Safetensors
qwen2
Qwen-1.5B-Claude / trainer_state.json
Mia Fournier
Upload folder using huggingface_hub
64ddfa1 verified
raw
history blame
63.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9814460437640404,
"eval_steps": 47,
"global_step": 374,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005324902238122972,
"grad_norm": 1.5,
"learning_rate": 1.4285714285714286e-06,
"loss": 1.7903,
"step": 1
},
{
"epoch": 0.005324902238122972,
"eval_loss": 1.775637149810791,
"eval_runtime": 77.1748,
"eval_samples_per_second": 15.29,
"eval_steps_per_second": 15.29,
"step": 1
},
{
"epoch": 0.010649804476245944,
"grad_norm": 1.484375,
"learning_rate": 2.8571428571428573e-06,
"loss": 1.761,
"step": 2
},
{
"epoch": 0.015974706714368916,
"grad_norm": 1.5546875,
"learning_rate": 4.2857142857142855e-06,
"loss": 1.8033,
"step": 3
},
{
"epoch": 0.02129960895249189,
"grad_norm": 1.3671875,
"learning_rate": 5.7142857142857145e-06,
"loss": 1.7335,
"step": 4
},
{
"epoch": 0.02662451119061486,
"grad_norm": 1.484375,
"learning_rate": 7.1428571428571436e-06,
"loss": 1.7532,
"step": 5
},
{
"epoch": 0.03194941342873783,
"grad_norm": 1.3203125,
"learning_rate": 8.571428571428571e-06,
"loss": 1.7546,
"step": 6
},
{
"epoch": 0.037274315666860805,
"grad_norm": 1.21875,
"learning_rate": 1e-05,
"loss": 1.8068,
"step": 7
},
{
"epoch": 0.04259921790498378,
"grad_norm": 1.1796875,
"learning_rate": 1.1428571428571429e-05,
"loss": 1.8295,
"step": 8
},
{
"epoch": 0.04792412014310675,
"grad_norm": 1.078125,
"learning_rate": 1.2857142857142859e-05,
"loss": 1.7343,
"step": 9
},
{
"epoch": 0.05324902238122972,
"grad_norm": 1.25,
"learning_rate": 1.4285714285714287e-05,
"loss": 1.8318,
"step": 10
},
{
"epoch": 0.058573924619352694,
"grad_norm": 1.1796875,
"learning_rate": 1.5714285714285715e-05,
"loss": 1.8064,
"step": 11
},
{
"epoch": 0.06389882685747567,
"grad_norm": 1.1484375,
"learning_rate": 1.7142857142857142e-05,
"loss": 1.7317,
"step": 12
},
{
"epoch": 0.06922372909559864,
"grad_norm": 1.2578125,
"learning_rate": 1.8571428571428575e-05,
"loss": 1.8281,
"step": 13
},
{
"epoch": 0.07454863133372161,
"grad_norm": 1.1328125,
"learning_rate": 2e-05,
"loss": 1.6915,
"step": 14
},
{
"epoch": 0.07987353357184458,
"grad_norm": 1.1484375,
"learning_rate": 1.9999619230641714e-05,
"loss": 1.7509,
"step": 15
},
{
"epoch": 0.08519843580996755,
"grad_norm": 1.0859375,
"learning_rate": 1.9998476951563914e-05,
"loss": 1.7416,
"step": 16
},
{
"epoch": 0.09052333804809053,
"grad_norm": 1.0859375,
"learning_rate": 1.9996573249755573e-05,
"loss": 1.7,
"step": 17
},
{
"epoch": 0.0958482402862135,
"grad_norm": 1.1640625,
"learning_rate": 1.999390827019096e-05,
"loss": 1.771,
"step": 18
},
{
"epoch": 0.10117314252433647,
"grad_norm": 1.1171875,
"learning_rate": 1.999048221581858e-05,
"loss": 1.7097,
"step": 19
},
{
"epoch": 0.10649804476245944,
"grad_norm": 1.1015625,
"learning_rate": 1.9986295347545738e-05,
"loss": 1.7411,
"step": 20
},
{
"epoch": 0.11182294700058241,
"grad_norm": 1.046875,
"learning_rate": 1.998134798421867e-05,
"loss": 1.7664,
"step": 21
},
{
"epoch": 0.11714784923870539,
"grad_norm": 1.1171875,
"learning_rate": 1.9975640502598243e-05,
"loss": 1.7283,
"step": 22
},
{
"epoch": 0.12247275147682836,
"grad_norm": 1.1015625,
"learning_rate": 1.9969173337331283e-05,
"loss": 1.8261,
"step": 23
},
{
"epoch": 0.12779765371495133,
"grad_norm": 1.078125,
"learning_rate": 1.9961946980917457e-05,
"loss": 1.7096,
"step": 24
},
{
"epoch": 0.1331225559530743,
"grad_norm": 1.078125,
"learning_rate": 1.9953961983671792e-05,
"loss": 1.8025,
"step": 25
},
{
"epoch": 0.13844745819119728,
"grad_norm": 1.0625,
"learning_rate": 1.9945218953682736e-05,
"loss": 1.7506,
"step": 26
},
{
"epoch": 0.14377236042932023,
"grad_norm": 1.0546875,
"learning_rate": 1.9935718556765878e-05,
"loss": 1.7492,
"step": 27
},
{
"epoch": 0.14909726266744322,
"grad_norm": 1.078125,
"learning_rate": 1.9925461516413224e-05,
"loss": 1.7108,
"step": 28
},
{
"epoch": 0.15442216490556618,
"grad_norm": 1.0546875,
"learning_rate": 1.9914448613738107e-05,
"loss": 1.6542,
"step": 29
},
{
"epoch": 0.15974706714368916,
"grad_norm": 1.0234375,
"learning_rate": 1.9902680687415704e-05,
"loss": 1.7548,
"step": 30
},
{
"epoch": 0.16507196938181212,
"grad_norm": 1.1171875,
"learning_rate": 1.989015863361917e-05,
"loss": 1.7417,
"step": 31
},
{
"epoch": 0.1703968716199351,
"grad_norm": 1.0546875,
"learning_rate": 1.9876883405951378e-05,
"loss": 1.6839,
"step": 32
},
{
"epoch": 0.17572177385805807,
"grad_norm": 1.0,
"learning_rate": 1.9862856015372315e-05,
"loss": 1.6547,
"step": 33
},
{
"epoch": 0.18104667609618105,
"grad_norm": 1.0625,
"learning_rate": 1.9848077530122083e-05,
"loss": 1.7696,
"step": 34
},
{
"epoch": 0.186371578334304,
"grad_norm": 1.1484375,
"learning_rate": 1.983254907563955e-05,
"loss": 1.6861,
"step": 35
},
{
"epoch": 0.191696480572427,
"grad_norm": 1.0703125,
"learning_rate": 1.9816271834476642e-05,
"loss": 1.7726,
"step": 36
},
{
"epoch": 0.19702138281054996,
"grad_norm": 1.0078125,
"learning_rate": 1.9799247046208297e-05,
"loss": 1.7046,
"step": 37
},
{
"epoch": 0.20234628504867294,
"grad_norm": 1.15625,
"learning_rate": 1.9781476007338058e-05,
"loss": 1.7071,
"step": 38
},
{
"epoch": 0.2076711872867959,
"grad_norm": 1.0859375,
"learning_rate": 1.9762960071199334e-05,
"loss": 1.8033,
"step": 39
},
{
"epoch": 0.21299608952491889,
"grad_norm": 1.0859375,
"learning_rate": 1.9743700647852356e-05,
"loss": 1.8173,
"step": 40
},
{
"epoch": 0.21832099176304184,
"grad_norm": 1.1171875,
"learning_rate": 1.9723699203976768e-05,
"loss": 1.7546,
"step": 41
},
{
"epoch": 0.22364589400116483,
"grad_norm": 1.09375,
"learning_rate": 1.9702957262759964e-05,
"loss": 1.7599,
"step": 42
},
{
"epoch": 0.2289707962392878,
"grad_norm": 1.03125,
"learning_rate": 1.968147640378108e-05,
"loss": 1.6765,
"step": 43
},
{
"epoch": 0.23429569847741077,
"grad_norm": 1.046875,
"learning_rate": 1.9659258262890683e-05,
"loss": 1.7651,
"step": 44
},
{
"epoch": 0.23962060071553373,
"grad_norm": 1.0546875,
"learning_rate": 1.963630453208623e-05,
"loss": 1.6026,
"step": 45
},
{
"epoch": 0.24494550295365672,
"grad_norm": 1.1015625,
"learning_rate": 1.961261695938319e-05,
"loss": 1.7446,
"step": 46
},
{
"epoch": 0.2502704051917797,
"grad_norm": 1.015625,
"learning_rate": 1.958819734868193e-05,
"loss": 1.7374,
"step": 47
},
{
"epoch": 0.2502704051917797,
"eval_loss": 1.7246959209442139,
"eval_runtime": 84.4189,
"eval_samples_per_second": 13.978,
"eval_steps_per_second": 13.978,
"step": 47
},
{
"epoch": 0.25559530742990266,
"grad_norm": 1.0390625,
"learning_rate": 1.9563047559630356e-05,
"loss": 1.7224,
"step": 48
},
{
"epoch": 0.26092020966802565,
"grad_norm": 1.0703125,
"learning_rate": 1.953716950748227e-05,
"loss": 1.7919,
"step": 49
},
{
"epoch": 0.2662451119061486,
"grad_norm": 1.0625,
"learning_rate": 1.9510565162951538e-05,
"loss": 1.728,
"step": 50
},
{
"epoch": 0.27157001414427157,
"grad_norm": 1.109375,
"learning_rate": 1.9483236552061996e-05,
"loss": 1.758,
"step": 51
},
{
"epoch": 0.27689491638239455,
"grad_norm": 1.0078125,
"learning_rate": 1.945518575599317e-05,
"loss": 1.6651,
"step": 52
},
{
"epoch": 0.28221981862051754,
"grad_norm": 1.1015625,
"learning_rate": 1.9426414910921785e-05,
"loss": 1.7097,
"step": 53
},
{
"epoch": 0.28754472085864047,
"grad_norm": 1.0703125,
"learning_rate": 1.9396926207859085e-05,
"loss": 1.7315,
"step": 54
},
{
"epoch": 0.29286962309676345,
"grad_norm": 1.140625,
"learning_rate": 1.9366721892483976e-05,
"loss": 1.7535,
"step": 55
},
{
"epoch": 0.29819452533488644,
"grad_norm": 1.0859375,
"learning_rate": 1.9335804264972018e-05,
"loss": 1.7806,
"step": 56
},
{
"epoch": 0.3035194275730094,
"grad_norm": 1.046875,
"learning_rate": 1.9304175679820247e-05,
"loss": 1.7565,
"step": 57
},
{
"epoch": 0.30884432981113236,
"grad_norm": 1.0234375,
"learning_rate": 1.9271838545667876e-05,
"loss": 1.7056,
"step": 58
},
{
"epoch": 0.31416923204925534,
"grad_norm": 0.9921875,
"learning_rate": 1.9238795325112867e-05,
"loss": 1.7266,
"step": 59
},
{
"epoch": 0.31949413428737833,
"grad_norm": 1.046875,
"learning_rate": 1.9205048534524405e-05,
"loss": 1.6798,
"step": 60
},
{
"epoch": 0.3248190365255013,
"grad_norm": 1.1328125,
"learning_rate": 1.917060074385124e-05,
"loss": 1.6847,
"step": 61
},
{
"epoch": 0.33014393876362425,
"grad_norm": 1.0390625,
"learning_rate": 1.913545457642601e-05,
"loss": 1.6441,
"step": 62
},
{
"epoch": 0.33546884100174723,
"grad_norm": 1.0234375,
"learning_rate": 1.9099612708765432e-05,
"loss": 1.6839,
"step": 63
},
{
"epoch": 0.3407937432398702,
"grad_norm": 1.0625,
"learning_rate": 1.9063077870366504e-05,
"loss": 1.6653,
"step": 64
},
{
"epoch": 0.3461186454779932,
"grad_norm": 1.0,
"learning_rate": 1.902585284349861e-05,
"loss": 1.6688,
"step": 65
},
{
"epoch": 0.35144354771611613,
"grad_norm": 1.046875,
"learning_rate": 1.8987940462991673e-05,
"loss": 1.6317,
"step": 66
},
{
"epoch": 0.3567684499542391,
"grad_norm": 0.94921875,
"learning_rate": 1.894934361602025e-05,
"loss": 1.6889,
"step": 67
},
{
"epoch": 0.3620933521923621,
"grad_norm": 1.1015625,
"learning_rate": 1.891006524188368e-05,
"loss": 1.7744,
"step": 68
},
{
"epoch": 0.3674182544304851,
"grad_norm": 1.109375,
"learning_rate": 1.887010833178222e-05,
"loss": 1.7525,
"step": 69
},
{
"epoch": 0.372743156668608,
"grad_norm": 1.03125,
"learning_rate": 1.8829475928589272e-05,
"loss": 1.5786,
"step": 70
},
{
"epoch": 0.378068058906731,
"grad_norm": 0.984375,
"learning_rate": 1.8788171126619653e-05,
"loss": 1.7715,
"step": 71
},
{
"epoch": 0.383392961144854,
"grad_norm": 1.0078125,
"learning_rate": 1.874619707139396e-05,
"loss": 1.6526,
"step": 72
},
{
"epoch": 0.388717863382977,
"grad_norm": 1.0390625,
"learning_rate": 1.8703556959398998e-05,
"loss": 1.7511,
"step": 73
},
{
"epoch": 0.3940427656210999,
"grad_norm": 1.046875,
"learning_rate": 1.866025403784439e-05,
"loss": 1.789,
"step": 74
},
{
"epoch": 0.3993676678592229,
"grad_norm": 1.078125,
"learning_rate": 1.861629160441526e-05,
"loss": 1.7705,
"step": 75
},
{
"epoch": 0.4046925700973459,
"grad_norm": 1.0625,
"learning_rate": 1.8571673007021124e-05,
"loss": 1.7042,
"step": 76
},
{
"epoch": 0.4100174723354688,
"grad_norm": 0.98828125,
"learning_rate": 1.8526401643540924e-05,
"loss": 1.6971,
"step": 77
},
{
"epoch": 0.4153423745735918,
"grad_norm": 0.9765625,
"learning_rate": 1.848048096156426e-05,
"loss": 1.6873,
"step": 78
},
{
"epoch": 0.4206672768117148,
"grad_norm": 0.953125,
"learning_rate": 1.843391445812886e-05,
"loss": 1.6937,
"step": 79
},
{
"epoch": 0.42599217904983777,
"grad_norm": 1.0234375,
"learning_rate": 1.8386705679454243e-05,
"loss": 1.6798,
"step": 80
},
{
"epoch": 0.4313170812879607,
"grad_norm": 1.0703125,
"learning_rate": 1.8338858220671683e-05,
"loss": 1.7316,
"step": 81
},
{
"epoch": 0.4366419835260837,
"grad_norm": 1.0390625,
"learning_rate": 1.8290375725550417e-05,
"loss": 1.6617,
"step": 82
},
{
"epoch": 0.4419668857642067,
"grad_norm": 1.078125,
"learning_rate": 1.8241261886220155e-05,
"loss": 1.7817,
"step": 83
},
{
"epoch": 0.44729178800232966,
"grad_norm": 1.046875,
"learning_rate": 1.819152044288992e-05,
"loss": 1.7649,
"step": 84
},
{
"epoch": 0.4526166902404526,
"grad_norm": 1.0546875,
"learning_rate": 1.8141155183563195e-05,
"loss": 1.7158,
"step": 85
},
{
"epoch": 0.4579415924785756,
"grad_norm": 1.1171875,
"learning_rate": 1.8090169943749477e-05,
"loss": 1.7345,
"step": 86
},
{
"epoch": 0.46326649471669856,
"grad_norm": 1.0234375,
"learning_rate": 1.8038568606172172e-05,
"loss": 1.6563,
"step": 87
},
{
"epoch": 0.46859139695482155,
"grad_norm": 1.0234375,
"learning_rate": 1.798635510047293e-05,
"loss": 1.726,
"step": 88
},
{
"epoch": 0.4739162991929445,
"grad_norm": 0.9921875,
"learning_rate": 1.7933533402912354e-05,
"loss": 1.6767,
"step": 89
},
{
"epoch": 0.47924120143106747,
"grad_norm": 1.0234375,
"learning_rate": 1.788010753606722e-05,
"loss": 1.6585,
"step": 90
},
{
"epoch": 0.48456610366919045,
"grad_norm": 0.9609375,
"learning_rate": 1.782608156852414e-05,
"loss": 1.6202,
"step": 91
},
{
"epoch": 0.48989100590731344,
"grad_norm": 1.0234375,
"learning_rate": 1.777145961456971e-05,
"loss": 1.7857,
"step": 92
},
{
"epoch": 0.49521590814543637,
"grad_norm": 1.0546875,
"learning_rate": 1.7716245833877202e-05,
"loss": 1.7479,
"step": 93
},
{
"epoch": 0.5005408103835594,
"grad_norm": 1.0625,
"learning_rate": 1.766044443118978e-05,
"loss": 1.7516,
"step": 94
},
{
"epoch": 0.5005408103835594,
"eval_loss": 1.7072687149047852,
"eval_runtime": 77.7379,
"eval_samples_per_second": 15.179,
"eval_steps_per_second": 15.179,
"step": 94
},
{
"epoch": 0.5058657126216823,
"grad_norm": 1.0703125,
"learning_rate": 1.7604059656000313e-05,
"loss": 1.6983,
"step": 95
},
{
"epoch": 0.5111906148598053,
"grad_norm": 1.078125,
"learning_rate": 1.7547095802227723e-05,
"loss": 1.7144,
"step": 96
},
{
"epoch": 0.5165155170979283,
"grad_norm": 1.0546875,
"learning_rate": 1.7489557207890025e-05,
"loss": 1.754,
"step": 97
},
{
"epoch": 0.5218404193360513,
"grad_norm": 1.03125,
"learning_rate": 1.7431448254773943e-05,
"loss": 1.7862,
"step": 98
},
{
"epoch": 0.5271653215741742,
"grad_norm": 1.046875,
"learning_rate": 1.737277336810124e-05,
"loss": 1.7244,
"step": 99
},
{
"epoch": 0.5324902238122972,
"grad_norm": 1.0546875,
"learning_rate": 1.7313537016191706e-05,
"loss": 1.7129,
"step": 100
},
{
"epoch": 0.5378151260504201,
"grad_norm": 1.0390625,
"learning_rate": 1.7253743710122877e-05,
"loss": 1.6302,
"step": 101
},
{
"epoch": 0.5431400282885431,
"grad_norm": 0.99609375,
"learning_rate": 1.7193398003386514e-05,
"loss": 1.6831,
"step": 102
},
{
"epoch": 0.5484649305266661,
"grad_norm": 1.0,
"learning_rate": 1.713250449154182e-05,
"loss": 1.74,
"step": 103
},
{
"epoch": 0.5537898327647891,
"grad_norm": 1.0,
"learning_rate": 1.7071067811865477e-05,
"loss": 1.7333,
"step": 104
},
{
"epoch": 0.5591147350029121,
"grad_norm": 1.0546875,
"learning_rate": 1.700909264299851e-05,
"loss": 1.7359,
"step": 105
},
{
"epoch": 0.5644396372410351,
"grad_norm": 0.98828125,
"learning_rate": 1.6946583704589973e-05,
"loss": 1.7432,
"step": 106
},
{
"epoch": 0.569764539479158,
"grad_norm": 1.0078125,
"learning_rate": 1.688354575693754e-05,
"loss": 1.6974,
"step": 107
},
{
"epoch": 0.5750894417172809,
"grad_norm": 1.03125,
"learning_rate": 1.6819983600624986e-05,
"loss": 1.7011,
"step": 108
},
{
"epoch": 0.5804143439554039,
"grad_norm": 1.0703125,
"learning_rate": 1.6755902076156606e-05,
"loss": 1.665,
"step": 109
},
{
"epoch": 0.5857392461935269,
"grad_norm": 1.125,
"learning_rate": 1.6691306063588583e-05,
"loss": 1.8047,
"step": 110
},
{
"epoch": 0.5910641484316499,
"grad_norm": 0.9921875,
"learning_rate": 1.6626200482157378e-05,
"loss": 1.6664,
"step": 111
},
{
"epoch": 0.5963890506697729,
"grad_norm": 1.0234375,
"learning_rate": 1.6560590289905074e-05,
"loss": 1.7291,
"step": 112
},
{
"epoch": 0.6017139529078959,
"grad_norm": 1.0859375,
"learning_rate": 1.6494480483301836e-05,
"loss": 1.709,
"step": 113
},
{
"epoch": 0.6070388551460189,
"grad_norm": 1.0234375,
"learning_rate": 1.6427876096865394e-05,
"loss": 1.7286,
"step": 114
},
{
"epoch": 0.6123637573841417,
"grad_norm": 1.0078125,
"learning_rate": 1.636078220277764e-05,
"loss": 1.6269,
"step": 115
},
{
"epoch": 0.6176886596222647,
"grad_norm": 1.0234375,
"learning_rate": 1.6293203910498375e-05,
"loss": 1.6286,
"step": 116
},
{
"epoch": 0.6230135618603877,
"grad_norm": 1.09375,
"learning_rate": 1.6225146366376198e-05,
"loss": 1.78,
"step": 117
},
{
"epoch": 0.6283384640985107,
"grad_norm": 1.078125,
"learning_rate": 1.6156614753256583e-05,
"loss": 1.7336,
"step": 118
},
{
"epoch": 0.6336633663366337,
"grad_norm": 1.0625,
"learning_rate": 1.608761429008721e-05,
"loss": 1.6578,
"step": 119
},
{
"epoch": 0.6389882685747567,
"grad_norm": 1.015625,
"learning_rate": 1.6018150231520486e-05,
"loss": 1.6736,
"step": 120
},
{
"epoch": 0.6443131708128796,
"grad_norm": 1.0546875,
"learning_rate": 1.5948227867513416e-05,
"loss": 1.5976,
"step": 121
},
{
"epoch": 0.6496380730510026,
"grad_norm": 1.0078125,
"learning_rate": 1.5877852522924733e-05,
"loss": 1.7155,
"step": 122
},
{
"epoch": 0.6549629752891255,
"grad_norm": 1.0078125,
"learning_rate": 1.5807029557109398e-05,
"loss": 1.6595,
"step": 123
},
{
"epoch": 0.6602878775272485,
"grad_norm": 1.0234375,
"learning_rate": 1.573576436351046e-05,
"loss": 1.7354,
"step": 124
},
{
"epoch": 0.6656127797653715,
"grad_norm": 1.0703125,
"learning_rate": 1.566406236924833e-05,
"loss": 1.7401,
"step": 125
},
{
"epoch": 0.6709376820034945,
"grad_norm": 1.0625,
"learning_rate": 1.5591929034707468e-05,
"loss": 1.6774,
"step": 126
},
{
"epoch": 0.6762625842416174,
"grad_norm": 1.0078125,
"learning_rate": 1.5519369853120584e-05,
"loss": 1.6818,
"step": 127
},
{
"epoch": 0.6815874864797404,
"grad_norm": 1.0390625,
"learning_rate": 1.5446390350150272e-05,
"loss": 1.598,
"step": 128
},
{
"epoch": 0.6869123887178634,
"grad_norm": 1.015625,
"learning_rate": 1.5372996083468242e-05,
"loss": 1.7103,
"step": 129
},
{
"epoch": 0.6922372909559864,
"grad_norm": 1.015625,
"learning_rate": 1.529919264233205e-05,
"loss": 1.6196,
"step": 130
},
{
"epoch": 0.6975621931941093,
"grad_norm": 1.046875,
"learning_rate": 1.5224985647159489e-05,
"loss": 1.618,
"step": 131
},
{
"epoch": 0.7028870954322323,
"grad_norm": 1.03125,
"learning_rate": 1.5150380749100545e-05,
"loss": 1.7159,
"step": 132
},
{
"epoch": 0.7082119976703553,
"grad_norm": 0.9921875,
"learning_rate": 1.5075383629607043e-05,
"loss": 1.6372,
"step": 133
},
{
"epoch": 0.7135368999084782,
"grad_norm": 1.0625,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.7368,
"step": 134
},
{
"epoch": 0.7188618021466012,
"grad_norm": 0.97265625,
"learning_rate": 1.4924235601034673e-05,
"loss": 1.6675,
"step": 135
},
{
"epoch": 0.7241867043847242,
"grad_norm": 1.078125,
"learning_rate": 1.4848096202463373e-05,
"loss": 1.6651,
"step": 136
},
{
"epoch": 0.7295116066228472,
"grad_norm": 1.0078125,
"learning_rate": 1.4771587602596085e-05,
"loss": 1.6842,
"step": 137
},
{
"epoch": 0.7348365088609702,
"grad_norm": 1.015625,
"learning_rate": 1.469471562785891e-05,
"loss": 1.682,
"step": 138
},
{
"epoch": 0.7401614110990931,
"grad_norm": 1.03125,
"learning_rate": 1.4617486132350343e-05,
"loss": 1.697,
"step": 139
},
{
"epoch": 0.745486313337216,
"grad_norm": 1.03125,
"learning_rate": 1.4539904997395468e-05,
"loss": 1.6511,
"step": 140
},
{
"epoch": 0.750811215575339,
"grad_norm": 1.0625,
"learning_rate": 1.4461978131098089e-05,
"loss": 1.6586,
"step": 141
},
{
"epoch": 0.750811215575339,
"eval_loss": 1.6974835395812988,
"eval_runtime": 77.2891,
"eval_samples_per_second": 15.267,
"eval_steps_per_second": 15.267,
"step": 141
},
{
"epoch": 0.756136117813462,
"grad_norm": 1.0625,
"learning_rate": 1.4383711467890776e-05,
"loss": 1.7338,
"step": 142
},
{
"epoch": 0.761461020051585,
"grad_norm": 1.0234375,
"learning_rate": 1.4305110968082953e-05,
"loss": 1.6623,
"step": 143
},
{
"epoch": 0.766785922289708,
"grad_norm": 1.03125,
"learning_rate": 1.4226182617406996e-05,
"loss": 1.6748,
"step": 144
},
{
"epoch": 0.772110824527831,
"grad_norm": 1.0,
"learning_rate": 1.4146932426562391e-05,
"loss": 1.7057,
"step": 145
},
{
"epoch": 0.777435726765954,
"grad_norm": 1.0234375,
"learning_rate": 1.4067366430758004e-05,
"loss": 1.6403,
"step": 146
},
{
"epoch": 0.7827606290040768,
"grad_norm": 1.09375,
"learning_rate": 1.3987490689252463e-05,
"loss": 1.7262,
"step": 147
},
{
"epoch": 0.7880855312421998,
"grad_norm": 1.0703125,
"learning_rate": 1.3907311284892737e-05,
"loss": 1.7561,
"step": 148
},
{
"epoch": 0.7934104334803228,
"grad_norm": 1.109375,
"learning_rate": 1.3826834323650899e-05,
"loss": 1.6847,
"step": 149
},
{
"epoch": 0.7987353357184458,
"grad_norm": 1.015625,
"learning_rate": 1.3746065934159123e-05,
"loss": 1.5979,
"step": 150
},
{
"epoch": 0.8040602379565688,
"grad_norm": 1.0859375,
"learning_rate": 1.3665012267242974e-05,
"loss": 1.6537,
"step": 151
},
{
"epoch": 0.8093851401946918,
"grad_norm": 1.03125,
"learning_rate": 1.3583679495453e-05,
"loss": 1.7491,
"step": 152
},
{
"epoch": 0.8147100424328148,
"grad_norm": 1.0,
"learning_rate": 1.3502073812594677e-05,
"loss": 1.6909,
"step": 153
},
{
"epoch": 0.8200349446709376,
"grad_norm": 1.0390625,
"learning_rate": 1.342020143325669e-05,
"loss": 1.6917,
"step": 154
},
{
"epoch": 0.8253598469090606,
"grad_norm": 0.99609375,
"learning_rate": 1.333806859233771e-05,
"loss": 1.692,
"step": 155
},
{
"epoch": 0.8306847491471836,
"grad_norm": 1.0390625,
"learning_rate": 1.3255681544571568e-05,
"loss": 1.6995,
"step": 156
},
{
"epoch": 0.8360096513853066,
"grad_norm": 1.03125,
"learning_rate": 1.3173046564050923e-05,
"loss": 1.6612,
"step": 157
},
{
"epoch": 0.8413345536234296,
"grad_norm": 1.09375,
"learning_rate": 1.3090169943749475e-05,
"loss": 1.7376,
"step": 158
},
{
"epoch": 0.8466594558615526,
"grad_norm": 1.0,
"learning_rate": 1.300705799504273e-05,
"loss": 1.6703,
"step": 159
},
{
"epoch": 0.8519843580996755,
"grad_norm": 1.0546875,
"learning_rate": 1.2923717047227368e-05,
"loss": 1.6611,
"step": 160
},
{
"epoch": 0.8573092603377985,
"grad_norm": 0.95703125,
"learning_rate": 1.284015344703923e-05,
"loss": 1.6215,
"step": 161
},
{
"epoch": 0.8626341625759214,
"grad_norm": 1.046875,
"learning_rate": 1.2756373558169992e-05,
"loss": 1.7199,
"step": 162
},
{
"epoch": 0.8679590648140444,
"grad_norm": 1.0078125,
"learning_rate": 1.267238376078257e-05,
"loss": 1.6418,
"step": 163
},
{
"epoch": 0.8732839670521674,
"grad_norm": 0.9140625,
"learning_rate": 1.2588190451025209e-05,
"loss": 1.6476,
"step": 164
},
{
"epoch": 0.8786088692902904,
"grad_norm": 0.96484375,
"learning_rate": 1.2503800040544417e-05,
"loss": 1.6088,
"step": 165
},
{
"epoch": 0.8839337715284133,
"grad_norm": 0.9921875,
"learning_rate": 1.2419218955996677e-05,
"loss": 1.6919,
"step": 166
},
{
"epoch": 0.8892586737665363,
"grad_norm": 1.0625,
"learning_rate": 1.2334453638559057e-05,
"loss": 1.6118,
"step": 167
},
{
"epoch": 0.8945835760046593,
"grad_norm": 1.0546875,
"learning_rate": 1.2249510543438652e-05,
"loss": 1.7246,
"step": 168
},
{
"epoch": 0.8999084782427823,
"grad_norm": 1.0390625,
"learning_rate": 1.2164396139381029e-05,
"loss": 1.6821,
"step": 169
},
{
"epoch": 0.9052333804809052,
"grad_norm": 1.0625,
"learning_rate": 1.2079116908177592e-05,
"loss": 1.6474,
"step": 170
},
{
"epoch": 0.9105582827190282,
"grad_norm": 1.1015625,
"learning_rate": 1.1993679344171973e-05,
"loss": 1.7538,
"step": 171
},
{
"epoch": 0.9158831849571512,
"grad_norm": 1.0078125,
"learning_rate": 1.190808995376545e-05,
"loss": 1.6299,
"step": 172
},
{
"epoch": 0.9212080871952741,
"grad_norm": 1.0078125,
"learning_rate": 1.1822355254921478e-05,
"loss": 1.6671,
"step": 173
},
{
"epoch": 0.9265329894333971,
"grad_norm": 1.0078125,
"learning_rate": 1.1736481776669307e-05,
"loss": 1.6996,
"step": 174
},
{
"epoch": 0.9318578916715201,
"grad_norm": 1.0546875,
"learning_rate": 1.1650476058606776e-05,
"loss": 1.6863,
"step": 175
},
{
"epoch": 0.9371827939096431,
"grad_norm": 1.1171875,
"learning_rate": 1.156434465040231e-05,
"loss": 1.7013,
"step": 176
},
{
"epoch": 0.9425076961477661,
"grad_norm": 0.9921875,
"learning_rate": 1.1478094111296109e-05,
"loss": 1.7416,
"step": 177
},
{
"epoch": 0.947832598385889,
"grad_norm": 1.03125,
"learning_rate": 1.1391731009600655e-05,
"loss": 1.7964,
"step": 178
},
{
"epoch": 0.9531575006240119,
"grad_norm": 1.046875,
"learning_rate": 1.130526192220052e-05,
"loss": 1.761,
"step": 179
},
{
"epoch": 0.9584824028621349,
"grad_norm": 1.0234375,
"learning_rate": 1.1218693434051475e-05,
"loss": 1.6999,
"step": 180
},
{
"epoch": 0.9638073051002579,
"grad_norm": 1.0546875,
"learning_rate": 1.113203213767907e-05,
"loss": 1.69,
"step": 181
},
{
"epoch": 0.9691322073383809,
"grad_norm": 0.953125,
"learning_rate": 1.1045284632676535e-05,
"loss": 1.6777,
"step": 182
},
{
"epoch": 0.9744571095765039,
"grad_norm": 1.0234375,
"learning_rate": 1.0958457525202241e-05,
"loss": 1.6792,
"step": 183
},
{
"epoch": 0.9797820118146269,
"grad_norm": 1.03125,
"learning_rate": 1.0871557427476585e-05,
"loss": 1.6724,
"step": 184
},
{
"epoch": 0.9851069140527499,
"grad_norm": 1.0625,
"learning_rate": 1.0784590957278452e-05,
"loss": 1.7415,
"step": 185
},
{
"epoch": 0.9904318162908727,
"grad_norm": 1.0,
"learning_rate": 1.0697564737441254e-05,
"loss": 1.6796,
"step": 186
},
{
"epoch": 0.9957567185289957,
"grad_norm": 1.015625,
"learning_rate": 1.0610485395348571e-05,
"loss": 1.6186,
"step": 187
},
{
"epoch": 1.0010816207671187,
"grad_norm": 0.984375,
"learning_rate": 1.0523359562429441e-05,
"loss": 1.6741,
"step": 188
},
{
"epoch": 1.0010816207671187,
"eval_loss": 1.6922072172164917,
"eval_runtime": 77.3424,
"eval_samples_per_second": 15.257,
"eval_steps_per_second": 15.257,
"step": 188
},
{
"epoch": 1.0064065230052417,
"grad_norm": 0.9921875,
"learning_rate": 1.0436193873653362e-05,
"loss": 1.7202,
"step": 189
},
{
"epoch": 1.0016640319494134,
"grad_norm": 0.9921875,
"learning_rate": 1.0348994967025012e-05,
"loss": 1.639,
"step": 190
},
{
"epoch": 1.0069889341875364,
"grad_norm": 1.0546875,
"learning_rate": 1.0261769483078734e-05,
"loss": 1.6223,
"step": 191
},
{
"epoch": 1.0123138364256594,
"grad_norm": 1.0078125,
"learning_rate": 1.0174524064372837e-05,
"loss": 1.7193,
"step": 192
},
{
"epoch": 1.0176387386637824,
"grad_norm": 1.0078125,
"learning_rate": 1.008726535498374e-05,
"loss": 1.6904,
"step": 193
},
{
"epoch": 1.0229636409019054,
"grad_norm": 1.03125,
"learning_rate": 1e-05,
"loss": 1.6921,
"step": 194
},
{
"epoch": 1.0282885431400284,
"grad_norm": 0.9921875,
"learning_rate": 9.912734645016262e-06,
"loss": 1.6593,
"step": 195
},
{
"epoch": 1.0336134453781514,
"grad_norm": 0.97265625,
"learning_rate": 9.825475935627165e-06,
"loss": 1.6469,
"step": 196
},
{
"epoch": 1.0389383476162741,
"grad_norm": 0.9921875,
"learning_rate": 9.738230516921272e-06,
"loss": 1.5877,
"step": 197
},
{
"epoch": 1.0442632498543971,
"grad_norm": 1.03125,
"learning_rate": 9.651005032974994e-06,
"loss": 1.6726,
"step": 198
},
{
"epoch": 1.04958815209252,
"grad_norm": 1.0,
"learning_rate": 9.563806126346643e-06,
"loss": 1.6607,
"step": 199
},
{
"epoch": 1.054913054330643,
"grad_norm": 1.015625,
"learning_rate": 9.476640437570562e-06,
"loss": 1.6926,
"step": 200
},
{
"epoch": 1.060237956568766,
"grad_norm": 1.015625,
"learning_rate": 9.38951460465143e-06,
"loss": 1.6241,
"step": 201
},
{
"epoch": 1.065562858806889,
"grad_norm": 0.9921875,
"learning_rate": 9.302435262558748e-06,
"loss": 1.6431,
"step": 202
},
{
"epoch": 1.070887761045012,
"grad_norm": 1.0234375,
"learning_rate": 9.215409042721553e-06,
"loss": 1.6339,
"step": 203
},
{
"epoch": 1.076212663283135,
"grad_norm": 1.0,
"learning_rate": 9.128442572523418e-06,
"loss": 1.6701,
"step": 204
},
{
"epoch": 1.081537565521258,
"grad_norm": 0.98828125,
"learning_rate": 9.04154247479776e-06,
"loss": 1.6059,
"step": 205
},
{
"epoch": 1.086862467759381,
"grad_norm": 1.0234375,
"learning_rate": 8.954715367323468e-06,
"loss": 1.6638,
"step": 206
},
{
"epoch": 1.092187369997504,
"grad_norm": 1.09375,
"learning_rate": 8.867967862320935e-06,
"loss": 1.6428,
"step": 207
},
{
"epoch": 1.097512272235627,
"grad_norm": 0.9765625,
"learning_rate": 8.781306565948528e-06,
"loss": 1.6424,
"step": 208
},
{
"epoch": 1.10283717447375,
"grad_norm": 0.984375,
"learning_rate": 8.694738077799487e-06,
"loss": 1.6105,
"step": 209
},
{
"epoch": 1.108162076711873,
"grad_norm": 1.0,
"learning_rate": 8.60826899039935e-06,
"loss": 1.7068,
"step": 210
},
{
"epoch": 1.113486978949996,
"grad_norm": 1.0859375,
"learning_rate": 8.521905888703894e-06,
"loss": 1.7118,
"step": 211
},
{
"epoch": 1.118811881188119,
"grad_norm": 1.0625,
"learning_rate": 8.43565534959769e-06,
"loss": 1.6553,
"step": 212
},
{
"epoch": 1.1241367834262417,
"grad_norm": 1.0703125,
"learning_rate": 8.349523941393224e-06,
"loss": 1.6909,
"step": 213
},
{
"epoch": 1.1294616856643647,
"grad_norm": 1.0546875,
"learning_rate": 8.263518223330698e-06,
"loss": 1.7384,
"step": 214
},
{
"epoch": 1.1347865879024877,
"grad_norm": 1.03125,
"learning_rate": 8.177644745078525e-06,
"loss": 1.6182,
"step": 215
},
{
"epoch": 1.1401114901406106,
"grad_norm": 1.125,
"learning_rate": 8.091910046234552e-06,
"loss": 1.7063,
"step": 216
},
{
"epoch": 1.1454363923787336,
"grad_norm": 0.96484375,
"learning_rate": 8.00632065582803e-06,
"loss": 1.6621,
"step": 217
},
{
"epoch": 1.1507612946168566,
"grad_norm": 0.98828125,
"learning_rate": 7.92088309182241e-06,
"loss": 1.7231,
"step": 218
},
{
"epoch": 1.1560861968549796,
"grad_norm": 1.015625,
"learning_rate": 7.835603860618973e-06,
"loss": 1.6707,
"step": 219
},
{
"epoch": 1.1614110990931026,
"grad_norm": 1.015625,
"learning_rate": 7.750489456561351e-06,
"loss": 1.6226,
"step": 220
},
{
"epoch": 1.1667360013312256,
"grad_norm": 1.0703125,
"learning_rate": 7.66554636144095e-06,
"loss": 1.6862,
"step": 221
},
{
"epoch": 1.1720609035693486,
"grad_norm": 1.0625,
"learning_rate": 7.580781044003324e-06,
"loss": 1.7325,
"step": 222
},
{
"epoch": 1.1773858058074715,
"grad_norm": 1.03125,
"learning_rate": 7.496199959455584e-06,
"loss": 1.6573,
"step": 223
},
{
"epoch": 1.1827107080455945,
"grad_norm": 1.03125,
"learning_rate": 7.411809548974792e-06,
"loss": 1.6594,
"step": 224
},
{
"epoch": 1.1880356102837175,
"grad_norm": 1.015625,
"learning_rate": 7.327616239217432e-06,
"loss": 1.6523,
"step": 225
},
{
"epoch": 1.1933605125218405,
"grad_norm": 1.0546875,
"learning_rate": 7.243626441830009e-06,
"loss": 1.6895,
"step": 226
},
{
"epoch": 1.1986854147599635,
"grad_norm": 0.99609375,
"learning_rate": 7.159846552960774e-06,
"loss": 1.6883,
"step": 227
},
{
"epoch": 1.2040103169980862,
"grad_norm": 0.9921875,
"learning_rate": 7.076282952772634e-06,
"loss": 1.5706,
"step": 228
},
{
"epoch": 1.2093352192362095,
"grad_norm": 0.95703125,
"learning_rate": 6.992942004957271e-06,
"loss": 1.5938,
"step": 229
},
{
"epoch": 1.2146601214743322,
"grad_norm": 1.046875,
"learning_rate": 6.909830056250527e-06,
"loss": 1.6963,
"step": 230
},
{
"epoch": 1.2199850237124552,
"grad_norm": 1.0703125,
"learning_rate": 6.826953435949081e-06,
"loss": 1.6565,
"step": 231
},
{
"epoch": 1.2253099259505782,
"grad_norm": 1.0078125,
"learning_rate": 6.744318455428436e-06,
"loss": 1.657,
"step": 232
},
{
"epoch": 1.2306348281887012,
"grad_norm": 1.09375,
"learning_rate": 6.661931407662292e-06,
"loss": 1.6942,
"step": 233
},
{
"epoch": 1.2359597304268242,
"grad_norm": 0.94921875,
"learning_rate": 6.579798566743314e-06,
"loss": 1.6247,
"step": 234
},
{
"epoch": 1.2412846326649472,
"grad_norm": 1.0078125,
"learning_rate": 6.497926187405326e-06,
"loss": 1.6845,
"step": 235
},
{
"epoch": 1.2412846326649472,
"eval_loss": 1.6904007196426392,
"eval_runtime": 77.2338,
"eval_samples_per_second": 15.278,
"eval_steps_per_second": 15.278,
"step": 235
},
{
"epoch": 1.2466095349030701,
"grad_norm": 1.046875,
"learning_rate": 6.4163205045469975e-06,
"loss": 1.6958,
"step": 236
},
{
"epoch": 1.2519344371411931,
"grad_norm": 1.109375,
"learning_rate": 6.334987732757028e-06,
"loss": 1.589,
"step": 237
},
{
"epoch": 1.257259339379316,
"grad_norm": 1.0390625,
"learning_rate": 6.25393406584088e-06,
"loss": 1.6417,
"step": 238
},
{
"epoch": 1.262584241617439,
"grad_norm": 0.9609375,
"learning_rate": 6.173165676349103e-06,
"loss": 1.6412,
"step": 239
},
{
"epoch": 1.267909143855562,
"grad_norm": 1.046875,
"learning_rate": 6.092688715107265e-06,
"loss": 1.6539,
"step": 240
},
{
"epoch": 1.273234046093685,
"grad_norm": 1.03125,
"learning_rate": 6.0125093107475385e-06,
"loss": 1.6194,
"step": 241
},
{
"epoch": 1.278558948331808,
"grad_norm": 0.9921875,
"learning_rate": 5.932633569242e-06,
"loss": 1.6566,
"step": 242
},
{
"epoch": 1.2838838505699308,
"grad_norm": 1.0234375,
"learning_rate": 5.853067573437612e-06,
"loss": 1.6734,
"step": 243
},
{
"epoch": 1.289208752808054,
"grad_norm": 1.046875,
"learning_rate": 5.773817382593008e-06,
"loss": 1.7109,
"step": 244
},
{
"epoch": 1.2945336550461768,
"grad_norm": 1.015625,
"learning_rate": 5.694889031917047e-06,
"loss": 1.5984,
"step": 245
},
{
"epoch": 1.2998585572842998,
"grad_norm": 1.046875,
"learning_rate": 5.616288532109225e-06,
"loss": 1.7059,
"step": 246
},
{
"epoch": 1.3051834595224228,
"grad_norm": 1.0390625,
"learning_rate": 5.5380218689019125e-06,
"loss": 1.6666,
"step": 247
},
{
"epoch": 1.3105083617605457,
"grad_norm": 1.0234375,
"learning_rate": 5.460095002604533e-06,
"loss": 1.6752,
"step": 248
},
{
"epoch": 1.3158332639986687,
"grad_norm": 1.0625,
"learning_rate": 5.382513867649663e-06,
"loss": 1.684,
"step": 249
},
{
"epoch": 1.3211581662367917,
"grad_norm": 0.98046875,
"learning_rate": 5.305284372141095e-06,
"loss": 1.6072,
"step": 250
},
{
"epoch": 1.3264830684749147,
"grad_norm": 0.9296875,
"learning_rate": 5.228412397403916e-06,
"loss": 1.4978,
"step": 251
},
{
"epoch": 1.3318079707130377,
"grad_norm": 1.0390625,
"learning_rate": 5.151903797536631e-06,
"loss": 1.6164,
"step": 252
},
{
"epoch": 1.3371328729511607,
"grad_norm": 1.0703125,
"learning_rate": 5.075764398965331e-06,
"loss": 1.5904,
"step": 253
},
{
"epoch": 1.3424577751892837,
"grad_norm": 1.0,
"learning_rate": 5.000000000000003e-06,
"loss": 1.5924,
"step": 254
},
{
"epoch": 1.3477826774274067,
"grad_norm": 1.0390625,
"learning_rate": 4.924616370392962e-06,
"loss": 1.6521,
"step": 255
},
{
"epoch": 1.3531075796655296,
"grad_norm": 1.0234375,
"learning_rate": 4.849619250899458e-06,
"loss": 1.6124,
"step": 256
},
{
"epoch": 1.3584324819036526,
"grad_norm": 1.0234375,
"learning_rate": 4.775014352840512e-06,
"loss": 1.6634,
"step": 257
},
{
"epoch": 1.3637573841417754,
"grad_norm": 0.984375,
"learning_rate": 4.700807357667953e-06,
"loss": 1.628,
"step": 258
},
{
"epoch": 1.3690822863798986,
"grad_norm": 1.046875,
"learning_rate": 4.627003916531761e-06,
"loss": 1.7282,
"step": 259
},
{
"epoch": 1.3744071886180214,
"grad_norm": 1.0625,
"learning_rate": 4.5536096498497295e-06,
"loss": 1.7081,
"step": 260
},
{
"epoch": 1.3797320908561446,
"grad_norm": 1.03125,
"learning_rate": 4.480630146879419e-06,
"loss": 1.6772,
"step": 261
},
{
"epoch": 1.3850569930942673,
"grad_norm": 1.0234375,
"learning_rate": 4.408070965292534e-06,
"loss": 1.695,
"step": 262
},
{
"epoch": 1.3903818953323903,
"grad_norm": 0.97265625,
"learning_rate": 4.335937630751675e-06,
"loss": 1.6414,
"step": 263
},
{
"epoch": 1.3957067975705133,
"grad_norm": 1.015625,
"learning_rate": 4.264235636489542e-06,
"loss": 1.6425,
"step": 264
},
{
"epoch": 1.4010316998086363,
"grad_norm": 1.0390625,
"learning_rate": 4.192970442890602e-06,
"loss": 1.6466,
"step": 265
},
{
"epoch": 1.4063566020467593,
"grad_norm": 1.0,
"learning_rate": 4.12214747707527e-06,
"loss": 1.6378,
"step": 266
},
{
"epoch": 1.4116815042848823,
"grad_norm": 1.015625,
"learning_rate": 4.051772132486589e-06,
"loss": 1.718,
"step": 267
},
{
"epoch": 1.4170064065230052,
"grad_norm": 1.1015625,
"learning_rate": 3.981849768479516e-06,
"loss": 1.6534,
"step": 268
},
{
"epoch": 1.4223313087611282,
"grad_norm": 0.98046875,
"learning_rate": 3.912385709912794e-06,
"loss": 1.6769,
"step": 269
},
{
"epoch": 1.4276562109992512,
"grad_norm": 1.046875,
"learning_rate": 3.8433852467434175e-06,
"loss": 1.6337,
"step": 270
},
{
"epoch": 1.4329811132373742,
"grad_norm": 1.0625,
"learning_rate": 3.774853633623806e-06,
"loss": 1.7151,
"step": 271
},
{
"epoch": 1.4383060154754972,
"grad_norm": 1.0234375,
"learning_rate": 3.7067960895016277e-06,
"loss": 1.6018,
"step": 272
},
{
"epoch": 1.4436309177136202,
"grad_norm": 1.03125,
"learning_rate": 3.6392177972223596e-06,
"loss": 1.597,
"step": 273
},
{
"epoch": 1.4489558199517432,
"grad_norm": 1.0390625,
"learning_rate": 3.5721239031346067e-06,
"loss": 1.6465,
"step": 274
},
{
"epoch": 1.454280722189866,
"grad_norm": 1.03125,
"learning_rate": 3.505519516698165e-06,
"loss": 1.7173,
"step": 275
},
{
"epoch": 1.4596056244279891,
"grad_norm": 1.015625,
"learning_rate": 3.4394097100949286e-06,
"loss": 1.5711,
"step": 276
},
{
"epoch": 1.464930526666112,
"grad_norm": 1.03125,
"learning_rate": 3.3737995178426276e-06,
"loss": 1.7184,
"step": 277
},
{
"epoch": 1.4702554289042349,
"grad_norm": 1.0234375,
"learning_rate": 3.308693936411421e-06,
"loss": 1.6222,
"step": 278
},
{
"epoch": 1.4755803311423579,
"grad_norm": 0.99609375,
"learning_rate": 3.2440979238433977e-06,
"loss": 1.7164,
"step": 279
},
{
"epoch": 1.4809052333804809,
"grad_norm": 1.03125,
"learning_rate": 3.1800163993750166e-06,
"loss": 1.8001,
"step": 280
},
{
"epoch": 1.4862301356186038,
"grad_norm": 1.125,
"learning_rate": 3.116454243062459e-06,
"loss": 1.6933,
"step": 281
},
{
"epoch": 1.4915550378567268,
"grad_norm": 1.0234375,
"learning_rate": 3.0534162954100264e-06,
"loss": 1.6367,
"step": 282
},
{
"epoch": 1.4915550378567268,
"eval_loss": 1.6898616552352905,
"eval_runtime": 78.3804,
"eval_samples_per_second": 15.055,
"eval_steps_per_second": 15.055,
"step": 282
},
{
"epoch": 1.4968799400948498,
"grad_norm": 1.015625,
"learning_rate": 2.990907357001491e-06,
"loss": 1.6462,
"step": 283
},
{
"epoch": 1.5022048423329728,
"grad_norm": 0.9921875,
"learning_rate": 2.9289321881345257e-06,
"loss": 1.6232,
"step": 284
},
{
"epoch": 1.5075297445710958,
"grad_norm": 1.015625,
"learning_rate": 2.867495508458186e-06,
"loss": 1.7229,
"step": 285
},
{
"epoch": 1.5128546468092188,
"grad_norm": 1.03125,
"learning_rate": 2.8066019966134907e-06,
"loss": 1.6581,
"step": 286
},
{
"epoch": 1.5181795490473418,
"grad_norm": 0.98046875,
"learning_rate": 2.746256289877126e-06,
"loss": 1.6565,
"step": 287
},
{
"epoch": 1.5235044512854645,
"grad_norm": 1.015625,
"learning_rate": 2.6864629838082957e-06,
"loss": 1.646,
"step": 288
},
{
"epoch": 1.5288293535235877,
"grad_norm": 0.97265625,
"learning_rate": 2.6272266318987606e-06,
"loss": 1.6165,
"step": 289
},
{
"epoch": 1.5341542557617105,
"grad_norm": 0.953125,
"learning_rate": 2.5685517452260566e-06,
"loss": 1.6342,
"step": 290
},
{
"epoch": 1.5394791579998337,
"grad_norm": 1.0390625,
"learning_rate": 2.5104427921099783e-06,
"loss": 1.6765,
"step": 291
},
{
"epoch": 1.5448040602379565,
"grad_norm": 1.0078125,
"learning_rate": 2.45290419777228e-06,
"loss": 1.6634,
"step": 292
},
{
"epoch": 1.5501289624760797,
"grad_norm": 0.98828125,
"learning_rate": 2.395940343999691e-06,
"loss": 1.6478,
"step": 293
},
{
"epoch": 1.5554538647142024,
"grad_norm": 1.0546875,
"learning_rate": 2.339555568810221e-06,
"loss": 1.6321,
"step": 294
},
{
"epoch": 1.5607787669523256,
"grad_norm": 1.03125,
"learning_rate": 2.2837541661228024e-06,
"loss": 1.7033,
"step": 295
},
{
"epoch": 1.5661036691904484,
"grad_norm": 0.95703125,
"learning_rate": 2.2285403854302912e-06,
"loss": 1.562,
"step": 296
},
{
"epoch": 1.5714285714285714,
"grad_norm": 1.0078125,
"learning_rate": 2.173918431475861e-06,
"loss": 1.6686,
"step": 297
},
{
"epoch": 1.5767534736666944,
"grad_norm": 1.015625,
"learning_rate": 2.119892463932781e-06,
"loss": 1.5676,
"step": 298
},
{
"epoch": 1.5820783759048174,
"grad_norm": 0.9921875,
"learning_rate": 2.0664665970876496e-06,
"loss": 1.6761,
"step": 299
},
{
"epoch": 1.5874032781429404,
"grad_norm": 1.015625,
"learning_rate": 2.013644899527074e-06,
"loss": 1.6786,
"step": 300
},
{
"epoch": 1.5927281803810633,
"grad_norm": 1.0625,
"learning_rate": 1.961431393827827e-06,
"loss": 1.6917,
"step": 301
},
{
"epoch": 1.5980530826191863,
"grad_norm": 1.0,
"learning_rate": 1.9098300562505266e-06,
"loss": 1.6204,
"step": 302
},
{
"epoch": 1.6033779848573093,
"grad_norm": 1.046875,
"learning_rate": 1.858844816436809e-06,
"loss": 1.6689,
"step": 303
},
{
"epoch": 1.6087028870954323,
"grad_norm": 0.98046875,
"learning_rate": 1.808479557110081e-06,
"loss": 1.7041,
"step": 304
},
{
"epoch": 1.614027789333555,
"grad_norm": 0.96875,
"learning_rate": 1.7587381137798432e-06,
"loss": 1.6656,
"step": 305
},
{
"epoch": 1.6193526915716783,
"grad_norm": 1.0,
"learning_rate": 1.709624274449584e-06,
"loss": 1.6269,
"step": 306
},
{
"epoch": 1.624677593809801,
"grad_norm": 1.03125,
"learning_rate": 1.6611417793283192e-06,
"loss": 1.5737,
"step": 307
},
{
"epoch": 1.6300024960479242,
"grad_norm": 1.0078125,
"learning_rate": 1.6132943205457607e-06,
"loss": 1.722,
"step": 308
},
{
"epoch": 1.635327398286047,
"grad_norm": 0.99609375,
"learning_rate": 1.566085541871145e-06,
"loss": 1.683,
"step": 309
},
{
"epoch": 1.6406523005241702,
"grad_norm": 1.0546875,
"learning_rate": 1.5195190384357405e-06,
"loss": 1.6843,
"step": 310
},
{
"epoch": 1.645977202762293,
"grad_norm": 1.0390625,
"learning_rate": 1.4735983564590784e-06,
"loss": 1.6979,
"step": 311
},
{
"epoch": 1.651302105000416,
"grad_norm": 1.015625,
"learning_rate": 1.4283269929788779e-06,
"loss": 1.6396,
"step": 312
},
{
"epoch": 1.656627007238539,
"grad_norm": 0.99609375,
"learning_rate": 1.3837083955847418e-06,
"loss": 1.6738,
"step": 313
},
{
"epoch": 1.661951909476662,
"grad_norm": 0.94921875,
"learning_rate": 1.339745962155613e-06,
"loss": 1.6566,
"step": 314
},
{
"epoch": 1.667276811714785,
"grad_norm": 1.0078125,
"learning_rate": 1.2964430406010032e-06,
"loss": 1.6679,
"step": 315
},
{
"epoch": 1.672601713952908,
"grad_norm": 1.0,
"learning_rate": 1.2538029286060428e-06,
"loss": 1.6892,
"step": 316
},
{
"epoch": 1.677926616191031,
"grad_norm": 1.0390625,
"learning_rate": 1.2118288733803474e-06,
"loss": 1.6914,
"step": 317
},
{
"epoch": 1.6832515184291539,
"grad_norm": 1.015625,
"learning_rate": 1.1705240714107301e-06,
"loss": 1.5954,
"step": 318
},
{
"epoch": 1.6885764206672769,
"grad_norm": 0.9765625,
"learning_rate": 1.129891668217783e-06,
"loss": 1.633,
"step": 319
},
{
"epoch": 1.6939013229053996,
"grad_norm": 1.0546875,
"learning_rate": 1.0899347581163222e-06,
"loss": 1.6976,
"step": 320
},
{
"epoch": 1.6992262251435228,
"grad_norm": 0.9921875,
"learning_rate": 1.0506563839797501e-06,
"loss": 1.6283,
"step": 321
},
{
"epoch": 1.7045511273816456,
"grad_norm": 0.9765625,
"learning_rate": 1.012059537008332e-06,
"loss": 1.6094,
"step": 322
},
{
"epoch": 1.7098760296197688,
"grad_norm": 1.0390625,
"learning_rate": 9.74147156501396e-07,
"loss": 1.6049,
"step": 323
},
{
"epoch": 1.7152009318578916,
"grad_norm": 1.0546875,
"learning_rate": 9.369221296335007e-07,
"loss": 1.6529,
"step": 324
},
{
"epoch": 1.7205258340960148,
"grad_norm": 1.09375,
"learning_rate": 9.00387291234569e-07,
"loss": 1.7539,
"step": 325
},
{
"epoch": 1.7258507363341375,
"grad_norm": 1.03125,
"learning_rate": 8.645454235739903e-07,
"loss": 1.6844,
"step": 326
},
{
"epoch": 1.7311756385722605,
"grad_norm": 0.98046875,
"learning_rate": 8.293992561487596e-07,
"loss": 1.6409,
"step": 327
},
{
"epoch": 1.7365005408103835,
"grad_norm": 1.03125,
"learning_rate": 7.949514654755963e-07,
"loss": 1.7356,
"step": 328
},
{
"epoch": 1.7418254430485065,
"grad_norm": 1.0625,
"learning_rate": 7.612046748871327e-07,
"loss": 1.6681,
"step": 329
},
{
"epoch": 1.7418254430485065,
"eval_loss": 1.6896613836288452,
"eval_runtime": 77.1918,
"eval_samples_per_second": 15.287,
"eval_steps_per_second": 15.287,
"step": 329
},
{
"epoch": 1.7471503452866295,
"grad_norm": 1.046875,
"learning_rate": 7.281614543321269e-07,
"loss": 1.6493,
"step": 330
},
{
"epoch": 1.7524752475247525,
"grad_norm": 1.0234375,
"learning_rate": 6.958243201797554e-07,
"loss": 1.6299,
"step": 331
},
{
"epoch": 1.7578001497628755,
"grad_norm": 1.0234375,
"learning_rate": 6.641957350279838e-07,
"loss": 1.6882,
"step": 332
},
{
"epoch": 1.7631250520009984,
"grad_norm": 1.0390625,
"learning_rate": 6.332781075160244e-07,
"loss": 1.6256,
"step": 333
},
{
"epoch": 1.7684499542391214,
"grad_norm": 1.0234375,
"learning_rate": 6.030737921409169e-07,
"loss": 1.5845,
"step": 334
},
{
"epoch": 1.7737748564772442,
"grad_norm": 0.984375,
"learning_rate": 5.735850890782158e-07,
"loss": 1.6066,
"step": 335
},
{
"epoch": 1.7790997587153674,
"grad_norm": 1.03125,
"learning_rate": 5.448142440068316e-07,
"loss": 1.6751,
"step": 336
},
{
"epoch": 1.7844246609534902,
"grad_norm": 0.97265625,
"learning_rate": 5.167634479380068e-07,
"loss": 1.6368,
"step": 337
},
{
"epoch": 1.7897495631916134,
"grad_norm": 1.0234375,
"learning_rate": 4.894348370484648e-07,
"loss": 1.7731,
"step": 338
},
{
"epoch": 1.7950744654297361,
"grad_norm": 1.03125,
"learning_rate": 4.628304925177318e-07,
"loss": 1.6714,
"step": 339
},
{
"epoch": 1.8003993676678594,
"grad_norm": 1.1015625,
"learning_rate": 4.3695244036964567e-07,
"loss": 1.7154,
"step": 340
},
{
"epoch": 1.8057242699059821,
"grad_norm": 0.94921875,
"learning_rate": 4.118026513180695e-07,
"loss": 1.5225,
"step": 341
},
{
"epoch": 1.8110491721441053,
"grad_norm": 1.0,
"learning_rate": 3.8738304061681107e-07,
"loss": 1.6143,
"step": 342
},
{
"epoch": 1.816374074382228,
"grad_norm": 1.0,
"learning_rate": 3.6369546791377054e-07,
"loss": 1.6301,
"step": 343
},
{
"epoch": 1.821698976620351,
"grad_norm": 0.95703125,
"learning_rate": 3.4074173710931804e-07,
"loss": 1.5861,
"step": 344
},
{
"epoch": 1.827023878858474,
"grad_norm": 0.9921875,
"learning_rate": 3.185235962189237e-07,
"loss": 1.6469,
"step": 345
},
{
"epoch": 1.832348781096597,
"grad_norm": 0.95703125,
"learning_rate": 2.970427372400353e-07,
"loss": 1.5941,
"step": 346
},
{
"epoch": 1.83767368333472,
"grad_norm": 0.9609375,
"learning_rate": 2.7630079602323447e-07,
"loss": 1.6405,
"step": 347
},
{
"epoch": 1.842998585572843,
"grad_norm": 1.03125,
"learning_rate": 2.5629935214764866e-07,
"loss": 1.6329,
"step": 348
},
{
"epoch": 1.848323487810966,
"grad_norm": 1.03125,
"learning_rate": 2.370399288006664e-07,
"loss": 1.62,
"step": 349
},
{
"epoch": 1.853648390049089,
"grad_norm": 1.0078125,
"learning_rate": 2.1852399266194312e-07,
"loss": 1.5775,
"step": 350
},
{
"epoch": 1.858973292287212,
"grad_norm": 0.984375,
"learning_rate": 2.0075295379170413e-07,
"loss": 1.6226,
"step": 351
},
{
"epoch": 1.8642981945253347,
"grad_norm": 1.0234375,
"learning_rate": 1.8372816552336025e-07,
"loss": 1.5957,
"step": 352
},
{
"epoch": 1.869623096763458,
"grad_norm": 1.015625,
"learning_rate": 1.6745092436045495e-07,
"loss": 1.6389,
"step": 353
},
{
"epoch": 1.8749479990015807,
"grad_norm": 1.0546875,
"learning_rate": 1.519224698779198e-07,
"loss": 1.6588,
"step": 354
},
{
"epoch": 1.880272901239704,
"grad_norm": 0.9765625,
"learning_rate": 1.3714398462768563e-07,
"loss": 1.5915,
"step": 355
},
{
"epoch": 1.8855978034778267,
"grad_norm": 1.03125,
"learning_rate": 1.231165940486234e-07,
"loss": 1.6454,
"step": 356
},
{
"epoch": 1.89092270571595,
"grad_norm": 1.03125,
"learning_rate": 1.0984136638083176e-07,
"loss": 1.6706,
"step": 357
},
{
"epoch": 1.8962476079540727,
"grad_norm": 1.046875,
"learning_rate": 9.731931258429638e-08,
"loss": 1.6479,
"step": 358
},
{
"epoch": 1.9015725101921956,
"grad_norm": 0.93359375,
"learning_rate": 8.555138626189619e-08,
"loss": 1.6405,
"step": 359
},
{
"epoch": 1.9068974124303186,
"grad_norm": 1.0234375,
"learning_rate": 7.453848358678018e-08,
"loss": 1.6638,
"step": 360
},
{
"epoch": 1.9122223146684416,
"grad_norm": 1.046875,
"learning_rate": 6.428144323412544e-08,
"loss": 1.6709,
"step": 361
},
{
"epoch": 1.9175472169065646,
"grad_norm": 1.0546875,
"learning_rate": 5.4781046317267103e-08,
"loss": 1.6191,
"step": 362
},
{
"epoch": 1.9228721191446876,
"grad_norm": 1.0390625,
"learning_rate": 4.603801632821148e-08,
"loss": 1.7144,
"step": 363
},
{
"epoch": 1.9281970213828106,
"grad_norm": 1.0078125,
"learning_rate": 3.805301908254455e-08,
"loss": 1.6358,
"step": 364
},
{
"epoch": 1.9335219236209336,
"grad_norm": 1.0078125,
"learning_rate": 3.082666266872036e-08,
"loss": 1.6961,
"step": 365
},
{
"epoch": 1.9388468258590565,
"grad_norm": 1.046875,
"learning_rate": 2.4359497401758026e-08,
"loss": 1.6074,
"step": 366
},
{
"epoch": 1.9441717280971793,
"grad_norm": 1.03125,
"learning_rate": 1.86520157813308e-08,
"loss": 1.5905,
"step": 367
},
{
"epoch": 1.9494966303353025,
"grad_norm": 0.97265625,
"learning_rate": 1.370465245426167e-08,
"loss": 1.6317,
"step": 368
},
{
"epoch": 1.9548215325734253,
"grad_norm": 0.98828125,
"learning_rate": 9.517784181422018e-09,
"loss": 1.5783,
"step": 369
},
{
"epoch": 1.9601464348115485,
"grad_norm": 0.98828125,
"learning_rate": 6.091729809042379e-09,
"loss": 1.7104,
"step": 370
},
{
"epoch": 1.9654713370496713,
"grad_norm": 1.0546875,
"learning_rate": 3.4267502444274013e-09,
"loss": 1.7328,
"step": 371
},
{
"epoch": 1.9707962392877945,
"grad_norm": 1.03125,
"learning_rate": 1.5230484360873043e-09,
"loss": 1.6749,
"step": 372
},
{
"epoch": 1.9761211415259172,
"grad_norm": 0.98046875,
"learning_rate": 3.807693582869032e-10,
"loss": 1.5706,
"step": 373
},
{
"epoch": 1.9814460437640404,
"grad_norm": 1.0703125,
"learning_rate": 0.0,
"loss": 1.662,
"step": 374
}
],
"logging_steps": 1,
"max_steps": 374,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 187,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.8540467560146534e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}