{
  "best_metric": 1.0441503524780273,
  "best_model_checkpoint": "rm-ckpt-reward-p100-s0/checkpoint-400",
  "epoch": 0.4020504573323952,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 1.447,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.525749891599529e-06,
      "loss": 1.4166,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.192803136799156e-05,
      "loss": 1.417,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.5051499783199057e-05,
      "loss": 1.3947,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.7474250108400467e-05,
      "loss": 1.3739,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.945378125959109e-05,
      "loss": 1.3352,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.1127451000356418e-05,
      "loss": 1.3181,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.2577249674798584e-05,
      "loss": 1.3712,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.385606273598312e-05,
      "loss": 1.3858,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4999999999999998e-05,
      "loss": 1.4424,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6034817128955623e-05,
      "loss": 1.3381,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6979531151190617e-05,
      "loss": 1.2937,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.7848583807670913e-05,
      "loss": 1.3021,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8653200891955945e-05,
      "loss": 1.274,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.940228147639203e-05,
      "loss": 1.2896,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.0102999566398115e-05,
      "loss": 1.19,
      "step": 16
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.076122303445685e-05,
      "loss": 1.1889,
      "step": 17
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.1381812627582646e-05,
      "loss": 1.2028,
      "step": 18
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.1968840023820715e-05,
      "loss": 1.2259,
      "step": 19
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2525749891599525e-05,
      "loss": 1.1971,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.305548236834798e-05,
      "loss": 1.1972,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.3560567020555153e-05,
      "loss": 1.2193,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.404319590043982e-05,
      "loss": 1.1354,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.450528104279015e-05,
      "loss": 1.1434,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.4948500216800935e-05,
      "loss": 1.1237,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.537433369927044e-05,
      "loss": 1.1227,
      "step": 26
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.578409410397468e-05,
      "loss": 1.1554,
      "step": 27
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.6178950783555475e-05,
      "loss": 1.131,
      "step": 28
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.65599499474739e-05,
      "loss": 1.2016,
      "step": 29
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.6928031367991554e-05,
      "loss": 1.0968,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.728404234585681e-05,
      "loss": 1.0713,
      "step": 31
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.762874945799765e-05,
      "loss": 1.1537,
      "step": 32
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.796284849694718e-05,
      "loss": 1.0856,
      "step": 33
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.8286972926056376e-05,
      "loss": 1.08,
      "step": 34
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.8601701108756885e-05,
      "loss": 1.067,
      "step": 35
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.890756251918218e-05,
      "loss": 1.1298,
      "step": 36
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.920504310167487e-05,
      "loss": 1.0986,
      "step": 37
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.949458991542025e-05,
      "loss": 1.0649,
      "step": 38
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.977661517566247e-05,
      "loss": 1.0582,
      "step": 39
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.005149978319905e-05,
      "loss": 1.1037,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.031959641799338e-05,
      "loss": 1.052,
      "step": 41
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.058123225994751e-05,
      "loss": 1.1048,
      "step": 42
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.0836711389489654e-05,
      "loss": 1.0817,
      "step": 43
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.108631691215468e-05,
      "loss": 1.0712,
      "step": 44
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.133031284438358e-05,
      "loss": 1.0865,
      "step": 45
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.156894579203935e-05,
      "loss": 1.0837,
      "step": 46
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.180244644839293e-05,
      "loss": 1.0915,
      "step": 47
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.203103093438968e-05,
      "loss": 1.0845,
      "step": 48
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.2254902000712836e-05,
      "loss": 1.0425,
      "step": 49
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.247425010840046e-05,
      "loss": 1.0479,
      "step": 50
    },
    {
      "epoch": 0.05,
      "eval_val_accuracy": 0.6191666666666666,
      "eval_val_loss": 1.1118515729904175,
      "eval_val_runtime": 913.0126,
      "eval_val_samples_per_second": 1.095,
      "eval_val_steps_per_second": 0.137,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.2689254402448405e-05,
      "loss": 1.079,
      "step": 51
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.290008359086998e-05,
      "loss": 1.0855,
      "step": 52
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.310689674001973e-05,
      "loss": 1.084,
      "step": 53
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.330984399557421e-05,
      "loss": 1.0787,
      "step": 54
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.350906723735609e-05,
      "loss": 1.1333,
      "step": 55
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.370470067515501e-05,
      "loss": 1.1016,
      "step": 56
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.3896871391812285e-05,
      "loss": 1.0716,
      "step": 57
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.408569983907343e-05,
      "loss": 1.0861,
      "step": 58
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.42713002910536e-05,
      "loss": 1.0583,
      "step": 59
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.445378125959108e-05,
      "loss": 1.0793,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.463324587526917e-05,
      "loss": 1.0761,
      "step": 61
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.4809792237456346e-05,
      "loss": 1.0995,
      "step": 62
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.498351373633954e-05,
      "loss": 1.0915,
      "step": 63
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.515449934959717e-05,
      "loss": 1.0415,
      "step": 64
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.532283391607138e-05,
      "loss": 1.0429,
      "step": 65
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.548859838854671e-05,
      "loss": 1.0886,
      "step": 66
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.565187006752065e-05,
      "loss": 1.0332,
      "step": 67
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.581272281765591e-05,
      "loss": 1.0271,
      "step": 68
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.597122726843138e-05,
      "loss": 1.0591,
      "step": 69
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.612745100035642e-05,
      "loss": 1.023,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.628145871797688e-05,
      "loss": 1.0665,
      "step": 71
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.643331241078171e-05,
      "loss": 1.064,
      "step": 72
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.658307150301139e-05,
      "loss": 1.1339,
      "step": 73
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.67307929932744e-05,
      "loss": 1.0609,
      "step": 74
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.687653158479249e-05,
      "loss": 1.1128,
      "step": 75
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.702033980701978e-05,
      "loss": 1.0733,
      "step": 76
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.716226812931204e-05,
      "loss": 1.0761,
      "step": 77
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.7302365067262006e-05,
      "loss": 1.0609,
      "step": 78
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.744067728226103e-05,
      "loss": 1.0306,
      "step": 79
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.757724967479858e-05,
      "loss": 1.0882,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.771212547196624e-05,
      "loss": 1.0556,
      "step": 81
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.7845346309592914e-05,
      "loss": 1.0455,
      "step": 82
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.7976952309401844e-05,
      "loss": 1.0653,
      "step": 83
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.810698215154703e-05,
      "loss": 1.0128,
      "step": 84
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.823547314285732e-05,
      "loss": 1.0739,
      "step": 85
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.836246128108918e-05,
      "loss": 1.161,
      "step": 86
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.8487981315465456e-05,
      "loss": 1.0686,
      "step": 87
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.8612066803754214e-05,
      "loss": 1.0785,
      "step": 88
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.873475016612281e-05,
      "loss": 1.0362,
      "step": 89
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.885606273598312e-05,
      "loss": 1.0775,
      "step": 90
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.897603480802733e-05,
      "loss": 1.0445,
      "step": 91
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.909469568363888e-05,
      "loss": 1.0452,
      "step": 92
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9212073713848375e-05,
      "loss": 1.0687,
      "step": 93
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.932819633999246e-05,
      "loss": 1.0775,
      "step": 94
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9443090132221186e-05,
      "loss": 1.0239,
      "step": 95
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9556780825989205e-05,
      "loss": 1.0532,
      "step": 96
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9669293356656114e-05,
      "loss": 1.0628,
      "step": 97
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.978065189231237e-05,
      "loss": 1.0562,
      "step": 98
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.989087986493874e-05,
      "loss": 1.0404,
      "step": 99
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 1.0711,
      "step": 100
    },
    {
      "epoch": 0.1,
      "eval_val_accuracy": 0.6268333333333334,
      "eval_val_loss": 1.0909922122955322,
      "eval_val_runtime": 906.1076,
      "eval_val_samples_per_second": 1.104,
      "eval_val_steps_per_second": 0.138,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 1.0378,
      "step": 101
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 1.0447,
      "step": 102
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 1.0323,
      "step": 103
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 1.0135,
      "step": 104
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 1.0168,
      "step": 105
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 1.0689,
      "step": 106
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 1.0389,
      "step": 107
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 1.0665,
      "step": 108
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.0668,
      "step": 109
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.0728,
      "step": 110
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.0747,
      "step": 111
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.0314,
      "step": 112
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.1075,
      "step": 113
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.0645,
      "step": 114
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.0528,
      "step": 115
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.0783,
      "step": 116
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.0524,
      "step": 117
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.0451,
      "step": 118
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 1.0281,
      "step": 119
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 1.0829,
      "step": 120
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 1.0088,
      "step": 121
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 1.0634,
      "step": 122
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 1.0836,
      "step": 123
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 1.08,
      "step": 124
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 1.0523,
      "step": 125
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 1.0564,
      "step": 126
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 1.038,
      "step": 127
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 1.0494,
      "step": 128
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 1.0329,
      "step": 129
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 1.0806,
      "step": 130
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 1.0763,
      "step": 131
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 1.0504,
      "step": 132
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 1.044,
      "step": 133
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 0.9895,
      "step": 134
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 1.0688,
      "step": 135
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 1.0471,
      "step": 136
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 1.0711,
      "step": 137
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 1.0506,
      "step": 138
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.0789,
      "step": 139
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.0888,
      "step": 140
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.0746,
      "step": 141
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.1229,
      "step": 142
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.0826,
      "step": 143
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.0504,
      "step": 144
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.0311,
      "step": 145
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.0456,
      "step": 146
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.0097,
      "step": 147
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.0282,
      "step": 148
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 1.0507,
      "step": 149
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 1.054,
      "step": 150
    },
    {
      "epoch": 0.15,
      "eval_val_accuracy": 0.626,
      "eval_val_loss": 1.0630038976669312,
      "eval_val_runtime": 907.7978,
      "eval_val_samples_per_second": 1.102,
      "eval_val_steps_per_second": 0.138,
      "step": 150
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 1.0165,
      "step": 151
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 0.9992,
      "step": 152
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 1.045,
      "step": 153
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 1.0378,
      "step": 154
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 1.0502,
      "step": 155
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 0.9911,
      "step": 156
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 1.063,
      "step": 157
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 1.0383,
      "step": 158
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 1.0511,
      "step": 159
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 1.0204,
      "step": 160
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 1.084,
      "step": 161
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 1.0873,
      "step": 162
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 1.0304,
      "step": 163
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 1.0118,
      "step": 164
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 1.04,
      "step": 165
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 1.0018,
      "step": 166
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 1.0432,
      "step": 167
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 1.0116,
      "step": 168
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 1.0647,
      "step": 169
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.091,
      "step": 170
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.0167,
      "step": 171
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.0952,
      "step": 172
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.0423,
      "step": 173
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.0198,
      "step": 174
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.0341,
      "step": 175
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.0657,
      "step": 176
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.0084,
      "step": 177
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.0483,
      "step": 178
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.0493,
      "step": 179
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 1.0328,
      "step": 180
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 1.0585,
      "step": 181
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 0.9869,
      "step": 182
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 1.0266,
      "step": 183
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 1.0462,
      "step": 184
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 1.0306,
      "step": 185
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 1.0459,
      "step": 186
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 1.0004,
      "step": 187
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 1.0417,
      "step": 188
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 1.0712,
      "step": 189
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 1.0228,
      "step": 190
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 0.9888,
      "step": 191
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 0.9393,
      "step": 192
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 1.052,
      "step": 193
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 1.0751,
      "step": 194
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 1.0468,
      "step": 195
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 1.0235,
      "step": 196
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 1.0428,
      "step": 197
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 1.0408,
      "step": 198
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 1.0112,
      "step": 199
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 1.0329,
      "step": 200
    },
    {
      "epoch": 0.19,
      "eval_val_accuracy": 0.6278333333333334,
      "eval_val_loss": 1.0557304620742798,
      "eval_val_runtime": 906.1331,
      "eval_val_samples_per_second": 1.104,
      "eval_val_steps_per_second": 0.138,
      "step": 200
    },
    {
      "epoch": 0.2,
      "learning_rate": 1e-05,
      "loss": 1.0219,
      "step": 201
    },
    {
      "epoch": 0.2,
      "learning_rate": 1e-05,
      "loss": 1.0479,
      "step": 202
    },
    {
      "epoch": 0.2,
      "learning_rate": 1e-05,
      "loss": 0.9808,
      "step": 203
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 1.0404,
      "step": 204
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 1.0214,
      "step": 205
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 0.9991,
      "step": 206
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 0.9435,
      "step": 207
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 1.0083,
      "step": 208
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 1.0187,
      "step": 209
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 1.0493,
      "step": 210
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 0.9925,
      "step": 211
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 1.0142,
      "step": 212
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 1.0131,
      "step": 213
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 1.0041,
      "step": 214
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 1.0187,
      "step": 215
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 1.0551,
      "step": 216
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 1.0224,
      "step": 217
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 1.0654,
      "step": 218
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 1.0472,
      "step": 219
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 0.9667,
      "step": 220
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 0.9944,
      "step": 221
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 1.0283,
      "step": 222
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 1.0047,
      "step": 223
    },
    {
      "epoch": 0.23,
      "learning_rate": 1e-05,
      "loss": 0.9781,
      "step": 224
    },
    {
      "epoch": 0.23,
      "learning_rate": 1e-05,
      "loss": 1.0127,
      "step": 225
    },
    {
      "epoch": 0.23,
      "learning_rate": 1e-05,
      "loss": 1.035,
      "step": 226
    },
    {
      "epoch": 0.23,
      "learning_rate": 1e-05,
      "loss": 0.9573,
      "step": 227
    },
    {
      "epoch": 0.23,
      "learning_rate": 1e-05,
      "loss": 1.0365,
      "step": 228
    },
    {
      "epoch": 0.23,
      "learning_rate": 1e-05,
      "loss": 1.0508,
      "step": 229
    },
    {
      "epoch": 0.23,
      "learning_rate": 1e-05,
      "loss": 1.0138,
      "step": 230
    },
    {
      "epoch": 0.23,
      "learning_rate": 1e-05,
      "loss": 1.0037,
      "step": 231
    },
    {
      "epoch": 0.23,
      "learning_rate": 1e-05,
      "loss": 1.013,
      "step": 232
    },
    {
      "epoch": 0.23,
      "learning_rate": 1e-05,
      "loss": 1.0025,
      "step": 233
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 1.0309,
      "step": 234
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 0.9718,
      "step": 235
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 0.9968,
      "step": 236
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 1.024,
      "step": 237
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 1.0028,
      "step": 238
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 1.0701,
      "step": 239
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 1.0428,
      "step": 240
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 0.9651,
      "step": 241
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 1.0095,
      "step": 242
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 1.0495,
      "step": 243
    },
    {
      "epoch": 0.25,
      "learning_rate": 1e-05,
      "loss": 1.0441,
      "step": 244
    },
    {
      "epoch": 0.25,
      "learning_rate": 1e-05,
      "loss": 1.0412,
      "step": 245
    },
    {
      "epoch": 0.25,
      "learning_rate": 1e-05,
      "loss": 1.0335,
      "step": 246
    },
    {
      "epoch": 0.25,
      "learning_rate": 1e-05,
      "loss": 1.0092,
      "step": 247
    },
    {
      "epoch": 0.25,
      "learning_rate": 1e-05,
      "loss": 1.0408,
      "step": 248
    },
    {
      "epoch": 0.25,
      "learning_rate": 1e-05,
      "loss": 0.993,
      "step": 249
    },
    {
      "epoch": 0.25,
      "learning_rate": 1e-05,
      "loss": 0.9546,
      "step": 250
    },
    {
      "epoch": 0.25,
      "eval_val_accuracy": 0.6341666666666667,
      "eval_val_loss": 1.053076148033142,
      "eval_val_runtime": 906.4123,
      "eval_val_samples_per_second": 1.103,
      "eval_val_steps_per_second": 0.138,
      "step": 250
    },
    {
      "epoch": 0.25,
      "learning_rate": 1e-05,
      "loss": 1.043,
      "step": 251
    },
    {
      "epoch": 0.25,
      "learning_rate": 1e-05,
      "loss": 1.0082,
      "step": 252
    },
    {
      "epoch": 0.25,
      "learning_rate": 1e-05,
      "loss": 1.0281,
      "step": 253
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 0.9779,
      "step": 254
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 1.0074,
      "step": 255
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 0.9639,
      "step": 256
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 1.0121,
      "step": 257
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 1.036,
      "step": 258
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 1.0143,
      "step": 259
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 1.0407,
      "step": 260
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 1.0202,
      "step": 261
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 1.0099,
      "step": 262
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 1.0226,
      "step": 263
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 1.02,
      "step": 264
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 1.0197,
      "step": 265
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 1.0621,
      "step": 266
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 1.0261,
      "step": 267
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 1.0392,
      "step": 268
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 0.9644,
      "step": 269
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 0.9943,
      "step": 270
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 1.0354,
      "step": 271
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 0.9826,
      "step": 272
    },
    {
      "epoch": 0.27,
      "learning_rate": 1e-05,
      "loss": 0.9934,
      "step": 273
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 1.0222,
      "step": 274
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 1.0752,
      "step": 275
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 1.0337,
      "step": 276
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 0.976,
      "step": 277
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 1.051,
      "step": 278
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 1.0338,
      "step": 279
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 1.0026,
      "step": 280
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 1.0118,
      "step": 281
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 0.9982,
      "step": 282
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 1.0136,
      "step": 283
    },
    {
      "epoch": 0.29,
      "learning_rate": 1e-05,
      "loss": 0.9613,
      "step": 284
    },
    {
      "epoch": 0.29,
      "learning_rate": 1e-05,
      "loss": 1.0122,
      "step": 285
    },
    {
      "epoch": 0.29,
      "learning_rate": 1e-05,
      "loss": 1.049,
      "step": 286
    },
    {
      "epoch": 0.29,
      "learning_rate": 1e-05,
      "loss": 1.0164,
      "step": 287
    },
    {
      "epoch": 0.29,
      "learning_rate": 1e-05,
      "loss": 1.0052,
      "step": 288
    },
    {
      "epoch": 0.29,
      "learning_rate": 1e-05,
      "loss": 1.0244,
      "step": 289
    },
    {
      "epoch": 0.29,
      "learning_rate": 1e-05,
      "loss": 0.9886,
      "step": 290
    },
    {
      "epoch": 0.29,
      "learning_rate": 1e-05,
      "loss": 1.0039,
      "step": 291
    },
    {
      "epoch": 0.29,
      "learning_rate": 1e-05,
      "loss": 1.0088,
      "step": 292
    },
    {
      "epoch": 0.29,
      "learning_rate": 1e-05,
      "loss": 1.0003,
      "step": 293
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 0.9984,
      "step": 294
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 1.0288,
      "step": 295
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 0.9928,
      "step": 296
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 0.992,
      "step": 297
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 0.9863,
      "step": 298
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 0.9959,
      "step": 299
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 1.0094,
      "step": 300
    },
    {
      "epoch": 0.3,
      "eval_val_accuracy": 0.6303333333333334,
      "eval_val_loss": 1.0518085956573486,
      "eval_val_runtime": 905.7847,
      "eval_val_samples_per_second": 1.104,
      "eval_val_steps_per_second": 0.138,
      "step": 300
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 1.0049,
      "step": 301
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 1.005,
      "step": 302
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 1.0033,
      "step": 303
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 1.054,
      "step": 304
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 0.9742,
      "step": 305
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 1.0061,
      "step": 306
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 1.015,
      "step": 307
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 1.0414,
      "step": 308
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 0.9995,
      "step": 309
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 0.9901,
      "step": 310
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 0.9936,
      "step": 311
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 1.0476,
      "step": 312
    },
    {
      "epoch": 0.31,
      "learning_rate": 1e-05,
      "loss": 0.9987,
      "step": 313
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 1.0564,
      "step": 314
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 1.0129,
      "step": 315
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 0.9667,
      "step": 316
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 1.0264,
      "step": 317
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 0.9835,
      "step": 318
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 1.0199,
      "step": 319
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 0.9652,
      "step": 320
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 0.9874,
      "step": 321
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 1.0079,
      "step": 322
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 1.0858,
      "step": 323
    },
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 1.015,
      "step": 324
    },
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 0.9782,
      "step": 325
    },
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 1.0589,
      "step": 326
    },
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 1.0152,
      "step": 327
    },
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 0.9639,
      "step": 328
    },
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 1.0089,
      "step": 329
    },
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 1.056,
      "step": 330
    },
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 0.985,
      "step": 331
    },
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 1.027,
      "step": 332
    },
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 1.0565,
      "step": 333
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 1.0337,
      "step": 334
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 1.0453,
      "step": 335
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 1.0108,
      "step": 336
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 1.0289,
      "step": 337
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 1.0096,
      "step": 338
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 1.0241,
      "step": 339
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 0.9743,
      "step": 340
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 1.0387,
      "step": 341
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 1.0023,
      "step": 342
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 1.0257,
      "step": 343
    },
    {
      "epoch": 0.35,
      "learning_rate": 1e-05,
      "loss": 0.9827,
      "step": 344
    },
    {
      "epoch": 0.35,
      "learning_rate": 1e-05,
      "loss": 1.0269,
      "step": 345
    },
    {
      "epoch": 0.35,
      "learning_rate": 1e-05,
      "loss": 1.0017,
      "step": 346
    },
    {
      "epoch": 0.35,
      "learning_rate": 1e-05,
      "loss": 0.994,
      "step": 347
    },
    {
      "epoch": 0.35,
      "learning_rate": 1e-05,
      "loss": 1.0285,
      "step": 348
    },
    {
      "epoch": 0.35,
      "learning_rate": 1e-05,
      "loss": 1.0634,
      "step": 349
    },
    {
      "epoch": 0.35,
      "learning_rate": 1e-05,
      "loss": 1.0224,
      "step": 350
    },
    {
      "epoch": 0.35,
      "eval_val_accuracy": 0.6265,
      "eval_val_loss": 1.0556230545043945,
      "eval_val_runtime": 905.4395,
      "eval_val_samples_per_second": 1.104,
      "eval_val_steps_per_second": 0.138,
      "step": 350
    },
    {
      "epoch": 0.35,
      "learning_rate": 1e-05,
      "loss": 0.9755,
      "step": 351
    },
    {
      "epoch": 0.35,
      "learning_rate": 1e-05,
      "loss": 1.0004,
      "step": 352
    },
    {
      "epoch": 0.35,
      "learning_rate": 1e-05,
      "loss": 1.0171,
      "step": 353
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 1.0,
      "step": 354
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 0.9887,
      "step": 355
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 1.0387,
      "step": 356
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 0.9966,
      "step": 357
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 1.0213,
      "step": 358
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 1.0168,
      "step": 359
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 1.0332,
      "step": 360
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 1.039,
      "step": 361
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 1.0034,
      "step": 362
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 0.9631,
      "step": 363
    },
    {
      "epoch": 0.37,
      "learning_rate": 1e-05,
      "loss": 1.0406,
      "step": 364
    },
    {
      "epoch": 0.37,
      "learning_rate": 1e-05,
      "loss": 0.9821,
      "step": 365
    },
    {
      "epoch": 0.37,
      "learning_rate": 1e-05,
      "loss": 1.0231,
      "step": 366
    },
    {
      "epoch": 0.37,
      "learning_rate": 1e-05,
      "loss": 1.0272,
      "step": 367
    },
    {
      "epoch": 0.37,
      "learning_rate": 1e-05,
      "loss": 1.0231,
      "step": 368
    },
    {
      "epoch": 0.37,
      "learning_rate": 1e-05,
      "loss": 0.9833,
      "step": 369
    },
    {
      "epoch": 0.37,
      "learning_rate": 1e-05,
      "loss": 1.0219,
      "step": 370
    },
    {
      "epoch": 0.37,
      "learning_rate": 1e-05,
      "loss": 0.9647,
      "step": 371
    },
    {
      "epoch": 0.37,
      "learning_rate": 1e-05,
      "loss": 1.0044,
      "step": 372
    },
    {
      "epoch": 0.37,
      "learning_rate": 1e-05,
      "loss": 0.9968,
      "step": 373
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 0.9956,
      "step": 374
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 1.0278,
      "step": 375
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 0.9908,
      "step": 376
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 1.0058,
      "step": 377
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 1.0185,
      "step": 378
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 0.97,
      "step": 379
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 0.9491,
      "step": 380
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 1.0639,
      "step": 381
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 1.0,
      "step": 382
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 0.9812,
      "step": 383
    },
    {
      "epoch": 0.39,
      "learning_rate": 1e-05,
      "loss": 1.0691,
      "step": 384
    },
    {
      "epoch": 0.39,
      "learning_rate": 1e-05,
      "loss": 1.0074,
      "step": 385
    },
    {
      "epoch": 0.39,
      "learning_rate": 1e-05,
      "loss": 0.9924,
      "step": 386
    },
    {
      "epoch": 0.39,
      "learning_rate": 1e-05,
      "loss": 0.9976,
      "step": 387
    },
    {
      "epoch": 0.39,
      "learning_rate": 1e-05,
      "loss": 1.0217,
      "step": 388
    },
    {
      "epoch": 0.39,
      "learning_rate": 1e-05,
      "loss": 0.9745,
      "step": 389
    },
    {
      "epoch": 0.39,
      "learning_rate": 1e-05,
      "loss": 1.0014,
      "step": 390
    },
    {
      "epoch": 0.39,
      "learning_rate": 1e-05,
      "loss": 1.0192,
      "step": 391
    },
    {
      "epoch": 0.39,
      "learning_rate": 1e-05,
      "loss": 0.9825,
      "step": 392
    },
    {
      "epoch": 0.4,
      "learning_rate": 1e-05,
      "loss": 1.007,
      "step": 393
    },
    {
      "epoch": 0.4,
      "learning_rate": 1e-05,
      "loss": 1.0288,
      "step": 394
    },
    {
      "epoch": 0.4,
      "learning_rate": 1e-05,
      "loss": 1.0342,
      "step": 395
    },
    {
      "epoch": 0.4,
      "learning_rate": 1e-05,
      "loss": 1.0183,
      "step": 396
    },
    {
      "epoch": 0.4,
      "learning_rate": 1e-05,
      "loss": 0.9884,
      "step": 397
    },
    {
      "epoch": 0.4,
      "learning_rate": 1e-05,
      "loss": 0.9674,
      "step": 398
    },
    {
      "epoch": 0.4,
      "learning_rate": 1e-05,
      "loss": 0.9795,
      "step": 399
    },
    {
      "epoch": 0.4,
      "learning_rate": 1e-05,
      "loss": 0.9885,
      "step": 400
    },
    {
      "epoch": 0.4,
      "eval_val_accuracy": 0.627,
      "eval_val_loss": 1.0441503524780273,
      "eval_val_runtime": 905.3415,
      "eval_val_samples_per_second": 1.105,
      "eval_val_steps_per_second": 0.138,
      "step": 400
    }
  ],
  "logging_steps": 1,
  "max_steps": 1988,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}