lfm-cpt / checkpoint-2102 /trainer_state.json
Ba2han's picture
Training in progress, step 2102, checkpoint
bb2e0c3 verified
Raw
History Blame Contribute Delete
172 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4999554035974431,
"eval_steps": 500,
"global_step": 2102,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0004756949606065111,
"grad_norm": 17.125,
"learning_rate": 3.80952380952381e-07,
"loss": 3.0223777294158936,
"step": 2
},
{
"epoch": 0.0009513899212130222,
"grad_norm": 18.875,
"learning_rate": 1.142857142857143e-06,
"loss": 3.0833311080932617,
"step": 4
},
{
"epoch": 0.0014270848818195333,
"grad_norm": 17.5,
"learning_rate": 1.904761904761905e-06,
"loss": 3.0257577896118164,
"step": 6
},
{
"epoch": 0.0019027798424260443,
"grad_norm": 14.375,
"learning_rate": 2.666666666666667e-06,
"loss": 2.894188642501831,
"step": 8
},
{
"epoch": 0.002378474803032555,
"grad_norm": 11.6875,
"learning_rate": 3.428571428571429e-06,
"loss": 2.8602077960968018,
"step": 10
},
{
"epoch": 0.0028541697636390666,
"grad_norm": 9.1875,
"learning_rate": 4.190476190476191e-06,
"loss": 2.8444406986236572,
"step": 12
},
{
"epoch": 0.0033298647242455777,
"grad_norm": 5.75,
"learning_rate": 4.952380952380953e-06,
"loss": 2.7274436950683594,
"step": 14
},
{
"epoch": 0.0038055596848520887,
"grad_norm": 3.96875,
"learning_rate": 5.7142857142857145e-06,
"loss": 2.6735000610351562,
"step": 16
},
{
"epoch": 0.0042812546454586,
"grad_norm": 3.46875,
"learning_rate": 6.476190476190477e-06,
"loss": 2.7295286655426025,
"step": 18
},
{
"epoch": 0.00475694960606511,
"grad_norm": 3.390625,
"learning_rate": 7.238095238095239e-06,
"loss": 2.674283027648926,
"step": 20
},
{
"epoch": 0.005232644566671622,
"grad_norm": 2.375,
"learning_rate": 8.000000000000001e-06,
"loss": 2.604132652282715,
"step": 22
},
{
"epoch": 0.005708339527278133,
"grad_norm": 1.984375,
"learning_rate": 8.761904761904763e-06,
"loss": 2.5608315467834473,
"step": 24
},
{
"epoch": 0.006184034487884644,
"grad_norm": 1.6484375,
"learning_rate": 9.523809523809525e-06,
"loss": 2.4369235038757324,
"step": 26
},
{
"epoch": 0.006659729448491155,
"grad_norm": 1.3125,
"learning_rate": 1.0285714285714285e-05,
"loss": 2.526822090148926,
"step": 28
},
{
"epoch": 0.007135424409097666,
"grad_norm": 1.1015625,
"learning_rate": 1.104761904761905e-05,
"loss": 2.478888511657715,
"step": 30
},
{
"epoch": 0.007611119369704177,
"grad_norm": 1.015625,
"learning_rate": 1.180952380952381e-05,
"loss": 2.4330101013183594,
"step": 32
},
{
"epoch": 0.008086814330310688,
"grad_norm": 0.88671875,
"learning_rate": 1.2571428571428572e-05,
"loss": 2.412613868713379,
"step": 34
},
{
"epoch": 0.0085625092909172,
"grad_norm": 0.828125,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.4466609954833984,
"step": 36
},
{
"epoch": 0.009038204251523711,
"grad_norm": 0.9140625,
"learning_rate": 1.4095238095238097e-05,
"loss": 2.3658487796783447,
"step": 38
},
{
"epoch": 0.00951389921213022,
"grad_norm": 0.84375,
"learning_rate": 1.4857142857142858e-05,
"loss": 2.355985164642334,
"step": 40
},
{
"epoch": 0.009989594172736732,
"grad_norm": 0.796875,
"learning_rate": 1.5619047619047622e-05,
"loss": 2.2941904067993164,
"step": 42
},
{
"epoch": 0.010465289133343244,
"grad_norm": 0.80078125,
"learning_rate": 1.6380952380952384e-05,
"loss": 2.2010486125946045,
"step": 44
},
{
"epoch": 0.010940984093949755,
"grad_norm": 0.890625,
"learning_rate": 1.7142857142857142e-05,
"loss": 2.2753114700317383,
"step": 46
},
{
"epoch": 0.011416679054556267,
"grad_norm": 0.79296875,
"learning_rate": 1.7904761904761907e-05,
"loss": 2.248267650604248,
"step": 48
},
{
"epoch": 0.011892374015162776,
"grad_norm": 0.76953125,
"learning_rate": 1.866666666666667e-05,
"loss": 2.219675064086914,
"step": 50
},
{
"epoch": 0.012368068975769288,
"grad_norm": 0.77734375,
"learning_rate": 1.942857142857143e-05,
"loss": 2.195375919342041,
"step": 52
},
{
"epoch": 0.0128437639363758,
"grad_norm": 0.8203125,
"learning_rate": 2.0190476190476192e-05,
"loss": 2.113194227218628,
"step": 54
},
{
"epoch": 0.01331945889698231,
"grad_norm": 0.89453125,
"learning_rate": 2.0952380952380954e-05,
"loss": 2.1435773372650146,
"step": 56
},
{
"epoch": 0.01379515385758882,
"grad_norm": 0.9609375,
"learning_rate": 2.1714285714285715e-05,
"loss": 2.1617753505706787,
"step": 58
},
{
"epoch": 0.014270848818195332,
"grad_norm": 0.9140625,
"learning_rate": 2.2476190476190477e-05,
"loss": 2.0906386375427246,
"step": 60
},
{
"epoch": 0.014746543778801843,
"grad_norm": 0.890625,
"learning_rate": 2.3238095238095242e-05,
"loss": 2.13519024848938,
"step": 62
},
{
"epoch": 0.015222238739408355,
"grad_norm": 0.74609375,
"learning_rate": 2.4e-05,
"loss": 2.0451605319976807,
"step": 64
},
{
"epoch": 0.015697933700014866,
"grad_norm": 0.703125,
"learning_rate": 2.4761904761904766e-05,
"loss": 2.18241548538208,
"step": 66
},
{
"epoch": 0.016173628660621376,
"grad_norm": 0.734375,
"learning_rate": 2.5523809523809524e-05,
"loss": 2.0362777709960938,
"step": 68
},
{
"epoch": 0.01664932362122789,
"grad_norm": 0.68359375,
"learning_rate": 2.628571428571429e-05,
"loss": 2.0474891662597656,
"step": 70
},
{
"epoch": 0.0171250185818344,
"grad_norm": 0.81640625,
"learning_rate": 2.704761904761905e-05,
"loss": 2.0943374633789062,
"step": 72
},
{
"epoch": 0.01760071354244091,
"grad_norm": 0.703125,
"learning_rate": 2.780952380952381e-05,
"loss": 2.007606029510498,
"step": 74
},
{
"epoch": 0.018076408503047422,
"grad_norm": 0.79296875,
"learning_rate": 2.8571428571428574e-05,
"loss": 2.010784149169922,
"step": 76
},
{
"epoch": 0.01855210346365393,
"grad_norm": 0.859375,
"learning_rate": 2.9333333333333333e-05,
"loss": 2.0787105560302734,
"step": 78
},
{
"epoch": 0.01902779842426044,
"grad_norm": 0.78515625,
"learning_rate": 3.0095238095238098e-05,
"loss": 2.0407357215881348,
"step": 80
},
{
"epoch": 0.019503493384866954,
"grad_norm": 0.75390625,
"learning_rate": 3.085714285714286e-05,
"loss": 1.9725031852722168,
"step": 82
},
{
"epoch": 0.019979188345473464,
"grad_norm": 0.8671875,
"learning_rate": 3.161904761904762e-05,
"loss": 1.9424755573272705,
"step": 84
},
{
"epoch": 0.020454883306079977,
"grad_norm": 0.9921875,
"learning_rate": 3.2380952380952386e-05,
"loss": 2.0050058364868164,
"step": 86
},
{
"epoch": 0.020930578266686487,
"grad_norm": 0.7421875,
"learning_rate": 3.314285714285715e-05,
"loss": 1.9476414918899536,
"step": 88
},
{
"epoch": 0.021406273227292997,
"grad_norm": 0.94140625,
"learning_rate": 3.390476190476191e-05,
"loss": 1.9908151626586914,
"step": 90
},
{
"epoch": 0.02188196818789951,
"grad_norm": 0.81640625,
"learning_rate": 3.466666666666667e-05,
"loss": 1.9584457874298096,
"step": 92
},
{
"epoch": 0.02235766314850602,
"grad_norm": 0.9609375,
"learning_rate": 3.542857142857143e-05,
"loss": 1.9743244647979736,
"step": 94
},
{
"epoch": 0.022833358109112533,
"grad_norm": 1.1015625,
"learning_rate": 3.6190476190476195e-05,
"loss": 1.9396190643310547,
"step": 96
},
{
"epoch": 0.023309053069719043,
"grad_norm": 0.93359375,
"learning_rate": 3.6952380952380956e-05,
"loss": 1.8824760913848877,
"step": 98
},
{
"epoch": 0.023784748030325552,
"grad_norm": 0.859375,
"learning_rate": 3.771428571428572e-05,
"loss": 1.8970260620117188,
"step": 100
},
{
"epoch": 0.024260442990932066,
"grad_norm": 0.7890625,
"learning_rate": 3.847619047619048e-05,
"loss": 1.9105536937713623,
"step": 102
},
{
"epoch": 0.024736137951538575,
"grad_norm": 0.84765625,
"learning_rate": 3.923809523809524e-05,
"loss": 1.8593096733093262,
"step": 104
},
{
"epoch": 0.02521183291214509,
"grad_norm": 0.76953125,
"learning_rate": 4e-05,
"loss": 1.8682916164398193,
"step": 106
},
{
"epoch": 0.0256875278727516,
"grad_norm": 0.83984375,
"learning_rate": 4.0761904761904765e-05,
"loss": 1.9372856616973877,
"step": 108
},
{
"epoch": 0.026163222833358108,
"grad_norm": 1.2890625,
"learning_rate": 4.1523809523809533e-05,
"loss": 1.9114850759506226,
"step": 110
},
{
"epoch": 0.02663891779396462,
"grad_norm": 1.0625,
"learning_rate": 4.228571428571429e-05,
"loss": 1.8821630477905273,
"step": 112
},
{
"epoch": 0.02711461275457113,
"grad_norm": 1.015625,
"learning_rate": 4.304761904761905e-05,
"loss": 1.8732749223709106,
"step": 114
},
{
"epoch": 0.02759030771517764,
"grad_norm": 0.7890625,
"learning_rate": 4.380952380952382e-05,
"loss": 1.8635611534118652,
"step": 116
},
{
"epoch": 0.028066002675784154,
"grad_norm": 0.90625,
"learning_rate": 4.4571428571428574e-05,
"loss": 1.8261184692382812,
"step": 118
},
{
"epoch": 0.028541697636390664,
"grad_norm": 0.9140625,
"learning_rate": 4.5333333333333335e-05,
"loss": 1.8533995151519775,
"step": 120
},
{
"epoch": 0.029017392596997177,
"grad_norm": 1.03125,
"learning_rate": 4.60952380952381e-05,
"loss": 1.816650390625,
"step": 122
},
{
"epoch": 0.029493087557603687,
"grad_norm": 0.87890625,
"learning_rate": 4.6857142857142865e-05,
"loss": 1.823215365409851,
"step": 124
},
{
"epoch": 0.029968782518210196,
"grad_norm": 0.83984375,
"learning_rate": 4.761904761904762e-05,
"loss": 1.8113462924957275,
"step": 126
},
{
"epoch": 0.03044447747881671,
"grad_norm": 0.8046875,
"learning_rate": 4.838095238095238e-05,
"loss": 1.7880184650421143,
"step": 128
},
{
"epoch": 0.03092017243942322,
"grad_norm": 0.97265625,
"learning_rate": 4.914285714285715e-05,
"loss": 1.8012118339538574,
"step": 130
},
{
"epoch": 0.03139586740002973,
"grad_norm": 1.046875,
"learning_rate": 4.990476190476191e-05,
"loss": 1.783468246459961,
"step": 132
},
{
"epoch": 0.03187156236063624,
"grad_norm": 1.015625,
"learning_rate": 5.066666666666667e-05,
"loss": 1.7474174499511719,
"step": 134
},
{
"epoch": 0.03234725732124275,
"grad_norm": 0.95703125,
"learning_rate": 5.1428571428571436e-05,
"loss": 1.8491697311401367,
"step": 136
},
{
"epoch": 0.03282295228184926,
"grad_norm": 0.984375,
"learning_rate": 5.21904761904762e-05,
"loss": 1.77945077419281,
"step": 138
},
{
"epoch": 0.03329864724245578,
"grad_norm": 1.046875,
"learning_rate": 5.295238095238095e-05,
"loss": 1.7462689876556396,
"step": 140
},
{
"epoch": 0.03377434220306229,
"grad_norm": 1.25,
"learning_rate": 5.3714285714285714e-05,
"loss": 1.77305006980896,
"step": 142
},
{
"epoch": 0.0342500371636688,
"grad_norm": 0.91015625,
"learning_rate": 5.447619047619048e-05,
"loss": 1.7020612955093384,
"step": 144
},
{
"epoch": 0.03472573212427531,
"grad_norm": 0.921875,
"learning_rate": 5.5238095238095244e-05,
"loss": 1.8065619468688965,
"step": 146
},
{
"epoch": 0.03520142708488182,
"grad_norm": 0.8828125,
"learning_rate": 5.6e-05,
"loss": 1.6848450899124146,
"step": 148
},
{
"epoch": 0.035677122045488334,
"grad_norm": 0.80859375,
"learning_rate": 5.676190476190477e-05,
"loss": 1.747304916381836,
"step": 150
},
{
"epoch": 0.036152817006094844,
"grad_norm": 1.1015625,
"learning_rate": 5.752380952380953e-05,
"loss": 1.7690556049346924,
"step": 152
},
{
"epoch": 0.03662851196670135,
"grad_norm": 1.03125,
"learning_rate": 5.828571428571429e-05,
"loss": 1.7610713243484497,
"step": 154
},
{
"epoch": 0.03710420692730786,
"grad_norm": 1.1640625,
"learning_rate": 5.904761904761905e-05,
"loss": 1.6751768589019775,
"step": 156
},
{
"epoch": 0.03757990188791437,
"grad_norm": 0.9375,
"learning_rate": 5.9809523809523814e-05,
"loss": 1.6568293571472168,
"step": 158
},
{
"epoch": 0.03805559684852088,
"grad_norm": 0.84765625,
"learning_rate": 6.0571428571428576e-05,
"loss": 1.7163995504379272,
"step": 160
},
{
"epoch": 0.0385312918091274,
"grad_norm": 1.1875,
"learning_rate": 6.133333333333334e-05,
"loss": 1.7115540504455566,
"step": 162
},
{
"epoch": 0.03900698676973391,
"grad_norm": 0.9453125,
"learning_rate": 6.20952380952381e-05,
"loss": 1.6549824476242065,
"step": 164
},
{
"epoch": 0.03948268173034042,
"grad_norm": 0.828125,
"learning_rate": 6.285714285714286e-05,
"loss": 1.6670048236846924,
"step": 166
},
{
"epoch": 0.03995837669094693,
"grad_norm": 0.89453125,
"learning_rate": 6.361904761904762e-05,
"loss": 1.6787292957305908,
"step": 168
},
{
"epoch": 0.04043407165155344,
"grad_norm": 0.87890625,
"learning_rate": 6.438095238095238e-05,
"loss": 1.6751407384872437,
"step": 170
},
{
"epoch": 0.040909766612159955,
"grad_norm": 0.78125,
"learning_rate": 6.514285714285715e-05,
"loss": 1.679162621498108,
"step": 172
},
{
"epoch": 0.041385461572766465,
"grad_norm": 0.75,
"learning_rate": 6.590476190476191e-05,
"loss": 1.6422595977783203,
"step": 174
},
{
"epoch": 0.041861156533372974,
"grad_norm": 0.97265625,
"learning_rate": 6.666666666666667e-05,
"loss": 1.693905234336853,
"step": 176
},
{
"epoch": 0.042336851493979484,
"grad_norm": 0.99609375,
"learning_rate": 6.742857142857143e-05,
"loss": 1.7319214344024658,
"step": 178
},
{
"epoch": 0.042812546454585994,
"grad_norm": 1.1171875,
"learning_rate": 6.81904761904762e-05,
"loss": 1.7077994346618652,
"step": 180
},
{
"epoch": 0.04328824141519251,
"grad_norm": 0.87890625,
"learning_rate": 6.895238095238095e-05,
"loss": 1.6633131504058838,
"step": 182
},
{
"epoch": 0.04376393637579902,
"grad_norm": 1.3515625,
"learning_rate": 6.971428571428572e-05,
"loss": 1.6569929122924805,
"step": 184
},
{
"epoch": 0.04423963133640553,
"grad_norm": 1.078125,
"learning_rate": 7.047619047619048e-05,
"loss": 1.6756895780563354,
"step": 186
},
{
"epoch": 0.04471532629701204,
"grad_norm": 1.296875,
"learning_rate": 7.123809523809524e-05,
"loss": 1.7126249074935913,
"step": 188
},
{
"epoch": 0.04519102125761855,
"grad_norm": 0.9609375,
"learning_rate": 7.2e-05,
"loss": 1.6484733819961548,
"step": 190
},
{
"epoch": 0.045666716218225066,
"grad_norm": 1.1015625,
"learning_rate": 7.276190476190476e-05,
"loss": 1.71817147731781,
"step": 192
},
{
"epoch": 0.046142411178831576,
"grad_norm": 0.96484375,
"learning_rate": 7.352380952380953e-05,
"loss": 1.7061476707458496,
"step": 194
},
{
"epoch": 0.046618106139438086,
"grad_norm": 0.9375,
"learning_rate": 7.42857142857143e-05,
"loss": 1.654850959777832,
"step": 196
},
{
"epoch": 0.047093801100044595,
"grad_norm": 0.8984375,
"learning_rate": 7.504761904761905e-05,
"loss": 1.6332194805145264,
"step": 198
},
{
"epoch": 0.047569496060651105,
"grad_norm": 0.890625,
"learning_rate": 7.580952380952381e-05,
"loss": 1.6425645351409912,
"step": 200
},
{
"epoch": 0.04804519102125762,
"grad_norm": 0.80078125,
"learning_rate": 7.657142857142859e-05,
"loss": 1.6112370491027832,
"step": 202
},
{
"epoch": 0.04852088598186413,
"grad_norm": 0.875,
"learning_rate": 7.733333333333333e-05,
"loss": 1.6736791133880615,
"step": 204
},
{
"epoch": 0.04899658094247064,
"grad_norm": 0.90234375,
"learning_rate": 7.80952380952381e-05,
"loss": 1.5582149028778076,
"step": 206
},
{
"epoch": 0.04947227590307715,
"grad_norm": 0.859375,
"learning_rate": 7.885714285714287e-05,
"loss": 1.605231523513794,
"step": 208
},
{
"epoch": 0.04994797086368366,
"grad_norm": 0.95703125,
"learning_rate": 7.961904761904763e-05,
"loss": 1.6272740364074707,
"step": 210
},
{
"epoch": 0.05042366582429018,
"grad_norm": 1.0234375,
"learning_rate": 8e-05,
"loss": 1.6227126121520996,
"step": 212
},
{
"epoch": 0.05089936078489669,
"grad_norm": 0.99609375,
"learning_rate": 8e-05,
"loss": 1.7201282978057861,
"step": 214
},
{
"epoch": 0.0513750557455032,
"grad_norm": 0.8203125,
"learning_rate": 8e-05,
"loss": 1.671586036682129,
"step": 216
},
{
"epoch": 0.051850750706109706,
"grad_norm": 0.82421875,
"learning_rate": 8e-05,
"loss": 1.596938133239746,
"step": 218
},
{
"epoch": 0.052326445666716216,
"grad_norm": 0.71875,
"learning_rate": 8e-05,
"loss": 1.5416910648345947,
"step": 220
},
{
"epoch": 0.052802140627322726,
"grad_norm": 0.93359375,
"learning_rate": 8e-05,
"loss": 1.6337580680847168,
"step": 222
},
{
"epoch": 0.05327783558792924,
"grad_norm": 0.89453125,
"learning_rate": 8e-05,
"loss": 1.694180965423584,
"step": 224
},
{
"epoch": 0.05375353054853575,
"grad_norm": 1.1015625,
"learning_rate": 8e-05,
"loss": 1.5831806659698486,
"step": 226
},
{
"epoch": 0.05422922550914226,
"grad_norm": 1.328125,
"learning_rate": 8e-05,
"loss": 1.6646983623504639,
"step": 228
},
{
"epoch": 0.05470492046974877,
"grad_norm": 1.53125,
"learning_rate": 8e-05,
"loss": 1.632063627243042,
"step": 230
},
{
"epoch": 0.05518061543035528,
"grad_norm": 1.3515625,
"learning_rate": 8e-05,
"loss": 1.6186381578445435,
"step": 232
},
{
"epoch": 0.0556563103909618,
"grad_norm": 0.9296875,
"learning_rate": 8e-05,
"loss": 1.5822536945343018,
"step": 234
},
{
"epoch": 0.05613200535156831,
"grad_norm": 0.9765625,
"learning_rate": 8e-05,
"loss": 1.598821759223938,
"step": 236
},
{
"epoch": 0.05660770031217482,
"grad_norm": 0.8203125,
"learning_rate": 8e-05,
"loss": 1.6583571434020996,
"step": 238
},
{
"epoch": 0.05708339527278133,
"grad_norm": 0.94921875,
"learning_rate": 8e-05,
"loss": 1.6493302583694458,
"step": 240
},
{
"epoch": 0.05755909023338784,
"grad_norm": 0.9296875,
"learning_rate": 8e-05,
"loss": 1.5849549770355225,
"step": 242
},
{
"epoch": 0.058034785193994354,
"grad_norm": 0.71875,
"learning_rate": 8e-05,
"loss": 1.5187630653381348,
"step": 244
},
{
"epoch": 0.058510480154600863,
"grad_norm": 0.8046875,
"learning_rate": 8e-05,
"loss": 1.6261816024780273,
"step": 246
},
{
"epoch": 0.05898617511520737,
"grad_norm": 0.94140625,
"learning_rate": 8e-05,
"loss": 1.5440542697906494,
"step": 248
},
{
"epoch": 0.05946187007581388,
"grad_norm": 0.80859375,
"learning_rate": 8e-05,
"loss": 1.5579140186309814,
"step": 250
},
{
"epoch": 0.05993756503642039,
"grad_norm": 0.671875,
"learning_rate": 8e-05,
"loss": 1.5661745071411133,
"step": 252
},
{
"epoch": 0.06041325999702691,
"grad_norm": 0.76171875,
"learning_rate": 8e-05,
"loss": 1.5916748046875,
"step": 254
},
{
"epoch": 0.06088895495763342,
"grad_norm": 0.765625,
"learning_rate": 8e-05,
"loss": 1.582345724105835,
"step": 256
},
{
"epoch": 0.06136464991823993,
"grad_norm": 0.78125,
"learning_rate": 8e-05,
"loss": 1.6371424198150635,
"step": 258
},
{
"epoch": 0.06184034487884644,
"grad_norm": 0.7265625,
"learning_rate": 8e-05,
"loss": 1.5874426364898682,
"step": 260
},
{
"epoch": 0.06231603983945295,
"grad_norm": 0.6796875,
"learning_rate": 8e-05,
"loss": 1.5973892211914062,
"step": 262
},
{
"epoch": 0.06279173480005946,
"grad_norm": 0.859375,
"learning_rate": 8e-05,
"loss": 1.6360384225845337,
"step": 264
},
{
"epoch": 0.06326742976066597,
"grad_norm": 0.703125,
"learning_rate": 8e-05,
"loss": 1.4682174921035767,
"step": 266
},
{
"epoch": 0.06374312472127248,
"grad_norm": 0.69140625,
"learning_rate": 8e-05,
"loss": 1.5434261560440063,
"step": 268
},
{
"epoch": 0.064218819681879,
"grad_norm": 0.671875,
"learning_rate": 8e-05,
"loss": 1.5429248809814453,
"step": 270
},
{
"epoch": 0.0646945146424855,
"grad_norm": 0.6328125,
"learning_rate": 8e-05,
"loss": 1.520768404006958,
"step": 272
},
{
"epoch": 0.06517020960309201,
"grad_norm": 0.63671875,
"learning_rate": 8e-05,
"loss": 1.6287932395935059,
"step": 274
},
{
"epoch": 0.06564590456369852,
"grad_norm": 0.75,
"learning_rate": 8e-05,
"loss": 1.574143409729004,
"step": 276
},
{
"epoch": 0.06612159952430503,
"grad_norm": 0.64453125,
"learning_rate": 8e-05,
"loss": 1.5749611854553223,
"step": 278
},
{
"epoch": 0.06659729448491156,
"grad_norm": 0.66796875,
"learning_rate": 8e-05,
"loss": 1.511296033859253,
"step": 280
},
{
"epoch": 0.06707298944551807,
"grad_norm": 0.6171875,
"learning_rate": 8e-05,
"loss": 1.5300962924957275,
"step": 282
},
{
"epoch": 0.06754868440612458,
"grad_norm": 0.59375,
"learning_rate": 8e-05,
"loss": 1.5132012367248535,
"step": 284
},
{
"epoch": 0.06802437936673109,
"grad_norm": 0.59375,
"learning_rate": 8e-05,
"loss": 1.5248513221740723,
"step": 286
},
{
"epoch": 0.0685000743273376,
"grad_norm": 0.64453125,
"learning_rate": 8e-05,
"loss": 1.4714152812957764,
"step": 288
},
{
"epoch": 0.0689757692879441,
"grad_norm": 0.5859375,
"learning_rate": 8e-05,
"loss": 1.536270022392273,
"step": 290
},
{
"epoch": 0.06945146424855062,
"grad_norm": 0.66796875,
"learning_rate": 8e-05,
"loss": 1.5859988927841187,
"step": 292
},
{
"epoch": 0.06992715920915712,
"grad_norm": 0.640625,
"learning_rate": 8e-05,
"loss": 1.6076054573059082,
"step": 294
},
{
"epoch": 0.07040285416976363,
"grad_norm": 0.65234375,
"learning_rate": 8e-05,
"loss": 1.537914752960205,
"step": 296
},
{
"epoch": 0.07087854913037014,
"grad_norm": 0.68359375,
"learning_rate": 8e-05,
"loss": 1.530918002128601,
"step": 298
},
{
"epoch": 0.07135424409097667,
"grad_norm": 0.63671875,
"learning_rate": 8e-05,
"loss": 1.5722606182098389,
"step": 300
},
{
"epoch": 0.07182993905158318,
"grad_norm": 0.6328125,
"learning_rate": 8e-05,
"loss": 1.5380263328552246,
"step": 302
},
{
"epoch": 0.07230563401218969,
"grad_norm": 0.62109375,
"learning_rate": 8e-05,
"loss": 1.543945074081421,
"step": 304
},
{
"epoch": 0.0727813289727962,
"grad_norm": 0.671875,
"learning_rate": 8e-05,
"loss": 1.4990713596343994,
"step": 306
},
{
"epoch": 0.0732570239334027,
"grad_norm": 0.5703125,
"learning_rate": 8e-05,
"loss": 1.5049118995666504,
"step": 308
},
{
"epoch": 0.07373271889400922,
"grad_norm": 0.546875,
"learning_rate": 8e-05,
"loss": 1.5481094121932983,
"step": 310
},
{
"epoch": 0.07420841385461573,
"grad_norm": 0.6015625,
"learning_rate": 8e-05,
"loss": 1.5431925058364868,
"step": 312
},
{
"epoch": 0.07468410881522224,
"grad_norm": 0.59375,
"learning_rate": 8e-05,
"loss": 1.5000509023666382,
"step": 314
},
{
"epoch": 0.07515980377582875,
"grad_norm": 0.640625,
"learning_rate": 8e-05,
"loss": 1.453176498413086,
"step": 316
},
{
"epoch": 0.07563549873643526,
"grad_norm": 0.59375,
"learning_rate": 8e-05,
"loss": 1.5792964696884155,
"step": 318
},
{
"epoch": 0.07611119369704177,
"grad_norm": 0.6171875,
"learning_rate": 8e-05,
"loss": 1.5420498847961426,
"step": 320
},
{
"epoch": 0.07658688865764829,
"grad_norm": 0.578125,
"learning_rate": 8e-05,
"loss": 1.5112196207046509,
"step": 322
},
{
"epoch": 0.0770625836182548,
"grad_norm": 0.5859375,
"learning_rate": 8e-05,
"loss": 1.5195896625518799,
"step": 324
},
{
"epoch": 0.07753827857886131,
"grad_norm": 0.578125,
"learning_rate": 8e-05,
"loss": 1.4650981426239014,
"step": 326
},
{
"epoch": 0.07801397353946782,
"grad_norm": 0.6015625,
"learning_rate": 8e-05,
"loss": 1.4874310493469238,
"step": 328
},
{
"epoch": 0.07848966850007433,
"grad_norm": 0.5546875,
"learning_rate": 8e-05,
"loss": 1.4700895547866821,
"step": 330
},
{
"epoch": 0.07896536346068084,
"grad_norm": 0.59765625,
"learning_rate": 8e-05,
"loss": 1.4657363891601562,
"step": 332
},
{
"epoch": 0.07944105842128735,
"grad_norm": 0.63671875,
"learning_rate": 8e-05,
"loss": 1.5102603435516357,
"step": 334
},
{
"epoch": 0.07991675338189386,
"grad_norm": 0.63671875,
"learning_rate": 8e-05,
"loss": 1.48199462890625,
"step": 336
},
{
"epoch": 0.08039244834250037,
"grad_norm": 0.58984375,
"learning_rate": 8e-05,
"loss": 1.573965072631836,
"step": 338
},
{
"epoch": 0.08086814330310688,
"grad_norm": 0.5859375,
"learning_rate": 8e-05,
"loss": 1.552716851234436,
"step": 340
},
{
"epoch": 0.0813438382637134,
"grad_norm": 0.59765625,
"learning_rate": 8e-05,
"loss": 1.5109150409698486,
"step": 342
},
{
"epoch": 0.08181953322431991,
"grad_norm": 0.62890625,
"learning_rate": 8e-05,
"loss": 1.478667974472046,
"step": 344
},
{
"epoch": 0.08229522818492642,
"grad_norm": 0.55859375,
"learning_rate": 8e-05,
"loss": 1.4951369762420654,
"step": 346
},
{
"epoch": 0.08277092314553293,
"grad_norm": 0.5234375,
"learning_rate": 8e-05,
"loss": 1.4743764400482178,
"step": 348
},
{
"epoch": 0.08324661810613944,
"grad_norm": 0.59375,
"learning_rate": 8e-05,
"loss": 1.5435149669647217,
"step": 350
},
{
"epoch": 0.08372231306674595,
"grad_norm": 0.5546875,
"learning_rate": 8e-05,
"loss": 1.4307265281677246,
"step": 352
},
{
"epoch": 0.08419800802735246,
"grad_norm": 0.60546875,
"learning_rate": 8e-05,
"loss": 1.5382444858551025,
"step": 354
},
{
"epoch": 0.08467370298795897,
"grad_norm": 0.56640625,
"learning_rate": 8e-05,
"loss": 1.4578557014465332,
"step": 356
},
{
"epoch": 0.08514939794856548,
"grad_norm": 0.5625,
"learning_rate": 8e-05,
"loss": 1.5319006443023682,
"step": 358
},
{
"epoch": 0.08562509290917199,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.511313796043396,
"step": 360
},
{
"epoch": 0.08610078786977851,
"grad_norm": 0.55078125,
"learning_rate": 8e-05,
"loss": 1.4577925205230713,
"step": 362
},
{
"epoch": 0.08657648283038502,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.5221188068389893,
"step": 364
},
{
"epoch": 0.08705217779099153,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.4162304401397705,
"step": 366
},
{
"epoch": 0.08752787275159804,
"grad_norm": 0.53515625,
"learning_rate": 8e-05,
"loss": 1.4972211122512817,
"step": 368
},
{
"epoch": 0.08800356771220455,
"grad_norm": 0.53515625,
"learning_rate": 8e-05,
"loss": 1.5569958686828613,
"step": 370
},
{
"epoch": 0.08847926267281106,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.467348337173462,
"step": 372
},
{
"epoch": 0.08895495763341757,
"grad_norm": 0.53515625,
"learning_rate": 8e-05,
"loss": 1.4739539623260498,
"step": 374
},
{
"epoch": 0.08943065259402408,
"grad_norm": 0.546875,
"learning_rate": 8e-05,
"loss": 1.478308916091919,
"step": 376
},
{
"epoch": 0.08990634755463059,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.4767718315124512,
"step": 378
},
{
"epoch": 0.0903820425152371,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.51509690284729,
"step": 380
},
{
"epoch": 0.09085773747584361,
"grad_norm": 0.5234375,
"learning_rate": 8e-05,
"loss": 1.4501855373382568,
"step": 382
},
{
"epoch": 0.09133343243645013,
"grad_norm": 0.5390625,
"learning_rate": 8e-05,
"loss": 1.45088529586792,
"step": 384
},
{
"epoch": 0.09180912739705664,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.4980132579803467,
"step": 386
},
{
"epoch": 0.09228482235766315,
"grad_norm": 0.51953125,
"learning_rate": 8e-05,
"loss": 1.5103974342346191,
"step": 388
},
{
"epoch": 0.09276051731826966,
"grad_norm": 0.58203125,
"learning_rate": 8e-05,
"loss": 1.4751368761062622,
"step": 390
},
{
"epoch": 0.09323621227887617,
"grad_norm": 0.62109375,
"learning_rate": 8e-05,
"loss": 1.494489073753357,
"step": 392
},
{
"epoch": 0.09371190723948268,
"grad_norm": 0.61328125,
"learning_rate": 8e-05,
"loss": 1.497837781906128,
"step": 394
},
{
"epoch": 0.09418760220008919,
"grad_norm": 0.55859375,
"learning_rate": 8e-05,
"loss": 1.5514724254608154,
"step": 396
},
{
"epoch": 0.0946632971606957,
"grad_norm": 0.86328125,
"learning_rate": 8e-05,
"loss": 1.5110323429107666,
"step": 398
},
{
"epoch": 0.09513899212130221,
"grad_norm": 0.63671875,
"learning_rate": 8e-05,
"loss": 1.4153172969818115,
"step": 400
},
{
"epoch": 0.09561468708190872,
"grad_norm": 0.51953125,
"learning_rate": 8e-05,
"loss": 1.4518225193023682,
"step": 402
},
{
"epoch": 0.09609038204251524,
"grad_norm": 0.578125,
"learning_rate": 8e-05,
"loss": 1.4477956295013428,
"step": 404
},
{
"epoch": 0.09656607700312175,
"grad_norm": 0.62109375,
"learning_rate": 8e-05,
"loss": 1.4921960830688477,
"step": 406
},
{
"epoch": 0.09704177196372826,
"grad_norm": 0.6328125,
"learning_rate": 8e-05,
"loss": 1.4914698600769043,
"step": 408
},
{
"epoch": 0.09751746692433477,
"grad_norm": 0.59375,
"learning_rate": 8e-05,
"loss": 1.4477533102035522,
"step": 410
},
{
"epoch": 0.09799316188494128,
"grad_norm": 0.546875,
"learning_rate": 8e-05,
"loss": 1.499894142150879,
"step": 412
},
{
"epoch": 0.09846885684554779,
"grad_norm": 0.5859375,
"learning_rate": 8e-05,
"loss": 1.5634784698486328,
"step": 414
},
{
"epoch": 0.0989445518061543,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.4383997917175293,
"step": 416
},
{
"epoch": 0.09942024676676081,
"grad_norm": 0.55859375,
"learning_rate": 8e-05,
"loss": 1.4373674392700195,
"step": 418
},
{
"epoch": 0.09989594172736732,
"grad_norm": 0.5703125,
"learning_rate": 8e-05,
"loss": 1.475003719329834,
"step": 420
},
{
"epoch": 0.10037163668797383,
"grad_norm": 0.5859375,
"learning_rate": 8e-05,
"loss": 1.4678364992141724,
"step": 422
},
{
"epoch": 0.10084733164858035,
"grad_norm": 0.5390625,
"learning_rate": 8e-05,
"loss": 1.45807945728302,
"step": 424
},
{
"epoch": 0.10132302660918686,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.5057690143585205,
"step": 426
},
{
"epoch": 0.10179872156979337,
"grad_norm": 0.50390625,
"learning_rate": 8e-05,
"loss": 1.4296057224273682,
"step": 428
},
{
"epoch": 0.10227441653039988,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.5102698802947998,
"step": 430
},
{
"epoch": 0.1027501114910064,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.37981116771698,
"step": 432
},
{
"epoch": 0.1032258064516129,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.4619908332824707,
"step": 434
},
{
"epoch": 0.10370150141221941,
"grad_norm": 0.55859375,
"learning_rate": 8e-05,
"loss": 1.4256863594055176,
"step": 436
},
{
"epoch": 0.10417719637282592,
"grad_norm": 0.6171875,
"learning_rate": 8e-05,
"loss": 1.4363038539886475,
"step": 438
},
{
"epoch": 0.10465289133343243,
"grad_norm": 0.58203125,
"learning_rate": 8e-05,
"loss": 1.3884978294372559,
"step": 440
},
{
"epoch": 0.10512858629403894,
"grad_norm": 0.62109375,
"learning_rate": 8e-05,
"loss": 1.4545469284057617,
"step": 442
},
{
"epoch": 0.10560428125464545,
"grad_norm": 0.5703125,
"learning_rate": 8e-05,
"loss": 1.4439201354980469,
"step": 444
},
{
"epoch": 0.10607997621525198,
"grad_norm": 0.58984375,
"learning_rate": 8e-05,
"loss": 1.5349268913269043,
"step": 446
},
{
"epoch": 0.10655567117585849,
"grad_norm": 0.609375,
"learning_rate": 8e-05,
"loss": 1.591422438621521,
"step": 448
},
{
"epoch": 0.107031366136465,
"grad_norm": 0.6640625,
"learning_rate": 8e-05,
"loss": 1.4320346117019653,
"step": 450
},
{
"epoch": 0.1075070610970715,
"grad_norm": 0.62109375,
"learning_rate": 8e-05,
"loss": 1.4518539905548096,
"step": 452
},
{
"epoch": 0.10798275605767801,
"grad_norm": 0.5859375,
"learning_rate": 8e-05,
"loss": 1.5056893825531006,
"step": 454
},
{
"epoch": 0.10845845101828452,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.3535287380218506,
"step": 456
},
{
"epoch": 0.10893414597889103,
"grad_norm": 0.57421875,
"learning_rate": 8e-05,
"loss": 1.4125394821166992,
"step": 458
},
{
"epoch": 0.10940984093949754,
"grad_norm": 0.51171875,
"learning_rate": 8e-05,
"loss": 1.3990814685821533,
"step": 460
},
{
"epoch": 0.10988553590010405,
"grad_norm": 0.5546875,
"learning_rate": 8e-05,
"loss": 1.4865885972976685,
"step": 462
},
{
"epoch": 0.11036123086071056,
"grad_norm": 0.5234375,
"learning_rate": 8e-05,
"loss": 1.415689468383789,
"step": 464
},
{
"epoch": 0.11083692582131709,
"grad_norm": 0.53515625,
"learning_rate": 8e-05,
"loss": 1.453460931777954,
"step": 466
},
{
"epoch": 0.1113126207819236,
"grad_norm": 0.56640625,
"learning_rate": 8e-05,
"loss": 1.4493913650512695,
"step": 468
},
{
"epoch": 0.1117883157425301,
"grad_norm": 0.578125,
"learning_rate": 8e-05,
"loss": 1.4510160684585571,
"step": 470
},
{
"epoch": 0.11226401070313662,
"grad_norm": 0.5859375,
"learning_rate": 8e-05,
"loss": 1.5191359519958496,
"step": 472
},
{
"epoch": 0.11273970566374313,
"grad_norm": 0.59375,
"learning_rate": 8e-05,
"loss": 1.5257389545440674,
"step": 474
},
{
"epoch": 0.11321540062434964,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.4620857238769531,
"step": 476
},
{
"epoch": 0.11369109558495614,
"grad_norm": 0.5390625,
"learning_rate": 8e-05,
"loss": 1.4049038887023926,
"step": 478
},
{
"epoch": 0.11416679054556265,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.387476921081543,
"step": 480
},
{
"epoch": 0.11464248550616916,
"grad_norm": 0.53125,
"learning_rate": 8e-05,
"loss": 1.4375786781311035,
"step": 482
},
{
"epoch": 0.11511818046677567,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.4502665996551514,
"step": 484
},
{
"epoch": 0.1155938754273822,
"grad_norm": 0.51171875,
"learning_rate": 8e-05,
"loss": 1.4172968864440918,
"step": 486
},
{
"epoch": 0.11606957038798871,
"grad_norm": 0.51171875,
"learning_rate": 8e-05,
"loss": 1.3814518451690674,
"step": 488
},
{
"epoch": 0.11654526534859522,
"grad_norm": 0.546875,
"learning_rate": 8e-05,
"loss": 1.4727611541748047,
"step": 490
},
{
"epoch": 0.11702096030920173,
"grad_norm": 0.55859375,
"learning_rate": 8e-05,
"loss": 1.4043948650360107,
"step": 492
},
{
"epoch": 0.11749665526980824,
"grad_norm": 0.53125,
"learning_rate": 8e-05,
"loss": 1.4327163696289062,
"step": 494
},
{
"epoch": 0.11797235023041475,
"grad_norm": 0.578125,
"learning_rate": 8e-05,
"loss": 1.4427610635757446,
"step": 496
},
{
"epoch": 0.11844804519102126,
"grad_norm": 0.5234375,
"learning_rate": 8e-05,
"loss": 1.4240474700927734,
"step": 498
},
{
"epoch": 0.11892374015162777,
"grad_norm": 0.578125,
"learning_rate": 8e-05,
"loss": 1.471658706665039,
"step": 500
},
{
"epoch": 0.11939943511223428,
"grad_norm": 0.63671875,
"learning_rate": 8e-05,
"loss": 1.4233098030090332,
"step": 502
},
{
"epoch": 0.11987513007284079,
"grad_norm": 0.5859375,
"learning_rate": 8e-05,
"loss": 1.3341891765594482,
"step": 504
},
{
"epoch": 0.1203508250334473,
"grad_norm": 0.5390625,
"learning_rate": 8e-05,
"loss": 1.3719563484191895,
"step": 506
},
{
"epoch": 0.12082651999405382,
"grad_norm": 0.6171875,
"learning_rate": 8e-05,
"loss": 1.4592832326889038,
"step": 508
},
{
"epoch": 0.12130221495466033,
"grad_norm": 0.6015625,
"learning_rate": 8e-05,
"loss": 1.4251080751419067,
"step": 510
},
{
"epoch": 0.12177790991526684,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.4636266231536865,
"step": 512
},
{
"epoch": 0.12225360487587335,
"grad_norm": 0.5703125,
"learning_rate": 8e-05,
"loss": 1.3918344974517822,
"step": 514
},
{
"epoch": 0.12272929983647986,
"grad_norm": 0.5625,
"learning_rate": 8e-05,
"loss": 1.4410995244979858,
"step": 516
},
{
"epoch": 0.12320499479708637,
"grad_norm": 0.53125,
"learning_rate": 8e-05,
"loss": 1.4553332328796387,
"step": 518
},
{
"epoch": 0.12368068975769288,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.4932277202606201,
"step": 520
},
{
"epoch": 0.12415638471829939,
"grad_norm": 0.5234375,
"learning_rate": 8e-05,
"loss": 1.4398219585418701,
"step": 522
},
{
"epoch": 0.1246320796789059,
"grad_norm": 0.5234375,
"learning_rate": 8e-05,
"loss": 1.4100382328033447,
"step": 524
},
{
"epoch": 0.12510777463951242,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.4194281101226807,
"step": 526
},
{
"epoch": 0.12558346960011893,
"grad_norm": 0.50390625,
"learning_rate": 8e-05,
"loss": 1.4007759094238281,
"step": 528
},
{
"epoch": 0.12605916456072544,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.3943548202514648,
"step": 530
},
{
"epoch": 0.12653485952133195,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.3672170639038086,
"step": 532
},
{
"epoch": 0.12701055448193846,
"grad_norm": 0.58203125,
"learning_rate": 8e-05,
"loss": 1.3937108516693115,
"step": 534
},
{
"epoch": 0.12748624944254497,
"grad_norm": 0.59375,
"learning_rate": 8e-05,
"loss": 1.4582862854003906,
"step": 536
},
{
"epoch": 0.12796194440315148,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.417186975479126,
"step": 538
},
{
"epoch": 0.128437639363758,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.3944048881530762,
"step": 540
},
{
"epoch": 0.1289133343243645,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.4348058700561523,
"step": 542
},
{
"epoch": 0.129389029284971,
"grad_norm": 0.56640625,
"learning_rate": 8e-05,
"loss": 1.4025098085403442,
"step": 544
},
{
"epoch": 0.12986472424557752,
"grad_norm": 0.5859375,
"learning_rate": 8e-05,
"loss": 1.4666318893432617,
"step": 546
},
{
"epoch": 0.13034041920618403,
"grad_norm": 0.50390625,
"learning_rate": 8e-05,
"loss": 1.3959743976593018,
"step": 548
},
{
"epoch": 0.13081611416679054,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.435917615890503,
"step": 550
},
{
"epoch": 0.13129180912739705,
"grad_norm": 0.5234375,
"learning_rate": 8e-05,
"loss": 1.4515659809112549,
"step": 552
},
{
"epoch": 0.13176750408800356,
"grad_norm": 0.51953125,
"learning_rate": 8e-05,
"loss": 1.4431695938110352,
"step": 554
},
{
"epoch": 0.13224319904861007,
"grad_norm": 0.5703125,
"learning_rate": 8e-05,
"loss": 1.3696998357772827,
"step": 556
},
{
"epoch": 0.1327188940092166,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.4764920473098755,
"step": 558
},
{
"epoch": 0.1331945889698231,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.3894143104553223,
"step": 560
},
{
"epoch": 0.13367028393042962,
"grad_norm": 0.51171875,
"learning_rate": 8e-05,
"loss": 1.4079980850219727,
"step": 562
},
{
"epoch": 0.13414597889103613,
"grad_norm": 0.49609375,
"learning_rate": 8e-05,
"loss": 1.3896784782409668,
"step": 564
},
{
"epoch": 0.13462167385164264,
"grad_norm": 0.498046875,
"learning_rate": 8e-05,
"loss": 1.4342916011810303,
"step": 566
},
{
"epoch": 0.13509736881224915,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.4243568181991577,
"step": 568
},
{
"epoch": 0.13557306377285566,
"grad_norm": 0.47265625,
"learning_rate": 8e-05,
"loss": 1.4043259620666504,
"step": 570
},
{
"epoch": 0.13604875873346217,
"grad_norm": 0.474609375,
"learning_rate": 8e-05,
"loss": 1.4198546409606934,
"step": 572
},
{
"epoch": 0.13652445369406868,
"grad_norm": 0.453125,
"learning_rate": 8e-05,
"loss": 1.3509985208511353,
"step": 574
},
{
"epoch": 0.1370001486546752,
"grad_norm": 0.48046875,
"learning_rate": 8e-05,
"loss": 1.3983509540557861,
"step": 576
},
{
"epoch": 0.1374758436152817,
"grad_norm": 0.4921875,
"learning_rate": 8e-05,
"loss": 1.4067437648773193,
"step": 578
},
{
"epoch": 0.1379515385758882,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.4863321781158447,
"step": 580
},
{
"epoch": 0.13842723353649472,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.4052914381027222,
"step": 582
},
{
"epoch": 0.13890292849710123,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.408928394317627,
"step": 584
},
{
"epoch": 0.13937862345770774,
"grad_norm": 0.55859375,
"learning_rate": 8e-05,
"loss": 1.4460136890411377,
"step": 586
},
{
"epoch": 0.13985431841831425,
"grad_norm": 0.51171875,
"learning_rate": 8e-05,
"loss": 1.4335639476776123,
"step": 588
},
{
"epoch": 0.14033001337892076,
"grad_norm": 0.53125,
"learning_rate": 8e-05,
"loss": 1.3965034484863281,
"step": 590
},
{
"epoch": 0.14080570833952727,
"grad_norm": 0.53125,
"learning_rate": 8e-05,
"loss": 1.4012255668640137,
"step": 592
},
{
"epoch": 0.14128140330013378,
"grad_norm": 0.53515625,
"learning_rate": 8e-05,
"loss": 1.4261143207550049,
"step": 594
},
{
"epoch": 0.1417570982607403,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.4008715152740479,
"step": 596
},
{
"epoch": 0.1422327932213468,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.4034451246261597,
"step": 598
},
{
"epoch": 0.14270848818195334,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.4082181453704834,
"step": 600
},
{
"epoch": 0.14318418314255985,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.3725682497024536,
"step": 602
},
{
"epoch": 0.14365987810316636,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.4293782711029053,
"step": 604
},
{
"epoch": 0.14413557306377286,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.4520360231399536,
"step": 606
},
{
"epoch": 0.14461126802437937,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.3525224924087524,
"step": 608
},
{
"epoch": 0.14508696298498588,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.4208955764770508,
"step": 610
},
{
"epoch": 0.1455626579455924,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.3334312438964844,
"step": 612
},
{
"epoch": 0.1460383529061989,
"grad_norm": 0.53125,
"learning_rate": 8e-05,
"loss": 1.3503882884979248,
"step": 614
},
{
"epoch": 0.1465140478668054,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.4191619157791138,
"step": 616
},
{
"epoch": 0.14698974282741192,
"grad_norm": 0.470703125,
"learning_rate": 8e-05,
"loss": 1.3381874561309814,
"step": 618
},
{
"epoch": 0.14746543778801843,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.3882290124893188,
"step": 620
},
{
"epoch": 0.14794113274862494,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.4173054695129395,
"step": 622
},
{
"epoch": 0.14841682770923145,
"grad_norm": 0.49609375,
"learning_rate": 8e-05,
"loss": 1.3113012313842773,
"step": 624
},
{
"epoch": 0.14889252266983796,
"grad_norm": 0.5390625,
"learning_rate": 8e-05,
"loss": 1.407628059387207,
"step": 626
},
{
"epoch": 0.14936821763044447,
"grad_norm": 0.5390625,
"learning_rate": 8e-05,
"loss": 1.447212815284729,
"step": 628
},
{
"epoch": 0.14984391259105098,
"grad_norm": 0.51171875,
"learning_rate": 8e-05,
"loss": 1.3606481552124023,
"step": 630
},
{
"epoch": 0.1503196075516575,
"grad_norm": 0.55078125,
"learning_rate": 8e-05,
"loss": 1.4575624465942383,
"step": 632
},
{
"epoch": 0.150795302512264,
"grad_norm": 0.56640625,
"learning_rate": 8e-05,
"loss": 1.355147123336792,
"step": 634
},
{
"epoch": 0.1512709974728705,
"grad_norm": 0.498046875,
"learning_rate": 8e-05,
"loss": 1.37825345993042,
"step": 636
},
{
"epoch": 0.15174669243347702,
"grad_norm": 0.50390625,
"learning_rate": 8e-05,
"loss": 1.4053802490234375,
"step": 638
},
{
"epoch": 0.15222238739408353,
"grad_norm": 0.478515625,
"learning_rate": 8e-05,
"loss": 1.3817956447601318,
"step": 640
},
{
"epoch": 0.15269808235469007,
"grad_norm": 0.498046875,
"learning_rate": 8e-05,
"loss": 1.3938934803009033,
"step": 642
},
{
"epoch": 0.15317377731529658,
"grad_norm": 0.53125,
"learning_rate": 8e-05,
"loss": 1.35261869430542,
"step": 644
},
{
"epoch": 0.1536494722759031,
"grad_norm": 0.51171875,
"learning_rate": 8e-05,
"loss": 1.3819756507873535,
"step": 646
},
{
"epoch": 0.1541251672365096,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.4077363014221191,
"step": 648
},
{
"epoch": 0.1546008621971161,
"grad_norm": 0.50390625,
"learning_rate": 8e-05,
"loss": 1.4303150177001953,
"step": 650
},
{
"epoch": 0.15507655715772262,
"grad_norm": 0.49609375,
"learning_rate": 8e-05,
"loss": 1.3727548122406006,
"step": 652
},
{
"epoch": 0.15555225211832913,
"grad_norm": 0.4921875,
"learning_rate": 8e-05,
"loss": 1.4012013673782349,
"step": 654
},
{
"epoch": 0.15602794707893564,
"grad_norm": 0.48046875,
"learning_rate": 8e-05,
"loss": 1.3778249025344849,
"step": 656
},
{
"epoch": 0.15650364203954215,
"grad_norm": 0.470703125,
"learning_rate": 8e-05,
"loss": 1.384866714477539,
"step": 658
},
{
"epoch": 0.15697933700014866,
"grad_norm": 0.51171875,
"learning_rate": 8e-05,
"loss": 1.4081860780715942,
"step": 660
},
{
"epoch": 0.15745503196075517,
"grad_norm": 0.482421875,
"learning_rate": 8e-05,
"loss": 1.3876349925994873,
"step": 662
},
{
"epoch": 0.15793072692136167,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.420417070388794,
"step": 664
},
{
"epoch": 0.15840642188196818,
"grad_norm": 0.50390625,
"learning_rate": 8e-05,
"loss": 1.427546501159668,
"step": 666
},
{
"epoch": 0.1588821168425747,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.404707431793213,
"step": 668
},
{
"epoch": 0.1593578118031812,
"grad_norm": 0.458984375,
"learning_rate": 8e-05,
"loss": 1.4167988300323486,
"step": 670
},
{
"epoch": 0.1598335067637877,
"grad_norm": 0.482421875,
"learning_rate": 8e-05,
"loss": 1.36492919921875,
"step": 672
},
{
"epoch": 0.16030920172439422,
"grad_norm": 0.546875,
"learning_rate": 8e-05,
"loss": 1.4290658235549927,
"step": 674
},
{
"epoch": 0.16078489668500073,
"grad_norm": 0.50390625,
"learning_rate": 8e-05,
"loss": 1.3939204216003418,
"step": 676
},
{
"epoch": 0.16126059164560724,
"grad_norm": 0.47265625,
"learning_rate": 8e-05,
"loss": 1.368532419204712,
"step": 678
},
{
"epoch": 0.16173628660621375,
"grad_norm": 0.466796875,
"learning_rate": 8e-05,
"loss": 1.4039356708526611,
"step": 680
},
{
"epoch": 0.1622119815668203,
"grad_norm": 0.453125,
"learning_rate": 8e-05,
"loss": 1.4631690979003906,
"step": 682
},
{
"epoch": 0.1626876765274268,
"grad_norm": 0.458984375,
"learning_rate": 8e-05,
"loss": 1.3834668397903442,
"step": 684
},
{
"epoch": 0.1631633714880333,
"grad_norm": 0.46484375,
"learning_rate": 8e-05,
"loss": 1.373947262763977,
"step": 686
},
{
"epoch": 0.16363906644863982,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.4164583683013916,
"step": 688
},
{
"epoch": 0.16411476140924633,
"grad_norm": 0.474609375,
"learning_rate": 8e-05,
"loss": 1.4322106838226318,
"step": 690
},
{
"epoch": 0.16459045636985284,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.3455379009246826,
"step": 692
},
{
"epoch": 0.16506615133045935,
"grad_norm": 0.482421875,
"learning_rate": 8e-05,
"loss": 1.34842050075531,
"step": 694
},
{
"epoch": 0.16554184629106586,
"grad_norm": 0.490234375,
"learning_rate": 8e-05,
"loss": 1.428257942199707,
"step": 696
},
{
"epoch": 0.16601754125167237,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.417719841003418,
"step": 698
},
{
"epoch": 0.16649323621227888,
"grad_norm": 0.453125,
"learning_rate": 8e-05,
"loss": 1.4131088256835938,
"step": 700
},
{
"epoch": 0.1669689311728854,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.356804370880127,
"step": 702
},
{
"epoch": 0.1674446261334919,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.355417251586914,
"step": 704
},
{
"epoch": 0.1679203210940984,
"grad_norm": 0.54296875,
"learning_rate": 8e-05,
"loss": 1.4380789995193481,
"step": 706
},
{
"epoch": 0.16839601605470492,
"grad_norm": 0.4921875,
"learning_rate": 8e-05,
"loss": 1.3789442777633667,
"step": 708
},
{
"epoch": 0.16887171101531143,
"grad_norm": 0.474609375,
"learning_rate": 8e-05,
"loss": 1.3488481044769287,
"step": 710
},
{
"epoch": 0.16934740597591794,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.3990561962127686,
"step": 712
},
{
"epoch": 0.16982310093652445,
"grad_norm": 0.490234375,
"learning_rate": 8e-05,
"loss": 1.3976104259490967,
"step": 714
},
{
"epoch": 0.17029879589713096,
"grad_norm": 0.494140625,
"learning_rate": 8e-05,
"loss": 1.430433750152588,
"step": 716
},
{
"epoch": 0.17077449085773747,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.359434723854065,
"step": 718
},
{
"epoch": 0.17125018581834398,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.4045766592025757,
"step": 720
},
{
"epoch": 0.17172588077895048,
"grad_norm": 0.49609375,
"learning_rate": 8e-05,
"loss": 1.3606858253479004,
"step": 722
},
{
"epoch": 0.17220157573955702,
"grad_norm": 0.466796875,
"learning_rate": 8e-05,
"loss": 1.4614171981811523,
"step": 724
},
{
"epoch": 0.17267727070016353,
"grad_norm": 0.47265625,
"learning_rate": 8e-05,
"loss": 1.416619062423706,
"step": 726
},
{
"epoch": 0.17315296566077004,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.2924635410308838,
"step": 728
},
{
"epoch": 0.17362866062137655,
"grad_norm": 0.47265625,
"learning_rate": 8e-05,
"loss": 1.3354673385620117,
"step": 730
},
{
"epoch": 0.17410435558198306,
"grad_norm": 0.4765625,
"learning_rate": 8e-05,
"loss": 1.3578845262527466,
"step": 732
},
{
"epoch": 0.17458005054258957,
"grad_norm": 0.49609375,
"learning_rate": 8e-05,
"loss": 1.4009724855422974,
"step": 734
},
{
"epoch": 0.17505574550319608,
"grad_norm": 0.48046875,
"learning_rate": 8e-05,
"loss": 1.4139372110366821,
"step": 736
},
{
"epoch": 0.1755314404638026,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.3427128791809082,
"step": 738
},
{
"epoch": 0.1760071354244091,
"grad_norm": 0.51171875,
"learning_rate": 8e-05,
"loss": 1.3915586471557617,
"step": 740
},
{
"epoch": 0.1764828303850156,
"grad_norm": 0.48046875,
"learning_rate": 8e-05,
"loss": 1.3710131645202637,
"step": 742
},
{
"epoch": 0.17695852534562212,
"grad_norm": 0.48046875,
"learning_rate": 8e-05,
"loss": 1.3700971603393555,
"step": 744
},
{
"epoch": 0.17743422030622863,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.3621227741241455,
"step": 746
},
{
"epoch": 0.17790991526683514,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.38692307472229,
"step": 748
},
{
"epoch": 0.17838561022744165,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.352332592010498,
"step": 750
},
{
"epoch": 0.17886130518804816,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.4046599864959717,
"step": 752
},
{
"epoch": 0.17933700014865467,
"grad_norm": 0.5390625,
"learning_rate": 8e-05,
"loss": 1.3857762813568115,
"step": 754
},
{
"epoch": 0.17981269510926118,
"grad_norm": 0.546875,
"learning_rate": 8e-05,
"loss": 1.3184947967529297,
"step": 756
},
{
"epoch": 0.1802883900698677,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.3482776880264282,
"step": 758
},
{
"epoch": 0.1807640850304742,
"grad_norm": 0.51953125,
"learning_rate": 8e-05,
"loss": 1.434415340423584,
"step": 760
},
{
"epoch": 0.1812397799910807,
"grad_norm": 0.490234375,
"learning_rate": 8e-05,
"loss": 1.3801504373550415,
"step": 762
},
{
"epoch": 0.18171547495168722,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.3628723621368408,
"step": 764
},
{
"epoch": 0.18219116991229375,
"grad_norm": 0.46484375,
"learning_rate": 8e-05,
"loss": 1.3805229663848877,
"step": 766
},
{
"epoch": 0.18266686487290026,
"grad_norm": 0.494140625,
"learning_rate": 8e-05,
"loss": 1.3568819761276245,
"step": 768
},
{
"epoch": 0.18314255983350677,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.3049235343933105,
"step": 770
},
{
"epoch": 0.18361825479411328,
"grad_norm": 0.46875,
"learning_rate": 8e-05,
"loss": 1.3783180713653564,
"step": 772
},
{
"epoch": 0.1840939497547198,
"grad_norm": 0.48046875,
"learning_rate": 8e-05,
"loss": 1.3785371780395508,
"step": 774
},
{
"epoch": 0.1845696447153263,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.4072458744049072,
"step": 776
},
{
"epoch": 0.1850453396759328,
"grad_norm": 0.47265625,
"learning_rate": 8e-05,
"loss": 1.3426545858383179,
"step": 778
},
{
"epoch": 0.18552103463653932,
"grad_norm": 0.453125,
"learning_rate": 8e-05,
"loss": 1.352428674697876,
"step": 780
},
{
"epoch": 0.18599672959714583,
"grad_norm": 0.46875,
"learning_rate": 8e-05,
"loss": 1.3136948347091675,
"step": 782
},
{
"epoch": 0.18647242455775234,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.3649238348007202,
"step": 784
},
{
"epoch": 0.18694811951835885,
"grad_norm": 0.50390625,
"learning_rate": 8e-05,
"loss": 1.4003939628601074,
"step": 786
},
{
"epoch": 0.18742381447896536,
"grad_norm": 0.470703125,
"learning_rate": 8e-05,
"loss": 1.3522775173187256,
"step": 788
},
{
"epoch": 0.18789950943957187,
"grad_norm": 0.478515625,
"learning_rate": 8e-05,
"loss": 1.353920578956604,
"step": 790
},
{
"epoch": 0.18837520440017838,
"grad_norm": 0.458984375,
"learning_rate": 8e-05,
"loss": 1.4120471477508545,
"step": 792
},
{
"epoch": 0.1888508993607849,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.425047755241394,
"step": 794
},
{
"epoch": 0.1893265943213914,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.3698722124099731,
"step": 796
},
{
"epoch": 0.1898022892819979,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.3825695514678955,
"step": 798
},
{
"epoch": 0.19027798424260442,
"grad_norm": 0.466796875,
"learning_rate": 8e-05,
"loss": 1.384330153465271,
"step": 800
},
{
"epoch": 0.19075367920321093,
"grad_norm": 0.4765625,
"learning_rate": 8e-05,
"loss": 1.365710735321045,
"step": 802
},
{
"epoch": 0.19122937416381744,
"grad_norm": 0.466796875,
"learning_rate": 8e-05,
"loss": 1.351928472518921,
"step": 804
},
{
"epoch": 0.19170506912442398,
"grad_norm": 0.458984375,
"learning_rate": 8e-05,
"loss": 1.364558458328247,
"step": 806
},
{
"epoch": 0.1921807640850305,
"grad_norm": 0.466796875,
"learning_rate": 8e-05,
"loss": 1.4033458232879639,
"step": 808
},
{
"epoch": 0.192656459045637,
"grad_norm": 0.494140625,
"learning_rate": 8e-05,
"loss": 1.378347635269165,
"step": 810
},
{
"epoch": 0.1931321540062435,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.364283561706543,
"step": 812
},
{
"epoch": 0.19360784896685002,
"grad_norm": 0.53125,
"learning_rate": 8e-05,
"loss": 1.414649248123169,
"step": 814
},
{
"epoch": 0.19408354392745653,
"grad_norm": 0.4453125,
"learning_rate": 8e-05,
"loss": 1.3634638786315918,
"step": 816
},
{
"epoch": 0.19455923888806304,
"grad_norm": 0.55859375,
"learning_rate": 8e-05,
"loss": 1.4743528366088867,
"step": 818
},
{
"epoch": 0.19503493384866954,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.3400163650512695,
"step": 820
},
{
"epoch": 0.19551062880927605,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.3880252838134766,
"step": 822
},
{
"epoch": 0.19598632376988256,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.395135521888733,
"step": 824
},
{
"epoch": 0.19646201873048907,
"grad_norm": 0.4609375,
"learning_rate": 8e-05,
"loss": 1.3433012962341309,
"step": 826
},
{
"epoch": 0.19693771369109558,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.317229986190796,
"step": 828
},
{
"epoch": 0.1974134086517021,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.3179906606674194,
"step": 830
},
{
"epoch": 0.1978891036123086,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.3207850456237793,
"step": 832
},
{
"epoch": 0.1983647985729151,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.4160897731781006,
"step": 834
},
{
"epoch": 0.19884049353352162,
"grad_norm": 0.51953125,
"learning_rate": 8e-05,
"loss": 1.34122633934021,
"step": 836
},
{
"epoch": 0.19931618849412813,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.3531912565231323,
"step": 838
},
{
"epoch": 0.19979188345473464,
"grad_norm": 0.482421875,
"learning_rate": 8e-05,
"loss": 1.3703558444976807,
"step": 840
},
{
"epoch": 0.20026757841534115,
"grad_norm": 0.46875,
"learning_rate": 8e-05,
"loss": 1.3876454830169678,
"step": 842
},
{
"epoch": 0.20074327337594766,
"grad_norm": 0.453125,
"learning_rate": 8e-05,
"loss": 1.3795206546783447,
"step": 844
},
{
"epoch": 0.20121896833655417,
"grad_norm": 0.482421875,
"learning_rate": 8e-05,
"loss": 1.3170604705810547,
"step": 846
},
{
"epoch": 0.2016946632971607,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.3548598289489746,
"step": 848
},
{
"epoch": 0.20217035825776722,
"grad_norm": 0.5546875,
"learning_rate": 8e-05,
"loss": 1.359254002571106,
"step": 850
},
{
"epoch": 0.20264605321837373,
"grad_norm": 0.46484375,
"learning_rate": 8e-05,
"loss": 1.389087438583374,
"step": 852
},
{
"epoch": 0.20312174817898024,
"grad_norm": 0.447265625,
"learning_rate": 8e-05,
"loss": 1.3296732902526855,
"step": 854
},
{
"epoch": 0.20359744313958675,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.3714617490768433,
"step": 856
},
{
"epoch": 0.20407313810019326,
"grad_norm": 0.4765625,
"learning_rate": 8e-05,
"loss": 1.3371829986572266,
"step": 858
},
{
"epoch": 0.20454883306079977,
"grad_norm": 0.498046875,
"learning_rate": 8e-05,
"loss": 1.386389970779419,
"step": 860
},
{
"epoch": 0.20502452802140628,
"grad_norm": 0.46484375,
"learning_rate": 8e-05,
"loss": 1.338608741760254,
"step": 862
},
{
"epoch": 0.2055002229820128,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.328315019607544,
"step": 864
},
{
"epoch": 0.2059759179426193,
"grad_norm": 0.4921875,
"learning_rate": 8e-05,
"loss": 1.3264660835266113,
"step": 866
},
{
"epoch": 0.2064516129032258,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.4002896547317505,
"step": 868
},
{
"epoch": 0.20692730786383232,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.3713188171386719,
"step": 870
},
{
"epoch": 0.20740300282443883,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.350874900817871,
"step": 872
},
{
"epoch": 0.20787869778504534,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.3784689903259277,
"step": 874
},
{
"epoch": 0.20835439274565185,
"grad_norm": 0.59765625,
"learning_rate": 8e-05,
"loss": 1.3428910970687866,
"step": 876
},
{
"epoch": 0.20883008770625835,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.3714317083358765,
"step": 878
},
{
"epoch": 0.20930578266686486,
"grad_norm": 0.494140625,
"learning_rate": 8e-05,
"loss": 1.3759992122650146,
"step": 880
},
{
"epoch": 0.20978147762747137,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.2990326881408691,
"step": 882
},
{
"epoch": 0.21025717258807788,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.3624963760375977,
"step": 884
},
{
"epoch": 0.2107328675486844,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.3324933052062988,
"step": 886
},
{
"epoch": 0.2112085625092909,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.4013808965682983,
"step": 888
},
{
"epoch": 0.21168425746989744,
"grad_norm": 0.4765625,
"learning_rate": 8e-05,
"loss": 1.338510274887085,
"step": 890
},
{
"epoch": 0.21215995243050395,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.4126381874084473,
"step": 892
},
{
"epoch": 0.21263564739111046,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.371493935585022,
"step": 894
},
{
"epoch": 0.21311134235171697,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.383441686630249,
"step": 896
},
{
"epoch": 0.21358703731232348,
"grad_norm": 0.51953125,
"learning_rate": 8e-05,
"loss": 1.3659964799880981,
"step": 898
},
{
"epoch": 0.21406273227293,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.2908456325531006,
"step": 900
},
{
"epoch": 0.2145384272335365,
"grad_norm": 0.498046875,
"learning_rate": 8e-05,
"loss": 1.3610074520111084,
"step": 902
},
{
"epoch": 0.215014122194143,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.3580766916275024,
"step": 904
},
{
"epoch": 0.21548981715474952,
"grad_norm": 0.4921875,
"learning_rate": 8e-05,
"loss": 1.458742618560791,
"step": 906
},
{
"epoch": 0.21596551211535603,
"grad_norm": 0.4921875,
"learning_rate": 8e-05,
"loss": 1.2720565795898438,
"step": 908
},
{
"epoch": 0.21644120707596254,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.3226542472839355,
"step": 910
},
{
"epoch": 0.21691690203656905,
"grad_norm": 0.46875,
"learning_rate": 8e-05,
"loss": 1.3100987672805786,
"step": 912
},
{
"epoch": 0.21739259699717556,
"grad_norm": 0.482421875,
"learning_rate": 8e-05,
"loss": 1.3754308223724365,
"step": 914
},
{
"epoch": 0.21786829195778207,
"grad_norm": 0.53515625,
"learning_rate": 8e-05,
"loss": 1.3694303035736084,
"step": 916
},
{
"epoch": 0.21834398691838858,
"grad_norm": 0.515625,
"learning_rate": 8e-05,
"loss": 1.394423007965088,
"step": 918
},
{
"epoch": 0.2188196818789951,
"grad_norm": 0.4609375,
"learning_rate": 8e-05,
"loss": 1.3577532768249512,
"step": 920
},
{
"epoch": 0.2192953768396016,
"grad_norm": 0.453125,
"learning_rate": 8e-05,
"loss": 1.2522318363189697,
"step": 922
},
{
"epoch": 0.2197710718002081,
"grad_norm": 0.466796875,
"learning_rate": 8e-05,
"loss": 1.3532583713531494,
"step": 924
},
{
"epoch": 0.22024676676081462,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.3816845417022705,
"step": 926
},
{
"epoch": 0.22072246172142113,
"grad_norm": 0.494140625,
"learning_rate": 8e-05,
"loss": 1.362253189086914,
"step": 928
},
{
"epoch": 0.22119815668202766,
"grad_norm": 0.494140625,
"learning_rate": 8e-05,
"loss": 1.3231050968170166,
"step": 930
},
{
"epoch": 0.22167385164263417,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.3791143894195557,
"step": 932
},
{
"epoch": 0.22214954660324068,
"grad_norm": 0.470703125,
"learning_rate": 8e-05,
"loss": 1.3647040128707886,
"step": 934
},
{
"epoch": 0.2226252415638472,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.3556348085403442,
"step": 936
},
{
"epoch": 0.2231009365244537,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.3153495788574219,
"step": 938
},
{
"epoch": 0.2235766314850602,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2898294925689697,
"step": 940
},
{
"epoch": 0.22405232644566672,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.3297260999679565,
"step": 942
},
{
"epoch": 0.22452802140627323,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.3505053520202637,
"step": 944
},
{
"epoch": 0.22500371636687974,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.3983497619628906,
"step": 946
},
{
"epoch": 0.22547941132748625,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.3593679666519165,
"step": 948
},
{
"epoch": 0.22595510628809276,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.336477518081665,
"step": 950
},
{
"epoch": 0.22643080124869927,
"grad_norm": 0.453125,
"learning_rate": 8e-05,
"loss": 1.3708462715148926,
"step": 952
},
{
"epoch": 0.22690649620930578,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.4065918922424316,
"step": 954
},
{
"epoch": 0.2273821911699123,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.361413836479187,
"step": 956
},
{
"epoch": 0.2278578861305188,
"grad_norm": 0.49609375,
"learning_rate": 8e-05,
"loss": 1.3337655067443848,
"step": 958
},
{
"epoch": 0.2283335810911253,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.2802634239196777,
"step": 960
},
{
"epoch": 0.22880927605173182,
"grad_norm": 0.46484375,
"learning_rate": 8e-05,
"loss": 1.3333477973937988,
"step": 962
},
{
"epoch": 0.22928497101233833,
"grad_norm": 0.48046875,
"learning_rate": 8e-05,
"loss": 1.3998594284057617,
"step": 964
},
{
"epoch": 0.22976066597294484,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.3377106189727783,
"step": 966
},
{
"epoch": 0.23023636093355135,
"grad_norm": 0.458984375,
"learning_rate": 8e-05,
"loss": 1.2901934385299683,
"step": 968
},
{
"epoch": 0.23071205589415786,
"grad_norm": 0.498046875,
"learning_rate": 8e-05,
"loss": 1.3435245752334595,
"step": 970
},
{
"epoch": 0.2311877508547644,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.3464173078536987,
"step": 972
},
{
"epoch": 0.2316634458153709,
"grad_norm": 0.453125,
"learning_rate": 8e-05,
"loss": 1.3196808099746704,
"step": 974
},
{
"epoch": 0.23213914077597742,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.3490209579467773,
"step": 976
},
{
"epoch": 0.23261483573658392,
"grad_norm": 0.474609375,
"learning_rate": 8e-05,
"loss": 1.3755543231964111,
"step": 978
},
{
"epoch": 0.23309053069719043,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.3209686279296875,
"step": 980
},
{
"epoch": 0.23356622565779694,
"grad_norm": 0.474609375,
"learning_rate": 8e-05,
"loss": 1.3944644927978516,
"step": 982
},
{
"epoch": 0.23404192061840345,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.3737695217132568,
"step": 984
},
{
"epoch": 0.23451761557900996,
"grad_norm": 0.447265625,
"learning_rate": 8e-05,
"loss": 1.352348804473877,
"step": 986
},
{
"epoch": 0.23499331053961647,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.2491270303726196,
"step": 988
},
{
"epoch": 0.23546900550022298,
"grad_norm": 0.478515625,
"learning_rate": 8e-05,
"loss": 1.4017226696014404,
"step": 990
},
{
"epoch": 0.2359447004608295,
"grad_norm": 0.46875,
"learning_rate": 8e-05,
"loss": 1.3329687118530273,
"step": 992
},
{
"epoch": 0.236420395421436,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.2956058979034424,
"step": 994
},
{
"epoch": 0.2368960903820425,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.376798391342163,
"step": 996
},
{
"epoch": 0.23737178534264902,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.3533029556274414,
"step": 998
},
{
"epoch": 0.23784748030325553,
"grad_norm": 0.4453125,
"learning_rate": 8e-05,
"loss": 1.3347084522247314,
"step": 1000
},
{
"epoch": 0.23832317526386204,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.3693647384643555,
"step": 1002
},
{
"epoch": 0.23879887022446855,
"grad_norm": 0.4453125,
"learning_rate": 8e-05,
"loss": 1.3653826713562012,
"step": 1004
},
{
"epoch": 0.23927456518507506,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.345597505569458,
"step": 1006
},
{
"epoch": 0.23975026014568157,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.2825236320495605,
"step": 1008
},
{
"epoch": 0.24022595510628808,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.3502631187438965,
"step": 1010
},
{
"epoch": 0.2407016500668946,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.3079496622085571,
"step": 1012
},
{
"epoch": 0.24117734502750113,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.3474180698394775,
"step": 1014
},
{
"epoch": 0.24165303998810764,
"grad_norm": 0.4765625,
"learning_rate": 8e-05,
"loss": 1.3570088148117065,
"step": 1016
},
{
"epoch": 0.24212873494871415,
"grad_norm": 0.466796875,
"learning_rate": 8e-05,
"loss": 1.3702566623687744,
"step": 1018
},
{
"epoch": 0.24260442990932066,
"grad_norm": 0.453125,
"learning_rate": 8e-05,
"loss": 1.3773030042648315,
"step": 1020
},
{
"epoch": 0.24308012486992717,
"grad_norm": 0.470703125,
"learning_rate": 8e-05,
"loss": 1.333245873451233,
"step": 1022
},
{
"epoch": 0.24355581983053368,
"grad_norm": 0.4609375,
"learning_rate": 8e-05,
"loss": 1.3305965662002563,
"step": 1024
},
{
"epoch": 0.24403151479114019,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.3149254322052002,
"step": 1026
},
{
"epoch": 0.2445072097517467,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.34800124168396,
"step": 1028
},
{
"epoch": 0.2449829047123532,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.3632348775863647,
"step": 1030
},
{
"epoch": 0.24545859967295972,
"grad_norm": 0.482421875,
"learning_rate": 8e-05,
"loss": 1.3612074851989746,
"step": 1032
},
{
"epoch": 0.24593429463356622,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.3488757610321045,
"step": 1034
},
{
"epoch": 0.24640998959417273,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.3559046983718872,
"step": 1036
},
{
"epoch": 0.24688568455477924,
"grad_norm": 0.453125,
"learning_rate": 8e-05,
"loss": 1.3708908557891846,
"step": 1038
},
{
"epoch": 0.24736137951538575,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.33760666847229,
"step": 1040
},
{
"epoch": 0.24783707447599226,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.2863125801086426,
"step": 1042
},
{
"epoch": 0.24831276943659877,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.3174580335617065,
"step": 1044
},
{
"epoch": 0.24878846439720528,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.3641953468322754,
"step": 1046
},
{
"epoch": 0.2492641593578118,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.3469069004058838,
"step": 1048
},
{
"epoch": 0.2497398543184183,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.3538458347320557,
"step": 1050
},
{
"epoch": 0.25021554927902484,
"grad_norm": 0.48046875,
"learning_rate": 8e-05,
"loss": 1.354750633239746,
"step": 1052
},
{
"epoch": 0.25069124423963135,
"grad_norm": 0.4609375,
"learning_rate": 8e-05,
"loss": 1.3567293882369995,
"step": 1054
},
{
"epoch": 0.25116693920023786,
"grad_norm": 0.4921875,
"learning_rate": 8e-05,
"loss": 1.3444650173187256,
"step": 1056
},
{
"epoch": 0.25164263416084437,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.3146984577178955,
"step": 1058
},
{
"epoch": 0.2521183291214509,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.3101708889007568,
"step": 1060
},
{
"epoch": 0.2525940240820574,
"grad_norm": 0.48046875,
"learning_rate": 8e-05,
"loss": 1.3136630058288574,
"step": 1062
},
{
"epoch": 0.2530697190426639,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.35286545753479,
"step": 1064
},
{
"epoch": 0.2535454140032704,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.319314956665039,
"step": 1066
},
{
"epoch": 0.2540211089638769,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.3844151496887207,
"step": 1068
},
{
"epoch": 0.25449680392448343,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.2962524890899658,
"step": 1070
},
{
"epoch": 0.25497249888508994,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.3922219276428223,
"step": 1072
},
{
"epoch": 0.25544819384569645,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.3131260871887207,
"step": 1074
},
{
"epoch": 0.25592388880630296,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.322244644165039,
"step": 1076
},
{
"epoch": 0.25639958376690947,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.3516499996185303,
"step": 1078
},
{
"epoch": 0.256875278727516,
"grad_norm": 0.470703125,
"learning_rate": 8e-05,
"loss": 1.3630871772766113,
"step": 1080
},
{
"epoch": 0.2573509736881225,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.3094751834869385,
"step": 1082
},
{
"epoch": 0.257826668648729,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.306774616241455,
"step": 1084
},
{
"epoch": 0.2583023636093355,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.3254430294036865,
"step": 1086
},
{
"epoch": 0.258778058569942,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.306220293045044,
"step": 1088
},
{
"epoch": 0.2592537535305485,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.337794303894043,
"step": 1090
},
{
"epoch": 0.25972944849115503,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.324033260345459,
"step": 1092
},
{
"epoch": 0.26020514345176154,
"grad_norm": 0.46484375,
"learning_rate": 8e-05,
"loss": 1.3060619831085205,
"step": 1094
},
{
"epoch": 0.26068083841236805,
"grad_norm": 0.46875,
"learning_rate": 8e-05,
"loss": 1.411613941192627,
"step": 1096
},
{
"epoch": 0.26115653337297456,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.3333206176757812,
"step": 1098
},
{
"epoch": 0.2616322283335811,
"grad_norm": 0.494140625,
"learning_rate": 8e-05,
"loss": 1.3340492248535156,
"step": 1100
},
{
"epoch": 0.2621079232941876,
"grad_norm": 0.5234375,
"learning_rate": 8e-05,
"loss": 1.3538923263549805,
"step": 1102
},
{
"epoch": 0.2625836182547941,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.2844221591949463,
"step": 1104
},
{
"epoch": 0.2630593132154006,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2786577939987183,
"step": 1106
},
{
"epoch": 0.2635350081760071,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.3393871784210205,
"step": 1108
},
{
"epoch": 0.2640107031366136,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.3317300081253052,
"step": 1110
},
{
"epoch": 0.26448639809722013,
"grad_norm": 0.470703125,
"learning_rate": 8e-05,
"loss": 1.329606056213379,
"step": 1112
},
{
"epoch": 0.26496209305782664,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.3412857055664062,
"step": 1114
},
{
"epoch": 0.2654377880184332,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.3141382932662964,
"step": 1116
},
{
"epoch": 0.2659134829790397,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.3066372871398926,
"step": 1118
},
{
"epoch": 0.2663891779396462,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.336663007736206,
"step": 1120
},
{
"epoch": 0.26686487290025274,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.3393672704696655,
"step": 1122
},
{
"epoch": 0.26734056786085925,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.338028907775879,
"step": 1124
},
{
"epoch": 0.26781626282146576,
"grad_norm": 0.447265625,
"learning_rate": 8e-05,
"loss": 1.25938880443573,
"step": 1126
},
{
"epoch": 0.26829195778207227,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.3836978673934937,
"step": 1128
},
{
"epoch": 0.2687676527426788,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.3326656818389893,
"step": 1130
},
{
"epoch": 0.2692433477032853,
"grad_norm": 0.470703125,
"learning_rate": 8e-05,
"loss": 1.2927348613739014,
"step": 1132
},
{
"epoch": 0.2697190426638918,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.4277849197387695,
"step": 1134
},
{
"epoch": 0.2701947376244983,
"grad_norm": 0.498046875,
"learning_rate": 8e-05,
"loss": 1.3989144563674927,
"step": 1136
},
{
"epoch": 0.2706704325851048,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.3444643020629883,
"step": 1138
},
{
"epoch": 0.2711461275457113,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.2833266258239746,
"step": 1140
},
{
"epoch": 0.27162182250631783,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.358147382736206,
"step": 1142
},
{
"epoch": 0.27209751746692434,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.3105173110961914,
"step": 1144
},
{
"epoch": 0.27257321242753085,
"grad_norm": 0.478515625,
"learning_rate": 8e-05,
"loss": 1.3114371299743652,
"step": 1146
},
{
"epoch": 0.27304890738813736,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.2814993858337402,
"step": 1148
},
{
"epoch": 0.2735246023487439,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.3203294277191162,
"step": 1150
},
{
"epoch": 0.2740002973093504,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.2979755401611328,
"step": 1152
},
{
"epoch": 0.2744759922699569,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.3081634044647217,
"step": 1154
},
{
"epoch": 0.2749516872305634,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.3281807899475098,
"step": 1156
},
{
"epoch": 0.2754273821911699,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.3202593326568604,
"step": 1158
},
{
"epoch": 0.2759030771517764,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.3806310892105103,
"step": 1160
},
{
"epoch": 0.27637877211238293,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.3173789978027344,
"step": 1162
},
{
"epoch": 0.27685446707298944,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.3223962783813477,
"step": 1164
},
{
"epoch": 0.27733016203359595,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.3117542266845703,
"step": 1166
},
{
"epoch": 0.27780585699420246,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.3533828258514404,
"step": 1168
},
{
"epoch": 0.27828155195480897,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.3214187622070312,
"step": 1170
},
{
"epoch": 0.2787572469154155,
"grad_norm": 0.458984375,
"learning_rate": 8e-05,
"loss": 1.3294625282287598,
"step": 1172
},
{
"epoch": 0.279232941876022,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.3171840906143188,
"step": 1174
},
{
"epoch": 0.2797086368366285,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.3028992414474487,
"step": 1176
},
{
"epoch": 0.280184331797235,
"grad_norm": 0.47265625,
"learning_rate": 8e-05,
"loss": 1.3446723222732544,
"step": 1178
},
{
"epoch": 0.2806600267578415,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.296749472618103,
"step": 1180
},
{
"epoch": 0.28113572171844803,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.3563461303710938,
"step": 1182
},
{
"epoch": 0.28161141667905454,
"grad_norm": 0.5,
"learning_rate": 8e-05,
"loss": 1.3181467056274414,
"step": 1184
},
{
"epoch": 0.28208711163966105,
"grad_norm": 0.48046875,
"learning_rate": 8e-05,
"loss": 1.3786540031433105,
"step": 1186
},
{
"epoch": 0.28256280660026756,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.3328609466552734,
"step": 1188
},
{
"epoch": 0.28303850156087407,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.3462462425231934,
"step": 1190
},
{
"epoch": 0.2835141965214806,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.3369724750518799,
"step": 1192
},
{
"epoch": 0.2839898914820871,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.3191611766815186,
"step": 1194
},
{
"epoch": 0.2844655864426936,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.3197510242462158,
"step": 1196
},
{
"epoch": 0.2849412814033001,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.3486484289169312,
"step": 1198
},
{
"epoch": 0.28541697636390667,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.3362209796905518,
"step": 1200
},
{
"epoch": 0.2858926713245132,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.322070837020874,
"step": 1202
},
{
"epoch": 0.2863683662851197,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.3231661319732666,
"step": 1204
},
{
"epoch": 0.2868440612457262,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.2671769857406616,
"step": 1206
},
{
"epoch": 0.2873197562063327,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.3193705081939697,
"step": 1208
},
{
"epoch": 0.2877954511669392,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.3454172611236572,
"step": 1210
},
{
"epoch": 0.28827114612754573,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.351203441619873,
"step": 1212
},
{
"epoch": 0.28874684108815224,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.3364512920379639,
"step": 1214
},
{
"epoch": 0.28922253604875875,
"grad_norm": 0.46875,
"learning_rate": 8e-05,
"loss": 1.3189178705215454,
"step": 1216
},
{
"epoch": 0.28969823100936526,
"grad_norm": 0.48828125,
"learning_rate": 8e-05,
"loss": 1.2867472171783447,
"step": 1218
},
{
"epoch": 0.29017392596997177,
"grad_norm": 0.46484375,
"learning_rate": 8e-05,
"loss": 1.3088388442993164,
"step": 1220
},
{
"epoch": 0.2906496209305783,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.2755553722381592,
"step": 1222
},
{
"epoch": 0.2911253158911848,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.3116247653961182,
"step": 1224
},
{
"epoch": 0.2916010108517913,
"grad_norm": 0.4453125,
"learning_rate": 8e-05,
"loss": 1.2760411500930786,
"step": 1226
},
{
"epoch": 0.2920767058123978,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.3090481758117676,
"step": 1228
},
{
"epoch": 0.2925524007730043,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.3445281982421875,
"step": 1230
},
{
"epoch": 0.2930280957336108,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.3193836212158203,
"step": 1232
},
{
"epoch": 0.29350379069421734,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.20814847946167,
"step": 1234
},
{
"epoch": 0.29397948565482385,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.266977310180664,
"step": 1236
},
{
"epoch": 0.29445518061543036,
"grad_norm": 0.486328125,
"learning_rate": 8e-05,
"loss": 1.3388676643371582,
"step": 1238
},
{
"epoch": 0.29493087557603687,
"grad_norm": 0.46484375,
"learning_rate": 8e-05,
"loss": 1.3216158151626587,
"step": 1240
},
{
"epoch": 0.2954065705366434,
"grad_norm": 0.4609375,
"learning_rate": 8e-05,
"loss": 1.3377256393432617,
"step": 1242
},
{
"epoch": 0.2958822654972499,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.3120627403259277,
"step": 1244
},
{
"epoch": 0.2963579604578564,
"grad_norm": 0.482421875,
"learning_rate": 8e-05,
"loss": 1.38155198097229,
"step": 1246
},
{
"epoch": 0.2968336554184629,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.3631592988967896,
"step": 1248
},
{
"epoch": 0.2973093503790694,
"grad_norm": 0.466796875,
"learning_rate": 8e-05,
"loss": 1.342321515083313,
"step": 1250
},
{
"epoch": 0.2977850453396759,
"grad_norm": 0.478515625,
"learning_rate": 8e-05,
"loss": 1.391056776046753,
"step": 1252
},
{
"epoch": 0.29826074030028243,
"grad_norm": 0.447265625,
"learning_rate": 8e-05,
"loss": 1.275477409362793,
"step": 1254
},
{
"epoch": 0.29873643526088894,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.3247549533843994,
"step": 1256
},
{
"epoch": 0.29921213022149545,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.3454852104187012,
"step": 1258
},
{
"epoch": 0.29968782518210196,
"grad_norm": 0.46875,
"learning_rate": 8e-05,
"loss": 1.3124552965164185,
"step": 1260
},
{
"epoch": 0.3001635201427085,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.309496521949768,
"step": 1262
},
{
"epoch": 0.300639215103315,
"grad_norm": 0.412109375,
"learning_rate": 8e-05,
"loss": 1.3047943115234375,
"step": 1264
},
{
"epoch": 0.3011149100639215,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.348783016204834,
"step": 1266
},
{
"epoch": 0.301590605024528,
"grad_norm": 0.4453125,
"learning_rate": 8e-05,
"loss": 1.2833664417266846,
"step": 1268
},
{
"epoch": 0.3020662999851345,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.3276420831680298,
"step": 1270
},
{
"epoch": 0.302541994945741,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.3440744876861572,
"step": 1272
},
{
"epoch": 0.30301768990634753,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.2924749851226807,
"step": 1274
},
{
"epoch": 0.30349338486695404,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.3171639442443848,
"step": 1276
},
{
"epoch": 0.30396907982756055,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.3555333614349365,
"step": 1278
},
{
"epoch": 0.30444477478816706,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.2927653789520264,
"step": 1280
},
{
"epoch": 0.3049204697487736,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.34412682056427,
"step": 1282
},
{
"epoch": 0.30539616470938014,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.3178520202636719,
"step": 1284
},
{
"epoch": 0.30587185966998665,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.278599739074707,
"step": 1286
},
{
"epoch": 0.30634755463059316,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.254746437072754,
"step": 1288
},
{
"epoch": 0.30682324959119966,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.3239991664886475,
"step": 1290
},
{
"epoch": 0.3072989445518062,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.2205564975738525,
"step": 1292
},
{
"epoch": 0.3077746395124127,
"grad_norm": 0.412109375,
"learning_rate": 8e-05,
"loss": 1.301189661026001,
"step": 1294
},
{
"epoch": 0.3082503344730192,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.3148789405822754,
"step": 1296
},
{
"epoch": 0.3087260294336257,
"grad_norm": 0.412109375,
"learning_rate": 8e-05,
"loss": 1.3096203804016113,
"step": 1298
},
{
"epoch": 0.3092017243942322,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.3105592727661133,
"step": 1300
},
{
"epoch": 0.3096774193548387,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.312976360321045,
"step": 1302
},
{
"epoch": 0.31015311431544523,
"grad_norm": 0.412109375,
"learning_rate": 8e-05,
"loss": 1.2987452745437622,
"step": 1304
},
{
"epoch": 0.31062880927605174,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.3321504592895508,
"step": 1306
},
{
"epoch": 0.31110450423665825,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2754004001617432,
"step": 1308
},
{
"epoch": 0.31158019919726476,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.3137989044189453,
"step": 1310
},
{
"epoch": 0.31205589415787127,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.311619520187378,
"step": 1312
},
{
"epoch": 0.3125315891184778,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.3559669256210327,
"step": 1314
},
{
"epoch": 0.3130072840790843,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.3143202066421509,
"step": 1316
},
{
"epoch": 0.3134829790396908,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.27866530418396,
"step": 1318
},
{
"epoch": 0.3139586740002973,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.3592901229858398,
"step": 1320
},
{
"epoch": 0.3144343689609038,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2884161472320557,
"step": 1322
},
{
"epoch": 0.31491006392151033,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.3565433025360107,
"step": 1324
},
{
"epoch": 0.31538575888211684,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.237494945526123,
"step": 1326
},
{
"epoch": 0.31586145384272335,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.2647333145141602,
"step": 1328
},
{
"epoch": 0.31633714880332986,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.303452968597412,
"step": 1330
},
{
"epoch": 0.31681284376393637,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.297559142112732,
"step": 1332
},
{
"epoch": 0.3172885387245429,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.2743000984191895,
"step": 1334
},
{
"epoch": 0.3177642336851494,
"grad_norm": 0.4453125,
"learning_rate": 8e-05,
"loss": 1.3135099411010742,
"step": 1336
},
{
"epoch": 0.3182399286457559,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.3139266967773438,
"step": 1338
},
{
"epoch": 0.3187156236063624,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.2548094987869263,
"step": 1340
},
{
"epoch": 0.3191913185669689,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.324897289276123,
"step": 1342
},
{
"epoch": 0.3196670135275754,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.256618618965149,
"step": 1344
},
{
"epoch": 0.32014270848818194,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.3173911571502686,
"step": 1346
},
{
"epoch": 0.32061840344878845,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.3058103322982788,
"step": 1348
},
{
"epoch": 0.32109409840939496,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.2872593402862549,
"step": 1350
},
{
"epoch": 0.32156979337000147,
"grad_norm": 0.451171875,
"learning_rate": 8e-05,
"loss": 1.3403403759002686,
"step": 1352
},
{
"epoch": 0.322045488330608,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.320298433303833,
"step": 1354
},
{
"epoch": 0.3225211832912145,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2507272958755493,
"step": 1356
},
{
"epoch": 0.322996878251821,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.2136597633361816,
"step": 1358
},
{
"epoch": 0.3234725732124275,
"grad_norm": 0.447265625,
"learning_rate": 8e-05,
"loss": 1.302070140838623,
"step": 1360
},
{
"epoch": 0.323948268173034,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.3372619152069092,
"step": 1362
},
{
"epoch": 0.3244239631336406,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.2919752597808838,
"step": 1364
},
{
"epoch": 0.3248996580942471,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.3035356998443604,
"step": 1366
},
{
"epoch": 0.3253753530548536,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.3196332454681396,
"step": 1368
},
{
"epoch": 0.3258510480154601,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.2436224222183228,
"step": 1370
},
{
"epoch": 0.3263267429760666,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.3428776264190674,
"step": 1372
},
{
"epoch": 0.32680243793667313,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.2375438213348389,
"step": 1374
},
{
"epoch": 0.32727813289727964,
"grad_norm": 0.4609375,
"learning_rate": 8e-05,
"loss": 1.2973229885101318,
"step": 1376
},
{
"epoch": 0.32775382785788615,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.327859878540039,
"step": 1378
},
{
"epoch": 0.32822952281849266,
"grad_norm": 0.47265625,
"learning_rate": 8e-05,
"loss": 1.286755919456482,
"step": 1380
},
{
"epoch": 0.32870521777909917,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.2941248416900635,
"step": 1382
},
{
"epoch": 0.3291809127397057,
"grad_norm": 0.4609375,
"learning_rate": 8e-05,
"loss": 1.304626226425171,
"step": 1384
},
{
"epoch": 0.3296566077003122,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.2754319906234741,
"step": 1386
},
{
"epoch": 0.3301323026609187,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.2561947107315063,
"step": 1388
},
{
"epoch": 0.3306079976215252,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.2895267009735107,
"step": 1390
},
{
"epoch": 0.3310836925821317,
"grad_norm": 0.474609375,
"learning_rate": 8e-05,
"loss": 1.386023759841919,
"step": 1392
},
{
"epoch": 0.3315593875427382,
"grad_norm": 0.466796875,
"learning_rate": 8e-05,
"loss": 1.2892621755599976,
"step": 1394
},
{
"epoch": 0.33203508250334474,
"grad_norm": 0.466796875,
"learning_rate": 8e-05,
"loss": 1.2891567945480347,
"step": 1396
},
{
"epoch": 0.33251077746395125,
"grad_norm": 0.5078125,
"learning_rate": 8e-05,
"loss": 1.322417140007019,
"step": 1398
},
{
"epoch": 0.33298647242455776,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.3004422187805176,
"step": 1400
},
{
"epoch": 0.33346216738516427,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.2988290786743164,
"step": 1402
},
{
"epoch": 0.3339378623457708,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.3143279552459717,
"step": 1404
},
{
"epoch": 0.3344135573063773,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.281175136566162,
"step": 1406
},
{
"epoch": 0.3348892522669838,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.289182424545288,
"step": 1408
},
{
"epoch": 0.3353649472275903,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.2937148809432983,
"step": 1410
},
{
"epoch": 0.3358406421881968,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.2338749170303345,
"step": 1412
},
{
"epoch": 0.3363163371488033,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.2975019216537476,
"step": 1414
},
{
"epoch": 0.33679203210940983,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.2488545179367065,
"step": 1416
},
{
"epoch": 0.33726772707001634,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.289847493171692,
"step": 1418
},
{
"epoch": 0.33774342203062285,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.2936429977416992,
"step": 1420
},
{
"epoch": 0.33821911699122936,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.2761449813842773,
"step": 1422
},
{
"epoch": 0.3386948119518359,
"grad_norm": 0.412109375,
"learning_rate": 8e-05,
"loss": 1.2870736122131348,
"step": 1424
},
{
"epoch": 0.3391705069124424,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.33278489112854,
"step": 1426
},
{
"epoch": 0.3396462018730489,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2804453372955322,
"step": 1428
},
{
"epoch": 0.3401218968336554,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.303015112876892,
"step": 1430
},
{
"epoch": 0.3405975917942619,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.333322286605835,
"step": 1432
},
{
"epoch": 0.3410732867548684,
"grad_norm": 0.447265625,
"learning_rate": 8e-05,
"loss": 1.320211410522461,
"step": 1434
},
{
"epoch": 0.34154898171547493,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.3331108093261719,
"step": 1436
},
{
"epoch": 0.34202467667608144,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.26707923412323,
"step": 1438
},
{
"epoch": 0.34250037163668795,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.3269259929656982,
"step": 1440
},
{
"epoch": 0.34297606659729446,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.3051103353500366,
"step": 1442
},
{
"epoch": 0.34345176155790097,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.307328701019287,
"step": 1444
},
{
"epoch": 0.3439274565185075,
"grad_norm": 0.6171875,
"learning_rate": 8e-05,
"loss": 1.3046774864196777,
"step": 1446
},
{
"epoch": 0.34440315147911404,
"grad_norm": 0.412109375,
"learning_rate": 8e-05,
"loss": 1.3187592029571533,
"step": 1448
},
{
"epoch": 0.34487884643972055,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.289937973022461,
"step": 1450
},
{
"epoch": 0.34535454140032706,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.300656795501709,
"step": 1452
},
{
"epoch": 0.3458302363609336,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.328467607498169,
"step": 1454
},
{
"epoch": 0.3463059313215401,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.3533457517623901,
"step": 1456
},
{
"epoch": 0.3467816262821466,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.2739849090576172,
"step": 1458
},
{
"epoch": 0.3472573212427531,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.3364741802215576,
"step": 1460
},
{
"epoch": 0.3477330162033596,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.2574357986450195,
"step": 1462
},
{
"epoch": 0.3482087111639661,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.3151860237121582,
"step": 1464
},
{
"epoch": 0.34868440612457263,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.3361979722976685,
"step": 1466
},
{
"epoch": 0.34916010108517914,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.3134095668792725,
"step": 1468
},
{
"epoch": 0.34963579604578565,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.2602635622024536,
"step": 1470
},
{
"epoch": 0.35011149100639216,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.2942792177200317,
"step": 1472
},
{
"epoch": 0.35058718596699867,
"grad_norm": 0.4453125,
"learning_rate": 8e-05,
"loss": 1.3020391464233398,
"step": 1474
},
{
"epoch": 0.3510628809276052,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.2818697690963745,
"step": 1476
},
{
"epoch": 0.3515385758882117,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.357285976409912,
"step": 1478
},
{
"epoch": 0.3520142708488182,
"grad_norm": 0.4453125,
"learning_rate": 8e-05,
"loss": 1.256792664527893,
"step": 1480
},
{
"epoch": 0.3524899658094247,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2922112941741943,
"step": 1482
},
{
"epoch": 0.3529656607700312,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.313403606414795,
"step": 1484
},
{
"epoch": 0.35344135573063773,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.3349361419677734,
"step": 1486
},
{
"epoch": 0.35391705069124424,
"grad_norm": 0.38671875,
"learning_rate": 8e-05,
"loss": 1.2362300157546997,
"step": 1488
},
{
"epoch": 0.35439274565185075,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.2810988426208496,
"step": 1490
},
{
"epoch": 0.35486844061245726,
"grad_norm": 0.4765625,
"learning_rate": 8e-05,
"loss": 1.3440229892730713,
"step": 1492
},
{
"epoch": 0.35534413557306377,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.3103101253509521,
"step": 1494
},
{
"epoch": 0.3558198305336703,
"grad_norm": 0.447265625,
"learning_rate": 8e-05,
"loss": 1.2558884620666504,
"step": 1496
},
{
"epoch": 0.3562955254942768,
"grad_norm": 0.447265625,
"learning_rate": 8e-05,
"loss": 1.3156042098999023,
"step": 1498
},
{
"epoch": 0.3567712204548833,
"grad_norm": 0.46484375,
"learning_rate": 8e-05,
"loss": 1.294625997543335,
"step": 1500
},
{
"epoch": 0.3572469154154898,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.2535991668701172,
"step": 1502
},
{
"epoch": 0.3577226103760963,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.281435489654541,
"step": 1504
},
{
"epoch": 0.3581983053367028,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.3105072975158691,
"step": 1506
},
{
"epoch": 0.35867400029730934,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.3389477729797363,
"step": 1508
},
{
"epoch": 0.35914969525791585,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.3460373878479004,
"step": 1510
},
{
"epoch": 0.35962539021852236,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.2376234531402588,
"step": 1512
},
{
"epoch": 0.36010108517912887,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.3217864036560059,
"step": 1514
},
{
"epoch": 0.3605767801397354,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2773277759552002,
"step": 1516
},
{
"epoch": 0.3610524751003419,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2766404151916504,
"step": 1518
},
{
"epoch": 0.3615281700609484,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.2760717868804932,
"step": 1520
},
{
"epoch": 0.3620038650215549,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.3625264167785645,
"step": 1522
},
{
"epoch": 0.3624795599821614,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.247987985610962,
"step": 1524
},
{
"epoch": 0.3629552549427679,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2980639934539795,
"step": 1526
},
{
"epoch": 0.36343094990337443,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.2997593879699707,
"step": 1528
},
{
"epoch": 0.363906644863981,
"grad_norm": 0.384765625,
"learning_rate": 8e-05,
"loss": 1.2603178024291992,
"step": 1530
},
{
"epoch": 0.3643823398245875,
"grad_norm": 0.384765625,
"learning_rate": 8e-05,
"loss": 1.302708625793457,
"step": 1532
},
{
"epoch": 0.364858034785194,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.2671213150024414,
"step": 1534
},
{
"epoch": 0.36533372974580053,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.3167269229888916,
"step": 1536
},
{
"epoch": 0.36580942470640704,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.3100299835205078,
"step": 1538
},
{
"epoch": 0.36628511966701355,
"grad_norm": 0.380859375,
"learning_rate": 8e-05,
"loss": 1.2652174234390259,
"step": 1540
},
{
"epoch": 0.36676081462762006,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.3316433429718018,
"step": 1542
},
{
"epoch": 0.36723650958822657,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.2940750122070312,
"step": 1544
},
{
"epoch": 0.3677122045488331,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.3008698225021362,
"step": 1546
},
{
"epoch": 0.3681878995094396,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.2859610319137573,
"step": 1548
},
{
"epoch": 0.3686635944700461,
"grad_norm": 0.4609375,
"learning_rate": 8e-05,
"loss": 1.2531521320343018,
"step": 1550
},
{
"epoch": 0.3691392894306526,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.2496728897094727,
"step": 1552
},
{
"epoch": 0.3696149843912591,
"grad_norm": 0.462890625,
"learning_rate": 8e-05,
"loss": 1.33748459815979,
"step": 1554
},
{
"epoch": 0.3700906793518656,
"grad_norm": 0.47265625,
"learning_rate": 8e-05,
"loss": 1.2866451740264893,
"step": 1556
},
{
"epoch": 0.37056637431247214,
"grad_norm": 0.46484375,
"learning_rate": 8e-05,
"loss": 1.34792160987854,
"step": 1558
},
{
"epoch": 0.37104206927307865,
"grad_norm": 0.52734375,
"learning_rate": 8e-05,
"loss": 1.2783215045928955,
"step": 1560
},
{
"epoch": 0.37151776423368515,
"grad_norm": 0.50390625,
"learning_rate": 8e-05,
"loss": 1.2765138149261475,
"step": 1562
},
{
"epoch": 0.37199345919429166,
"grad_norm": 0.458984375,
"learning_rate": 8e-05,
"loss": 1.3496522903442383,
"step": 1564
},
{
"epoch": 0.3724691541548982,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.3075356483459473,
"step": 1566
},
{
"epoch": 0.3729448491155047,
"grad_norm": 0.494140625,
"learning_rate": 8e-05,
"loss": 1.2998372316360474,
"step": 1568
},
{
"epoch": 0.3734205440761112,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.2793023586273193,
"step": 1570
},
{
"epoch": 0.3738962390367177,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.2992515563964844,
"step": 1572
},
{
"epoch": 0.3743719339973242,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.2910690307617188,
"step": 1574
},
{
"epoch": 0.3748476289579307,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.2138452529907227,
"step": 1576
},
{
"epoch": 0.37532332391853723,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.2589681148529053,
"step": 1578
},
{
"epoch": 0.37579901887914374,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.3131399154663086,
"step": 1580
},
{
"epoch": 0.37627471383975025,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.2620333433151245,
"step": 1582
},
{
"epoch": 0.37675040880035676,
"grad_norm": 0.4453125,
"learning_rate": 8e-05,
"loss": 1.2692234516143799,
"step": 1584
},
{
"epoch": 0.37722610376096327,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.3276705741882324,
"step": 1586
},
{
"epoch": 0.3777017987215698,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.2581058740615845,
"step": 1588
},
{
"epoch": 0.3781774936821763,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.3049333095550537,
"step": 1590
},
{
"epoch": 0.3786531886427828,
"grad_norm": 0.439453125,
"learning_rate": 8e-05,
"loss": 1.2860021591186523,
"step": 1592
},
{
"epoch": 0.3791288836033893,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.3235461711883545,
"step": 1594
},
{
"epoch": 0.3796045785639958,
"grad_norm": 0.412109375,
"learning_rate": 8e-05,
"loss": 1.2726843357086182,
"step": 1596
},
{
"epoch": 0.38008027352460233,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2600030899047852,
"step": 1598
},
{
"epoch": 0.38055596848520884,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.3035047054290771,
"step": 1600
},
{
"epoch": 0.38103166344581535,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.2810437679290771,
"step": 1602
},
{
"epoch": 0.38150735840642186,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.3053010702133179,
"step": 1604
},
{
"epoch": 0.38198305336702837,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.285233497619629,
"step": 1606
},
{
"epoch": 0.3824587483276349,
"grad_norm": 0.474609375,
"learning_rate": 8e-05,
"loss": 1.328747034072876,
"step": 1608
},
{
"epoch": 0.3829344432882414,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.3264154195785522,
"step": 1610
},
{
"epoch": 0.38341013824884795,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2244741916656494,
"step": 1612
},
{
"epoch": 0.38388583320945446,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.247675895690918,
"step": 1614
},
{
"epoch": 0.384361528170061,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.289712905883789,
"step": 1616
},
{
"epoch": 0.3848372231306675,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.299727439880371,
"step": 1618
},
{
"epoch": 0.385312918091274,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.229569911956787,
"step": 1620
},
{
"epoch": 0.3857886130518805,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.322393774986267,
"step": 1622
},
{
"epoch": 0.386264308012487,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.2661751508712769,
"step": 1624
},
{
"epoch": 0.3867400029730935,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.2912821769714355,
"step": 1626
},
{
"epoch": 0.38721569793370003,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2871348857879639,
"step": 1628
},
{
"epoch": 0.38769139289430654,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2939109802246094,
"step": 1630
},
{
"epoch": 0.38816708785491305,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2797859907150269,
"step": 1632
},
{
"epoch": 0.38864278281551956,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2935690879821777,
"step": 1634
},
{
"epoch": 0.38911847777612607,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.2815215587615967,
"step": 1636
},
{
"epoch": 0.3895941727367326,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2466614246368408,
"step": 1638
},
{
"epoch": 0.3900698676973391,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.3364429473876953,
"step": 1640
},
{
"epoch": 0.3905455626579456,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2810378074645996,
"step": 1642
},
{
"epoch": 0.3910212576185521,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.2879207134246826,
"step": 1644
},
{
"epoch": 0.3914969525791586,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.258134365081787,
"step": 1646
},
{
"epoch": 0.39197264753976513,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.2918128967285156,
"step": 1648
},
{
"epoch": 0.39244834250037164,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.2425835132598877,
"step": 1650
},
{
"epoch": 0.39292403746097815,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.213120698928833,
"step": 1652
},
{
"epoch": 0.39339973242158466,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.2344098091125488,
"step": 1654
},
{
"epoch": 0.39387542738219117,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2660351991653442,
"step": 1656
},
{
"epoch": 0.3943511223427977,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.330662488937378,
"step": 1658
},
{
"epoch": 0.3948268173034042,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2738041877746582,
"step": 1660
},
{
"epoch": 0.3953025122640107,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2888221740722656,
"step": 1662
},
{
"epoch": 0.3957782072246172,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.288313865661621,
"step": 1664
},
{
"epoch": 0.3962539021852237,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.290661096572876,
"step": 1666
},
{
"epoch": 0.3967295971458302,
"grad_norm": 0.380859375,
"learning_rate": 8e-05,
"loss": 1.249962568283081,
"step": 1668
},
{
"epoch": 0.39720529210643674,
"grad_norm": 0.37890625,
"learning_rate": 8e-05,
"loss": 1.2480006217956543,
"step": 1670
},
{
"epoch": 0.39768098706704325,
"grad_norm": 0.36328125,
"learning_rate": 8e-05,
"loss": 1.2179031372070312,
"step": 1672
},
{
"epoch": 0.39815668202764976,
"grad_norm": 0.388671875,
"learning_rate": 8e-05,
"loss": 1.3344948291778564,
"step": 1674
},
{
"epoch": 0.39863237698825627,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2962273359298706,
"step": 1676
},
{
"epoch": 0.3991080719488628,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.266413688659668,
"step": 1678
},
{
"epoch": 0.3995837669094693,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.2850923538208008,
"step": 1680
},
{
"epoch": 0.4000594618700758,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.2746737003326416,
"step": 1682
},
{
"epoch": 0.4005351568306823,
"grad_norm": 0.412109375,
"learning_rate": 8e-05,
"loss": 1.2807002067565918,
"step": 1684
},
{
"epoch": 0.4010108517912888,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.2683579921722412,
"step": 1686
},
{
"epoch": 0.4014865467518953,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.2930378913879395,
"step": 1688
},
{
"epoch": 0.40196224171250183,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.2729506492614746,
"step": 1690
},
{
"epoch": 0.40243793667310834,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.2865461111068726,
"step": 1692
},
{
"epoch": 0.40291363163371485,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.249645709991455,
"step": 1694
},
{
"epoch": 0.4033893265943214,
"grad_norm": 0.3671875,
"learning_rate": 8e-05,
"loss": 1.2383712530136108,
"step": 1696
},
{
"epoch": 0.4038650215549279,
"grad_norm": 0.3828125,
"learning_rate": 8e-05,
"loss": 1.246313452720642,
"step": 1698
},
{
"epoch": 0.40434071651553444,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.2288974523544312,
"step": 1700
},
{
"epoch": 0.40481641147614095,
"grad_norm": 0.38671875,
"learning_rate": 8e-05,
"loss": 1.2907836437225342,
"step": 1702
},
{
"epoch": 0.40529210643674746,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.2730671167373657,
"step": 1704
},
{
"epoch": 0.40576780139735397,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.3130565881729126,
"step": 1706
},
{
"epoch": 0.4062434963579605,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.2681382894515991,
"step": 1708
},
{
"epoch": 0.406719191318567,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.296158790588379,
"step": 1710
},
{
"epoch": 0.4071948862791735,
"grad_norm": 0.3828125,
"learning_rate": 8e-05,
"loss": 1.247192144393921,
"step": 1712
},
{
"epoch": 0.40767058123978,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2639563083648682,
"step": 1714
},
{
"epoch": 0.4081462762003865,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.2656540870666504,
"step": 1716
},
{
"epoch": 0.408621971160993,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.205491542816162,
"step": 1718
},
{
"epoch": 0.40909766612159953,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.277217984199524,
"step": 1720
},
{
"epoch": 0.40957336108220604,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.3079639673233032,
"step": 1722
},
{
"epoch": 0.41004905604281255,
"grad_norm": 0.458984375,
"learning_rate": 8e-05,
"loss": 1.2672646045684814,
"step": 1724
},
{
"epoch": 0.41052475100341906,
"grad_norm": 0.474609375,
"learning_rate": 8e-05,
"loss": 1.2784157991409302,
"step": 1726
},
{
"epoch": 0.4110004459640256,
"grad_norm": 0.484375,
"learning_rate": 8e-05,
"loss": 1.2682194709777832,
"step": 1728
},
{
"epoch": 0.4114761409246321,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.2786941528320312,
"step": 1730
},
{
"epoch": 0.4119518358852386,
"grad_norm": 0.3828125,
"learning_rate": 8e-05,
"loss": 1.281358003616333,
"step": 1732
},
{
"epoch": 0.4124275308458451,
"grad_norm": 0.384765625,
"learning_rate": 8e-05,
"loss": 1.246321678161621,
"step": 1734
},
{
"epoch": 0.4129032258064516,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2259719371795654,
"step": 1736
},
{
"epoch": 0.4133789207670581,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.3222472667694092,
"step": 1738
},
{
"epoch": 0.41385461572766463,
"grad_norm": 0.384765625,
"learning_rate": 8e-05,
"loss": 1.216452956199646,
"step": 1740
},
{
"epoch": 0.41433031068827114,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.3299109935760498,
"step": 1742
},
{
"epoch": 0.41480600564887765,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.250302791595459,
"step": 1744
},
{
"epoch": 0.41528170060948416,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.2744085788726807,
"step": 1746
},
{
"epoch": 0.41575739557009067,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2700858116149902,
"step": 1748
},
{
"epoch": 0.4162330905306972,
"grad_norm": 0.38671875,
"learning_rate": 8e-05,
"loss": 1.2627267837524414,
"step": 1750
},
{
"epoch": 0.4167087854913037,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.269378423690796,
"step": 1752
},
{
"epoch": 0.4171844804519102,
"grad_norm": 0.384765625,
"learning_rate": 8e-05,
"loss": 1.3320337533950806,
"step": 1754
},
{
"epoch": 0.4176601754125167,
"grad_norm": 0.380859375,
"learning_rate": 8e-05,
"loss": 1.2717125415802002,
"step": 1756
},
{
"epoch": 0.4181358703731232,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2660107612609863,
"step": 1758
},
{
"epoch": 0.41861156533372973,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2718021869659424,
"step": 1760
},
{
"epoch": 0.41908726029433624,
"grad_norm": 0.38671875,
"learning_rate": 8e-05,
"loss": 1.2778680324554443,
"step": 1762
},
{
"epoch": 0.41956295525494275,
"grad_norm": 0.3828125,
"learning_rate": 8e-05,
"loss": 1.247718334197998,
"step": 1764
},
{
"epoch": 0.42003865021554926,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.2594034671783447,
"step": 1766
},
{
"epoch": 0.42051434517615577,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.2796156406402588,
"step": 1768
},
{
"epoch": 0.4209900401367623,
"grad_norm": 0.388671875,
"learning_rate": 8e-05,
"loss": 1.2971086502075195,
"step": 1770
},
{
"epoch": 0.4214657350973688,
"grad_norm": 0.431640625,
"learning_rate": 8e-05,
"loss": 1.2875339984893799,
"step": 1772
},
{
"epoch": 0.4219414300579753,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.2802563905715942,
"step": 1774
},
{
"epoch": 0.4224171250185818,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.297211766242981,
"step": 1776
},
{
"epoch": 0.4228928199791884,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.1946825981140137,
"step": 1778
},
{
"epoch": 0.4233685149397949,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.256436824798584,
"step": 1780
},
{
"epoch": 0.4238442099004014,
"grad_norm": 0.380859375,
"learning_rate": 8e-05,
"loss": 1.2787179946899414,
"step": 1782
},
{
"epoch": 0.4243199048610079,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.2537882328033447,
"step": 1784
},
{
"epoch": 0.4247955998216144,
"grad_norm": 0.380859375,
"learning_rate": 8e-05,
"loss": 1.2897108793258667,
"step": 1786
},
{
"epoch": 0.4252712947822209,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2501720190048218,
"step": 1788
},
{
"epoch": 0.42574698974282743,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.2753134965896606,
"step": 1790
},
{
"epoch": 0.42622268470343394,
"grad_norm": 0.46875,
"learning_rate": 8e-05,
"loss": 1.2809417247772217,
"step": 1792
},
{
"epoch": 0.42669837966404045,
"grad_norm": 0.51171875,
"learning_rate": 8e-05,
"loss": 1.2722747325897217,
"step": 1794
},
{
"epoch": 0.42717407462464696,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.294141411781311,
"step": 1796
},
{
"epoch": 0.42764976958525347,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.2701992988586426,
"step": 1798
},
{
"epoch": 0.42812546454586,
"grad_norm": 0.44140625,
"learning_rate": 8e-05,
"loss": 1.2379639148712158,
"step": 1800
},
{
"epoch": 0.4286011595064665,
"grad_norm": 0.443359375,
"learning_rate": 8e-05,
"loss": 1.262845516204834,
"step": 1802
},
{
"epoch": 0.429076854467073,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.213247299194336,
"step": 1804
},
{
"epoch": 0.4295525494276795,
"grad_norm": 0.421875,
"learning_rate": 8e-05,
"loss": 1.270270824432373,
"step": 1806
},
{
"epoch": 0.430028244388286,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.1981269121170044,
"step": 1808
},
{
"epoch": 0.43050393934889253,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.2772140502929688,
"step": 1810
},
{
"epoch": 0.43097963430949904,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.2868304252624512,
"step": 1812
},
{
"epoch": 0.43145532927010555,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2759490013122559,
"step": 1814
},
{
"epoch": 0.43193102423071206,
"grad_norm": 0.4140625,
"learning_rate": 8e-05,
"loss": 1.292006015777588,
"step": 1816
},
{
"epoch": 0.43240671919131857,
"grad_norm": 0.435546875,
"learning_rate": 8e-05,
"loss": 1.2290836572647095,
"step": 1818
},
{
"epoch": 0.4328824141519251,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2799795866012573,
"step": 1820
},
{
"epoch": 0.4333581091125316,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2700903415679932,
"step": 1822
},
{
"epoch": 0.4338338040731381,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.276972770690918,
"step": 1824
},
{
"epoch": 0.4343094990337446,
"grad_norm": 0.376953125,
"learning_rate": 8e-05,
"loss": 1.2546138763427734,
"step": 1826
},
{
"epoch": 0.4347851939943511,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.2350144386291504,
"step": 1828
},
{
"epoch": 0.4352608889549576,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.255623459815979,
"step": 1830
},
{
"epoch": 0.43573658391556414,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.3046503067016602,
"step": 1832
},
{
"epoch": 0.43621227887617064,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.2888526916503906,
"step": 1834
},
{
"epoch": 0.43668797383677715,
"grad_norm": 0.384765625,
"learning_rate": 8e-05,
"loss": 1.2555067539215088,
"step": 1836
},
{
"epoch": 0.43716366879738366,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.3039183616638184,
"step": 1838
},
{
"epoch": 0.4376393637579902,
"grad_norm": 0.3828125,
"learning_rate": 8e-05,
"loss": 1.2199631929397583,
"step": 1840
},
{
"epoch": 0.4381150587185967,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.2994630336761475,
"step": 1842
},
{
"epoch": 0.4385907536792032,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.241573452949524,
"step": 1844
},
{
"epoch": 0.4390664486398097,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2570286989212036,
"step": 1846
},
{
"epoch": 0.4395421436004162,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2594881057739258,
"step": 1848
},
{
"epoch": 0.4400178385610227,
"grad_norm": 0.423828125,
"learning_rate": 8e-05,
"loss": 1.2928112745285034,
"step": 1850
},
{
"epoch": 0.44049353352162923,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.2726936340332031,
"step": 1852
},
{
"epoch": 0.44096922848223574,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.32316255569458,
"step": 1854
},
{
"epoch": 0.44144492344284225,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2438604831695557,
"step": 1856
},
{
"epoch": 0.44192061840344876,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.293677568435669,
"step": 1858
},
{
"epoch": 0.4423963133640553,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.3002068996429443,
"step": 1860
},
{
"epoch": 0.44287200832466184,
"grad_norm": 0.45703125,
"learning_rate": 8e-05,
"loss": 1.294407844543457,
"step": 1862
},
{
"epoch": 0.44334770328526835,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.242573857307434,
"step": 1864
},
{
"epoch": 0.44382339824587486,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2922019958496094,
"step": 1866
},
{
"epoch": 0.44429909320648137,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.2213215827941895,
"step": 1868
},
{
"epoch": 0.4447747881670879,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2707006931304932,
"step": 1870
},
{
"epoch": 0.4452504831276944,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.2314999103546143,
"step": 1872
},
{
"epoch": 0.4457261780883009,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.3218889236450195,
"step": 1874
},
{
"epoch": 0.4462018730489074,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2159051895141602,
"step": 1876
},
{
"epoch": 0.4466775680095139,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.3076913356781006,
"step": 1878
},
{
"epoch": 0.4471532629701204,
"grad_norm": 0.37890625,
"learning_rate": 8e-05,
"loss": 1.2779921293258667,
"step": 1880
},
{
"epoch": 0.44762895793072693,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.2604446411132812,
"step": 1882
},
{
"epoch": 0.44810465289133344,
"grad_norm": 0.376953125,
"learning_rate": 8e-05,
"loss": 1.2382320165634155,
"step": 1884
},
{
"epoch": 0.44858034785193995,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.3830101490020752,
"step": 1886
},
{
"epoch": 0.44905604281254646,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.228447675704956,
"step": 1888
},
{
"epoch": 0.449531737773153,
"grad_norm": 0.43359375,
"learning_rate": 8e-05,
"loss": 1.2446924448013306,
"step": 1890
},
{
"epoch": 0.4500074327337595,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.2444430589675903,
"step": 1892
},
{
"epoch": 0.450483127694366,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.1985334157943726,
"step": 1894
},
{
"epoch": 0.4509588226549725,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2600021362304688,
"step": 1896
},
{
"epoch": 0.451434517615579,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.2708806991577148,
"step": 1898
},
{
"epoch": 0.4519102125761855,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.273937702178955,
"step": 1900
},
{
"epoch": 0.45238590753679203,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2232747077941895,
"step": 1902
},
{
"epoch": 0.45286160249739854,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.2665836811065674,
"step": 1904
},
{
"epoch": 0.45333729745800505,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.2973511219024658,
"step": 1906
},
{
"epoch": 0.45381299241861156,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.239840030670166,
"step": 1908
},
{
"epoch": 0.45428868737921807,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2163124084472656,
"step": 1910
},
{
"epoch": 0.4547643823398246,
"grad_norm": 0.3828125,
"learning_rate": 8e-05,
"loss": 1.245084285736084,
"step": 1912
},
{
"epoch": 0.4552400773004311,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.3053221702575684,
"step": 1914
},
{
"epoch": 0.4557157722610376,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2788605690002441,
"step": 1916
},
{
"epoch": 0.4561914672216441,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.2649834156036377,
"step": 1918
},
{
"epoch": 0.4566671621822506,
"grad_norm": 0.38671875,
"learning_rate": 8e-05,
"loss": 1.2921392917633057,
"step": 1920
},
{
"epoch": 0.45714285714285713,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.2440087795257568,
"step": 1922
},
{
"epoch": 0.45761855210346364,
"grad_norm": 0.36328125,
"learning_rate": 8e-05,
"loss": 1.2340590953826904,
"step": 1924
},
{
"epoch": 0.45809424706407015,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.2697665691375732,
"step": 1926
},
{
"epoch": 0.45856994202467666,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2789232730865479,
"step": 1928
},
{
"epoch": 0.45904563698528317,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.262975811958313,
"step": 1930
},
{
"epoch": 0.4595213319458897,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.286508321762085,
"step": 1932
},
{
"epoch": 0.4599970269064962,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2848749160766602,
"step": 1934
},
{
"epoch": 0.4604727218671027,
"grad_norm": 0.4296875,
"learning_rate": 8e-05,
"loss": 1.253462314605713,
"step": 1936
},
{
"epoch": 0.4609484168277092,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2408068180084229,
"step": 1938
},
{
"epoch": 0.4614241117883157,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.2684673070907593,
"step": 1940
},
{
"epoch": 0.4618998067489222,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.2076165676116943,
"step": 1942
},
{
"epoch": 0.4623755017095288,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.2525750398635864,
"step": 1944
},
{
"epoch": 0.4628511966701353,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.2482715845108032,
"step": 1946
},
{
"epoch": 0.4633268916307418,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2954301834106445,
"step": 1948
},
{
"epoch": 0.4638025865913483,
"grad_norm": 0.4375,
"learning_rate": 8e-05,
"loss": 1.2526676654815674,
"step": 1950
},
{
"epoch": 0.46427828155195483,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.270956039428711,
"step": 1952
},
{
"epoch": 0.46475397651256134,
"grad_norm": 0.40234375,
"learning_rate": 8e-05,
"loss": 1.2305779457092285,
"step": 1954
},
{
"epoch": 0.46522967147316785,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.3026628494262695,
"step": 1956
},
{
"epoch": 0.46570536643377436,
"grad_norm": 0.42578125,
"learning_rate": 8e-05,
"loss": 1.276360273361206,
"step": 1958
},
{
"epoch": 0.46618106139438087,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2271491289138794,
"step": 1960
},
{
"epoch": 0.4666567563549874,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.27445650100708,
"step": 1962
},
{
"epoch": 0.4671324513155939,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2661042213439941,
"step": 1964
},
{
"epoch": 0.4676081462762004,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.2653608322143555,
"step": 1966
},
{
"epoch": 0.4680838412368069,
"grad_norm": 0.388671875,
"learning_rate": 8e-05,
"loss": 1.2979223728179932,
"step": 1968
},
{
"epoch": 0.4685595361974134,
"grad_norm": 0.376953125,
"learning_rate": 8e-05,
"loss": 1.2312049865722656,
"step": 1970
},
{
"epoch": 0.4690352311580199,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.3057024478912354,
"step": 1972
},
{
"epoch": 0.46951092611862644,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.2951257228851318,
"step": 1974
},
{
"epoch": 0.46998662107923295,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.2718441486358643,
"step": 1976
},
{
"epoch": 0.47046231603983946,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2305831909179688,
"step": 1978
},
{
"epoch": 0.47093801100044597,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.2023491859436035,
"step": 1980
},
{
"epoch": 0.4714137059610525,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.219580888748169,
"step": 1982
},
{
"epoch": 0.471889400921659,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.247983455657959,
"step": 1984
},
{
"epoch": 0.4723650958822655,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2529908418655396,
"step": 1986
},
{
"epoch": 0.472840790842872,
"grad_norm": 0.38671875,
"learning_rate": 8e-05,
"loss": 1.2776696681976318,
"step": 1988
},
{
"epoch": 0.4733164858034785,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.249483585357666,
"step": 1990
},
{
"epoch": 0.473792180764085,
"grad_norm": 0.412109375,
"learning_rate": 8e-05,
"loss": 1.3180161714553833,
"step": 1992
},
{
"epoch": 0.47426787572469153,
"grad_norm": 0.36328125,
"learning_rate": 8e-05,
"loss": 1.2910526990890503,
"step": 1994
},
{
"epoch": 0.47474357068529804,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.2458434104919434,
"step": 1996
},
{
"epoch": 0.47521926564590455,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.3033870458602905,
"step": 1998
},
{
"epoch": 0.47569496060651106,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2500510215759277,
"step": 2000
},
{
"epoch": 0.4761706555671176,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2625623941421509,
"step": 2002
},
{
"epoch": 0.4766463505277241,
"grad_norm": 0.384765625,
"learning_rate": 8e-05,
"loss": 1.2688162326812744,
"step": 2004
},
{
"epoch": 0.4771220454883306,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.2744543552398682,
"step": 2006
},
{
"epoch": 0.4775977404489371,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.28806471824646,
"step": 2008
},
{
"epoch": 0.4780734354095436,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.2513093948364258,
"step": 2010
},
{
"epoch": 0.4785491303701501,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2578754425048828,
"step": 2012
},
{
"epoch": 0.47902482533075663,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2690682411193848,
"step": 2014
},
{
"epoch": 0.47950052029136314,
"grad_norm": 0.3828125,
"learning_rate": 8e-05,
"loss": 1.244710922241211,
"step": 2016
},
{
"epoch": 0.47997621525196965,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2703763246536255,
"step": 2018
},
{
"epoch": 0.48045191021257616,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.289364218711853,
"step": 2020
},
{
"epoch": 0.48092760517318267,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.2618646621704102,
"step": 2022
},
{
"epoch": 0.4814033001337892,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.2179932594299316,
"step": 2024
},
{
"epoch": 0.48187899509439575,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2760300636291504,
"step": 2026
},
{
"epoch": 0.48235469005500226,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2909011840820312,
"step": 2028
},
{
"epoch": 0.48283038501560877,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.2532756328582764,
"step": 2030
},
{
"epoch": 0.4833060799762153,
"grad_norm": 0.37890625,
"learning_rate": 8e-05,
"loss": 1.2610164880752563,
"step": 2032
},
{
"epoch": 0.4837817749368218,
"grad_norm": 0.376953125,
"learning_rate": 8e-05,
"loss": 1.2327613830566406,
"step": 2034
},
{
"epoch": 0.4842574698974283,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.2339394092559814,
"step": 2036
},
{
"epoch": 0.4847331648580348,
"grad_norm": 0.3828125,
"learning_rate": 8e-05,
"loss": 1.2110052108764648,
"step": 2038
},
{
"epoch": 0.4852088598186413,
"grad_norm": 0.3671875,
"learning_rate": 8e-05,
"loss": 1.2191238403320312,
"step": 2040
},
{
"epoch": 0.4856845547792478,
"grad_norm": 0.37109375,
"learning_rate": 8e-05,
"loss": 1.2192617654800415,
"step": 2042
},
{
"epoch": 0.48616024973985433,
"grad_norm": 0.380859375,
"learning_rate": 8e-05,
"loss": 1.2636759281158447,
"step": 2044
},
{
"epoch": 0.48663594470046084,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.207831621170044,
"step": 2046
},
{
"epoch": 0.48711163966106735,
"grad_norm": 0.419921875,
"learning_rate": 8e-05,
"loss": 1.1997129917144775,
"step": 2048
},
{
"epoch": 0.48758733462167386,
"grad_norm": 0.455078125,
"learning_rate": 8e-05,
"loss": 1.2564668655395508,
"step": 2050
},
{
"epoch": 0.48806302958228037,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.2735317945480347,
"step": 2052
},
{
"epoch": 0.4885387245428869,
"grad_norm": 0.427734375,
"learning_rate": 8e-05,
"loss": 1.2732312679290771,
"step": 2054
},
{
"epoch": 0.4890144195034934,
"grad_norm": 0.408203125,
"learning_rate": 8e-05,
"loss": 1.2548601627349854,
"step": 2056
},
{
"epoch": 0.4894901144640999,
"grad_norm": 0.396484375,
"learning_rate": 8e-05,
"loss": 1.2576682567596436,
"step": 2058
},
{
"epoch": 0.4899658094247064,
"grad_norm": 0.373046875,
"learning_rate": 8e-05,
"loss": 1.2264012098312378,
"step": 2060
},
{
"epoch": 0.4904415043853129,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.2854325771331787,
"step": 2062
},
{
"epoch": 0.49091719934591943,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.3236126899719238,
"step": 2064
},
{
"epoch": 0.49139289430652594,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.2489556074142456,
"step": 2066
},
{
"epoch": 0.49186858926713245,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.2574775218963623,
"step": 2068
},
{
"epoch": 0.49234428422773896,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2095019817352295,
"step": 2070
},
{
"epoch": 0.49281997918834547,
"grad_norm": 0.36328125,
"learning_rate": 8e-05,
"loss": 1.2634193897247314,
"step": 2072
},
{
"epoch": 0.493295674148952,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.2667688131332397,
"step": 2074
},
{
"epoch": 0.4937713691095585,
"grad_norm": 0.37890625,
"learning_rate": 8e-05,
"loss": 1.2418756484985352,
"step": 2076
},
{
"epoch": 0.494247064070165,
"grad_norm": 0.390625,
"learning_rate": 8e-05,
"loss": 1.2592451572418213,
"step": 2078
},
{
"epoch": 0.4947227590307715,
"grad_norm": 0.39453125,
"learning_rate": 8e-05,
"loss": 1.2803057432174683,
"step": 2080
},
{
"epoch": 0.495198453991378,
"grad_norm": 0.44921875,
"learning_rate": 8e-05,
"loss": 1.2541866302490234,
"step": 2082
},
{
"epoch": 0.49567414895198453,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2359161376953125,
"step": 2084
},
{
"epoch": 0.49614984391259104,
"grad_norm": 0.41015625,
"learning_rate": 8e-05,
"loss": 1.2950963973999023,
"step": 2086
},
{
"epoch": 0.49662553887319755,
"grad_norm": 0.400390625,
"learning_rate": 8e-05,
"loss": 1.283148169517517,
"step": 2088
},
{
"epoch": 0.49710123383380406,
"grad_norm": 0.416015625,
"learning_rate": 8e-05,
"loss": 1.2806365489959717,
"step": 2090
},
{
"epoch": 0.49757692879441057,
"grad_norm": 0.404296875,
"learning_rate": 8e-05,
"loss": 1.21940279006958,
"step": 2092
},
{
"epoch": 0.4980526237550171,
"grad_norm": 0.41796875,
"learning_rate": 8e-05,
"loss": 1.243825912475586,
"step": 2094
},
{
"epoch": 0.4985283187156236,
"grad_norm": 0.392578125,
"learning_rate": 8e-05,
"loss": 1.271630048751831,
"step": 2096
},
{
"epoch": 0.4990040136762301,
"grad_norm": 0.38671875,
"learning_rate": 8e-05,
"loss": 1.2829158306121826,
"step": 2098
},
{
"epoch": 0.4994797086368366,
"grad_norm": 0.40625,
"learning_rate": 8e-05,
"loss": 1.244653582572937,
"step": 2100
},
{
"epoch": 0.4999554035974431,
"grad_norm": 0.3984375,
"learning_rate": 8e-05,
"loss": 1.2149741649627686,
"step": 2102
}
],
"logging_steps": 2,
"max_steps": 4205,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 1051,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8.402817806420148e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}