad_norm": 0.1339305192232132,
"learning_rate": 0.0008,
"loss": 2.8269896507263184,
"step": 1080
},
{
"epoch": 0.05679790026246719,
"grad_norm": 0.10039006918668747,
"learning_rate": 0.0008,
"loss": 2.785451889038086,
"step": 1082
},
{
"epoch": 0.056902887139107614,
"grad_norm": 0.09588530659675598,
"learning_rate": 0.0008,
"loss": 2.751840353012085,
"step": 1084
},
{
"epoch": 0.057007874015748035,
"grad_norm": 0.09678629785776138,
"learning_rate": 0.0008,
"loss": 2.820312738418579,
"step": 1086
},
{
"epoch": 0.05711286089238845,
"grad_norm": 0.09806337207555771,
"learning_rate": 0.0008,
"loss": 2.735081434249878,
"step": 1088
},
{
"epoch": 0.05721784776902887,
"grad_norm": 0.11089258641004562,
"learning_rate": 0.0008,
"loss": 2.7608463764190674,
"step": 1090
},
{
"epoch": 0.05732283464566929,
"grad_norm": 0.09958311170339584,
"learning_rate": 0.0008,
"loss": 2.7519888877868652,
"step": 1092
},
{
"epoch": 0.05742782152230971,
"grad_norm": 0.10076095163822174,
"learning_rate": 0.0008,
"loss": 2.8068771362304688,
"step": 1094
},
{
"epoch": 0.057532808398950135,
"grad_norm": 0.09349599480628967,
"learning_rate": 0.0008,
"loss": 2.8188719749450684,
"step": 1096
},
{
"epoch": 0.05763779527559055,
"grad_norm": 0.09559649974107742,
"learning_rate": 0.0008,
"loss": 2.8073160648345947,
"step": 1098
},
{
"epoch": 0.05774278215223097,
"grad_norm": 0.0973324403166771,
"learning_rate": 0.0008,
"loss": 2.81024432182312,
"step": 1100
},
{
"epoch": 0.05784776902887139,
"grad_norm": 0.10361398011445999,
"learning_rate": 0.0008,
"loss": 2.7769150733947754,
"step": 1102
},
{
"epoch": 0.05795275590551181,
"grad_norm": 0.09911870211362839,
"learning_rate": 0.0008,
"loss": 2.7836496829986572,
"step": 1104
},
{
"epoch": 0.058057742782152234,
"grad_norm": 0.0959470123052597,
"learning_rate": 0.0008,
"loss": 2.824338436126709,
"step": 1106
},
{
"epoch": 0.05816272965879265,
"grad_norm": 0.10547234117984772,
"learning_rate": 0.0008,
"loss": 2.8017425537109375,
"step": 1108
},
{
"epoch": 0.05826771653543307,
"grad_norm": 0.11770127713680267,
"learning_rate": 0.0008,
"loss": 2.778801918029785,
"step": 1110
},
{
"epoch": 0.05837270341207349,
"grad_norm": 0.10263510793447495,
"learning_rate": 0.0008,
"loss": 2.7272756099700928,
"step": 1112
},
{
"epoch": 0.05847769028871391,
"grad_norm": 0.10365133732557297,
"learning_rate": 0.0008,
"loss": 2.6706371307373047,
"step": 1114
},
{
"epoch": 0.058582677165354334,
"grad_norm": 0.10239488631486893,
"learning_rate": 0.0008,
"loss": 2.7648658752441406,
"step": 1116
},
{
"epoch": 0.05868766404199475,
"grad_norm": 0.10074584931135178,
"learning_rate": 0.0008,
"loss": 2.7860660552978516,
"step": 1118
},
{
"epoch": 0.05879265091863517,
"grad_norm": 0.09691484272480011,
"learning_rate": 0.0008,
"loss": 2.776440382003784,
"step": 1120
},
{
"epoch": 0.05889763779527559,
"grad_norm": 0.09571411460638046,
"learning_rate": 0.0008,
"loss": 2.7625234127044678,
"step": 1122
},
{
"epoch": 0.05900262467191601,
"grad_norm": 0.10247057676315308,
"learning_rate": 0.0008,
"loss": 2.749131679534912,
"step": 1124
},
{
"epoch": 0.059107611548556434,
"grad_norm": 0.10407362133264542,
"learning_rate": 0.0008,
"loss": 2.8207249641418457,
"step": 1126
},
{
"epoch": 0.05921259842519685,
"grad_norm": 0.09510679543018341,
"learning_rate": 0.0008,
"loss": 2.6953272819519043,
"step": 1128
},
{
"epoch": 0.05931758530183727,
"grad_norm": 0.10698787122964859,
"learning_rate": 0.0008,
"loss": 2.795836925506592,
"step": 1130
},
{
"epoch": 0.05942257217847769,
"grad_norm": 0.09319344162940979,
"learning_rate": 0.0008,
"loss": 2.751784324645996,
"step": 1132
},
{
"epoch": 0.05952755905511811,
"grad_norm": 0.1036166325211525,
"learning_rate": 0.0008,
"loss": 2.768706798553467,
"step": 1134
},
{
"epoch": 0.059632545931758534,
"grad_norm": 0.1037125214934349,
"learning_rate": 0.0008,
"loss": 2.7052805423736572,
"step": 1136
},
{
"epoch": 0.05973753280839895,
"grad_norm": 0.09657058864831924,
"learning_rate": 0.0008,
"loss": 2.7239277362823486,
"step": 1138
},
{
"epoch": 0.05984251968503937,
"grad_norm": 0.09930210560560226,
"learning_rate": 0.0008,
"loss": 2.7407634258270264,
"step": 1140
},
{
"epoch": 0.05994750656167979,
"grad_norm": 0.10446039587259293,
"learning_rate": 0.0008,
"loss": 2.7894794940948486,
"step": 1142
},
{
"epoch": 0.06005249343832021,
"grad_norm": 0.09340780973434448,
"learning_rate": 0.0008,
"loss": 2.7534453868865967,
"step": 1144
},
{
"epoch": 0.06015748031496063,
"grad_norm": 0.09551321715116501,
"learning_rate": 0.0008,
"loss": 2.690730571746826,
"step": 1146
},
{
"epoch": 0.06026246719160105,
"grad_norm": 0.10366897284984589,
"learning_rate": 0.0008,
"loss": 2.773142099380493,
"step": 1148
},
{
"epoch": 0.06036745406824147,
"grad_norm": 0.09920721501111984,
"learning_rate": 0.0008,
"loss": 2.736051321029663,
"step": 1150
},
{
"epoch": 0.06047244094488189,
"grad_norm": 0.09954190999269485,
"learning_rate": 0.0008,
"loss": 2.7246105670928955,
"step": 1152
},
{
"epoch": 0.06057742782152231,
"grad_norm": 0.0974222794175148,
"learning_rate": 0.0008,
"loss": 2.731856107711792,
"step": 1154
},
{
"epoch": 0.06068241469816273,
"grad_norm": 0.097303107380867,
"learning_rate": 0.0008,
"loss": 2.7895407676696777,
"step": 1156
},
{
"epoch": 0.06078740157480315,
"grad_norm": 0.09522704035043716,
"learning_rate": 0.0008,
"loss": 2.7590274810791016,
"step": 1158
},
{
"epoch": 0.06089238845144357,
"grad_norm": 0.09463141113519669,
"learning_rate": 0.0008,
"loss": 2.765191078186035,
"step": 1160
},
{
"epoch": 0.06099737532808399,
"grad_norm": 0.09408853203058243,
"learning_rate": 0.0008,
"loss": 2.7823188304901123,
"step": 1162
},
{
"epoch": 0.06110236220472441,
"grad_norm": 0.09858901798725128,
"learning_rate": 0.0008,
"loss": 2.707946538925171,
"step": 1164
},
{
"epoch": 0.06120734908136483,
"grad_norm": 0.09399278461933136,
"learning_rate": 0.0008,
"loss": 2.7710776329040527,
"step": 1166
},
{
"epoch": 0.06131233595800525,
"grad_norm": 0.09577006846666336,
"learning_rate": 0.0008,
"loss": 2.7472236156463623,
"step": 1168
},
{
"epoch": 0.06141732283464567,
"grad_norm": 0.10166503489017487,
"learning_rate": 0.0008,
"loss": 2.774897575378418,
"step": 1170
},
{
"epoch": 0.06152230971128609,
"grad_norm": 0.09624114632606506,
"learning_rate": 0.0008,
"loss": 2.748838424682617,
"step": 1172
},
{
"epoch": 0.06162729658792651,
"grad_norm": 0.09472914040088654,
"learning_rate": 0.0008,
"loss": 2.771334171295166,
"step": 1174
},
{
"epoch": 0.06173228346456693,
"grad_norm": 0.09809508174657822,
"learning_rate": 0.0008,
"loss": 2.8077011108398438,
"step": 1176
},
{
"epoch": 0.06183727034120735,
"grad_norm": 0.09370114654302597,
"learning_rate": 0.0008,
"loss": 2.724283218383789,
"step": 1178
},
{
"epoch": 0.06194225721784777,
"grad_norm": 0.0985821783542633,
"learning_rate": 0.0008,
"loss": 2.880124568939209,
"step": 1180
},
{
"epoch": 0.06204724409448819,
"grad_norm": 0.09660397469997406,
"learning_rate": 0.0008,
"loss": 2.8263754844665527,
"step": 1182
},
{
"epoch": 0.06215223097112861,
"grad_norm": 0.09598527103662491,
"learning_rate": 0.0008,
"loss": 2.666367530822754,
"step": 1184
},
{
"epoch": 0.06225721784776903,
"grad_norm": 0.09384316205978394,
"learning_rate": 0.0008,
"loss": 2.7239773273468018,
"step": 1186
},
{
"epoch": 0.06236220472440945,
"grad_norm": 0.0932997465133667,
"learning_rate": 0.0008,
"loss": 2.7118349075317383,
"step": 1188
},
{
"epoch": 0.06246719160104987,
"grad_norm": 0.09373453259468079,
"learning_rate": 0.0008,
"loss": 2.7382428646087646,
"step": 1190
},
{
"epoch": 0.06257217847769028,
"grad_norm": 0.09803857654333115,
"learning_rate": 0.0008,
"loss": 2.755943775177002,
"step": 1192
},
{
"epoch": 0.06267716535433071,
"grad_norm": 0.09311717003583908,
"learning_rate": 0.0008,
"loss": 2.7395267486572266,
"step": 1194
},
{
"epoch": 0.06278215223097112,
"grad_norm": 0.09369563311338425,
"learning_rate": 0.0008,
"loss": 2.785970449447632,
"step": 1196
},
{
"epoch": 0.06288713910761155,
"grad_norm": 0.09036700427532196,
"learning_rate": 0.0008,
"loss": 2.776278257369995,
"step": 1198
},
{
"epoch": 0.06299212598425197,
"grad_norm": 0.09363891929388046,
"learning_rate": 0.0008,
"loss": 2.7700867652893066,
"step": 1200
},
{
"epoch": 0.06309711286089238,
"grad_norm": 0.09650267660617828,
"learning_rate": 0.0008,
"loss": 2.713502883911133,
"step": 1202
},
{
"epoch": 0.06320209973753281,
"grad_norm": 0.10293524712324142,
"learning_rate": 0.0008,
"loss": 2.9022140502929688,
"step": 1204
},
{
"epoch": 0.06330708661417322,
"grad_norm": 0.09519843757152557,
"learning_rate": 0.0008,
"loss": 2.7313969135284424,
"step": 1206
},
{
"epoch": 0.06341207349081365,
"grad_norm": 0.0950169712305069,
"learning_rate": 0.0008,
"loss": 2.774022340774536,
"step": 1208
},
{
"epoch": 0.06351706036745407,
"grad_norm": 0.09091480821371078,
"learning_rate": 0.0008,
"loss": 2.7015767097473145,
"step": 1210
},
{
"epoch": 0.06362204724409448,
"grad_norm": 0.09598124027252197,
"learning_rate": 0.0008,
"loss": 2.7730629444122314,
"step": 1212
},
{
"epoch": 0.06372703412073491,
"grad_norm": 0.09794464707374573,
"learning_rate": 0.0008,
"loss": 2.8449044227600098,
"step": 1214
},
{
"epoch": 0.06383202099737532,
"grad_norm": 0.10073459148406982,
"learning_rate": 0.0008,
"loss": 2.7421374320983887,
"step": 1216
},
{
"epoch": 0.06393700787401575,
"grad_norm": 0.09479549527168274,
"learning_rate": 0.0008,
"loss": 2.726524829864502,
"step": 1218
},
{
"epoch": 0.06404199475065617,
"grad_norm": 0.09764054417610168,
"learning_rate": 0.0008,
"loss": 2.7664859294891357,
"step": 1220
},
{
"epoch": 0.06414698162729658,
"grad_norm": 0.09193890541791916,
"learning_rate": 0.0008,
"loss": 2.7090096473693848,
"step": 1222
},
{
"epoch": 0.06425196850393701,
"grad_norm": 0.0995439738035202,
"learning_rate": 0.0008,
"loss": 2.6843483448028564,
"step": 1224
},
{
"epoch": 0.06435695538057742,
"grad_norm": 0.09356983751058578,
"learning_rate": 0.0008,
"loss": 2.7224812507629395,
"step": 1226
},
{
"epoch": 0.06446194225721785,
"grad_norm": 0.0965329185128212,
"learning_rate": 0.0008,
"loss": 2.739919900894165,
"step": 1228
},
{
"epoch": 0.06456692913385827,
"grad_norm": 0.09178649634122849,
"learning_rate": 0.0008,
"loss": 2.7742674350738525,
"step": 1230
},
{
"epoch": 0.06467191601049868,
"grad_norm": 0.09057556837797165,
"learning_rate": 0.0008,
"loss": 2.6888370513916016,
"step": 1232
},
{
"epoch": 0.06477690288713911,
"grad_norm": 0.09977737814188004,
"learning_rate": 0.0008,
"loss": 2.7652909755706787,
"step": 1234
},
{
"epoch": 0.06488188976377952,
"grad_norm": 0.09570503234863281,
"learning_rate": 0.0008,
"loss": 2.719186782836914,
"step": 1236
},
{
"epoch": 0.06498687664041995,
"grad_norm": 0.09464333951473236,
"learning_rate": 0.0008,
"loss": 2.682467460632324,
"step": 1238
},
{
"epoch": 0.06509186351706037,
"grad_norm": 0.10610726475715637,
"learning_rate": 0.0008,
"loss": 2.6956610679626465,
"step": 1240
},
{
"epoch": 0.06519685039370078,
"grad_norm": 0.09222975373268127,
"learning_rate": 0.0008,
"loss": 2.741663694381714,
"step": 1242
},
{
"epoch": 0.06530183727034121,
"grad_norm": 0.09509462118148804,
"learning_rate": 0.0008,
"loss": 2.739074468612671,
"step": 1244
},
{
"epoch": 0.06540682414698162,
"grad_norm": 0.09526625275611877,
"learning_rate": 0.0008,
"loss": 2.716810464859009,
"step": 1246
},
{
"epoch": 0.06551181102362205,
"grad_norm": 0.08917568624019623,
"learning_rate": 0.0008,
"loss": 2.7790722846984863,
"step": 1248
},
{
"epoch": 0.06561679790026247,
"grad_norm": 0.08985543996095657,
"learning_rate": 0.0008,
"loss": 2.748087167739868,
"step": 1250
},
{
"epoch": 0.06572178477690288,
"grad_norm": 0.09263970702886581,
"learning_rate": 0.0008,
"loss": 2.6896450519561768,
"step": 1252
},
{
"epoch": 0.06582677165354331,
"grad_norm": 0.09330984950065613,
"learning_rate": 0.0008,
"loss": 2.6958892345428467,
"step": 1254
},
{
"epoch": 0.06593175853018372,
"grad_norm": 0.08814782649278641,
"learning_rate": 0.0008,
"loss": 2.7310869693756104,
"step": 1256
},
{
"epoch": 0.06603674540682415,
"grad_norm": 0.09247346967458725,
"learning_rate": 0.0008,
"loss": 2.6854116916656494,
"step": 1258
},
{
"epoch": 0.06614173228346457,
"grad_norm": 0.0904579684138298,
"learning_rate": 0.0008,
"loss": 2.7304842472076416,
"step": 1260
},
{
"epoch": 0.06624671916010498,
"grad_norm": 0.10152405500411987,
"learning_rate": 0.0008,
"loss": 2.702768325805664,
"step": 1262
},
{
"epoch": 0.06635170603674541,
"grad_norm": 0.09937993437051773,
"learning_rate": 0.0008,
"loss": 2.766422986984253,
"step": 1264
},
{
"epoch": 0.06645669291338582,
"grad_norm": 0.09391853213310242,
"learning_rate": 0.0008,
"loss": 2.707615613937378,
"step": 1266
},
{
"epoch": 0.06656167979002625,
"grad_norm": 0.08916128426790237,
"learning_rate": 0.0008,
"loss": 2.6421377658843994,
"step": 1268
},
{
"epoch": 0.06666666666666667,
"grad_norm": 0.11973083019256592,
"learning_rate": 0.0008,
"loss": 2.764481782913208,
"step": 1270
},
{
"epoch": 0.06677165354330708,
"grad_norm": 0.09177809208631516,
"learning_rate": 0.0008,
"loss": 2.782212972640991,
"step": 1272
},
{
"epoch": 0.06687664041994751,
"grad_norm": 0.09051013737916946,
"learning_rate": 0.0008,
"loss": 2.728666067123413,
"step": 1274
},
{
"epoch": 0.06698162729658792,
"grad_norm": 0.0887698158621788,
"learning_rate": 0.0008,
"loss": 2.6825649738311768,
"step": 1276
},
{
"epoch": 0.06708661417322835,
"grad_norm": 0.08877133578062057,
"learning_rate": 0.0008,
"loss": 2.770366668701172,
"step": 1278
},
{
"epoch": 0.06719160104986877,
"grad_norm": 0.09202440083026886,
"learning_rate": 0.0008,
"loss": 2.774871826171875,
"step": 1280
},
{
"epoch": 0.06729658792650918,
"grad_norm": 0.09336346387863159,
"learning_rate": 0.0008,
"loss": 2.733929395675659,
"step": 1282
},
{
"epoch": 0.06740157480314961,
"grad_norm": 0.09517822414636612,
"learning_rate": 0.0008,
"loss": 2.7393155097961426,
"step": 1284
},
{
"epoch": 0.06750656167979002,
"grad_norm": 0.09316384792327881,
"learning_rate": 0.0008,
"loss": 2.726889133453369,
"step": 1286
},
{
"epoch": 0.06761154855643045,
"grad_norm": 0.09062747657299042,
"learning_rate": 0.0008,
"loss": 2.676839590072632,
"step": 1288
},
{
"epoch": 0.06771653543307087,
"grad_norm": 0.0867094025015831,
"learning_rate": 0.0008,
"loss": 2.712338924407959,
"step": 1290
},
{
"epoch": 0.06782152230971128,
"grad_norm": 0.09216507524251938,
"learning_rate": 0.0008,
"loss": 2.76090931892395,
"step": 1292
},
{
"epoch": 0.06792650918635171,
"grad_norm": 0.09290657192468643,
"learning_rate": 0.0008,
"loss": 2.7047674655914307,
"step": 1294
},
{
"epoch": 0.06803149606299212,
"grad_norm": 0.09055540710687637,
"learning_rate": 0.0008,
"loss": 2.725385904312134,
"step": 1296
},
{
"epoch": 0.06813648293963255,
"grad_norm": 0.09026801586151123,
"learning_rate": 0.0008,
"loss": 2.7393622398376465,
"step": 1298
},
{
"epoch": 0.06824146981627296,
"grad_norm": 0.08923443406820297,
"learning_rate": 0.0008,
"loss": 2.70747709274292,
"step": 1300
},
{
"epoch": 0.06834645669291338,
"grad_norm": 0.09018641710281372,
"learning_rate": 0.0008,
"loss": 2.687223434448242,
"step": 1302
},
{
"epoch": 0.06845144356955381,
"grad_norm": 0.08945067226886749,
"learning_rate": 0.0008,
"loss": 2.758821964263916,
"step": 1304
},
{
"epoch": 0.06855643044619422,
"grad_norm": 0.08930539339780807,
"learning_rate": 0.0008,
"loss": 2.7447938919067383,
"step": 1306
},
{
"epoch": 0.06866141732283465,
"grad_norm": 0.09555280953645706,
"learning_rate": 0.0008,
"loss": 2.6633846759796143,
"step": 1308
},
{
"epoch": 0.06876640419947506,
"grad_norm": 0.09034199267625809,
"learning_rate": 0.0008,
"loss": 2.7054800987243652,
"step": 1310
},
{
"epoch": 0.06887139107611548,
"grad_norm": 0.0911264568567276,
"learning_rate": 0.0008,
"loss": 2.703281879425049,
"step": 1312
},
{
"epoch": 0.06897637795275591,
"grad_norm": 0.11208830028772354,
"learning_rate": 0.0008,
"loss": 2.7217724323272705,
"step": 1314
},
{
"epoch": 0.06908136482939632,
"grad_norm": 0.09283586591482162,
"learning_rate": 0.0008,
"loss": 2.6326820850372314,
"step": 1316
},
{
"epoch": 0.06918635170603675,
"grad_norm": 0.09743106365203857,
"learning_rate": 0.0008,
"loss": 2.7401678562164307,
"step": 1318
},
{
"epoch": 0.06929133858267716,
"grad_norm": 0.10332754254341125,
"learning_rate": 0.0008,
"loss": 2.6880064010620117,
"step": 1320
},
{
"epoch": 0.06939632545931758,
"grad_norm": 0.0905320793390274,
"learning_rate": 0.0008,
"loss": 2.8321988582611084,
"step": 1322
},
{
"epoch": 0.06950131233595801,
"grad_norm": 0.09661230444908142,
"learning_rate": 0.0008,
"loss": 2.820366144180298,
"step": 1324
},
{
"epoch": 0.06960629921259842,
"grad_norm": 0.1010541319847107,
"learning_rate": 0.0008,
"loss": 2.669790506362915,
"step": 1326
},
{
"epoch": 0.06971128608923885,
"grad_norm": 0.10069449245929718,
"learning_rate": 0.0008,
"loss": 2.6688294410705566,
"step": 1328
},
{
"epoch": 0.06981627296587926,
"grad_norm": 0.0907818153500557,
"learning_rate": 0.0008,
"loss": 2.711893081665039,
"step": 1330
},
{
"epoch": 0.06992125984251968,
"grad_norm": 0.08876825869083405,
"learning_rate": 0.0008,
"loss": 2.7334165573120117,
"step": 1332
},
{
"epoch": 0.0700262467191601,
"grad_norm": 0.08738885074853897,
"learning_rate": 0.0008,
"loss": 2.6676371097564697,
"step": 1334
},
{
"epoch": 0.07013123359580052,
"grad_norm": 0.09067124128341675,
"learning_rate": 0.0008,
"loss": 2.7439775466918945,
"step": 1336
},
{
"epoch": 0.07023622047244095,
"grad_norm": 0.08947622030973434,
"learning_rate": 0.0008,
"loss": 2.773383617401123,
"step": 1338
},
{
"epoch": 0.07034120734908136,
"grad_norm": 0.08832672238349915,
"learning_rate": 0.0008,
"loss": 2.684849500656128,
"step": 1340
},
{
"epoch": 0.07044619422572178,
"grad_norm": 0.09062019735574722,
"learning_rate": 0.0008,
"loss": 2.6650891304016113,
"step": 1342
},
{
"epoch": 0.0705511811023622,
"grad_norm": 0.09270370006561279,
"learning_rate": 0.0008,
"loss": 2.7085578441619873,
"step": 1344
},
{
"epoch": 0.07065616797900262,
"grad_norm": 0.08942906558513641,
"learning_rate": 0.0008,
"loss": 2.7183375358581543,
"step": 1346
},
{
"epoch": 0.07076115485564305,
"grad_norm": 0.08755499869585037,
"learning_rate": 0.0008,
"loss": 2.6928529739379883,
"step": 1348
},
{
"epoch": 0.07086614173228346,
"grad_norm": 0.0885811522603035,
"learning_rate": 0.0008,
"loss": 2.7188720703125,
"step": 1350
},
{
"epoch": 0.07097112860892388,
"grad_norm": 0.08931387960910797,
"learning_rate": 0.0008,
"loss": 2.6251308917999268,
"step": 1352
},
{
"epoch": 0.0710761154855643,
"grad_norm": 0.0879686251282692,
"learning_rate": 0.0008,
"loss": 2.74489688873291,
"step": 1354
},
{
"epoch": 0.07118110236220472,
"grad_norm": 0.08499078452587128,
"learning_rate": 0.0008,
"loss": 2.6151463985443115,
"step": 1356
},
{
"epoch": 0.07128608923884515,
"grad_norm": 0.08597178012132645,
"learning_rate": 0.0008,
"loss": 2.6897919178009033,
"step": 1358
},
{
"epoch": 0.07139107611548556,
"grad_norm": 0.09871555864810944,
"learning_rate": 0.0008,
"loss": 2.6851541996002197,
"step": 1360
},
{
"epoch": 0.07149606299212598,
"grad_norm": 0.08770178258419037,
"learning_rate": 0.0008,
"loss": 2.628960371017456,
"step": 1362
},
{
"epoch": 0.0716010498687664,
"grad_norm": 0.09183717519044876,
"learning_rate": 0.0008,
"loss": 2.6417086124420166,
"step": 1364
},
{
"epoch": 0.07170603674540682,
"grad_norm": 0.08580727875232697,
"learning_rate": 0.0008,
"loss": 2.6884584426879883,
"step": 1366
},
{
"epoch": 0.07181102362204725,
"grad_norm": 0.08483970910310745,
"learning_rate": 0.0008,
"loss": 2.75624942779541,
"step": 1368
},
{
"epoch": 0.07191601049868766,
"grad_norm": 0.09414925426244736,
"learning_rate": 0.0008,
"loss": 2.690917730331421,
"step": 1370
},
{
"epoch": 0.07202099737532808,
"grad_norm": 0.0874631330370903,
"learning_rate": 0.0008,
"loss": 2.6809377670288086,
"step": 1372
},
{
"epoch": 0.0721259842519685,
"grad_norm": 0.09258206188678741,
"learning_rate": 0.0008,
"loss": 2.6989850997924805,
"step": 1374
},
{
"epoch": 0.07223097112860892,
"grad_norm": 0.08777697384357452,
"learning_rate": 0.0008,
"loss": 2.5786826610565186,
"step": 1376
},
{
"epoch": 0.07233595800524935,
"grad_norm": 0.09499172866344452,
"learning_rate": 0.0008,
"loss": 2.704826593399048,
"step": 1378
},
{
"epoch": 0.07244094488188976,
"grad_norm": 0.08798379451036453,
"learning_rate": 0.0008,
"loss": 2.6959006786346436,
"step": 1380
},
{
"epoch": 0.07254593175853018,
"grad_norm": 0.09166393429040909,
"learning_rate": 0.0008,
"loss": 2.744873523712158,
"step": 1382
},
{
"epoch": 0.0726509186351706,
"grad_norm": 0.08753436803817749,
"learning_rate": 0.0008,
"loss": 2.647568464279175,
"step": 1384
},
{
"epoch": 0.07275590551181102,
"grad_norm": 0.0951622724533081,
"learning_rate": 0.0008,
"loss": 2.769989490509033,
"step": 1386
},
{
"epoch": 0.07286089238845145,
"grad_norm": 0.08674084395170212,
"learning_rate": 0.0008,
"loss": 2.747138261795044,
"step": 1388
},
{
"epoch": 0.07296587926509186,
"grad_norm": 0.09108833223581314,
"learning_rate": 0.0008,
"loss": 2.6137795448303223,
"step": 1390
},
{
"epoch": 0.07307086614173228,
"grad_norm": 0.08870238810777664,
"learning_rate": 0.0008,
"loss": 2.666318655014038,
"step": 1392
},
{
"epoch": 0.0731758530183727,
"grad_norm": 0.08854766190052032,
"learning_rate": 0.0008,
"loss": 2.6619858741760254,
"step": 1394
},
{
"epoch": 0.07328083989501312,
"grad_norm": 0.08897228538990021,
"learning_rate": 0.0008,
"loss": 2.64046049118042,
"step": 1396
},
{
"epoch": 0.07338582677165355,
"grad_norm": 0.08897323161363602,
"learning_rate": 0.0008,
"loss": 2.7652525901794434,
"step": 1398
},
{
"epoch": 0.07349081364829396,
"grad_norm": 0.08516496419906616,
"learning_rate": 0.0008,
"loss": 2.5715649127960205,
"step": 1400
},
{
"epoch": 0.07359580052493438,
"grad_norm": 0.08876385539770126,
"learning_rate": 0.0008,
"loss": 2.7622568607330322,
"step": 1402
},
{
"epoch": 0.0737007874015748,
"grad_norm": 0.08872676640748978,
"learning_rate": 0.0008,
"loss": 2.7113258838653564,
"step": 1404
},
{
"epoch": 0.07380577427821522,
"grad_norm": 0.08686773478984833,
"learning_rate": 0.0008,
"loss": 2.6650986671447754,
"step": 1406
},
{
"epoch": 0.07391076115485565,
"grad_norm": 0.09066683799028397,
"learning_rate": 0.0008,
"loss": 2.636753559112549,
"step": 1408
},
{
"epoch": 0.07401574803149606,
"grad_norm": 0.08717681467533112,
"learning_rate": 0.0008,
"loss": 2.6704976558685303,
"step": 1410
},
{
"epoch": 0.07412073490813648,
"grad_norm": 0.08846788853406906,
"learning_rate": 0.0008,
"loss": 2.6926631927490234,
"step": 1412
},
{
"epoch": 0.0742257217847769,
"grad_norm": 0.09278976172208786,
"learning_rate": 0.0008,
"loss": 2.6709396839141846,
"step": 1414
},
{
"epoch": 0.07433070866141732,
"grad_norm": 0.08742888271808624,
"learning_rate": 0.0008,
"loss": 2.691894769668579,
"step": 1416
},
{
"epoch": 0.07443569553805775,
"grad_norm": 0.08882424980401993,
"learning_rate": 0.0008,
"loss": 2.6744706630706787,
"step": 1418
},
{
"epoch": 0.07454068241469816,
"grad_norm": 0.09900332987308502,
"learning_rate": 0.0008,
"loss": 2.6957004070281982,
"step": 1420
},
{
"epoch": 0.07464566929133858,
"grad_norm": 0.08583637326955795,
"learning_rate": 0.0008,
"loss": 2.629910707473755,
"step": 1422
},
{
"epoch": 0.074750656167979,
"grad_norm": 0.09553971141576767,
"learning_rate": 0.0008,
"loss": 2.7146975994110107,
"step": 1424
},
{
"epoch": 0.07485564304461942,
"grad_norm": 0.08393795043230057,
"learning_rate": 0.0008,
"loss": 2.644871234893799,
"step": 1426
},
{
"epoch": 0.07496062992125985,
"grad_norm": 0.08811771124601364,
"learning_rate": 0.0008,
"loss": 2.74150013923645,
"step": 1428
},
{
"epoch": 0.07506561679790026,
"grad_norm": 0.08552783727645874,
"learning_rate": 0.0008,
"loss": 2.626519203186035,
"step": 1430
},
{
"epoch": 0.07517060367454068,
"grad_norm": 0.10242731124162674,
"learning_rate": 0.0008,
"loss": 2.641078472137451,
"step": 1432
},
{
"epoch": 0.0752755905511811,
"grad_norm": 0.09166337549686432,
"learning_rate": 0.0008,
"loss": 2.6449639797210693,
"step": 1434
},
{
"epoch": 0.07538057742782152,
"grad_norm": 0.08761779218912125,
"learning_rate": 0.0008,
"loss": 2.677574634552002,
"step": 1436
},
{
"epoch": 0.07548556430446195,
"grad_norm": 0.08642394095659256,
"learning_rate": 0.0008,
"loss": 2.6905453205108643,
"step": 1438
},
{
"epoch": 0.07559055118110236,
"grad_norm": 0.08333615213632584,
"learning_rate": 0.0008,
"loss": 2.592236280441284,
"step": 1440
},
{
"epoch": 0.07569553805774278,
"grad_norm": 0.08484560251235962,
"learning_rate": 0.0008,
"loss": 2.6854631900787354,
"step": 1442
},
{
"epoch": 0.0758005249343832,
"grad_norm": 0.0837368294596672,
"learning_rate": 0.0008,
"loss": 2.6374318599700928,
"step": 1444
},
{
"epoch": 0.07590551181102362,
"grad_norm": 0.09100774675607681,
"learning_rate": 0.0008,
"loss": 2.6125762462615967,
"step": 1446
},
{
"epoch": 0.07601049868766405,
"grad_norm": 0.08711443096399307,
"learning_rate": 0.0008,
"loss": 2.597930669784546,
"step": 1448
},
{
"epoch": 0.07611548556430446,
"grad_norm": 0.08646796643733978,
"learning_rate": 0.0008,
"loss": 2.648893356323242,
"step": 1450
},
{
"epoch": 0.07622047244094488,
"grad_norm": 0.09896808862686157,
"learning_rate": 0.0008,
"loss": 2.6535043716430664,
"step": 1452
},
{
"epoch": 0.0763254593175853,
"grad_norm": 0.08856473863124847,
"learning_rate": 0.0008,
"loss": 2.602234363555908,
"step": 1454
},
{
"epoch": 0.07643044619422572,
"grad_norm": 0.0864076167345047,
"learning_rate": 0.0008,
"loss": 2.689237594604492,
"step": 1456
},
{
"epoch": 0.07653543307086615,
"grad_norm": 0.08773746341466904,
"learning_rate": 0.0008,
"loss": 2.6581928730010986,
"step": 1458
},
{
"epoch": 0.07664041994750656,
"grad_norm": 0.08633334189653397,
"learning_rate": 0.0008,
"loss": 2.5990493297576904,
"step": 1460
},
{
"epoch": 0.07674540682414698,
"grad_norm": 0.08365172892808914,
"learning_rate": 0.0008,
"loss": 2.6227877140045166,
"step": 1462
},
{
"epoch": 0.0768503937007874,
"grad_norm": 0.08256988227367401,
"learning_rate": 0.0008,
"loss": 2.5598974227905273,
"step": 1464
},
{
"epoch": 0.07695538057742782,
"grad_norm": 0.08591403067111969,
"learning_rate": 0.0008,
"loss": 2.673539400100708,
"step": 1466
},
{
"epoch": 0.07706036745406825,
"grad_norm": 0.15994617342948914,
"learning_rate": 0.0008,
"loss": 2.664999008178711,
"step": 1468
},
{
"epoch": 0.07716535433070866,
"grad_norm": 0.0995364636182785,
"learning_rate": 0.0008,
"loss": 2.6732304096221924,
"step": 1470
},
{
"epoch": 0.07727034120734907,
"grad_norm": 0.49649930000305176,
"learning_rate": 0.0008,
"loss": 2.6371679306030273,
"step": 1472
},
{
"epoch": 0.0773753280839895,
"grad_norm": 0.13202159106731415,
"learning_rate": 0.0008,
"loss": 2.666672468185425,
"step": 1474
},
{
"epoch": 0.07748031496062992,
"grad_norm": 0.14444680511951447,
"learning_rate": 0.0008,
"loss": 2.6946022510528564,
"step": 1476
},
{
"epoch": 0.07758530183727035,
"grad_norm": 0.26887446641921997,
"learning_rate": 0.0008,
"loss": 2.8010661602020264,
"step": 1478
},
{
"epoch": 0.07769028871391076,
"grad_norm": 0.1028187945485115,
"learning_rate": 0.0008,
"loss": 2.7120325565338135,
"step": 1480
},
{
"epoch": 0.07779527559055117,
"grad_norm": 0.10403750836849213,
"learning_rate": 0.0008,
"loss": 2.7645153999328613,
"step": 1482
},
{
"epoch": 0.0779002624671916,
"grad_norm": 0.097693532705307,
"learning_rate": 0.0008,
"loss": 2.569256067276001,
"step": 1484
},
{
"epoch": 0.07800524934383202,
"grad_norm": 0.09556399285793304,
"learning_rate": 0.0008,
"loss": 2.5498592853546143,
"step": 1486
},
{
"epoch": 0.07811023622047245,
"grad_norm": 0.09795936942100525,
"learning_rate": 0.0008,
"loss": 2.6981966495513916,
"step": 1488
},
{
"epoch": 0.07821522309711286,
"grad_norm": 0.16835343837738037,
"learning_rate": 0.0008,
"loss": 2.602991819381714,
"step": 1490
},
{
"epoch": 0.07832020997375327,
"grad_norm": 0.08939483761787415,
"learning_rate": 0.0008,
"loss": 2.639512062072754,
"step": 1492
},
{
"epoch": 0.0784251968503937,
"grad_norm": 0.08930263668298721,
"learning_rate": 0.0008,
"loss": 2.6877212524414062,
"step": 1494
},
{
"epoch": 0.07853018372703412,
"grad_norm": 0.08753892779350281,
"learning_rate": 0.0008,
"loss": 2.748821973800659,
"step": 1496
},
{
"epoch": 0.07863517060367455,
"grad_norm": 0.08467117697000504,
"learning_rate": 0.0008,
"loss": 2.636019706726074,
"step": 1498
},
{
"epoch": 0.07874015748031496,
"grad_norm": 0.08635459095239639,
"learning_rate": 0.0008,
"loss": 2.6212708950042725,
"step": 1500
},
{
"epoch": 0.07884514435695537,
"grad_norm": 0.08619186282157898,
"learning_rate": 0.0008,
"loss": 2.6356201171875,
"step": 1502
},
{
"epoch": 0.0789501312335958,
"grad_norm": 0.08826661854982376,
"learning_rate": 0.0008,
"loss": 2.682232618331909,
"step": 1504
},
{
"epoch": 0.07905511811023622,
"grad_norm": 0.08308306336402893,
"learning_rate": 0.0008,
"loss": 2.6641902923583984,
"step": 1506
},
{
"epoch": 0.07916010498687664,
"grad_norm": 0.08432268351316452,
"learning_rate": 0.0008,
"loss": 2.608417272567749,
"step": 1508
},
{
"epoch": 0.07926509186351706,
"grad_norm": 0.08366723358631134,
"learning_rate": 0.0008,
"loss": 2.6295907497406006,
"step": 1510
},
{
"epoch": 0.07937007874015747,
"grad_norm": 0.08625472337007523,
"learning_rate": 0.0008,
"loss": 2.6681504249572754,
"step": 1512
},
{
"epoch": 0.0794750656167979,
"grad_norm": 0.08417803794145584,
"learning_rate": 0.0008,
"loss": 2.6194047927856445,
"step": 1514
},
{
"epoch": 0.07958005249343832,
"grad_norm": 0.08445578813552856,
"learning_rate": 0.0008,
"loss": 2.603327751159668,
"step": 1516
},
{
"epoch": 0.07968503937007874,
"grad_norm": 0.0818251222372055,
"learning_rate": 0.0008,
"loss": 2.602876901626587,
"step": 1518
},
{
"epoch": 0.07979002624671916,
"grad_norm": 0.08363281935453415,
"learning_rate": 0.0008,
"loss": 2.632730484008789,
"step": 1520
},
{
"epoch": 0.07989501312335957,
"grad_norm": 0.08214236050844193,
"learning_rate": 0.0008,
"loss": 2.5745739936828613,
"step": 1522
},
{
"epoch": 0.08,
"grad_norm": 0.08501773327589035,
"learning_rate": 0.0008,
"loss": 2.5629425048828125,
"step": 1524
},
{
"epoch": 0.08010498687664042,
"grad_norm": 0.0836695060133934,
"learning_rate": 0.0008,
"loss": 2.6567468643188477,
"step": 1526
},
{
"epoch": 0.08020997375328084,
"grad_norm": 0.09470122307538986,
"learning_rate": 0.0008,
"loss": 2.6306705474853516,
"step": 1528
},
{
"epoch": 0.08031496062992126,
"grad_norm": 0.08731096982955933,
"learning_rate": 0.0008,
"loss": 2.6195871829986572,
"step": 1530
},
{
"epoch": 0.08041994750656167,
"grad_norm": 0.08617392182350159,
"learning_rate": 0.0008,
"loss": 2.6669445037841797,
"step": 1532
},
{
"epoch": 0.0805249343832021,
"grad_norm": 0.09462998807430267,
"learning_rate": 0.0008,
"loss": 2.6400246620178223,
"step": 1534
},
{
"epoch": 0.08062992125984252,
"grad_norm": 0.08441915363073349,
"learning_rate": 0.0008,
"loss": 2.645432710647583,
"step": 1536
},
{
"epoch": 0.08073490813648294,
"grad_norm": 0.08263417333364487,
"learning_rate": 0.0008,
"loss": 2.6180851459503174,
"step": 1538
},
{
"epoch": 0.08083989501312336,
"grad_norm": 0.08703829348087311,
"learning_rate": 0.0008,
"loss": 2.5585739612579346,
"step": 1540
},
{
"epoch": 0.08094488188976377,
"grad_norm": 0.08523893356323242,
"learning_rate": 0.0008,
"loss": 2.614161968231201,
"step": 1542
},
{
"epoch": 0.0810498687664042,
"grad_norm": 0.08841872215270996,
"learning_rate": 0.0008,
"loss": 2.6348488330841064,
"step": 1544
},
{
"epoch": 0.08115485564304462,
"grad_norm": 0.08768261969089508,
"learning_rate": 0.0008,
"loss": 2.6650583744049072,
"step": 1546
},
{
"epoch": 0.08125984251968504,
"grad_norm": 0.08522971719503403,
"learning_rate": 0.0008,
"loss": 2.6248960494995117,
"step": 1548
},
{
"epoch": 0.08136482939632546,
"grad_norm": 0.08117776364088058,
"learning_rate": 0.0008,
"loss": 2.5123472213745117,
"step": 1550
},
{
"epoch": 0.08146981627296587,
"grad_norm": 0.10297319293022156,
"learning_rate": 0.0008,
"loss": 2.6397876739501953,
"step": 1552
},
{
"epoch": 0.0815748031496063,
"grad_norm": 0.08273671567440033,
"learning_rate": 0.0008,
"loss": 2.671487808227539,
"step": 1554
},
{
"epoch": 0.08167979002624672,
"grad_norm": 0.08913425356149673,
"learning_rate": 0.0008,
"loss": 2.619361400604248,
"step": 1556
},
{
"epoch": 0.08178477690288714,
"grad_norm": 0.08676572889089584,
"learning_rate": 0.0008,
"loss": 2.646219253540039,
"step": 1558
},
{
"epoch": 0.08188976377952756,
"grad_norm": 0.08558576554059982,
"learning_rate": 0.0008,
"loss": 2.6649773120880127,
"step": 1560
},
{
"epoch": 0.08199475065616797,
"grad_norm": 0.08772425353527069,
"learning_rate": 0.0008,
"loss": 2.5893633365631104,
"step": 1562
},
{
"epoch": 0.0820997375328084,
"grad_norm": 0.0831882581114769,
"learning_rate": 0.0008,
"loss": 2.6974833011627197,
"step": 1564
},
{
"epoch": 0.08220472440944881,
"grad_norm": 0.08178865164518356,
"learning_rate": 0.0008,
"loss": 2.583035707473755,
"step": 1566
},
{
"epoch": 0.08230971128608924,
"grad_norm": 0.08514456450939178,
"learning_rate": 0.0008,
"loss": 2.6143856048583984,
"step": 1568
},
{
"epoch": 0.08241469816272966,
"grad_norm": 0.0887722596526146,
"learning_rate": 0.0008,
"loss": 2.6891093254089355,
"step": 1570
},
{
"epoch": 0.08251968503937007,
"grad_norm": 0.08339700102806091,
"learning_rate": 0.0008,
"loss": 2.6601476669311523,
"step": 1572
},
{
"epoch": 0.0826246719160105,
"grad_norm": 0.09619136154651642,
"learning_rate": 0.0008,
"loss": 2.7047266960144043,
"step": 1574
},
{
"epoch": 0.08272965879265091,
"grad_norm": 0.08555737882852554,
"learning_rate": 0.0008,
"loss": 2.641420602798462,
"step": 1576
},
{
"epoch": 0.08283464566929134,
"grad_norm": 0.09187690168619156,
"learning_rate": 0.0008,
"loss": 2.682300567626953,
"step": 1578
},
{
"epoch": 0.08293963254593176,
"grad_norm": 0.08391961455345154,
"learning_rate": 0.0008,
"loss": 2.596982479095459,
"step": 1580
},
{
"epoch": 0.08304461942257217,
"grad_norm": 0.08660521358251572,
"learning_rate": 0.0008,
"loss": 2.5704190731048584,
"step": 1582
},
{
"epoch": 0.0831496062992126,
"grad_norm": 0.09145216643810272,
"learning_rate": 0.0008,
"loss": 2.610621690750122,
"step": 1584
},
{
"epoch": 0.08325459317585301,
"grad_norm": 0.09076787531375885,
"learning_rate": 0.0008,
"loss": 2.6265766620635986,
"step": 1586
},
{
"epoch": 0.08335958005249344,
"grad_norm": 0.08473757654428482,
"learning_rate": 0.0008,
"loss": 2.5840325355529785,
"step": 1588
},
{
"epoch": 0.08346456692913386,
"grad_norm": 0.08764895796775818,
"learning_rate": 0.0008,
"loss": 2.650861978530884,
"step": 1590
},
{
"epoch": 0.08356955380577427,
"grad_norm": 0.08604638278484344,
"learning_rate": 0.0008,
"loss": 2.5880215167999268,
"step": 1592
},
{
"epoch": 0.0836745406824147,
"grad_norm": 0.08875894546508789,
"learning_rate": 0.0008,
"loss": 2.5545339584350586,
"step": 1594
},
{
"epoch": 0.08377952755905511,
"grad_norm": 0.08827130496501923,
"learning_rate": 0.0008,
"loss": 2.6456351280212402,
"step": 1596
},
{
"epoch": 0.08388451443569554,
"grad_norm": 0.08176963776350021,
"learning_rate": 0.0008,
"loss": 2.5623390674591064,
"step": 1598
},
{
"epoch": 0.08398950131233596,
"grad_norm": 0.086766816675663,
"learning_rate": 0.0008,
"loss": 2.7536349296569824,
"step": 1600
},
{
"epoch": 0.08409448818897637,
"grad_norm": 0.09060511738061905,
"learning_rate": 0.0008,
"loss": 2.631099224090576,
"step": 1602
},
{
"epoch": 0.0841994750656168,
"grad_norm": 0.08291477710008621,
"learning_rate": 0.0008,
"loss": 2.6116275787353516,
"step": 1604
},
{
"epoch": 0.08430446194225721,
"grad_norm": 0.08625714480876923,
"learning_rate": 0.0008,
"loss": 2.647369146347046,
"step": 1606
},
{
"epoch": 0.08440944881889764,
"grad_norm": 0.08942336589097977,
"learning_rate": 0.0008,
"loss": 2.6680569648742676,
"step": 1608
},
{
"epoch": 0.08451443569553806,
"grad_norm": 0.08428546786308289,
"learning_rate": 0.0008,
"loss": 2.6465890407562256,
"step": 1610
},
{
"epoch": 0.08461942257217847,
"grad_norm": 0.08562791347503662,
"learning_rate": 0.0008,
"loss": 2.625067949295044,
"step": 1612
},
{
"epoch": 0.0847244094488189,
"grad_norm": 0.0880139097571373,
"learning_rate": 0.0008,
"loss": 2.5922048091888428,
"step": 1614
},
{
"epoch": 0.08482939632545931,
"grad_norm": 0.08246537297964096,
"learning_rate": 0.0008,
"loss": 2.5575156211853027,
"step": 1616
},
{
"epoch": 0.08493438320209974,
"grad_norm": 0.0834057629108429,
"learning_rate": 0.0008,
"loss": 2.641045570373535,
"step": 1618
},
{
"epoch": 0.08503937007874016,
"grad_norm": 0.08735916763544083,
"learning_rate": 0.0008,
"loss": 2.5660972595214844,
"step": 1620
},
{
"epoch": 0.08514435695538057,
"grad_norm": 0.08078532665967941,
"learning_rate": 0.0008,
"loss": 2.608192205429077,
"step": 1622
},
{
"epoch": 0.085249343832021,
"grad_norm": 0.08159651607275009,
"learning_rate": 0.0008,
"loss": 2.628239631652832,
"step": 1624
},
{
"epoch": 0.08535433070866141,
"grad_norm": 0.08421457558870316,
"learning_rate": 0.0008,
"loss": 2.590017318725586,
"step": 1626
},
{
"epoch": 0.08545931758530184,
"grad_norm": 0.08065648376941681,
"learning_rate": 0.0008,
"loss": 2.5932815074920654,
"step": 1628
},
{
"epoch": 0.08556430446194226,
"grad_norm": 0.08451144397258759,
"learning_rate": 0.0008,
"loss": 2.526507616043091,
"step": 1630
},
{
"epoch": 0.08566929133858267,
"grad_norm": 0.0815906673669815,
"learning_rate": 0.0008,
"loss": 2.6585793495178223,
"step": 1632
},
{
"epoch": 0.0857742782152231,
"grad_norm": 0.0857076346874237,
"learning_rate": 0.0008,
"loss": 2.603756904602051,
"step": 1634
},
{
"epoch": 0.08587926509186351,
"grad_norm": 0.0849592387676239,
"learning_rate": 0.0008,
"loss": 2.5701847076416016,
"step": 1636
},
{
"epoch": 0.08598425196850394,
"grad_norm": 0.0825916975736618,
"learning_rate": 0.0008,
"loss": 2.601931095123291,
"step": 1638
},
{
"epoch": 0.08608923884514436,
"grad_norm": 0.0850144624710083,
"learning_rate": 0.0008,
"loss": 2.6899642944335938,
"step": 1640
},
{
"epoch": 0.08619422572178477,
"grad_norm": 0.07960861921310425,
"learning_rate": 0.0008,
"loss": 2.628523349761963,
"step": 1642
},
{
"epoch": 0.0862992125984252,
"grad_norm": 0.09087909013032913,
"learning_rate": 0.0008,
"loss": 2.637486457824707,
"step": 1644
},
{
"epoch": 0.08640419947506561,
"grad_norm": 0.10057082772254944,
"learning_rate": 0.0008,
"loss": 2.61989688873291,
"step": 1646
},
{
"epoch": 0.08650918635170604,
"grad_norm": 0.08616212755441666,
"learning_rate": 0.0008,
"loss": 2.6472818851470947,
"step": 1648
},
{
"epoch": 0.08661417322834646,
"grad_norm": 0.0801684781908989,
"learning_rate": 0.0008,
"loss": 2.5400612354278564,
"step": 1650
},
{
"epoch": 0.08671916010498687,
"grad_norm": 0.08322037756443024,
"learning_rate": 0.0008,
"loss": 2.6284127235412598,
"step": 1652
},
{
"epoch": 0.0868241469816273,
"grad_norm": 0.08782251924276352,
"learning_rate": 0.0008,
"loss": 2.571457624435425,
"step": 1654
},
{
"epoch": 0.08692913385826771,
"grad_norm": 0.07917717844247818,
"learning_rate": 0.0008,
"loss": 2.583712100982666,
"step": 1656
},
{
"epoch": 0.08703412073490814,
"grad_norm": 0.08118360489606857,
"learning_rate": 0.0008,
"loss": 2.5801053047180176,
"step": 1658
},
{
"epoch": 0.08713910761154856,
"grad_norm": 0.08316761255264282,
"learning_rate": 0.0008,
"loss": 2.6475930213928223,
"step": 1660
},
{
"epoch": 0.08724409448818897,
"grad_norm": 0.08366121351718903,
"learning_rate": 0.0008,
"loss": 2.5696606636047363,
"step": 1662
},
{
"epoch": 0.0873490813648294,
"grad_norm": 0.08328234404325485,
"learning_rate": 0.0008,
"loss": 2.632983922958374,
"step": 1664
},
{
"epoch": 0.08745406824146981,
"grad_norm": 0.09022201597690582,
"learning_rate": 0.0008,
"loss": 2.6194865703582764,
"step": 1666
},
{
"epoch": 0.08755905511811024,
"grad_norm": 0.09023604542016983,
"learning_rate": 0.0008,
"loss": 2.616377592086792,
"step": 1668
},
{
"epoch": 0.08766404199475065,
"grad_norm": 0.08536537736654282,
"learning_rate": 0.0008,
"loss": 2.5466952323913574,
"step": 1670
},
{
"epoch": 0.08776902887139107,
"grad_norm": 0.099100261926651,
"learning_rate": 0.0008,
"loss": 2.659147262573242,
"step": 1672
},
{
"epoch": 0.0878740157480315,
"grad_norm": 0.08265551924705505,
"learning_rate": 0.0008,
"loss": 2.589916229248047,
"step": 1674
},
{
"epoch": 0.08797900262467191,
"grad_norm": 0.09555111080408096,
"learning_rate": 0.0008,
"loss": 2.6505472660064697,
"step": 1676
},
{
"epoch": 0.08808398950131234,
"grad_norm": 0.09552125632762909,
"learning_rate": 0.0008,
"loss": 2.5794239044189453,
"step": 1678
},
{
"epoch": 0.08818897637795275,
"grad_norm": 0.08678983151912689,
"learning_rate": 0.0008,
"loss": 2.643092632293701,
"step": 1680
},
{
"epoch": 0.08829396325459317,
"grad_norm": 0.08301737904548645,
"learning_rate": 0.0008,
"loss": 2.6255621910095215,
"step": 1682
},
{
"epoch": 0.0883989501312336,
"grad_norm": 0.08073344081640244,
"learning_rate": 0.0008,
"loss": 2.5802159309387207,
"step": 1684
},
{
"epoch": 0.08850393700787401,
"grad_norm": 0.08115082234144211,
"learning_rate": 0.0008,
"loss": 2.607386589050293,
"step": 1686
},
{
"epoch": 0.08860892388451444,
"grad_norm": 0.0805412232875824,
"learning_rate": 0.0008,
"loss": 2.598745822906494,
"step": 1688
},
{
"epoch": 0.08871391076115485,
"grad_norm": 0.08753439038991928,
"learning_rate": 0.0008,
"loss": 2.6611311435699463,
"step": 1690
},
{
"epoch": 0.08881889763779527,
"grad_norm": 0.08298667520284653,
"learning_rate": 0.0008,
"loss": 2.5831384658813477,
"step": 1692
},
{
"epoch": 0.0889238845144357,
"grad_norm": 0.08127131313085556,
"learning_rate": 0.0008,
"loss": 2.6378657817840576,
"step": 1694
},
{
"epoch": 0.08902887139107611,
"grad_norm": 0.08537666499614716,
"learning_rate": 0.0008,
"loss": 2.639033079147339,
"step": 1696
},
{
"epoch": 0.08913385826771654,
"grad_norm": 0.0840623676776886,
"learning_rate": 0.0008,
"loss": 2.565019130706787,
"step": 1698
},
{
"epoch": 0.08923884514435695,
"grad_norm": 0.08272294700145721,
"learning_rate": 0.0008,
"loss": 2.636948347091675,
"step": 1700
},
{
"epoch": 0.08934383202099737,
"grad_norm": 0.08278897404670715,
"learning_rate": 0.0008,
"loss": 2.6079483032226562,
"step": 1702
},
{
"epoch": 0.0894488188976378,
"grad_norm": 0.0801597386598587,
"learning_rate": 0.0008,
"loss": 2.5585684776306152,
"step": 1704
},
{
"epoch": 0.08955380577427821,
"grad_norm": 0.08294755220413208,
"learning_rate": 0.0008,
"loss": 2.572537899017334,
"step": 1706
},
{
"epoch": 0.08965879265091864,
"grad_norm": 0.07987018674612045,
"learning_rate": 0.0008,
"loss": 2.6297359466552734,
"step": 1708
},
{
"epoch": 0.08976377952755905,
"grad_norm": 0.07916128635406494,
"learning_rate": 0.0008,
"loss": 2.573946952819824,
"step": 1710
},
{
"epoch": 0.08986876640419947,
"grad_norm": 0.08582612127065659,
"learning_rate": 0.0008,
"loss": 2.510253429412842,
"step": 1712
},
{
"epoch": 0.0899737532808399,
"grad_norm": 0.08121506869792938,
"learning_rate": 0.0008,
"loss": 2.561246395111084,
"step": 1714
},
{
"epoch": 0.09007874015748031,
"grad_norm": 0.07797350734472275,
"learning_rate": 0.0008,
"loss": 2.6328437328338623,
"step": 1716
}
],
"logging_steps": 2,
"max_steps": 19050,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 572,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.429426018965286e+18,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}