{
  "best_metric": 1.3908014297485352,
  "best_model_checkpoint": "./lora-outA/checkpoint-150",
  "epoch": 2.2522522522522523,
  "eval_steps": 25,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.027,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.0877,
      "step": 2
    },
    {
      "epoch": 0.05,
      "learning_rate": 6e-06,
      "loss": 2.4458,
      "step": 3
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.2379,
      "step": 4
    },
    {
      "epoch": 0.08,
      "learning_rate": 1e-05,
      "loss": 2.4292,
      "step": 5
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.2e-05,
      "loss": 2.0784,
      "step": 6
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.4e-05,
      "loss": 2.1768,
      "step": 7
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.0902,
      "step": 8
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.8e-05,
      "loss": 2.3488,
      "step": 9
    },
    {
      "epoch": 0.15,
      "learning_rate": 2e-05,
      "loss": 2.3467,
      "step": 10
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9998603811858573e-05,
      "loss": 1.9468,
      "step": 11
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9994415637302545e-05,
      "loss": 2.2701,
      "step": 12
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.998743664582786e-05,
      "loss": 2.1306,
      "step": 13
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9977668786231536e-05,
      "loss": 2.2113,
      "step": 14
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.9965114786067515e-05,
      "loss": 2.2447,
      "step": 15
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.994977815088504e-05,
      "loss": 1.9715,
      "step": 16
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.9931663163249744e-05,
      "loss": 2.1725,
      "step": 17
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.9910774881547803e-05,
      "loss": 1.9481,
      "step": 18
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9887119138573462e-05,
      "loss": 1.9348,
      "step": 19
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.9860702539900288e-05,
      "loss": 2.1486,
      "step": 20
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9831532462036634e-05,
      "loss": 1.8827,
      "step": 21
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.979961705036587e-05,
      "loss": 1.8206,
      "step": 22
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.9764965216871848e-05,
      "loss": 2.1399,
      "step": 23
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.9727586637650373e-05,
      "loss": 1.807,
      "step": 24
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.9687491750207255e-05,
      "loss": 1.955,
      "step": 25
    },
    {
      "epoch": 0.38,
      "eval_loss": 1.9037058353424072,
      "eval_runtime": 10.8675,
      "eval_samples_per_second": 2.576,
      "eval_steps_per_second": 0.644,
      "step": 25
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.964469175054377e-05,
      "loss": 1.8608,
      "step": 26
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.9599198590030308e-05,
      "loss": 2.1292,
      "step": 27
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.9551024972069127e-05,
      "loss": 1.9422,
      "step": 28
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.950018434854704e-05,
      "loss": 1.846,
      "step": 29
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.944669091607919e-05,
      "loss": 1.8679,
      "step": 30
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.9390559612044783e-05,
      "loss": 1.7104,
      "step": 31
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.9331806110416027e-05,
      "loss": 1.7278,
      "step": 32
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.9270446817381377e-05,
      "loss": 2.0227,
      "step": 33
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.920649886676429e-05,
      "loss": 1.8487,
      "step": 34
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.9139980115238827e-05,
      "loss": 1.6051,
      "step": 35
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.907090913734341e-05,
      "loss": 1.6792,
      "step": 36
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.899930522029408e-05,
      "loss": 1.9176,
      "step": 37
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.8925188358598815e-05,
      "loss": 1.629,
      "step": 38
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.8848579248474286e-05,
      "loss": 1.8579,
      "step": 39
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.8769499282066716e-05,
      "loss": 1.6583,
      "step": 40
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.8687970541478367e-05,
      "loss": 1.7202,
      "step": 41
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.8604015792601395e-05,
      "loss": 1.7408,
      "step": 42
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.851765847876076e-05,
      "loss": 1.7131,
      "step": 43
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.842892271416797e-05,
      "loss": 1.7969,
      "step": 44
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.8337833277187472e-05,
      "loss": 1.6165,
      "step": 45
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.8244415603417603e-05,
      "loss": 1.6652,
      "step": 46
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.8148695778588034e-05,
      "loss": 1.7009,
      "step": 47
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.8050700531275632e-05,
      "loss": 2.0433,
      "step": 48
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.795045722544083e-05,
      "loss": 1.577,
      "step": 49
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.7847993852786612e-05,
      "loss": 1.6598,
      "step": 50
    },
    {
      "epoch": 0.75,
      "eval_loss": 1.6191542148590088,
      "eval_runtime": 10.8699,
      "eval_samples_per_second": 2.576,
      "eval_steps_per_second": 0.644,
      "step": 50
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.7743339024942135e-05,
      "loss": 1.7067,
      "step": 51
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.7636521965473324e-05,
      "loss": 1.6212,
      "step": 52
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.7527572501722516e-05,
      "loss": 1.5661,
      "step": 53
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7416521056479577e-05,
      "loss": 1.5579,
      "step": 54
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7303398639486696e-05,
      "loss": 1.6506,
      "step": 55
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.7188236838779297e-05,
      "loss": 1.7512,
      "step": 56
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 1.6908,
      "step": 57
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.6951924276746425e-05,
      "loss": 1.778,
      "step": 58
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.683083950278031e-05,
      "loss": 1.451,
      "step": 59
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.6707847301392237e-05,
      "loss": 1.7809,
      "step": 60
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.6582982016632818e-05,
      "loss": 1.6405,
      "step": 61
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.6456278515588023e-05,
      "loss": 1.6913,
      "step": 62
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.6327772178642986e-05,
      "loss": 1.7667,
      "step": 63
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.619749888960245e-05,
      "loss": 1.4675,
      "step": 64
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.6065495025670675e-05,
      "loss": 1.5044,
      "step": 65
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.5931797447293553e-05,
      "loss": 1.6187,
      "step": 66
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.5796443487865774e-05,
      "loss": 1.6726,
      "step": 67
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.5659470943305956e-05,
      "loss": 1.5999,
      "step": 68
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.552091806150257e-05,
      "loss": 1.4913,
      "step": 69
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.5380823531633727e-05,
      "loss": 1.4692,
      "step": 70
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.523922647336369e-05,
      "loss": 1.5326,
      "step": 71
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.5096166425919176e-05,
      "loss": 1.4767,
      "step": 72
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.4951683337048536e-05,
      "loss": 1.3673,
      "step": 73
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.4805817551866839e-05,
      "loss": 1.6663,
      "step": 74
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.4658609801589982e-05,
      "loss": 1.5649,
      "step": 75
    },
    {
      "epoch": 1.13,
      "eval_loss": 1.5010281801223755,
      "eval_runtime": 10.8975,
      "eval_samples_per_second": 2.569,
      "eval_steps_per_second": 0.642,
      "step": 75
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.451010119216102e-05,
      "loss": 1.4662,
      "step": 76
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.436033319277183e-05,
      "loss": 1.5699,
      "step": 77
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.4209347624283352e-05,
      "loss": 1.5471,
      "step": 78
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.4057186647547638e-05,
      "loss": 1.5028,
      "step": 79
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.3903892751634949e-05,
      "loss": 1.6067,
      "step": 80
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.3749508741969213e-05,
      "loss": 1.5703,
      "step": 81
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.3594077728375129e-05,
      "loss": 1.4915,
      "step": 82
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.3437643113040302e-05,
      "loss": 1.4674,
      "step": 83
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.328024857839569e-05,
      "loss": 1.6161,
      "step": 84
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.3121938074917866e-05,
      "loss": 1.5415,
      "step": 85
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.2962755808856341e-05,
      "loss": 1.4845,
      "step": 86
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.2802746229889563e-05,
      "loss": 1.3974,
      "step": 87
    },
    {
      "epoch": 1.32,
      "learning_rate": 1.2641954018712863e-05,
      "loss": 1.5752,
      "step": 88
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.2480424074561934e-05,
      "loss": 1.856,
      "step": 89
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.2318201502675285e-05,
      "loss": 1.4777,
      "step": 90
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.2155331601699136e-05,
      "loss": 1.4124,
      "step": 91
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.1991859851038362e-05,
      "loss": 1.3642,
      "step": 92
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.1827831898156905e-05,
      "loss": 1.4942,
      "step": 93
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.1663293545831302e-05,
      "loss": 1.5128,
      "step": 94
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.1498290739360815e-05,
      "loss": 1.5812,
      "step": 95
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.133286955373779e-05,
      "loss": 1.5092,
      "step": 96
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.1167076180781764e-05,
      "loss": 1.4185,
      "step": 97
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.1000956916240985e-05,
      "loss": 1.6486,
      "step": 98
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.08345581468649e-05,
      "loss": 1.5457,
      "step": 99
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.0667926337451217e-05,
      "loss": 1.4424,
      "step": 100
    },
    {
      "epoch": 1.5,
      "eval_loss": 1.44235098361969,
      "eval_runtime": 10.8826,
      "eval_samples_per_second": 2.573,
      "eval_steps_per_second": 0.643,
      "step": 100
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.0501108017871193e-05,
      "loss": 1.5011,
      "step": 101
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.0334149770076747e-05,
      "loss": 1.5162,
      "step": 102
    },
    {
      "epoch": 1.55,
      "learning_rate": 1.016709821509301e-05,
      "loss": 1.4612,
      "step": 103
    },
    {
      "epoch": 1.56,
      "learning_rate": 1e-05,
      "loss": 1.4465,
      "step": 104
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.83290178490699e-06,
      "loss": 1.7689,
      "step": 105
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.665850229923258e-06,
      "loss": 1.4932,
      "step": 106
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.498891982128809e-06,
      "loss": 1.524,
      "step": 107
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.332073662548785e-06,
      "loss": 1.4308,
      "step": 108
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.165441853135104e-06,
      "loss": 1.5015,
      "step": 109
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.999043083759016e-06,
      "loss": 1.6896,
      "step": 110
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.832923819218238e-06,
      "loss": 1.4334,
      "step": 111
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.667130446262214e-06,
      "loss": 1.342,
      "step": 112
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.501709260639187e-06,
      "loss": 1.6292,
      "step": 113
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.336706454168701e-06,
      "loss": 1.3967,
      "step": 114
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.1721681018431e-06,
      "loss": 1.3275,
      "step": 115
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.008140148961642e-06,
      "loss": 1.3956,
      "step": 116
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.844668398300866e-06,
      "loss": 1.4647,
      "step": 117
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.681798497324717e-06,
      "loss": 1.4231,
      "step": 118
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.5195759254380674e-06,
      "loss": 1.4382,
      "step": 119
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.358045981287141e-06,
      "loss": 1.4577,
      "step": 120
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.197253770110438e-06,
      "loss": 1.4717,
      "step": 121
    },
    {
      "epoch": 1.83,
      "learning_rate": 7.037244191143662e-06,
      "loss": 1.4299,
      "step": 122
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.878061925082138e-06,
      "loss": 1.5763,
      "step": 123
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.719751421604309e-06,
      "loss": 1.3964,
      "step": 124
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.562356886959704e-06,
      "loss": 1.4142,
      "step": 125
    },
    {
      "epoch": 1.88,
      "eval_loss": 1.4067628383636475,
      "eval_runtime": 10.8837,
      "eval_samples_per_second": 2.573,
      "eval_steps_per_second": 0.643,
      "step": 125
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.405922271624874e-06,
      "loss": 1.397,
      "step": 126
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.2504912580307905e-06,
      "loss": 1.5261,
      "step": 127
    },
    {
      "epoch": 1.92,
      "learning_rate": 6.0961072483650526e-06,
      "loss": 1.4375,
      "step": 128
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.942813352452365e-06,
      "loss": 1.4193,
      "step": 129
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.790652375716653e-06,
      "loss": 1.5296,
      "step": 130
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.6396668072281745e-06,
      "loss": 1.4173,
      "step": 131
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.48989880783898e-06,
      "loss": 1.5766,
      "step": 132
    },
    {
      "epoch": 2.0,
      "learning_rate": 5.3413901984100195e-06,
      "loss": 1.4055,
      "step": 133
    },
    {
      "epoch": 2.01,
      "learning_rate": 5.194182448133163e-06,
      "loss": 1.2706,
      "step": 134
    },
    {
      "epoch": 2.03,
      "learning_rate": 5.0483166629514654e-06,
      "loss": 1.4166,
      "step": 135
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.903833574080825e-06,
      "loss": 1.3389,
      "step": 136
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.760773526636315e-06,
      "loss": 1.472,
      "step": 137
    },
    {
      "epoch": 2.07,
      "learning_rate": 4.619176468366274e-06,
      "loss": 1.3816,
      "step": 138
    },
    {
      "epoch": 2.09,
      "learning_rate": 4.479081938497435e-06,
      "loss": 1.3801,
      "step": 139
    },
    {
      "epoch": 2.1,
      "learning_rate": 4.3405290566940475e-06,
      "loss": 1.2649,
      "step": 140
    },
    {
      "epoch": 2.12,
      "learning_rate": 4.203556512134225e-06,
      "loss": 1.3603,
      "step": 141
    },
    {
      "epoch": 2.13,
      "learning_rate": 4.0682025527064486e-06,
      "loss": 1.2548,
      "step": 142
    },
    {
      "epoch": 2.15,
      "learning_rate": 3.934504974329326e-06,
      "loss": 1.5477,
      "step": 143
    },
    {
      "epoch": 2.16,
      "learning_rate": 3.802501110397553e-06,
      "loss": 1.3545,
      "step": 144
    },
    {
      "epoch": 2.18,
      "learning_rate": 3.672227821357014e-06,
      "loss": 1.3932,
      "step": 145
    },
    {
      "epoch": 2.19,
      "learning_rate": 3.543721484411976e-06,
      "loss": 1.5203,
      "step": 146
    },
    {
      "epoch": 2.21,
      "learning_rate": 3.4170179833671847e-06,
      "loss": 1.4399,
      "step": 147
    },
    {
      "epoch": 2.22,
      "learning_rate": 3.292152698607768e-06,
      "loss": 1.3587,
      "step": 148
    },
    {
      "epoch": 2.24,
      "learning_rate": 3.1691604972196922e-06,
      "loss": 1.4239,
      "step": 149
    },
    {
      "epoch": 2.25,
      "learning_rate": 3.0480757232535773e-06,
      "loss": 1.4951,
      "step": 150
    },
    {
      "epoch": 2.25,
      "eval_loss": 1.3908014297485352,
      "eval_runtime": 10.8882,
      "eval_samples_per_second": 2.572,
      "eval_steps_per_second": 0.643,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 198,
  "num_train_epochs": 3,
  "save_steps": 50,
  "total_flos": 3.848852284322611e+17,
  "trial_name": null,
  "trial_params": null
}