gsmyrnis's picture
End of training
78fc757 verified
raw
history blame
43.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 249,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012048192771084338,
"grad_norm": 6.947944879111486,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.1152,
"step": 1
},
{
"epoch": 0.024096385542168676,
"grad_norm": 6.551895316152613,
"learning_rate": 8.000000000000001e-07,
"loss": 1.0964,
"step": 2
},
{
"epoch": 0.03614457831325301,
"grad_norm": 6.846850714143195,
"learning_rate": 1.2000000000000002e-06,
"loss": 1.1132,
"step": 3
},
{
"epoch": 0.04819277108433735,
"grad_norm": 6.73500827774856,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.1177,
"step": 4
},
{
"epoch": 0.060240963855421686,
"grad_norm": 6.486042838258102,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.1165,
"step": 5
},
{
"epoch": 0.07228915662650602,
"grad_norm": 5.080164944992832,
"learning_rate": 2.4000000000000003e-06,
"loss": 1.0333,
"step": 6
},
{
"epoch": 0.08433734939759036,
"grad_norm": 4.8162640470965545,
"learning_rate": 2.8000000000000003e-06,
"loss": 1.0607,
"step": 7
},
{
"epoch": 0.0963855421686747,
"grad_norm": 2.9636266881255633,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.995,
"step": 8
},
{
"epoch": 0.10843373493975904,
"grad_norm": 2.9149441840060883,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.9953,
"step": 9
},
{
"epoch": 0.12048192771084337,
"grad_norm": 2.5104086655988858,
"learning_rate": 4.000000000000001e-06,
"loss": 0.9657,
"step": 10
},
{
"epoch": 0.13253012048192772,
"grad_norm": 3.3748794057111042,
"learning_rate": 4.4e-06,
"loss": 0.9279,
"step": 11
},
{
"epoch": 0.14457831325301204,
"grad_norm": 3.739579521016211,
"learning_rate": 4.800000000000001e-06,
"loss": 0.9651,
"step": 12
},
{
"epoch": 0.1566265060240964,
"grad_norm": 3.3881771742497793,
"learning_rate": 5.2e-06,
"loss": 0.945,
"step": 13
},
{
"epoch": 0.1686746987951807,
"grad_norm": 2.710732348285535,
"learning_rate": 5.600000000000001e-06,
"loss": 0.9118,
"step": 14
},
{
"epoch": 0.18072289156626506,
"grad_norm": 2.5647590385181345,
"learning_rate": 6e-06,
"loss": 0.8692,
"step": 15
},
{
"epoch": 0.1927710843373494,
"grad_norm": 2.4867313006793017,
"learning_rate": 6.4000000000000006e-06,
"loss": 0.8708,
"step": 16
},
{
"epoch": 0.20481927710843373,
"grad_norm": 2.1051348582551803,
"learning_rate": 6.800000000000001e-06,
"loss": 0.8491,
"step": 17
},
{
"epoch": 0.21686746987951808,
"grad_norm": 1.612401197421157,
"learning_rate": 7.2000000000000005e-06,
"loss": 0.8337,
"step": 18
},
{
"epoch": 0.2289156626506024,
"grad_norm": 1.3293177079518312,
"learning_rate": 7.600000000000001e-06,
"loss": 0.835,
"step": 19
},
{
"epoch": 0.24096385542168675,
"grad_norm": 1.5157822774844878,
"learning_rate": 8.000000000000001e-06,
"loss": 0.8007,
"step": 20
},
{
"epoch": 0.25301204819277107,
"grad_norm": 1.737006171655161,
"learning_rate": 8.400000000000001e-06,
"loss": 0.8012,
"step": 21
},
{
"epoch": 0.26506024096385544,
"grad_norm": 1.500594706792283,
"learning_rate": 8.8e-06,
"loss": 0.8001,
"step": 22
},
{
"epoch": 0.27710843373493976,
"grad_norm": 1.1039643208102183,
"learning_rate": 9.200000000000002e-06,
"loss": 0.7822,
"step": 23
},
{
"epoch": 0.2891566265060241,
"grad_norm": 1.0368896326465078,
"learning_rate": 9.600000000000001e-06,
"loss": 0.793,
"step": 24
},
{
"epoch": 0.30120481927710846,
"grad_norm": 1.218355881230325,
"learning_rate": 1e-05,
"loss": 0.7781,
"step": 25
},
{
"epoch": 0.3132530120481928,
"grad_norm": 1.038423389608468,
"learning_rate": 9.999508258797876e-06,
"loss": 0.7701,
"step": 26
},
{
"epoch": 0.3253012048192771,
"grad_norm": 0.9316952575939548,
"learning_rate": 9.998033131915266e-06,
"loss": 0.7603,
"step": 27
},
{
"epoch": 0.3373493975903614,
"grad_norm": 0.9000603093167511,
"learning_rate": 9.995574909504434e-06,
"loss": 0.741,
"step": 28
},
{
"epoch": 0.3493975903614458,
"grad_norm": 0.930556207735138,
"learning_rate": 9.992134075089085e-06,
"loss": 0.7611,
"step": 29
},
{
"epoch": 0.3614457831325301,
"grad_norm": 0.8969974980816755,
"learning_rate": 9.987711305469232e-06,
"loss": 0.7476,
"step": 30
},
{
"epoch": 0.37349397590361444,
"grad_norm": 0.8890052593019384,
"learning_rate": 9.982307470588097e-06,
"loss": 0.7457,
"step": 31
},
{
"epoch": 0.3855421686746988,
"grad_norm": 0.820863872004277,
"learning_rate": 9.975923633360985e-06,
"loss": 0.7755,
"step": 32
},
{
"epoch": 0.39759036144578314,
"grad_norm": 0.9969711327635771,
"learning_rate": 9.968561049466214e-06,
"loss": 0.7392,
"step": 33
},
{
"epoch": 0.40963855421686746,
"grad_norm": 0.7953930725873727,
"learning_rate": 9.960221167098124e-06,
"loss": 0.7249,
"step": 34
},
{
"epoch": 0.42168674698795183,
"grad_norm": 0.8098618143284958,
"learning_rate": 9.950905626682229e-06,
"loss": 0.727,
"step": 35
},
{
"epoch": 0.43373493975903615,
"grad_norm": 0.9495875679755755,
"learning_rate": 9.940616260552545e-06,
"loss": 0.7462,
"step": 36
},
{
"epoch": 0.4457831325301205,
"grad_norm": 0.8278336434334101,
"learning_rate": 9.92935509259118e-06,
"loss": 0.7159,
"step": 37
},
{
"epoch": 0.4578313253012048,
"grad_norm": 0.9212979365231454,
"learning_rate": 9.917124337830242e-06,
"loss": 0.7421,
"step": 38
},
{
"epoch": 0.46987951807228917,
"grad_norm": 0.7883588253738649,
"learning_rate": 9.903926402016153e-06,
"loss": 0.7394,
"step": 39
},
{
"epoch": 0.4819277108433735,
"grad_norm": 0.8135336025707903,
"learning_rate": 9.889763881136439e-06,
"loss": 0.7407,
"step": 40
},
{
"epoch": 0.4939759036144578,
"grad_norm": 0.7284360537696872,
"learning_rate": 9.874639560909118e-06,
"loss": 0.723,
"step": 41
},
{
"epoch": 0.5060240963855421,
"grad_norm": 0.6886889463442112,
"learning_rate": 9.858556416234755e-06,
"loss": 0.7055,
"step": 42
},
{
"epoch": 0.5180722891566265,
"grad_norm": 0.7199574327858913,
"learning_rate": 9.841517610611309e-06,
"loss": 0.712,
"step": 43
},
{
"epoch": 0.5301204819277109,
"grad_norm": 0.6147988317749675,
"learning_rate": 9.82352649551188e-06,
"loss": 0.7027,
"step": 44
},
{
"epoch": 0.5421686746987951,
"grad_norm": 0.6882015749480584,
"learning_rate": 9.804586609725499e-06,
"loss": 0.7121,
"step": 45
},
{
"epoch": 0.5542168674698795,
"grad_norm": 0.7280391155676497,
"learning_rate": 9.784701678661045e-06,
"loss": 0.716,
"step": 46
},
{
"epoch": 0.5662650602409639,
"grad_norm": 0.7124213849751071,
"learning_rate": 9.763875613614482e-06,
"loss": 0.722,
"step": 47
},
{
"epoch": 0.5783132530120482,
"grad_norm": 0.6593949739833803,
"learning_rate": 9.742112510999516e-06,
"loss": 0.7156,
"step": 48
},
{
"epoch": 0.5903614457831325,
"grad_norm": 0.7348578544816223,
"learning_rate": 9.719416651541839e-06,
"loss": 0.7048,
"step": 49
},
{
"epoch": 0.6024096385542169,
"grad_norm": 0.594788013806163,
"learning_rate": 9.69579249943714e-06,
"loss": 0.7199,
"step": 50
},
{
"epoch": 0.6144578313253012,
"grad_norm": 0.7714227830284002,
"learning_rate": 9.671244701472999e-06,
"loss": 0.7161,
"step": 51
},
{
"epoch": 0.6265060240963856,
"grad_norm": 0.7134932535970153,
"learning_rate": 9.645778086114892e-06,
"loss": 0.7172,
"step": 52
},
{
"epoch": 0.6385542168674698,
"grad_norm": 0.6348354665227139,
"learning_rate": 9.619397662556434e-06,
"loss": 0.7122,
"step": 53
},
{
"epoch": 0.6506024096385542,
"grad_norm": 0.6536014485282127,
"learning_rate": 9.592108619734107e-06,
"loss": 0.7228,
"step": 54
},
{
"epoch": 0.6626506024096386,
"grad_norm": 0.6639976309067293,
"learning_rate": 9.563916325306595e-06,
"loss": 0.7039,
"step": 55
},
{
"epoch": 0.6746987951807228,
"grad_norm": 0.6055507064587089,
"learning_rate": 9.534826324599002e-06,
"loss": 0.7009,
"step": 56
},
{
"epoch": 0.6867469879518072,
"grad_norm": 0.7156208118389876,
"learning_rate": 9.504844339512096e-06,
"loss": 0.7112,
"step": 57
},
{
"epoch": 0.6987951807228916,
"grad_norm": 0.6794191467333306,
"learning_rate": 9.473976267396831e-06,
"loss": 0.7054,
"step": 58
},
{
"epoch": 0.7108433734939759,
"grad_norm": 0.6294077710372372,
"learning_rate": 9.442228179894362e-06,
"loss": 0.688,
"step": 59
},
{
"epoch": 0.7228915662650602,
"grad_norm": 0.7964098018273663,
"learning_rate": 9.409606321741776e-06,
"loss": 0.7157,
"step": 60
},
{
"epoch": 0.7349397590361446,
"grad_norm": 0.761322211412714,
"learning_rate": 9.376117109543769e-06,
"loss": 0.7015,
"step": 61
},
{
"epoch": 0.7469879518072289,
"grad_norm": 0.6726658910004847,
"learning_rate": 9.341767130510529e-06,
"loss": 0.7093,
"step": 62
},
{
"epoch": 0.7590361445783133,
"grad_norm": 0.7082226196205085,
"learning_rate": 9.306563141162046e-06,
"loss": 0.7068,
"step": 63
},
{
"epoch": 0.7710843373493976,
"grad_norm": 0.7585930321127647,
"learning_rate": 9.270512065999139e-06,
"loss": 0.7223,
"step": 64
},
{
"epoch": 0.7831325301204819,
"grad_norm": 0.6610590499726324,
"learning_rate": 9.233620996141421e-06,
"loss": 0.6997,
"step": 65
},
{
"epoch": 0.7951807228915663,
"grad_norm": 0.6097126115460089,
"learning_rate": 9.195897187932513e-06,
"loss": 0.688,
"step": 66
},
{
"epoch": 0.8072289156626506,
"grad_norm": 0.8193590896973392,
"learning_rate": 9.157348061512728e-06,
"loss": 0.6937,
"step": 67
},
{
"epoch": 0.8192771084337349,
"grad_norm": 0.6636823955768107,
"learning_rate": 9.117981199359575e-06,
"loss": 0.7165,
"step": 68
},
{
"epoch": 0.8313253012048193,
"grad_norm": 0.6320173996309013,
"learning_rate": 9.077804344796302e-06,
"loss": 0.7119,
"step": 69
},
{
"epoch": 0.8433734939759037,
"grad_norm": 0.6144715713587066,
"learning_rate": 9.036825400468814e-06,
"loss": 0.6931,
"step": 70
},
{
"epoch": 0.8554216867469879,
"grad_norm": 0.7395636253139917,
"learning_rate": 8.995052426791247e-06,
"loss": 0.6875,
"step": 71
},
{
"epoch": 0.8674698795180723,
"grad_norm": 0.5930149191622746,
"learning_rate": 8.952493640360518e-06,
"loss": 0.6937,
"step": 72
},
{
"epoch": 0.8795180722891566,
"grad_norm": 0.6740822123365926,
"learning_rate": 8.90915741234015e-06,
"loss": 0.6956,
"step": 73
},
{
"epoch": 0.891566265060241,
"grad_norm": 0.6734900730110069,
"learning_rate": 8.865052266813686e-06,
"loss": 0.6908,
"step": 74
},
{
"epoch": 0.9036144578313253,
"grad_norm": 0.6324954721691614,
"learning_rate": 8.820186879108038e-06,
"loss": 0.6879,
"step": 75
},
{
"epoch": 0.9156626506024096,
"grad_norm": 0.5728199230507313,
"learning_rate": 8.77457007408708e-06,
"loss": 0.6805,
"step": 76
},
{
"epoch": 0.927710843373494,
"grad_norm": 0.624518773096375,
"learning_rate": 8.728210824415829e-06,
"loss": 0.7028,
"step": 77
},
{
"epoch": 0.9397590361445783,
"grad_norm": 0.71821618407165,
"learning_rate": 8.681118248795548e-06,
"loss": 0.7087,
"step": 78
},
{
"epoch": 0.9518072289156626,
"grad_norm": 0.5810521850331176,
"learning_rate": 8.633301610170136e-06,
"loss": 0.6973,
"step": 79
},
{
"epoch": 0.963855421686747,
"grad_norm": 0.520059051210702,
"learning_rate": 8.584770313904138e-06,
"loss": 0.6891,
"step": 80
},
{
"epoch": 0.9759036144578314,
"grad_norm": 0.6165035125857066,
"learning_rate": 8.535533905932739e-06,
"loss": 0.6875,
"step": 81
},
{
"epoch": 0.9879518072289156,
"grad_norm": 0.6827006515832174,
"learning_rate": 8.485602070884118e-06,
"loss": 0.7065,
"step": 82
},
{
"epoch": 1.0,
"grad_norm": 0.6351337582735852,
"learning_rate": 8.43498463017451e-06,
"loss": 0.6899,
"step": 83
},
{
"epoch": 1.0120481927710843,
"grad_norm": 0.6511788455271817,
"learning_rate": 8.383691540076372e-06,
"loss": 0.6301,
"step": 84
},
{
"epoch": 1.0240963855421688,
"grad_norm": 0.5967211972196197,
"learning_rate": 8.331732889760021e-06,
"loss": 0.6374,
"step": 85
},
{
"epoch": 1.036144578313253,
"grad_norm": 0.7092464449638426,
"learning_rate": 8.279118899309121e-06,
"loss": 0.6203,
"step": 86
},
{
"epoch": 1.0481927710843373,
"grad_norm": 0.5845701177591752,
"learning_rate": 8.22585991771044e-06,
"loss": 0.6318,
"step": 87
},
{
"epoch": 1.0602409638554218,
"grad_norm": 0.6002752317965907,
"learning_rate": 8.171966420818227e-06,
"loss": 0.6467,
"step": 88
},
{
"epoch": 1.072289156626506,
"grad_norm": 0.6522220311834458,
"learning_rate": 8.117449009293668e-06,
"loss": 0.6356,
"step": 89
},
{
"epoch": 1.0843373493975903,
"grad_norm": 0.6502822017099245,
"learning_rate": 8.062318406519751e-06,
"loss": 0.6139,
"step": 90
},
{
"epoch": 1.0963855421686748,
"grad_norm": 0.6061197012036528,
"learning_rate": 8.00658545649203e-06,
"loss": 0.6323,
"step": 91
},
{
"epoch": 1.108433734939759,
"grad_norm": 0.5887887451794878,
"learning_rate": 7.950261121685642e-06,
"loss": 0.6291,
"step": 92
},
{
"epoch": 1.1204819277108433,
"grad_norm": 0.6612015091841277,
"learning_rate": 7.89335648089903e-06,
"loss": 0.6167,
"step": 93
},
{
"epoch": 1.1325301204819278,
"grad_norm": 0.6883130497488364,
"learning_rate": 7.835882727074779e-06,
"loss": 0.6187,
"step": 94
},
{
"epoch": 1.144578313253012,
"grad_norm": 0.6427426046369045,
"learning_rate": 7.777851165098012e-06,
"loss": 0.6475,
"step": 95
},
{
"epoch": 1.1566265060240963,
"grad_norm": 0.5978708484682433,
"learning_rate": 7.719273209572745e-06,
"loss": 0.6252,
"step": 96
},
{
"epoch": 1.1686746987951806,
"grad_norm": 0.5855601016209826,
"learning_rate": 7.660160382576683e-06,
"loss": 0.6135,
"step": 97
},
{
"epoch": 1.180722891566265,
"grad_norm": 0.7492491277249468,
"learning_rate": 7.600524311394873e-06,
"loss": 0.6087,
"step": 98
},
{
"epoch": 1.1927710843373494,
"grad_norm": 0.6627214296533939,
"learning_rate": 7.540376726232648e-06,
"loss": 0.6121,
"step": 99
},
{
"epoch": 1.2048192771084336,
"grad_norm": 0.5450802132108117,
"learning_rate": 7.4797294579083405e-06,
"loss": 0.6247,
"step": 100
},
{
"epoch": 1.216867469879518,
"grad_norm": 0.7526832546581198,
"learning_rate": 7.4185944355261996e-06,
"loss": 0.625,
"step": 101
},
{
"epoch": 1.2289156626506024,
"grad_norm": 0.6518223670625207,
"learning_rate": 7.3569836841299905e-06,
"loss": 0.6274,
"step": 102
},
{
"epoch": 1.2409638554216866,
"grad_norm": 0.5534033743461448,
"learning_rate": 7.294909322337689e-06,
"loss": 0.6266,
"step": 103
},
{
"epoch": 1.2530120481927711,
"grad_norm": 0.592926258071772,
"learning_rate": 7.232383559957815e-06,
"loss": 0.6185,
"step": 104
},
{
"epoch": 1.2650602409638554,
"grad_norm": 0.6375741825060003,
"learning_rate": 7.169418695587791e-06,
"loss": 0.6217,
"step": 105
},
{
"epoch": 1.2771084337349397,
"grad_norm": 0.5055671631407958,
"learning_rate": 7.106027114194856e-06,
"loss": 0.6177,
"step": 106
},
{
"epoch": 1.2891566265060241,
"grad_norm": 0.6595997797708595,
"learning_rate": 7.042221284679982e-06,
"loss": 0.6205,
"step": 107
},
{
"epoch": 1.3012048192771084,
"grad_norm": 0.6162416361134196,
"learning_rate": 6.978013757425295e-06,
"loss": 0.6223,
"step": 108
},
{
"epoch": 1.3132530120481927,
"grad_norm": 0.5370366676804204,
"learning_rate": 6.913417161825449e-06,
"loss": 0.5882,
"step": 109
},
{
"epoch": 1.3253012048192772,
"grad_norm": 0.5399960489088714,
"learning_rate": 6.848444203803476e-06,
"loss": 0.6289,
"step": 110
},
{
"epoch": 1.3373493975903614,
"grad_norm": 0.5674796084091516,
"learning_rate": 6.783107663311566e-06,
"loss": 0.6244,
"step": 111
},
{
"epoch": 1.3493975903614457,
"grad_norm": 0.5404297036496657,
"learning_rate": 6.717420391817306e-06,
"loss": 0.6,
"step": 112
},
{
"epoch": 1.3614457831325302,
"grad_norm": 0.6237792562306403,
"learning_rate": 6.651395309775837e-06,
"loss": 0.6159,
"step": 113
},
{
"epoch": 1.3734939759036144,
"grad_norm": 0.5282878577502261,
"learning_rate": 6.585045404088442e-06,
"loss": 0.623,
"step": 114
},
{
"epoch": 1.3855421686746987,
"grad_norm": 0.5981309403814754,
"learning_rate": 6.518383725548074e-06,
"loss": 0.6102,
"step": 115
},
{
"epoch": 1.3975903614457832,
"grad_norm": 0.6058914291786243,
"learning_rate": 6.451423386272312e-06,
"loss": 0.6239,
"step": 116
},
{
"epoch": 1.4096385542168675,
"grad_norm": 0.5850369846706815,
"learning_rate": 6.384177557124247e-06,
"loss": 0.6194,
"step": 117
},
{
"epoch": 1.4216867469879517,
"grad_norm": 0.6752460747433573,
"learning_rate": 6.3166594651218235e-06,
"loss": 0.6253,
"step": 118
},
{
"epoch": 1.4337349397590362,
"grad_norm": 0.5592890672490309,
"learning_rate": 6.248882390836135e-06,
"loss": 0.6407,
"step": 119
},
{
"epoch": 1.4457831325301205,
"grad_norm": 0.5784407179794009,
"learning_rate": 6.180859665779173e-06,
"loss": 0.6126,
"step": 120
},
{
"epoch": 1.4578313253012047,
"grad_norm": 0.6514449422611613,
"learning_rate": 6.112604669781572e-06,
"loss": 0.5998,
"step": 121
},
{
"epoch": 1.4698795180722892,
"grad_norm": 0.5800025517248629,
"learning_rate": 6.04413082836085e-06,
"loss": 0.6232,
"step": 122
},
{
"epoch": 1.4819277108433735,
"grad_norm": 0.6233783401088263,
"learning_rate": 5.975451610080643e-06,
"loss": 0.6125,
"step": 123
},
{
"epoch": 1.4939759036144578,
"grad_norm": 0.5337119115433385,
"learning_rate": 5.906580523901493e-06,
"loss": 0.6231,
"step": 124
},
{
"epoch": 1.5060240963855422,
"grad_norm": 0.5768923184837736,
"learning_rate": 5.837531116523683e-06,
"loss": 0.6225,
"step": 125
},
{
"epoch": 1.5180722891566265,
"grad_norm": 0.5381113068629061,
"learning_rate": 5.768316969722651e-06,
"loss": 0.601,
"step": 126
},
{
"epoch": 1.5301204819277108,
"grad_norm": 0.6056565356551226,
"learning_rate": 5.698951697677498e-06,
"loss": 0.6184,
"step": 127
},
{
"epoch": 1.5421686746987953,
"grad_norm": 0.525624946737704,
"learning_rate": 5.629448944293128e-06,
"loss": 0.6014,
"step": 128
},
{
"epoch": 1.5542168674698795,
"grad_norm": 0.5913097818886935,
"learning_rate": 5.559822380516539e-06,
"loss": 0.612,
"step": 129
},
{
"epoch": 1.5662650602409638,
"grad_norm": 0.6465501317905712,
"learning_rate": 5.490085701647805e-06,
"loss": 0.6168,
"step": 130
},
{
"epoch": 1.5783132530120483,
"grad_norm": 0.5768289213896209,
"learning_rate": 5.420252624646238e-06,
"loss": 0.611,
"step": 131
},
{
"epoch": 1.5903614457831325,
"grad_norm": 0.6042174223931454,
"learning_rate": 5.350336885432337e-06,
"loss": 0.6131,
"step": 132
},
{
"epoch": 1.6024096385542168,
"grad_norm": 0.6251689249617343,
"learning_rate": 5.2803522361859596e-06,
"loss": 0.6324,
"step": 133
},
{
"epoch": 1.6144578313253013,
"grad_norm": 0.6236393687846856,
"learning_rate": 5.210312442641327e-06,
"loss": 0.6038,
"step": 134
},
{
"epoch": 1.6265060240963856,
"grad_norm": 0.5691587883847324,
"learning_rate": 5.140231281379345e-06,
"loss": 0.6423,
"step": 135
},
{
"epoch": 1.6385542168674698,
"grad_norm": 0.5322090688844037,
"learning_rate": 5.070122537117812e-06,
"loss": 0.6353,
"step": 136
},
{
"epoch": 1.6506024096385543,
"grad_norm": 0.5383749289608458,
"learning_rate": 5e-06,
"loss": 0.6187,
"step": 137
},
{
"epoch": 1.6626506024096386,
"grad_norm": 0.5162216016045197,
"learning_rate": 4.92987746288219e-06,
"loss": 0.6085,
"step": 138
},
{
"epoch": 1.6746987951807228,
"grad_norm": 0.5584798604645789,
"learning_rate": 4.859768718620656e-06,
"loss": 0.6147,
"step": 139
},
{
"epoch": 1.6867469879518073,
"grad_norm": 0.5162198601842644,
"learning_rate": 4.789687557358676e-06,
"loss": 0.6139,
"step": 140
},
{
"epoch": 1.6987951807228916,
"grad_norm": 0.5697649494329119,
"learning_rate": 4.719647763814041e-06,
"loss": 0.6195,
"step": 141
},
{
"epoch": 1.7108433734939759,
"grad_norm": 0.511975229887655,
"learning_rate": 4.649663114567663e-06,
"loss": 0.6188,
"step": 142
},
{
"epoch": 1.7228915662650603,
"grad_norm": 0.5255171763725026,
"learning_rate": 4.579747375353763e-06,
"loss": 0.6218,
"step": 143
},
{
"epoch": 1.7349397590361446,
"grad_norm": 0.5524618942728109,
"learning_rate": 4.509914298352197e-06,
"loss": 0.6096,
"step": 144
},
{
"epoch": 1.7469879518072289,
"grad_norm": 0.5052514719235022,
"learning_rate": 4.4401776194834615e-06,
"loss": 0.6229,
"step": 145
},
{
"epoch": 1.7590361445783134,
"grad_norm": 0.5519602114427213,
"learning_rate": 4.3705510557068746e-06,
"loss": 0.6146,
"step": 146
},
{
"epoch": 1.7710843373493976,
"grad_norm": 0.5223041604156741,
"learning_rate": 4.3010483023225045e-06,
"loss": 0.6202,
"step": 147
},
{
"epoch": 1.783132530120482,
"grad_norm": 0.48632353132375417,
"learning_rate": 4.231683030277349e-06,
"loss": 0.6048,
"step": 148
},
{
"epoch": 1.7951807228915664,
"grad_norm": 0.5817221327934441,
"learning_rate": 4.162468883476319e-06,
"loss": 0.621,
"step": 149
},
{
"epoch": 1.8072289156626506,
"grad_norm": 0.5018230149071331,
"learning_rate": 4.0934194760985095e-06,
"loss": 0.5982,
"step": 150
},
{
"epoch": 1.819277108433735,
"grad_norm": 0.6010733865960758,
"learning_rate": 4.02454838991936e-06,
"loss": 0.6148,
"step": 151
},
{
"epoch": 1.8313253012048194,
"grad_norm": 0.5398862747771389,
"learning_rate": 3.955869171639151e-06,
"loss": 0.6239,
"step": 152
},
{
"epoch": 1.8433734939759037,
"grad_norm": 0.5294643193447254,
"learning_rate": 3.887395330218429e-06,
"loss": 0.6177,
"step": 153
},
{
"epoch": 1.855421686746988,
"grad_norm": 0.4808728735687609,
"learning_rate": 3.81914033422083e-06,
"loss": 0.5916,
"step": 154
},
{
"epoch": 1.8674698795180724,
"grad_norm": 0.5018762281121382,
"learning_rate": 3.751117609163865e-06,
"loss": 0.621,
"step": 155
},
{
"epoch": 1.8795180722891565,
"grad_norm": 0.544376505139809,
"learning_rate": 3.683340534878176e-06,
"loss": 0.6089,
"step": 156
},
{
"epoch": 1.891566265060241,
"grad_norm": 0.5054403811402102,
"learning_rate": 3.6158224428757538e-06,
"loss": 0.6221,
"step": 157
},
{
"epoch": 1.9036144578313254,
"grad_norm": 0.5468648536592757,
"learning_rate": 3.5485766137276894e-06,
"loss": 0.64,
"step": 158
},
{
"epoch": 1.9156626506024095,
"grad_norm": 0.53351231774059,
"learning_rate": 3.4816162744519266e-06,
"loss": 0.6076,
"step": 159
},
{
"epoch": 1.927710843373494,
"grad_norm": 0.5224911140859257,
"learning_rate": 3.4149545959115604e-06,
"loss": 0.6095,
"step": 160
},
{
"epoch": 1.9397590361445785,
"grad_norm": 0.4956768078646336,
"learning_rate": 3.3486046902241663e-06,
"loss": 0.6433,
"step": 161
},
{
"epoch": 1.9518072289156625,
"grad_norm": 0.5394838660039611,
"learning_rate": 3.2825796081826943e-06,
"loss": 0.5989,
"step": 162
},
{
"epoch": 1.963855421686747,
"grad_norm": 0.5882895452328137,
"learning_rate": 3.216892336688435e-06,
"loss": 0.6438,
"step": 163
},
{
"epoch": 1.9759036144578315,
"grad_norm": 0.5719005618760834,
"learning_rate": 3.1515557961965254e-06,
"loss": 0.5912,
"step": 164
},
{
"epoch": 1.9879518072289155,
"grad_norm": 0.5072127958299484,
"learning_rate": 3.0865828381745515e-06,
"loss": 0.5991,
"step": 165
},
{
"epoch": 2.0,
"grad_norm": 0.511444872643503,
"learning_rate": 3.021986242574707e-06,
"loss": 0.5906,
"step": 166
},
{
"epoch": 2.0120481927710845,
"grad_norm": 0.558646285679792,
"learning_rate": 2.95777871532002e-06,
"loss": 0.564,
"step": 167
},
{
"epoch": 2.0240963855421685,
"grad_norm": 0.4681676467833184,
"learning_rate": 2.893972885805148e-06,
"loss": 0.5602,
"step": 168
},
{
"epoch": 2.036144578313253,
"grad_norm": 0.5311210396221397,
"learning_rate": 2.83058130441221e-06,
"loss": 0.5653,
"step": 169
},
{
"epoch": 2.0481927710843375,
"grad_norm": 0.5134743590726569,
"learning_rate": 2.7676164400421864e-06,
"loss": 0.5694,
"step": 170
},
{
"epoch": 2.0602409638554215,
"grad_norm": 0.4783416685783163,
"learning_rate": 2.705090677662311e-06,
"loss": 0.5647,
"step": 171
},
{
"epoch": 2.072289156626506,
"grad_norm": 0.46340955591582167,
"learning_rate": 2.6430163158700116e-06,
"loss": 0.5637,
"step": 172
},
{
"epoch": 2.0843373493975905,
"grad_norm": 0.5060776877189238,
"learning_rate": 2.5814055644738013e-06,
"loss": 0.5711,
"step": 173
},
{
"epoch": 2.0963855421686746,
"grad_norm": 0.5097326865484699,
"learning_rate": 2.520270542091663e-06,
"loss": 0.5582,
"step": 174
},
{
"epoch": 2.108433734939759,
"grad_norm": 0.5092257252859715,
"learning_rate": 2.4596232737673544e-06,
"loss": 0.5554,
"step": 175
},
{
"epoch": 2.1204819277108435,
"grad_norm": 0.5197317924103939,
"learning_rate": 2.3994756886051267e-06,
"loss": 0.5792,
"step": 176
},
{
"epoch": 2.1325301204819276,
"grad_norm": 0.5510975774014351,
"learning_rate": 2.339839617423318e-06,
"loss": 0.5718,
"step": 177
},
{
"epoch": 2.144578313253012,
"grad_norm": 0.5446337856700941,
"learning_rate": 2.280726790427258e-06,
"loss": 0.5497,
"step": 178
},
{
"epoch": 2.1566265060240966,
"grad_norm": 0.5408576213489689,
"learning_rate": 2.2221488349019903e-06,
"loss": 0.5524,
"step": 179
},
{
"epoch": 2.1686746987951806,
"grad_norm": 0.5017965090675062,
"learning_rate": 2.1641172729252206e-06,
"loss": 0.5682,
"step": 180
},
{
"epoch": 2.180722891566265,
"grad_norm": 0.5141039319661626,
"learning_rate": 2.1066435191009717e-06,
"loss": 0.547,
"step": 181
},
{
"epoch": 2.1927710843373496,
"grad_norm": 0.5157721156590446,
"learning_rate": 2.04973887831436e-06,
"loss": 0.5709,
"step": 182
},
{
"epoch": 2.2048192771084336,
"grad_norm": 0.5870699701608006,
"learning_rate": 1.9934145435079705e-06,
"loss": 0.5447,
"step": 183
},
{
"epoch": 2.216867469879518,
"grad_norm": 0.6028935897052433,
"learning_rate": 1.9376815934802496e-06,
"loss": 0.5601,
"step": 184
},
{
"epoch": 2.2289156626506026,
"grad_norm": 0.4718903082783866,
"learning_rate": 1.8825509907063328e-06,
"loss": 0.5551,
"step": 185
},
{
"epoch": 2.2409638554216866,
"grad_norm": 0.5002810920888432,
"learning_rate": 1.8280335791817733e-06,
"loss": 0.5688,
"step": 186
},
{
"epoch": 2.253012048192771,
"grad_norm": 0.5294348388821193,
"learning_rate": 1.7741400822895633e-06,
"loss": 0.581,
"step": 187
},
{
"epoch": 2.2650602409638556,
"grad_norm": 0.5159109553291168,
"learning_rate": 1.7208811006908798e-06,
"loss": 0.5641,
"step": 188
},
{
"epoch": 2.2771084337349397,
"grad_norm": 0.47208482699892207,
"learning_rate": 1.6682671102399806e-06,
"loss": 0.5769,
"step": 189
},
{
"epoch": 2.289156626506024,
"grad_norm": 0.48487303053069875,
"learning_rate": 1.6163084599236278e-06,
"loss": 0.5682,
"step": 190
},
{
"epoch": 2.3012048192771086,
"grad_norm": 0.4569664582891425,
"learning_rate": 1.5650153698254916e-06,
"loss": 0.5803,
"step": 191
},
{
"epoch": 2.3132530120481927,
"grad_norm": 0.4695542073042292,
"learning_rate": 1.514397929115884e-06,
"loss": 0.5466,
"step": 192
},
{
"epoch": 2.325301204819277,
"grad_norm": 0.4883651576878005,
"learning_rate": 1.4644660940672628e-06,
"loss": 0.541,
"step": 193
},
{
"epoch": 2.337349397590361,
"grad_norm": 0.525384604033524,
"learning_rate": 1.4152296860958641e-06,
"loss": 0.5534,
"step": 194
},
{
"epoch": 2.3493975903614457,
"grad_norm": 0.4766107333921436,
"learning_rate": 1.3666983898298659e-06,
"loss": 0.5785,
"step": 195
},
{
"epoch": 2.36144578313253,
"grad_norm": 0.530501750758112,
"learning_rate": 1.3188817512044544e-06,
"loss": 0.5618,
"step": 196
},
{
"epoch": 2.3734939759036147,
"grad_norm": 0.41149448787680737,
"learning_rate": 1.2717891755841722e-06,
"loss": 0.5613,
"step": 197
},
{
"epoch": 2.3855421686746987,
"grad_norm": 0.47133376734164123,
"learning_rate": 1.225429925912921e-06,
"loss": 0.5456,
"step": 198
},
{
"epoch": 2.397590361445783,
"grad_norm": 0.44160978889629554,
"learning_rate": 1.1798131208919628e-06,
"loss": 0.5608,
"step": 199
},
{
"epoch": 2.4096385542168672,
"grad_norm": 0.4713207662270395,
"learning_rate": 1.134947733186315e-06,
"loss": 0.5671,
"step": 200
},
{
"epoch": 2.4216867469879517,
"grad_norm": 0.4735966149153215,
"learning_rate": 1.0908425876598512e-06,
"loss": 0.5562,
"step": 201
},
{
"epoch": 2.433734939759036,
"grad_norm": 0.4966573016169727,
"learning_rate": 1.047506359639483e-06,
"loss": 0.5622,
"step": 202
},
{
"epoch": 2.4457831325301207,
"grad_norm": 0.45702011307394225,
"learning_rate": 1.004947573208756e-06,
"loss": 0.5687,
"step": 203
},
{
"epoch": 2.4578313253012047,
"grad_norm": 0.4733539932472332,
"learning_rate": 9.631745995311881e-07,
"loss": 0.57,
"step": 204
},
{
"epoch": 2.4698795180722892,
"grad_norm": 0.42935877811723394,
"learning_rate": 9.221956552036992e-07,
"loss": 0.5688,
"step": 205
},
{
"epoch": 2.4819277108433733,
"grad_norm": 0.5401591357533175,
"learning_rate": 8.820188006404268e-07,
"loss": 0.5438,
"step": 206
},
{
"epoch": 2.4939759036144578,
"grad_norm": 0.48661222938058185,
"learning_rate": 8.426519384872733e-07,
"loss": 0.5878,
"step": 207
},
{
"epoch": 2.5060240963855422,
"grad_norm": 0.4665236617171864,
"learning_rate": 8.041028120674894e-07,
"loss": 0.5353,
"step": 208
},
{
"epoch": 2.5180722891566267,
"grad_norm": 0.4518632327746976,
"learning_rate": 7.663790038585794e-07,
"loss": 0.5614,
"step": 209
},
{
"epoch": 2.5301204819277108,
"grad_norm": 0.4721339046051855,
"learning_rate": 7.294879340008632e-07,
"loss": 0.567,
"step": 210
},
{
"epoch": 2.5421686746987953,
"grad_norm": 0.429139351792564,
"learning_rate": 6.934368588379553e-07,
"loss": 0.576,
"step": 211
},
{
"epoch": 2.5542168674698793,
"grad_norm": 0.5075035453973568,
"learning_rate": 6.582328694894729e-07,
"loss": 0.5703,
"step": 212
},
{
"epoch": 2.566265060240964,
"grad_norm": 0.4475281320044474,
"learning_rate": 6.238828904562316e-07,
"loss": 0.5631,
"step": 213
},
{
"epoch": 2.5783132530120483,
"grad_norm": 0.48913591285723984,
"learning_rate": 5.903936782582253e-07,
"loss": 0.5625,
"step": 214
},
{
"epoch": 2.5903614457831328,
"grad_norm": 0.45778937976857875,
"learning_rate": 5.577718201056392e-07,
"loss": 0.5504,
"step": 215
},
{
"epoch": 2.602409638554217,
"grad_norm": 0.4386055171062226,
"learning_rate": 5.260237326031698e-07,
"loss": 0.5566,
"step": 216
},
{
"epoch": 2.6144578313253013,
"grad_norm": 0.4455791135265807,
"learning_rate": 4.951556604879049e-07,
"loss": 0.5706,
"step": 217
},
{
"epoch": 2.6265060240963853,
"grad_norm": 0.45607445355118803,
"learning_rate": 4.651736754009972e-07,
"loss": 0.5484,
"step": 218
},
{
"epoch": 2.63855421686747,
"grad_norm": 0.4294752864219149,
"learning_rate": 4.3608367469340553e-07,
"loss": 0.5607,
"step": 219
},
{
"epoch": 2.6506024096385543,
"grad_norm": 0.4153517988579225,
"learning_rate": 4.078913802658946e-07,
"loss": 0.5679,
"step": 220
},
{
"epoch": 2.662650602409639,
"grad_norm": 0.43992411352059413,
"learning_rate": 3.8060233744356634e-07,
"loss": 0.5632,
"step": 221
},
{
"epoch": 2.674698795180723,
"grad_norm": 0.4753241876516238,
"learning_rate": 3.542219138851094e-07,
"loss": 0.5695,
"step": 222
},
{
"epoch": 2.6867469879518073,
"grad_norm": 0.4363375230009041,
"learning_rate": 3.287552985270015e-07,
"loss": 0.5578,
"step": 223
},
{
"epoch": 2.6987951807228914,
"grad_norm": 0.4939139048287021,
"learning_rate": 3.0420750056286195e-07,
"loss": 0.5525,
"step": 224
},
{
"epoch": 2.710843373493976,
"grad_norm": 0.4407433939031648,
"learning_rate": 2.8058334845816214e-07,
"loss": 0.5582,
"step": 225
},
{
"epoch": 2.7228915662650603,
"grad_norm": 0.4769224487486906,
"learning_rate": 2.5788748900048676e-07,
"loss": 0.563,
"step": 226
},
{
"epoch": 2.734939759036145,
"grad_norm": 0.45327939902074543,
"learning_rate": 2.3612438638551837e-07,
"loss": 0.5657,
"step": 227
},
{
"epoch": 2.746987951807229,
"grad_norm": 0.45824994236000044,
"learning_rate": 2.152983213389559e-07,
"loss": 0.5768,
"step": 228
},
{
"epoch": 2.7590361445783134,
"grad_norm": 0.41799106068990527,
"learning_rate": 1.9541339027450256e-07,
"loss": 0.5765,
"step": 229
},
{
"epoch": 2.7710843373493974,
"grad_norm": 0.44800928229406345,
"learning_rate": 1.7647350448812105e-07,
"loss": 0.5434,
"step": 230
},
{
"epoch": 2.783132530120482,
"grad_norm": 0.4786297933983056,
"learning_rate": 1.5848238938869332e-07,
"loss": 0.5644,
"step": 231
},
{
"epoch": 2.7951807228915664,
"grad_norm": 0.4495457623483388,
"learning_rate": 1.4144358376524504e-07,
"loss": 0.5711,
"step": 232
},
{
"epoch": 2.807228915662651,
"grad_norm": 0.4467368766784784,
"learning_rate": 1.253604390908819e-07,
"loss": 0.5747,
"step": 233
},
{
"epoch": 2.819277108433735,
"grad_norm": 0.42743637589347505,
"learning_rate": 1.10236118863562e-07,
"loss": 0.5741,
"step": 234
},
{
"epoch": 2.8313253012048194,
"grad_norm": 0.45971443043244103,
"learning_rate": 9.607359798384785e-08,
"loss": 0.5537,
"step": 235
},
{
"epoch": 2.8433734939759034,
"grad_norm": 0.45456136996123836,
"learning_rate": 8.287566216975795e-08,
"loss": 0.5436,
"step": 236
},
{
"epoch": 2.855421686746988,
"grad_norm": 0.45548000364213126,
"learning_rate": 7.064490740882057e-08,
"loss": 0.5481,
"step": 237
},
{
"epoch": 2.8674698795180724,
"grad_norm": 0.473130854594422,
"learning_rate": 5.938373944745612e-08,
"loss": 0.5745,
"step": 238
},
{
"epoch": 2.8795180722891565,
"grad_norm": 0.46051179937108094,
"learning_rate": 4.909437331777178e-08,
"loss": 0.569,
"step": 239
},
{
"epoch": 2.891566265060241,
"grad_norm": 0.44290071625137933,
"learning_rate": 3.977883290187667e-08,
"loss": 0.5433,
"step": 240
},
{
"epoch": 2.9036144578313254,
"grad_norm": 0.45323884161408806,
"learning_rate": 3.143895053378698e-08,
"loss": 0.5637,
"step": 241
},
{
"epoch": 2.9156626506024095,
"grad_norm": 0.42389164450454236,
"learning_rate": 2.4076366639015914e-08,
"loss": 0.5464,
"step": 242
},
{
"epoch": 2.927710843373494,
"grad_norm": 0.4695054217684337,
"learning_rate": 1.769252941190458e-08,
"loss": 0.5313,
"step": 243
},
{
"epoch": 2.9397590361445785,
"grad_norm": 0.4715323869865203,
"learning_rate": 1.2288694530769862e-08,
"loss": 0.5517,
"step": 244
},
{
"epoch": 2.9518072289156625,
"grad_norm": 0.45767533383001513,
"learning_rate": 7.865924910916977e-09,
"loss": 0.5535,
"step": 245
},
{
"epoch": 2.963855421686747,
"grad_norm": 0.45023688997317707,
"learning_rate": 4.4250904955656095e-09,
"loss": 0.5445,
"step": 246
},
{
"epoch": 2.9759036144578315,
"grad_norm": 0.4346661439099685,
"learning_rate": 1.9668680847356735e-09,
"loss": 0.5569,
"step": 247
},
{
"epoch": 2.9879518072289155,
"grad_norm": 0.4694101503195915,
"learning_rate": 4.91741202124918e-10,
"loss": 0.5643,
"step": 248
},
{
"epoch": 3.0,
"grad_norm": 0.44801681936473053,
"learning_rate": 0.0,
"loss": 0.5477,
"step": 249
},
{
"epoch": 3.0,
"step": 249,
"total_flos": 210646484844544.0,
"train_loss": 0.6536134277960383,
"train_runtime": 3799.3108,
"train_samples_per_second": 6.269,
"train_steps_per_second": 0.066
}
],
"logging_steps": 1,
"max_steps": 249,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 210646484844544.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}