{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9836867862969005,
  "eval_steps": 500,
  "global_step": 152,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.9706,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.9709,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 6e-06,
      "loss": 1.969,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.9386,
      "step": 4
    },
    {
      "epoch": 0.07,
      "learning_rate": 1e-05,
      "loss": 1.9129,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.99885820390154e-06,
      "loss": 1.8105,
      "step": 6
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.995433337085492e-06,
      "loss": 1.8118,
      "step": 7
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.989726963751683e-06,
      "loss": 1.7729,
      "step": 8
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.981741690106035e-06,
      "loss": 1.7652,
      "step": 9
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.97148116317027e-06,
      "loss": 1.7182,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.95895006911623e-06,
      "loss": 1.7277,
      "step": 11
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.944154131125643e-06,
      "loss": 1.6587,
      "step": 12
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.927100106776213e-06,
      "loss": 1.6772,
      "step": 13
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.907795784955327e-06,
      "loss": 1.6292,
      "step": 14
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.88624998230272e-06,
      "loss": 1.6161,
      "step": 15
    },
    {
      "epoch": 0.21,
      "learning_rate": 9.862472539183757e-06,
      "loss": 1.6353,
      "step": 16
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.836474315195148e-06,
      "loss": 1.6141,
      "step": 17
    },
    {
      "epoch": 0.23,
      "learning_rate": 9.808267184205182e-06,
      "loss": 1.6154,
      "step": 18
    },
    {
      "epoch": 0.25,
      "learning_rate": 9.777864028930705e-06,
      "loss": 1.568,
      "step": 19
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.745278735053345e-06,
      "loss": 1.6019,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.710526184877667e-06,
      "loss": 1.5974,
      "step": 21
    },
    {
      "epoch": 0.29,
      "learning_rate": 9.673622250534155e-06,
      "loss": 1.5645,
      "step": 22
    },
    {
      "epoch": 0.3,
      "learning_rate": 9.63458378673011e-06,
      "loss": 1.5472,
      "step": 23
    },
    {
      "epoch": 0.31,
      "learning_rate": 9.593428623051793e-06,
      "loss": 1.5662,
      "step": 24
    },
    {
      "epoch": 0.33,
      "learning_rate": 9.550175555821333e-06,
      "loss": 1.5278,
      "step": 25
    },
    {
      "epoch": 0.34,
      "learning_rate": 9.504844339512096e-06,
      "loss": 1.5819,
      "step": 26
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.457455677726447e-06,
      "loss": 1.5355,
      "step": 27
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.408031213740045e-06,
      "loss": 1.5449,
      "step": 28
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.356593520616948e-06,
      "loss": 1.5327,
      "step": 29
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.303166090900082e-06,
      "loss": 1.4996,
      "step": 30
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.24777332588177e-06,
      "loss": 1.4838,
      "step": 31
    },
    {
      "epoch": 0.42,
      "learning_rate": 9.190440524459203e-06,
      "loss": 1.5343,
      "step": 32
    },
    {
      "epoch": 0.43,
      "learning_rate": 9.131193871579975e-06,
      "loss": 1.5159,
      "step": 33
    },
    {
      "epoch": 0.44,
      "learning_rate": 9.070060426282924e-06,
      "loss": 1.5343,
      "step": 34
    },
    {
      "epoch": 0.46,
      "learning_rate": 9.007068109339783e-06,
      "loss": 1.5472,
      "step": 35
    },
    {
      "epoch": 0.47,
      "learning_rate": 8.94224569050324e-06,
      "loss": 1.4968,
      "step": 36
    },
    {
      "epoch": 0.48,
      "learning_rate": 8.87562277536726e-06,
      "loss": 1.5261,
      "step": 37
    },
    {
      "epoch": 0.5,
      "learning_rate": 8.807229791845673e-06,
      "loss": 1.4568,
      "step": 38
    },
    {
      "epoch": 0.51,
      "learning_rate": 8.737097976275177e-06,
      "loss": 1.5257,
      "step": 39
    },
    {
      "epoch": 0.52,
      "learning_rate": 8.665259359149132e-06,
      "loss": 1.5265,
      "step": 40
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.591746750488639e-06,
      "loss": 1.5067,
      "step": 41
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.516593724857598e-06,
      "loss": 1.4628,
      "step": 42
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.439834606028594e-06,
      "loss": 1.4626,
      "step": 43
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.361504451306585e-06,
      "loss": 1.5269,
      "step": 44
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.281639035517591e-06,
      "loss": 1.4551,
      "step": 45
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.200274834669675e-06,
      "loss": 1.4287,
      "step": 46
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.117449009293668e-06,
      "loss": 1.4808,
      "step": 47
    },
    {
      "epoch": 0.63,
      "learning_rate": 8.033199387471278e-06,
      "loss": 1.5128,
      "step": 48
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.9475644475583e-06,
      "loss": 1.4867,
      "step": 49
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.860583300610849e-06,
      "loss": 1.4873,
      "step": 50
    },
    {
      "epoch": 0.67,
      "learning_rate": 7.772295672522615e-06,
      "loss": 1.4294,
      "step": 51
    },
    {
      "epoch": 0.68,
      "learning_rate": 7.682741885881314e-06,
      "loss": 1.4629,
      "step": 52
    },
    {
      "epoch": 0.69,
      "learning_rate": 7.591962841552627e-06,
      "loss": 1.5219,
      "step": 53
    },
    {
      "epoch": 0.7,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.4715,
      "step": 54
    },
    {
      "epoch": 0.72,
      "learning_rate": 7.406895362348916e-06,
      "loss": 1.4632,
      "step": 55
    },
    {
      "epoch": 0.73,
      "learning_rate": 7.312691451204178e-06,
      "loss": 1.481,
      "step": 56
    },
    {
      "epoch": 0.74,
      "learning_rate": 7.217431291229068e-06,
      "loss": 1.4556,
      "step": 57
    },
    {
      "epoch": 0.76,
      "learning_rate": 7.121158389495187e-06,
      "loss": 1.4419,
      "step": 58
    },
    {
      "epoch": 0.77,
      "learning_rate": 7.023916715611969e-06,
      "loss": 1.4326,
      "step": 59
    },
    {
      "epoch": 0.78,
      "learning_rate": 6.925750681644954e-06,
      "loss": 1.4692,
      "step": 60
    },
    {
      "epoch": 0.8,
      "learning_rate": 6.8267051218319766e-06,
      "loss": 1.4426,
      "step": 61
    },
    {
      "epoch": 0.81,
      "learning_rate": 6.726825272106539e-06,
      "loss": 1.4479,
      "step": 62
    },
    {
      "epoch": 0.82,
      "learning_rate": 6.626156749437736e-06,
      "loss": 1.4601,
      "step": 63
    },
    {
      "epoch": 0.84,
      "learning_rate": 6.524745530996137e-06,
      "loss": 1.4852,
      "step": 64
    },
    {
      "epoch": 0.85,
      "learning_rate": 6.4226379331551625e-06,
      "loss": 1.4272,
      "step": 65
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.319880590337549e-06,
      "loss": 1.4784,
      "step": 66
    },
    {
      "epoch": 0.87,
      "learning_rate": 6.216520433716544e-06,
      "loss": 1.4409,
      "step": 67
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.112604669781572e-06,
      "loss": 1.4723,
      "step": 68
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.008180758778167e-06,
      "loss": 1.4417,
      "step": 69
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.903296393031996e-06,
      "loss": 1.4258,
      "step": 70
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.797999475166897e-06,
      "loss": 1.4418,
      "step": 71
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.69233809622687e-06,
      "loss": 1.4556,
      "step": 72
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.586360513712011e-06,
      "loss": 1.4235,
      "step": 73
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.480115129538409e-06,
      "loss": 1.4279,
      "step": 74
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.373650467932122e-06,
      "loss": 1.4399,
      "step": 75
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.267015153267246e-06,
      "loss": 1.4034,
      "step": 76
    },
    {
      "epoch": 0.99,
      "eval_runtime": 1301.4856,
      "eval_samples_per_second": 0.154,
      "eval_steps_per_second": 0.154,
      "step": 76
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.160257887858278e-06,
      "loss": 1.4125,
      "step": 77
    },
    {
      "epoch": 1.02,
      "learning_rate": 5.053427429716867e-06,
      "loss": 1.4199,
      "step": 78
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.946572570283135e-06,
      "loss": 1.4027,
      "step": 79
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.839742112141725e-06,
      "loss": 1.3917,
      "step": 80
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.732984846732755e-06,
      "loss": 1.4201,
      "step": 81
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.626349532067879e-06,
      "loss": 1.3852,
      "step": 82
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.5198848704615915e-06,
      "loss": 1.3846,
      "step": 83
    },
    {
      "epoch": 1.1,
      "learning_rate": 4.413639486287992e-06,
      "loss": 1.3979,
      "step": 84
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.307661903773129e-06,
      "loss": 1.381,
      "step": 85
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.2020005248331056e-06,
      "loss": 1.3978,
      "step": 86
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.096703606968007e-06,
      "loss": 1.4146,
      "step": 87
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.991819241221836e-06,
      "loss": 1.4094,
      "step": 88
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.887395330218429e-06,
      "loss": 1.3919,
      "step": 89
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.783479566283457e-06,
      "loss": 1.3931,
      "step": 90
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.6801194096624515e-06,
      "loss": 1.3984,
      "step": 91
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.5773620668448384e-06,
      "loss": 1.357,
      "step": 92
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.475254469003865e-06,
      "loss": 1.3806,
      "step": 93
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.3738432505622653e-06,
      "loss": 1.3789,
      "step": 94
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.273174727893463e-06,
      "loss": 1.3644,
      "step": 95
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.173294878168025e-06,
      "loss": 1.3892,
      "step": 96
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.074249318355046e-06,
      "loss": 1.3787,
      "step": 97
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.976083284388031e-06,
      "loss": 1.3989,
      "step": 98
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.8788416105048124e-06,
      "loss": 1.3673,
      "step": 99
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.782568708770933e-06,
      "loss": 1.3505,
      "step": 100
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.687308548795825e-06,
      "loss": 1.3426,
      "step": 101
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.5931046376510875e-06,
      "loss": 1.3851,
      "step": 102
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 1.3911,
      "step": 103
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.408037158447375e-06,
      "loss": 1.3748,
      "step": 104
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.317258114118686e-06,
      "loss": 1.385,
      "step": 105
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.2277043274773856e-06,
      "loss": 1.3342,
      "step": 106
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.139416699389153e-06,
      "loss": 1.3472,
      "step": 107
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.0524355524417017e-06,
      "loss": 1.3647,
      "step": 108
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.966800612528723e-06,
      "loss": 1.3827,
      "step": 109
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 1.3681,
      "step": 110
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.7997251653303249e-06,
      "loss": 1.4033,
      "step": 111
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.7183609644824096e-06,
      "loss": 1.3881,
      "step": 112
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.6384955486934157e-06,
      "loss": 1.3859,
      "step": 113
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.5601653939714073e-06,
      "loss": 1.3784,
      "step": 114
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.4834062751424018e-06,
      "loss": 1.3277,
      "step": 115
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.4082532495113627e-06,
      "loss": 1.4009,
      "step": 116
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.3347406408508695e-06,
      "loss": 1.3895,
      "step": 117
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.2629020237248241e-06,
      "loss": 1.3789,
      "step": 118
    },
    {
      "epoch": 1.55,
      "learning_rate": 1.1927702081543279e-06,
      "loss": 1.3381,
      "step": 119
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.1243772246327416e-06,
      "loss": 1.3618,
      "step": 120
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.0577543094967613e-06,
      "loss": 1.379,
      "step": 121
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.929318906602176e-07,
      "loss": 1.3335,
      "step": 122
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.299395737170758e-07,
      "loss": 1.3506,
      "step": 123
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.688061284200266e-07,
      "loss": 1.3791,
      "step": 124
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.095594755407971e-07,
      "loss": 1.401,
      "step": 125
    },
    {
      "epoch": 1.64,
      "learning_rate": 7.522266741182305e-07,
      "loss": 1.3791,
      "step": 126
    },
    {
      "epoch": 1.66,
      "learning_rate": 6.968339090999188e-07,
      "loss": 1.3748,
      "step": 127
    },
    {
      "epoch": 1.67,
      "learning_rate": 6.43406479383053e-07,
      "loss": 1.3614,
      "step": 128
    },
    {
      "epoch": 1.68,
      "learning_rate": 5.919687862599549e-07,
      "loss": 1.3902,
      "step": 129
    },
    {
      "epoch": 1.7,
      "learning_rate": 5.425443222735527e-07,
      "loss": 1.4062,
      "step": 130
    },
    {
      "epoch": 1.71,
      "learning_rate": 4.951556604879049e-07,
      "loss": 1.3798,
      "step": 131
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.4982444417866753e-07,
      "loss": 1.3926,
      "step": 132
    },
    {
      "epoch": 1.74,
      "learning_rate": 4.0657137694820826e-07,
      "loss": 1.3757,
      "step": 133
    },
    {
      "epoch": 1.75,
      "learning_rate": 3.6541621326989183e-07,
      "loss": 1.3645,
      "step": 134
    },
    {
      "epoch": 1.76,
      "learning_rate": 3.263777494658449e-07,
      "loss": 1.3553,
      "step": 135
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.894738151223331e-07,
      "loss": 1.3493,
      "step": 136
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.547212649466568e-07,
      "loss": 1.4113,
      "step": 137
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.2213597106929608e-07,
      "loss": 1.3679,
      "step": 138
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.9173281579481896e-07,
      "loss": 1.3833,
      "step": 139
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.6352568480485277e-07,
      "loss": 1.3852,
      "step": 140
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.375274608162447e-07,
      "loss": 1.3982,
      "step": 141
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.1375001769728e-07,
      "loss": 1.3666,
      "step": 142
    },
    {
      "epoch": 1.87,
      "learning_rate": 9.22042150446728e-08,
      "loss": 1.4037,
      "step": 143
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.289989322378732e-08,
      "loss": 1.3762,
      "step": 144
    },
    {
      "epoch": 1.89,
      "learning_rate": 5.584586887435739e-08,
      "loss": 1.4058,
      "step": 145
    },
    {
      "epoch": 1.91,
      "learning_rate": 4.104993088376974e-08,
      "loss": 1.3856,
      "step": 146
    },
    {
      "epoch": 1.92,
      "learning_rate": 2.8518836829732332e-08,
      "loss": 1.3612,
      "step": 147
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.8258309893965375e-08,
      "loss": 1.4054,
      "step": 148
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.0273036248318325e-08,
      "loss": 1.3982,
      "step": 149
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.56666291450858e-09,
      "loss": 1.3746,
      "step": 150
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.1417960984605459e-09,
      "loss": 1.3612,
      "step": 151
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0,
      "loss": 1.4018,
      "step": 152
    },
    {
      "epoch": 1.98,
      "eval_runtime": 1280.8781,
      "eval_samples_per_second": 0.156,
      "eval_steps_per_second": 0.156,
      "step": 152
    },
    {
      "epoch": 1.98,
      "step": 152,
      "total_flos": 4117616183476224.0,
      "train_loss": 1.4679964404357106,
      "train_runtime": 3899.9143,
      "train_samples_per_second": 5.026,
      "train_steps_per_second": 0.039
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 152,
  "num_train_epochs": 2,
  "save_steps": 100,
  "total_flos": 4117616183476224.0,
  "trial_name": null,
  "trial_params": null
}