{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 252,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01984126984126984,
      "grad_norm": 18.047539550790006,
      "learning_rate": 5.7692307692307695e-08,
      "logits/chosen": -1.703125,
      "logits/rejected": -1.6953125,
      "logps/chosen": -0.376953125,
      "logps/rejected": -0.427734375,
      "loss": 2.4555,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.765625,
      "rewards/margins": 0.50390625,
      "rewards/rejected": -4.28125,
      "step": 5
    },
    {
      "epoch": 0.03968253968253968,
      "grad_norm": 17.185434459136403,
      "learning_rate": 1.1538461538461539e-07,
      "logits/chosen": -1.2578125,
      "logits/rejected": -1.2578125,
      "logps/chosen": -0.32421875,
      "logps/rejected": -0.390625,
      "loss": 2.4857,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.234375,
      "rewards/margins": 0.6640625,
      "rewards/rejected": -3.90625,
      "step": 10
    },
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 17.039133125856026,
      "learning_rate": 1.7307692307692305e-07,
      "logits/chosen": -1.5078125,
      "logits/rejected": -1.5078125,
      "logps/chosen": -0.279296875,
      "logps/rejected": -0.34765625,
      "loss": 2.402,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.78125,
      "rewards/margins": 0.6796875,
      "rewards/rejected": -3.46875,
      "step": 15
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 17.10226682999204,
      "learning_rate": 2.3076923076923078e-07,
      "logits/chosen": -1.4765625,
      "logits/rejected": -1.4765625,
      "logps/chosen": -0.310546875,
      "logps/rejected": -0.39453125,
      "loss": 2.4703,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.09375,
      "rewards/margins": 0.84375,
      "rewards/rejected": -3.9375,
      "step": 20
    },
    {
      "epoch": 0.0992063492063492,
      "grad_norm": 14.47393175785549,
      "learning_rate": 2.8846153846153846e-07,
      "logits/chosen": -1.78125,
      "logits/rejected": -1.78125,
      "logps/chosen": -0.34375,
      "logps/rejected": -0.40234375,
      "loss": 2.3167,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.421875,
      "rewards/margins": 0.5859375,
      "rewards/rejected": -4.0,
      "step": 25
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 16.9612236979206,
      "learning_rate": 2.997681792980754e-07,
      "logits/chosen": -1.3359375,
      "logits/rejected": -1.3359375,
      "logps/chosen": -0.3046875,
      "logps/rejected": -0.357421875,
      "loss": 2.3476,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.03125,
      "rewards/margins": 0.54296875,
      "rewards/rejected": -3.578125,
      "step": 30
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 16.48721079930822,
      "learning_rate": 2.9882763562415516e-07,
      "logits/chosen": -1.5078125,
      "logits/rejected": -1.5078125,
      "logps/chosen": -0.408203125,
      "logps/rejected": -0.482421875,
      "loss": 2.391,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.0625,
      "rewards/margins": 0.75390625,
      "rewards/rejected": -4.8125,
      "step": 35
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 21.37387348387286,
      "learning_rate": 2.9716841847369104e-07,
      "logits/chosen": -1.5,
      "logits/rejected": -1.5,
      "logps/chosen": -0.2890625,
      "logps/rejected": -0.365234375,
      "loss": 2.3684,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.890625,
      "rewards/margins": 0.7578125,
      "rewards/rejected": -3.640625,
      "step": 40
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 17.871422332796683,
      "learning_rate": 2.94798540037113e-07,
      "logits/chosen": -1.546875,
      "logits/rejected": -1.546875,
      "logps/chosen": -0.287109375,
      "logps/rejected": -0.3515625,
      "loss": 2.3699,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.859375,
      "rewards/margins": 0.640625,
      "rewards/rejected": -3.5,
      "step": 45
    },
    {
      "epoch": 0.1984126984126984,
      "grad_norm": 29.190246701669263,
      "learning_rate": 2.917294442157359e-07,
      "logits/chosen": -1.3828125,
      "logits/rejected": -1.3828125,
      "logps/chosen": -0.265625,
      "logps/rejected": -0.34375,
      "loss": 2.3773,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.65625,
      "rewards/margins": 0.78125,
      "rewards/rejected": -3.4375,
      "step": 50
    },
    {
      "epoch": 0.21825396825396826,
      "grad_norm": 20.420712184187625,
      "learning_rate": 2.8797595136032675e-07,
      "logits/chosen": -1.4765625,
      "logits/rejected": -1.4765625,
      "logps/chosen": -0.31640625,
      "logps/rejected": -0.39453125,
      "loss": 2.3586,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.171875,
      "rewards/margins": 0.7734375,
      "rewards/rejected": -3.953125,
      "step": 55
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 17.704268736560135,
      "learning_rate": 2.8355618670514256e-07,
      "logits/chosen": -1.2890625,
      "logits/rejected": -1.2890625,
      "logps/chosen": -0.27734375,
      "logps/rejected": -0.328125,
      "loss": 2.3299,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -2.765625,
      "rewards/margins": 0.515625,
      "rewards/rejected": -3.28125,
      "step": 60
    },
    {
      "epoch": 0.25793650793650796,
      "grad_norm": 15.278992243473061,
      "learning_rate": 2.784914928430218e-07,
      "logits/chosen": -1.40625,
      "logits/rejected": -1.40625,
      "logps/chosen": -0.294921875,
      "logps/rejected": -0.37109375,
      "loss": 2.3791,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -2.953125,
      "rewards/margins": 0.7578125,
      "rewards/rejected": -3.703125,
      "step": 65
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 21.138997719744832,
      "learning_rate": 2.728063266641801e-07,
      "logits/chosen": -1.6484375,
      "logits/rejected": -1.6484375,
      "logps/chosen": -0.26953125,
      "logps/rejected": -0.361328125,
      "loss": 2.3719,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.703125,
      "rewards/margins": 0.9140625,
      "rewards/rejected": -3.625,
      "step": 70
    },
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 26.097345440204215,
      "learning_rate": 2.665281412563814e-07,
      "logits/chosen": -1.875,
      "logits/rejected": -1.875,
      "logps/chosen": -0.26171875,
      "logps/rejected": -0.37109375,
      "loss": 2.318,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.625,
      "rewards/margins": 1.0859375,
      "rewards/rejected": -3.703125,
      "step": 75
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 21.061149357230455,
      "learning_rate": 2.596872533367763e-07,
      "logits/chosen": -1.5,
      "logits/rejected": -1.5,
      "logps/chosen": -0.28125,
      "logps/rejected": -0.373046875,
      "loss": 2.2812,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.828125,
      "rewards/margins": 0.89453125,
      "rewards/rejected": -3.71875,
      "step": 80
    },
    {
      "epoch": 0.3373015873015873,
      "grad_norm": 34.0182184293618,
      "learning_rate": 2.5231669685556633e-07,
      "logits/chosen": -1.1875,
      "logits/rejected": -1.1875,
      "logps/chosen": -0.27734375,
      "logps/rejected": -0.39453125,
      "loss": 2.166,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.78125,
      "rewards/margins": 1.15625,
      "rewards/rejected": -3.9375,
      "step": 85
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 20.821123274301424,
      "learning_rate": 2.444520634784271e-07,
      "logits/chosen": -1.3359375,
      "logits/rejected": -1.3359375,
      "logps/chosen": -0.267578125,
      "logps/rejected": -0.361328125,
      "loss": 2.1671,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.671875,
      "rewards/margins": 0.9453125,
      "rewards/rejected": -3.625,
      "step": 90
    },
    {
      "epoch": 0.376984126984127,
      "grad_norm": 22.90486064935448,
      "learning_rate": 2.361313307179837e-07,
      "logits/chosen": -1.7265625,
      "logits/rejected": -1.7265625,
      "logps/chosen": -0.279296875,
      "logps/rejected": -0.353515625,
      "loss": 2.0894,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.78125,
      "rewards/margins": 0.74609375,
      "rewards/rejected": -3.53125,
      "step": 95
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 27.68913080972186,
      "learning_rate": 2.2739467854427513e-07,
      "logits/chosen": -1.65625,
      "logits/rejected": -1.65625,
      "logps/chosen": -0.353515625,
      "logps/rejected": -0.46875,
      "loss": 2.1033,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.546875,
      "rewards/margins": 1.1484375,
      "rewards/rejected": -4.6875,
      "step": 100
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 29.979641972346496,
      "learning_rate": 2.1828429535977582e-07,
      "logits/chosen": -1.6796875,
      "logits/rejected": -1.6796875,
      "logps/chosen": -0.3203125,
      "logps/rejected": -0.4296875,
      "loss": 2.0674,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -3.1875,
      "rewards/margins": 1.09375,
      "rewards/rejected": -4.28125,
      "step": 105
    },
    {
      "epoch": 0.4365079365079365,
      "grad_norm": 44.14626475514875,
      "learning_rate": 2.0884417427590215e-07,
      "logits/chosen": -1.65625,
      "logits/rejected": -1.65625,
      "logps/chosen": -0.34375,
      "logps/rejected": -0.46875,
      "loss": 2.0088,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.4375,
      "rewards/margins": 1.2578125,
      "rewards/rejected": -4.6875,
      "step": 110
    },
    {
      "epoch": 0.45634920634920634,
      "grad_norm": 33.80229631943301,
      "learning_rate": 1.9911990067476334e-07,
      "logits/chosen": -1.15625,
      "logits/rejected": -1.15625,
      "logps/chosen": -0.23828125,
      "logps/rejected": -0.34375,
      "loss": 1.9458,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.390625,
      "rewards/margins": 1.046875,
      "rewards/rejected": -3.4375,
      "step": 115
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 39.86801120602329,
      "learning_rate": 1.8915843208199963e-07,
      "logits/chosen": -1.625,
      "logits/rejected": -1.625,
      "logps/chosen": -0.4296875,
      "logps/rejected": -0.546875,
      "loss": 1.9224,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.3125,
      "rewards/margins": 1.171875,
      "rewards/rejected": -5.46875,
      "step": 120
    },
    {
      "epoch": 0.49603174603174605,
      "grad_norm": 33.949958184137344,
      "learning_rate": 1.7900787141367918e-07,
      "logits/chosen": -1.453125,
      "logits/rejected": -1.453125,
      "logps/chosen": -0.357421875,
      "logps/rejected": -0.4765625,
      "loss": 2.0021,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.578125,
      "rewards/margins": 1.1875,
      "rewards/rejected": -4.78125,
      "step": 125
    },
    {
      "epoch": 0.5158730158730159,
      "grad_norm": 37.35189108229666,
      "learning_rate": 1.687172346922213e-07,
      "logits/chosen": -1.546875,
      "logits/rejected": -1.546875,
      "logps/chosen": -0.419921875,
      "logps/rejected": -0.546875,
      "loss": 1.7533,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -4.1875,
      "rewards/margins": 1.2578125,
      "rewards/rejected": -5.46875,
      "step": 130
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 33.938784524888526,
      "learning_rate": 1.5833621435302245e-07,
      "logits/chosen": -1.734375,
      "logits/rejected": -1.734375,
      "logps/chosen": -0.421875,
      "logps/rejected": -0.63671875,
      "loss": 1.716,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.21875,
      "rewards/margins": 2.15625,
      "rewards/rejected": -6.34375,
      "step": 135
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 35.12217870275606,
      "learning_rate": 1.4791493928475273e-07,
      "logits/chosen": -1.5234375,
      "logits/rejected": -1.5234375,
      "logps/chosen": -0.30078125,
      "logps/rejected": -0.578125,
      "loss": 1.7479,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.015625,
      "rewards/margins": 2.765625,
      "rewards/rejected": -5.78125,
      "step": 140
    },
    {
      "epoch": 0.5753968253968254,
      "grad_norm": 34.0474825303708,
      "learning_rate": 1.3750373276206429e-07,
      "logits/chosen": -1.59375,
      "logits/rejected": -1.59375,
      "logps/chosen": -0.404296875,
      "logps/rejected": -0.60546875,
      "loss": 1.5267,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.03125,
      "rewards/margins": 2.015625,
      "rewards/rejected": -6.0625,
      "step": 145
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 40.81441971424475,
      "learning_rate": 1.2715286943962924e-07,
      "logits/chosen": -1.484375,
      "logits/rejected": -1.484375,
      "logps/chosen": -0.36328125,
      "logps/rejected": -0.5546875,
      "loss": 1.4843,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.625,
      "rewards/margins": 1.9375,
      "rewards/rejected": -5.5625,
      "step": 150
    },
    {
      "epoch": 0.6150793650793651,
      "grad_norm": 34.79982376085805,
      "learning_rate": 1.1691233258095889e-07,
      "logits/chosen": -1.484375,
      "logits/rejected": -1.484375,
      "logps/chosen": -0.306640625,
      "logps/rejected": -0.51953125,
      "loss": 1.3835,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.0625,
      "rewards/margins": 2.125,
      "rewards/rejected": -5.1875,
      "step": 155
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 42.42547672022662,
      "learning_rate": 1.0683157269432096e-07,
      "logits/chosen": -1.8046875,
      "logits/rejected": -1.8046875,
      "logps/chosen": -0.408203125,
      "logps/rejected": -0.5859375,
      "loss": 1.4352,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -4.0625,
      "rewards/margins": 1.796875,
      "rewards/rejected": -5.875,
      "step": 160
    },
    {
      "epoch": 0.6547619047619048,
      "grad_norm": 31.589553355930356,
      "learning_rate": 9.695926874127765e-08,
      "logits/chosen": -1.609375,
      "logits/rejected": -1.609375,
      "logps/chosen": -0.3125,
      "logps/rejected": -0.5546875,
      "loss": 1.2363,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.109375,
      "rewards/margins": 2.4375,
      "rewards/rejected": -5.5625,
      "step": 165
    },
    {
      "epoch": 0.6746031746031746,
      "grad_norm": 49.83108895416612,
      "learning_rate": 8.734309307094381e-08,
      "logits/chosen": -1.515625,
      "logits/rejected": -1.515625,
      "logps/chosen": -0.255859375,
      "logps/rejected": -0.39453125,
      "loss": 1.7128,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.5625,
      "rewards/margins": 1.3984375,
      "rewards/rejected": -3.953125,
      "step": 170
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 53.80975894133238,
      "learning_rate": 7.802948121507461e-08,
      "logits/chosen": -1.7265625,
      "logits/rejected": -1.7265625,
      "logps/chosen": -0.33203125,
      "logps/rejected": -0.52734375,
      "loss": 1.7579,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.3125,
      "rewards/margins": 1.953125,
      "rewards/rejected": -5.28125,
      "step": 175
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 26.370363764214527,
      "learning_rate": 6.906340765561734e-08,
      "logits/chosen": -1.265625,
      "logits/rejected": -1.265625,
      "logps/chosen": -0.42578125,
      "logps/rejected": -0.69140625,
      "loss": 1.1591,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.25,
      "rewards/margins": 2.65625,
      "rewards/rejected": -6.90625,
      "step": 180
    },
    {
      "epoch": 0.7341269841269841,
      "grad_norm": 36.18162633880284,
      "learning_rate": 6.048816864752422e-08,
      "logits/chosen": -1.609375,
      "logits/rejected": -1.609375,
      "logps/chosen": -0.421875,
      "logps/rejected": -0.7421875,
      "loss": 1.2978,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.21875,
      "rewards/margins": 3.1875,
      "rewards/rejected": -7.40625,
      "step": 185
    },
    {
      "epoch": 0.753968253968254,
      "grad_norm": 42.731435648770926,
      "learning_rate": 5.2345173145552125e-08,
      "logits/chosen": -1.78125,
      "logits/rejected": -1.78125,
      "logps/chosen": -0.32421875,
      "logps/rejected": -0.55859375,
      "loss": 1.5185,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.234375,
      "rewards/margins": 2.34375,
      "rewards/rejected": -5.5625,
      "step": 190
    },
    {
      "epoch": 0.7738095238095238,
      "grad_norm": 47.99973669165908,
      "learning_rate": 4.467374284464271e-08,
      "logits/chosen": -1.6171875,
      "logits/rejected": -1.6171875,
      "logps/chosen": -0.35546875,
      "logps/rejected": -0.62890625,
      "loss": 1.2557,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.546875,
      "rewards/margins": 2.75,
      "rewards/rejected": -6.28125,
      "step": 195
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 31.799179942413893,
      "learning_rate": 3.751092229946681e-08,
      "logits/chosen": -1.7421875,
      "logits/rejected": -1.7421875,
      "logps/chosen": -0.37890625,
      "logps/rejected": -0.578125,
      "loss": 1.3694,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.78125,
      "rewards/margins": 1.984375,
      "rewards/rejected": -5.78125,
      "step": 200
    },
    {
      "epoch": 0.8134920634920635,
      "grad_norm": 32.210040778412214,
      "learning_rate": 3.0891300040047544e-08,
      "logits/chosen": -1.390625,
      "logits/rejected": -1.390625,
      "logps/chosen": -0.423828125,
      "logps/rejected": -0.68359375,
      "loss": 1.3582,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.25,
      "rewards/margins": 2.578125,
      "rewards/rejected": -6.8125,
      "step": 205
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 41.74711583345937,
      "learning_rate": 2.4846841547275915e-08,
      "logits/chosen": -1.1640625,
      "logits/rejected": -1.1640625,
      "logps/chosen": -0.259765625,
      "logps/rejected": -0.396484375,
      "loss": 1.3447,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.59375,
      "rewards/margins": 1.3671875,
      "rewards/rejected": -3.96875,
      "step": 210
    },
    {
      "epoch": 0.8531746031746031,
      "grad_norm": 46.7470602788351,
      "learning_rate": 1.9406734894862847e-08,
      "logits/chosen": -1.1875,
      "logits/rejected": -1.1875,
      "logps/chosen": -0.412109375,
      "logps/rejected": -0.71484375,
      "loss": 1.2536,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.125,
      "rewards/margins": 3.03125,
      "rewards/rejected": -7.15625,
      "step": 215
    },
    {
      "epoch": 0.873015873015873,
      "grad_norm": 60.766181922921575,
      "learning_rate": 1.459724980310767e-08,
      "logits/chosen": -1.4765625,
      "logits/rejected": -1.484375,
      "logps/chosen": -0.34765625,
      "logps/rejected": -0.625,
      "loss": 1.2171,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.46875,
      "rewards/margins": 2.8125,
      "rewards/rejected": -6.28125,
      "step": 220
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 31.72970074806701,
      "learning_rate": 1.0441610785097471e-08,
      "logits/chosen": -1.3125,
      "logits/rejected": -1.3125,
      "logps/chosen": -0.34765625,
      "logps/rejected": -0.453125,
      "loss": 1.2928,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -3.46875,
      "rewards/margins": 1.0625,
      "rewards/rejected": -4.53125,
      "step": 225
    },
    {
      "epoch": 0.9126984126984127,
      "grad_norm": 35.90988337509379,
      "learning_rate": 6.959884997901705e-09,
      "logits/chosen": -1.203125,
      "logits/rejected": -1.203125,
      "logps/chosen": -0.2451171875,
      "logps/rejected": -0.484375,
      "loss": 1.2009,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.453125,
      "rewards/margins": 2.390625,
      "rewards/rejected": -4.84375,
      "step": 230
    },
    {
      "epoch": 0.9325396825396826,
      "grad_norm": 39.759595151629654,
      "learning_rate": 4.168885340316719e-09,
      "logits/chosen": -1.4296875,
      "logits/rejected": -1.4296875,
      "logps/chosen": -0.4453125,
      "logps/rejected": -0.5390625,
      "loss": 1.4925,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -4.4375,
      "rewards/margins": 0.9296875,
      "rewards/rejected": -5.375,
      "step": 235
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 45.2835359838723,
      "learning_rate": 2.0820892650920686e-09,
      "logits/chosen": -1.40625,
      "logits/rejected": -1.40625,
      "logps/chosen": -0.4296875,
      "logps/rejected": -0.8671875,
      "loss": 1.0995,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.3125,
      "rewards/margins": 4.375,
      "rewards/rejected": -8.6875,
      "step": 240
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 38.0802575489829,
      "learning_rate": 7.095736976853894e-10,
      "logits/chosen": -1.2578125,
      "logits/rejected": -1.2578125,
      "logps/chosen": -0.48046875,
      "logps/rejected": -0.890625,
      "loss": 1.3758,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.78125,
      "rewards/margins": 4.125,
      "rewards/rejected": -8.875,
      "step": 245
    },
    {
      "epoch": 0.9920634920634921,
      "grad_norm": 54.22110017894445,
      "learning_rate": 5.796637581689245e-11,
      "logits/chosen": -1.484375,
      "logits/rejected": -1.484375,
      "logps/chosen": -0.44921875,
      "logps/rejected": -0.6015625,
      "loss": 1.466,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.5,
      "rewards/margins": 1.515625,
      "rewards/rejected": -6.0,
      "step": 250
    },
    {
      "epoch": 1.0,
      "step": 252,
      "total_flos": 0.0,
      "train_loss": 1.8338732454511855,
      "train_runtime": 6099.2148,
      "train_samples_per_second": 0.33,
      "train_steps_per_second": 0.041
    }
  ],
  "logging_steps": 5,
  "max_steps": 252,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}