{
  "best_metric": 0.5233827829360962,
  "best_model_checkpoint": "./output_v2/7b_cluster00_Nous-Hermes-llama-2-7b_codellama_blob_1/checkpoint-400",
  "epoch": 1.1228070175438596,
  "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": 2e-06,
      "loss": 0.7795,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-06,
      "loss": 0.6789,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.999999999999999e-06,
      "loss": 0.6847,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-06,
      "loss": 0.6876,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.5964,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.1999999999999999e-05,
      "loss": 0.6592,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.4e-05,
      "loss": 0.6261,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.6e-05,
      "loss": 0.6892,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.7999999999999997e-05,
      "loss": 0.538,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.6015,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.2e-05,
      "loss": 0.7061,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.3999999999999997e-05,
      "loss": 0.6329,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.6e-05,
      "loss": 0.5633,
      "step": 13
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.8e-05,
      "loss": 0.5499,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.5846,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.2e-05,
      "loss": 0.7056,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.399999999999999e-05,
      "loss": 0.9478,
      "step": 17
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.5999999999999994e-05,
      "loss": 0.7119,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.8e-05,
      "loss": 0.5115,
      "step": 19
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.9999999999999996e-05,
      "loss": 0.6481,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.2e-05,
      "loss": 1.0479,
      "step": 21
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.4e-05,
      "loss": 0.9266,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.599999999999999e-05,
      "loss": 0.7517,
      "step": 23
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.7999999999999994e-05,
      "loss": 0.7024,
      "step": 24
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 0.6996,
      "step": 25
    },
    {
      "epoch": 0.07,
      "eval_loss": 0.6741535663604736,
      "eval_runtime": 26.372,
      "eval_samples_per_second": 7.584,
      "eval_steps_per_second": 1.896,
      "step": 25
    },
    {
      "dharma_eval_accuracy": 0.47090526975371527,
      "dharma_eval_accuracy_ARC-Challenge": 0.6296296296296297,
      "dharma_eval_accuracy_ARC-Easy": 0.7592592592592593,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.4444444444444444,
      "dharma_eval_accuracy_agieval": 0.2542372881355932,
      "dharma_eval_accuracy_bigbench": 0.4098360655737705,
      "dharma_eval_accuracy_openbookqa": 0.2962962962962963,
      "dharma_eval_accuracy_truthful_qa": 0.37037037037037035,
      "dharma_eval_accuracy_winogrande": 0.37037037037037035,
      "dharma_loss": 3.7834435443878176,
      "epoch": 0.07,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.2e-05,
      "loss": 0.6123,
      "step": 26
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.399999999999999e-05,
      "loss": 0.608,
      "step": 27
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.6e-05,
      "loss": 0.4845,
      "step": 28
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.7999999999999994e-05,
      "loss": 0.6026,
      "step": 29
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.87,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 6.199999999999999e-05,
      "loss": 0.9898,
      "step": 31
    },
    {
      "epoch": 0.09,
      "learning_rate": 6.4e-05,
      "loss": 0.7354,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 6.599999999999999e-05,
      "loss": 0.5053,
      "step": 33
    },
    {
      "epoch": 0.1,
      "learning_rate": 6.799999999999999e-05,
      "loss": 0.6644,
      "step": 34
    },
    {
      "epoch": 0.1,
      "learning_rate": 7e-05,
      "loss": 0.6932,
      "step": 35
    },
    {
      "epoch": 0.1,
      "learning_rate": 7.199999999999999e-05,
      "loss": 0.7425,
      "step": 36
    },
    {
      "epoch": 0.1,
      "learning_rate": 7.4e-05,
      "loss": 0.8268,
      "step": 37
    },
    {
      "epoch": 0.11,
      "learning_rate": 7.6e-05,
      "loss": 0.5957,
      "step": 38
    },
    {
      "epoch": 0.11,
      "learning_rate": 7.8e-05,
      "loss": 0.5579,
      "step": 39
    },
    {
      "epoch": 0.11,
      "learning_rate": 7.999999999999999e-05,
      "loss": 0.7978,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.199999999999999e-05,
      "loss": 0.8261,
      "step": 41
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.4e-05,
      "loss": 0.7618,
      "step": 42
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.6e-05,
      "loss": 0.6062,
      "step": 43
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.8e-05,
      "loss": 0.5791,
      "step": 44
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.6008,
      "step": 45
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.199999999999999e-05,
      "loss": 0.5143,
      "step": 46
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.4e-05,
      "loss": 0.5329,
      "step": 47
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.599999999999999e-05,
      "loss": 0.6973,
      "step": 48
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.799999999999998e-05,
      "loss": 0.615,
      "step": 49
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.999999999999999e-05,
      "loss": 0.6362,
      "step": 50
    },
    {
      "epoch": 0.14,
      "eval_loss": 0.6042094826698303,
      "eval_runtime": 26.344,
      "eval_samples_per_second": 7.592,
      "eval_steps_per_second": 1.898,
      "step": 50
    },
    {
      "dharma_eval_accuracy": 0.4825425901342051,
      "dharma_eval_accuracy_ARC-Challenge": 0.6666666666666666,
      "dharma_eval_accuracy_ARC-Easy": 0.6851851851851852,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.42592592592592593,
      "dharma_eval_accuracy_agieval": 0.2542372881355932,
      "dharma_eval_accuracy_bigbench": 0.45901639344262296,
      "dharma_eval_accuracy_openbookqa": 0.3333333333333333,
      "dharma_eval_accuracy_truthful_qa": 0.35185185185185186,
      "dharma_eval_accuracy_winogrande": 0.46296296296296297,
      "dharma_loss": 2.1548793907165527,
      "epoch": 0.14,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000102,
      "loss": 0.6567,
      "step": 51
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000104,
      "loss": 0.9786,
      "step": 52
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00010599999999999999,
      "loss": 0.6146,
      "step": 53
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00010799999999999998,
      "loss": 0.6402,
      "step": 54
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00010999999999999998,
      "loss": 0.5906,
      "step": 55
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000112,
      "loss": 0.6441,
      "step": 56
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.6887,
      "step": 57
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00011599999999999999,
      "loss": 0.6283,
      "step": 58
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00011799999999999998,
      "loss": 0.5929,
      "step": 59
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.6939,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000122,
      "loss": 0.5535,
      "step": 61
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00012399999999999998,
      "loss": 0.5457,
      "step": 62
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00012599999999999997,
      "loss": 0.6425,
      "step": 63
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000128,
      "loss": 0.6855,
      "step": 64
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00013,
      "loss": 0.5396,
      "step": 65
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00013199999999999998,
      "loss": 0.6307,
      "step": 66
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00013399999999999998,
      "loss": 0.6396,
      "step": 67
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00013599999999999997,
      "loss": 0.5727,
      "step": 68
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000138,
      "loss": 0.4812,
      "step": 69
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00014,
      "loss": 0.5658,
      "step": 70
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00014199999999999998,
      "loss": 0.6314,
      "step": 71
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00014399999999999998,
      "loss": 0.6175,
      "step": 72
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000146,
      "loss": 0.5468,
      "step": 73
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000148,
      "loss": 0.6233,
      "step": 74
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00015,
      "loss": 0.5276,
      "step": 75
    },
    {
      "epoch": 0.21,
      "eval_loss": 0.5642657279968262,
      "eval_runtime": 26.2701,
      "eval_samples_per_second": 7.613,
      "eval_steps_per_second": 1.903,
      "step": 75
    },
    {
      "dharma_eval_accuracy": 0.45038002097061713,
      "dharma_eval_accuracy_ARC-Challenge": 0.6111111111111112,
      "dharma_eval_accuracy_ARC-Easy": 0.6111111111111112,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.42592592592592593,
      "dharma_eval_accuracy_agieval": 0.2033898305084746,
      "dharma_eval_accuracy_bigbench": 0.4426229508196721,
      "dharma_eval_accuracy_openbookqa": 0.14814814814814814,
      "dharma_eval_accuracy_truthful_qa": 0.42592592592592593,
      "dharma_eval_accuracy_winogrande": 0.48148148148148145,
      "dharma_loss": 2.056876979827881,
      "epoch": 0.21,
      "step": 75
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000152,
      "loss": 0.5308,
      "step": 76
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015399999999999998,
      "loss": 0.6546,
      "step": 77
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000156,
      "loss": 0.6451,
      "step": 78
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015799999999999996,
      "loss": 0.5255,
      "step": 79
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015999999999999999,
      "loss": 0.5629,
      "step": 80
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000162,
      "loss": 0.6642,
      "step": 81
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00016399999999999997,
      "loss": 0.6393,
      "step": 82
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000166,
      "loss": 0.5073,
      "step": 83
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000168,
      "loss": 0.5628,
      "step": 84
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00016999999999999999,
      "loss": 0.5566,
      "step": 85
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000172,
      "loss": 0.4653,
      "step": 86
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017399999999999997,
      "loss": 0.5322,
      "step": 87
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000176,
      "loss": 0.7131,
      "step": 88
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000178,
      "loss": 0.5586,
      "step": 89
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.7246,
      "step": 90
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018199999999999998,
      "loss": 0.6527,
      "step": 91
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018399999999999997,
      "loss": 0.8067,
      "step": 92
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000186,
      "loss": 0.6427,
      "step": 93
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000188,
      "loss": 0.6309,
      "step": 94
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018999999999999998,
      "loss": 0.6111,
      "step": 95
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019199999999999998,
      "loss": 0.5911,
      "step": 96
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019399999999999997,
      "loss": 0.6372,
      "step": 97
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019599999999999997,
      "loss": 0.5664,
      "step": 98
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000198,
      "loss": 0.5618,
      "step": 99
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019999999999999998,
      "loss": 0.7154,
      "step": 100
    },
    {
      "epoch": 0.28,
      "eval_loss": 0.5470997095108032,
      "eval_runtime": 26.3144,
      "eval_samples_per_second": 7.6,
      "eval_steps_per_second": 1.9,
      "step": 100
    },
    {
      "dharma_eval_accuracy": 0.398478315307064,
      "dharma_eval_accuracy_ARC-Challenge": 0.5740740740740741,
      "dharma_eval_accuracy_ARC-Easy": 0.48148148148148145,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.4074074074074074,
      "dharma_eval_accuracy_agieval": 0.2711864406779661,
      "dharma_eval_accuracy_bigbench": 0.4262295081967213,
      "dharma_eval_accuracy_openbookqa": 0.07407407407407407,
      "dharma_eval_accuracy_truthful_qa": 0.3888888888888889,
      "dharma_eval_accuracy_winogrande": 0.25925925925925924,
      "dharma_loss": 2.5759267053604127,
      "epoch": 0.28,
      "step": 100
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00020199999999999998,
      "loss": 0.5837,
      "step": 101
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000204,
      "loss": 0.5707,
      "step": 102
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00020599999999999997,
      "loss": 0.7798,
      "step": 103
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000208,
      "loss": 0.4922,
      "step": 104
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.7033,
      "step": 105
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00021199999999999998,
      "loss": 0.7297,
      "step": 106
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000214,
      "loss": 0.5376,
      "step": 107
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00021599999999999996,
      "loss": 0.5372,
      "step": 108
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00021799999999999999,
      "loss": 0.7453,
      "step": 109
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00021999999999999995,
      "loss": 0.4582,
      "step": 110
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00022199999999999998,
      "loss": 0.54,
      "step": 111
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000224,
      "loss": 0.643,
      "step": 112
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00022599999999999996,
      "loss": 0.5972,
      "step": 113
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00022799999999999999,
      "loss": 0.5765,
      "step": 114
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00023,
      "loss": 0.6007,
      "step": 115
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00023199999999999997,
      "loss": 0.5343,
      "step": 116
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000234,
      "loss": 0.8235,
      "step": 117
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00023599999999999996,
      "loss": 0.6687,
      "step": 118
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00023799999999999998,
      "loss": 0.6696,
      "step": 119
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.77,
      "step": 120
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00024199999999999997,
      "loss": 0.5792,
      "step": 121
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000244,
      "loss": 0.3653,
      "step": 122
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00024599999999999996,
      "loss": 0.5344,
      "step": 123
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00024799999999999996,
      "loss": 0.5772,
      "step": 124
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00025,
      "loss": 0.7189,
      "step": 125
    },
    {
      "epoch": 0.35,
      "eval_loss": 0.5514405369758606,
      "eval_runtime": 26.3447,
      "eval_samples_per_second": 7.592,
      "eval_steps_per_second": 1.898,
      "step": 125
    },
    {
      "dharma_eval_accuracy": 0.3371043854202756,
      "dharma_eval_accuracy_ARC-Challenge": 0.37037037037037035,
      "dharma_eval_accuracy_ARC-Easy": 0.42592592592592593,
      "dharma_eval_accuracy_BoolQ": 0.37037037037037035,
      "dharma_eval_accuracy_MMLU": 0.35185185185185186,
      "dharma_eval_accuracy_agieval": 0.22033898305084745,
      "dharma_eval_accuracy_bigbench": 0.29508196721311475,
      "dharma_eval_accuracy_openbookqa": 0.18518518518518517,
      "dharma_eval_accuracy_truthful_qa": 0.3888888888888889,
      "dharma_eval_accuracy_winogrande": 0.42592592592592593,
      "dharma_loss": 2.1871530780792234,
      "epoch": 0.35,
      "step": 125
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00025199999999999995,
      "loss": 0.5891,
      "step": 126
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000254,
      "loss": 0.8225,
      "step": 127
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000256,
      "loss": 0.6104,
      "step": 128
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000258,
      "loss": 0.6571,
      "step": 129
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00026,
      "loss": 0.7562,
      "step": 130
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00026199999999999997,
      "loss": 0.7172,
      "step": 131
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00026399999999999997,
      "loss": 0.4353,
      "step": 132
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000266,
      "loss": 0.5576,
      "step": 133
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00026799999999999995,
      "loss": 0.553,
      "step": 134
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00027,
      "loss": 0.5062,
      "step": 135
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00027199999999999994,
      "loss": 0.4819,
      "step": 136
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000274,
      "loss": 0.6195,
      "step": 137
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000276,
      "loss": 0.7592,
      "step": 138
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000278,
      "loss": 0.6118,
      "step": 139
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00028,
      "loss": 0.7897,
      "step": 140
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00028199999999999997,
      "loss": 0.5879,
      "step": 141
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00028399999999999996,
      "loss": 0.6055,
      "step": 142
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00028599999999999996,
      "loss": 0.541,
      "step": 143
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00028799999999999995,
      "loss": 0.7665,
      "step": 144
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00029,
      "loss": 0.612,
      "step": 145
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000292,
      "loss": 0.5397,
      "step": 146
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000294,
      "loss": 0.5727,
      "step": 147
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000296,
      "loss": 1.1184,
      "step": 148
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000298,
      "loss": 0.5912,
      "step": 149
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.5581,
      "step": 150
    },
    {
      "epoch": 0.42,
      "eval_loss": 0.5423073768615723,
      "eval_runtime": 26.3108,
      "eval_samples_per_second": 7.601,
      "eval_steps_per_second": 1.9,
      "step": 150
    },
    {
      "dharma_eval_accuracy": 0.3860708907481159,
      "dharma_eval_accuracy_ARC-Challenge": 0.42592592592592593,
      "dharma_eval_accuracy_ARC-Easy": 0.4444444444444444,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.37037037037037035,
      "dharma_eval_accuracy_agieval": 0.2542372881355932,
      "dharma_eval_accuracy_bigbench": 0.4426229508196721,
      "dharma_eval_accuracy_openbookqa": 0.18518518518518517,
      "dharma_eval_accuracy_truthful_qa": 0.2962962962962963,
      "dharma_eval_accuracy_winogrande": 0.35185185185185186,
      "dharma_loss": 2.471666145801544,
      "epoch": 0.42,
      "step": 150
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002999999685313931,
      "loss": 0.656,
      "step": 151
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00029999987412558584,
      "loss": 0.5075,
      "step": 152
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002999997167826177,
      "loss": 0.4696,
      "step": 153
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00029999949650255474,
      "loss": 0.7349,
      "step": 154
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002999992132854894,
      "loss": 0.5935,
      "step": 155
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002999988671315404,
      "loss": 0.4127,
      "step": 156
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002999984580408531,
      "loss": 0.5503,
      "step": 157
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00029999798601359915,
      "loss": 0.5742,
      "step": 158
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00029999745104997654,
      "loss": 0.5606,
      "step": 159
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002999968531502098,
      "loss": 0.6209,
      "step": 160
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002999961923145497,
      "loss": 0.4977,
      "step": 161
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002999954685432736,
      "loss": 0.7474,
      "step": 162
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002999946818366852,
      "loss": 0.574,
      "step": 163
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00029999383219511444,
      "loss": 0.3991,
      "step": 164
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002999929196189179,
      "loss": 0.6335,
      "step": 165
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002999919441084786,
      "loss": 0.6144,
      "step": 166
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002999909056642057,
      "loss": 0.4695,
      "step": 167
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00029998980428653496,
      "loss": 0.5322,
      "step": 168
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00029998863997592843,
      "loss": 0.6111,
      "step": 169
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00029998741273287477,
      "loss": 0.5517,
      "step": 170
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002999861225578888,
      "loss": 0.5407,
      "step": 171
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00029998476945151183,
      "loss": 0.4942,
      "step": 172
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00029998335341431174,
      "loss": 0.4563,
      "step": 173
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002999818744468825,
      "loss": 0.4406,
      "step": 174
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002999803325498448,
      "loss": 0.5319,
      "step": 175
    },
    {
      "epoch": 0.49,
      "eval_loss": 0.5312690734863281,
      "eval_runtime": 26.3302,
      "eval_samples_per_second": 7.596,
      "eval_steps_per_second": 1.899,
      "step": 175
    },
    {
      "dharma_eval_accuracy": 0.40200352864364475,
      "dharma_eval_accuracy_ARC-Challenge": 0.42592592592592593,
      "dharma_eval_accuracy_ARC-Easy": 0.5,
      "dharma_eval_accuracy_BoolQ": 0.7592592592592593,
      "dharma_eval_accuracy_MMLU": 0.4074074074074074,
      "dharma_eval_accuracy_agieval": 0.22033898305084745,
      "dharma_eval_accuracy_bigbench": 0.36065573770491804,
      "dharma_eval_accuracy_openbookqa": 0.2222222222222222,
      "dharma_eval_accuracy_truthful_qa": 0.2962962962962963,
      "dharma_eval_accuracy_winogrande": 0.42592592592592593,
      "dharma_loss": 2.2439456572532652,
      "epoch": 0.49,
      "step": 175
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002999787277238455,
      "loss": 0.7389,
      "step": 176
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000299977059969558,
      "loss": 0.6848,
      "step": 177
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00029997532928768204,
      "loss": 0.5144,
      "step": 178
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00029997353567894384,
      "loss": 0.5707,
      "step": 179
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002999716791440959,
      "loss": 0.668,
      "step": 180
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00029996975968391715,
      "loss": 0.4851,
      "step": 181
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000299967777299213,
      "loss": 0.725,
      "step": 182
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002999657319908153,
      "loss": 0.6281,
      "step": 183
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002999636237595821,
      "loss": 0.6357,
      "step": 184
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00029996145260639806,
      "loss": 0.5517,
      "step": 185
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002999592185321741,
      "loss": 0.6792,
      "step": 186
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002999569215378477,
      "loss": 0.619,
      "step": 187
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002999545616243825,
      "loss": 0.5693,
      "step": 188
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00029995213879276876,
      "loss": 0.5759,
      "step": 189
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000299949653044023,
      "loss": 0.4382,
      "step": 190
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00029994710437918824,
      "loss": 0.7183,
      "step": 191
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002999444927993338,
      "loss": 0.7328,
      "step": 192
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00029994181830555555,
      "loss": 0.645,
      "step": 193
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00029993908089897555,
      "loss": 0.5784,
      "step": 194
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00029993628058074245,
      "loss": 0.4547,
      "step": 195
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00029993341735203114,
      "loss": 0.5243,
      "step": 196
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00029993049121404303,
      "loss": 0.5059,
      "step": 197
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002999275021680058,
      "loss": 0.6225,
      "step": 198
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002999244502151737,
      "loss": 0.5956,
      "step": 199
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00029992133535682725,
      "loss": 0.553,
      "step": 200
    },
    {
      "epoch": 0.56,
      "eval_loss": 0.5266188979148865,
      "eval_runtime": 26.3,
      "eval_samples_per_second": 7.605,
      "eval_steps_per_second": 1.901,
      "step": 200
    },
    {
      "dharma_eval_accuracy": 0.4282802607491564,
      "dharma_eval_accuracy_ARC-Challenge": 0.5185185185185185,
      "dharma_eval_accuracy_ARC-Easy": 0.5740740740740741,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.4074074074074074,
      "dharma_eval_accuracy_agieval": 0.22033898305084745,
      "dharma_eval_accuracy_bigbench": 0.39344262295081966,
      "dharma_eval_accuracy_openbookqa": 0.14814814814814814,
      "dharma_eval_accuracy_truthful_qa": 0.3148148148148148,
      "dharma_eval_accuracy_winogrande": 0.5740740740740741,
      "dharma_loss": 2.507861177444458,
      "epoch": 0.56,
      "step": 200
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002999181575942733,
      "loss": 0.4542,
      "step": 201
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002999149169288452,
      "loss": 0.568,
      "step": 202
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002999116133619028,
      "loss": 0.462,
      "step": 203
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002999082468948321,
      "loss": 0.4854,
      "step": 204
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00029990481752904563,
      "loss": 0.474,
      "step": 205
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002999013252659823,
      "loss": 0.5331,
      "step": 206
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002998977701071074,
      "loss": 0.606,
      "step": 207
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00029989415205391263,
      "loss": 0.5452,
      "step": 208
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00029989047110791595,
      "loss": 0.6128,
      "step": 209
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002998867272706619,
      "loss": 0.7108,
      "step": 210
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002998829205437214,
      "loss": 0.5557,
      "step": 211
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002998790509286915,
      "loss": 0.556,
      "step": 212
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000299875118427196,
      "loss": 0.6482,
      "step": 213
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00029987112304088483,
      "loss": 0.6108,
      "step": 214
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002998670647714343,
      "loss": 0.7099,
      "step": 215
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002998629436205473,
      "loss": 0.5939,
      "step": 216
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00029985875958995296,
      "loss": 0.6238,
      "step": 217
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00029985451268140683,
      "loss": 0.5144,
      "step": 218
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00029985020289669077,
      "loss": 0.7351,
      "step": 219
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00029984583023761317,
      "loss": 0.6136,
      "step": 220
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002998413947060086,
      "loss": 0.7544,
      "step": 221
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00029983689630373825,
      "loss": 0.5588,
      "step": 222
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002998323350326895,
      "loss": 0.5725,
      "step": 223
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002998277108947762,
      "loss": 0.6262,
      "step": 224
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00029982302389193856,
      "loss": 0.6217,
      "step": 225
    },
    {
      "epoch": 0.63,
      "eval_loss": 0.527147114276886,
      "eval_runtime": 26.3496,
      "eval_samples_per_second": 7.59,
      "eval_steps_per_second": 1.898,
      "step": 225
    },
    {
      "dharma_eval_accuracy": 0.39483532805751936,
      "dharma_eval_accuracy_ARC-Challenge": 0.48148148148148145,
      "dharma_eval_accuracy_ARC-Easy": 0.6111111111111112,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.5185185185185185,
      "dharma_eval_accuracy_agieval": 0.2711864406779661,
      "dharma_eval_accuracy_bigbench": 0.39344262295081966,
      "dharma_eval_accuracy_openbookqa": 0.037037037037037035,
      "dharma_eval_accuracy_truthful_qa": 0.18518518518518517,
      "dharma_eval_accuracy_winogrande": 0.35185185185185186,
      "dharma_loss": 2.334738277435303,
      "epoch": 0.63,
      "step": 225
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002998182740261432,
      "loss": 0.6376,
      "step": 226
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002998134612993829,
      "loss": 0.5943,
      "step": 227
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002998085857136772,
      "loss": 0.4096,
      "step": 228
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00029980364727107166,
      "loss": 0.5825,
      "step": 229
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00029979864597363845,
      "loss": 0.5372,
      "step": 230
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002997935818234759,
      "loss": 0.5376,
      "step": 231
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00029978845482270906,
      "loss": 0.4369,
      "step": 232
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002997832649734889,
      "loss": 0.5717,
      "step": 233
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002997780122779931,
      "loss": 0.6981,
      "step": 234
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002997726967384255,
      "loss": 0.5764,
      "step": 235
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002997673183570165,
      "loss": 0.5937,
      "step": 236
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00029976187713602273,
      "loss": 0.2708,
      "step": 237
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002997563730777273,
      "loss": 0.6383,
      "step": 238
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00029975080618443946,
      "loss": 0.491,
      "step": 239
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00029974517645849503,
      "loss": 0.5049,
      "step": 240
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002997394839022562,
      "loss": 0.5768,
      "step": 241
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00029973372851811145,
      "loss": 0.566,
      "step": 242
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00029972791030847553,
      "loss": 0.7687,
      "step": 243
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002997220292757898,
      "loss": 0.6399,
      "step": 244
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002997160854225217,
      "loss": 0.545,
      "step": 245
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00029971007875116527,
      "loss": 0.6108,
      "step": 246
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002997040092642407,
      "loss": 0.6478,
      "step": 247
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002996978769642947,
      "loss": 0.5959,
      "step": 248
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002996916818539003,
      "loss": 0.5995,
      "step": 249
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002996854239356567,
      "loss": 0.5721,
      "step": 250
    },
    {
      "epoch": 0.7,
      "eval_loss": 0.5253523588180542,
      "eval_runtime": 26.3162,
      "eval_samples_per_second": 7.6,
      "eval_steps_per_second": 1.9,
      "step": 250
    },
    {
      "dharma_eval_accuracy": 0.35750614311016893,
      "dharma_eval_accuracy_ARC-Challenge": 0.48148148148148145,
      "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371,
      "dharma_eval_accuracy_BoolQ": 0.6851851851851852,
      "dharma_eval_accuracy_MMLU": 0.3888888888888889,
      "dharma_eval_accuracy_agieval": 0.23728813559322035,
      "dharma_eval_accuracy_bigbench": 0.29508196721311475,
      "dharma_eval_accuracy_openbookqa": 0.018518518518518517,
      "dharma_eval_accuracy_truthful_qa": 0.2222222222222222,
      "dharma_eval_accuracy_winogrande": 0.35185185185185186,
      "dharma_loss": 3.018469988822937,
      "epoch": 0.7,
      "step": 250
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002996791032121898,
      "loss": 0.3632,
      "step": 251
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002996727196861515,
      "loss": 0.5306,
      "step": 252
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00029966627336022034,
      "loss": 0.4332,
      "step": 253
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000299659764237101,
      "loss": 0.4484,
      "step": 254
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00029965319231952455,
      "loss": 0.5353,
      "step": 255
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00029964655761024854,
      "loss": 0.6232,
      "step": 256
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00029963986011205675,
      "loss": 0.672,
      "step": 257
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002996330998277593,
      "loss": 0.5865,
      "step": 258
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002996262767601926,
      "loss": 0.8846,
      "step": 259
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002996193909122197,
      "loss": 0.4847,
      "step": 260
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00029961244228672953,
      "loss": 0.5886,
      "step": 261
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002996054308866378,
      "loss": 0.6324,
      "step": 262
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002995983567148862,
      "loss": 0.4812,
      "step": 263
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000299591219774443,
      "loss": 0.6549,
      "step": 264
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00029958402006830274,
      "loss": 0.4712,
      "step": 265
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002995767575994863,
      "loss": 0.452,
      "step": 266
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00029956943237104084,
      "loss": 0.5716,
      "step": 267
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002995620443860399,
      "loss": 0.6757,
      "step": 268
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002995545936475833,
      "loss": 0.5403,
      "step": 269
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002995470801587973,
      "loss": 0.6785,
      "step": 270
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002995395039228343,
      "loss": 0.6292,
      "step": 271
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00029953186494287336,
      "loss": 0.5181,
      "step": 272
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002995241632221195,
      "loss": 0.5219,
      "step": 273
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00029951639876380425,
      "loss": 0.5475,
      "step": 274
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002995085715711854,
      "loss": 0.5605,
      "step": 275
    },
    {
      "epoch": 0.77,
      "eval_loss": 0.5327661633491516,
      "eval_runtime": 26.3174,
      "eval_samples_per_second": 7.6,
      "eval_steps_per_second": 1.9,
      "step": 275
    },
    {
      "dharma_eval_accuracy": 0.4329237545408704,
      "dharma_eval_accuracy_ARC-Challenge": 0.5555555555555556,
      "dharma_eval_accuracy_ARC-Easy": 0.6111111111111112,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.37037037037037035,
      "dharma_eval_accuracy_agieval": 0.2542372881355932,
      "dharma_eval_accuracy_bigbench": 0.47540983606557374,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.3148148148148148,
      "dharma_eval_accuracy_winogrande": 0.5185185185185185,
      "dharma_loss": 2.377507550239563,
      "epoch": 0.77,
      "step": 275
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002995006816475471,
      "loss": 0.5067,
      "step": 276
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00029949272899619994,
      "loss": 0.6751,
      "step": 277
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002994847136204805,
      "loss": 0.5557,
      "step": 278
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002994766355237521,
      "loss": 0.6013,
      "step": 279
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002994684947094039,
      "loss": 0.4763,
      "step": 280
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00029946029118085193,
      "loss": 0.5,
      "step": 281
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000299452024941538,
      "loss": 0.4948,
      "step": 282
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002994436959949306,
      "loss": 0.4705,
      "step": 283
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002994353043445244,
      "loss": 0.8139,
      "step": 284
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002994268499938403,
      "loss": 0.4713,
      "step": 285
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002994183329464256,
      "loss": 0.5527,
      "step": 286
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00029940975320585396,
      "loss": 0.5425,
      "step": 287
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00029940111077572526,
      "loss": 0.5926,
      "step": 288
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00029939240565966574,
      "loss": 0.5987,
      "step": 289
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00029938363786132774,
      "loss": 0.6077,
      "step": 290
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00029937480738439023,
      "loss": 0.4822,
      "step": 291
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00029936591423255826,
      "loss": 0.6527,
      "step": 292
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00029935695840956327,
      "loss": 0.5724,
      "step": 293
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00029934793991916295,
      "loss": 0.6617,
      "step": 294
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00029933885876514115,
      "loss": 0.5795,
      "step": 295
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002993297149513083,
      "loss": 0.5049,
      "step": 296
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00029932050848150105,
      "loss": 0.5826,
      "step": 297
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002993112393595821,
      "loss": 0.4766,
      "step": 298
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002993019075894406,
      "loss": 0.4514,
      "step": 299
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002992925131749921,
      "loss": 0.5825,
      "step": 300
    },
    {
      "epoch": 0.84,
      "eval_loss": 0.5207599401473999,
      "eval_runtime": 26.3377,
      "eval_samples_per_second": 7.594,
      "eval_steps_per_second": 1.898,
      "step": 300
    },
    {
      "dharma_eval_accuracy": 0.42874678265681937,
      "dharma_eval_accuracy_ARC-Challenge": 0.5,
      "dharma_eval_accuracy_ARC-Easy": 0.6111111111111112,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.3333333333333333,
      "dharma_eval_accuracy_agieval": 0.23728813559322035,
      "dharma_eval_accuracy_bigbench": 0.4918032786885246,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.2962962962962963,
      "dharma_eval_accuracy_winogrande": 0.5925925925925926,
      "dharma_loss": 2.452057005882263,
      "epoch": 0.84,
      "step": 300
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00029928305612017823,
      "loss": 0.4251,
      "step": 301
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002992735364289671,
      "loss": 0.4762,
      "step": 302
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002992639541053528,
      "loss": 0.4531,
      "step": 303
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002992543091533561,
      "loss": 0.64,
      "step": 304
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00029924460157702376,
      "loss": 0.6483,
      "step": 305
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002992348313804289,
      "loss": 0.5646,
      "step": 306
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00029922499856767094,
      "loss": 0.4947,
      "step": 307
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00029921510314287545,
      "loss": 0.4793,
      "step": 308
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00029920514511019456,
      "loss": 0.3957,
      "step": 309
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00029919512447380625,
      "loss": 0.6941,
      "step": 310
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002991850412379151,
      "loss": 0.6013,
      "step": 311
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002991748954067519,
      "loss": 0.6011,
      "step": 312
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002991646869845736,
      "loss": 0.7579,
      "step": 313
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002991544159756634,
      "loss": 0.4339,
      "step": 314
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002991440823843309,
      "loss": 0.4666,
      "step": 315
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002991336862149119,
      "loss": 0.5458,
      "step": 316
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00029912322747176835,
      "loss": 0.6499,
      "step": 317
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002991127061592887,
      "loss": 0.7208,
      "step": 318
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00029910212228188734,
      "loss": 0.7648,
      "step": 319
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002990914758440051,
      "loss": 0.9322,
      "step": 320
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00029908076685010915,
      "loss": 0.6769,
      "step": 321
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002990699953046926,
      "loss": 0.6241,
      "step": 322
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00029905916121227515,
      "loss": 0.409,
      "step": 323
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00029904826457740247,
      "loss": 0.3138,
      "step": 324
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00029903730540464666,
      "loss": 0.5241,
      "step": 325
    },
    {
      "epoch": 0.91,
      "eval_loss": 0.5201582908630371,
      "eval_runtime": 26.3949,
      "eval_samples_per_second": 7.577,
      "eval_steps_per_second": 1.894,
      "step": 325
    },
    {
      "dharma_eval_accuracy": 0.3616831149942199,
      "dharma_eval_accuracy_ARC-Challenge": 0.4444444444444444,
      "dharma_eval_accuracy_ARC-Easy": 0.5,
      "dharma_eval_accuracy_BoolQ": 0.7222222222222222,
      "dharma_eval_accuracy_MMLU": 0.4444444444444444,
      "dharma_eval_accuracy_agieval": 0.2542372881355932,
      "dharma_eval_accuracy_bigbench": 0.2786885245901639,
      "dharma_eval_accuracy_openbookqa": 0.05555555555555555,
      "dharma_eval_accuracy_truthful_qa": 0.3888888888888889,
      "dharma_eval_accuracy_winogrande": 0.16666666666666666,
      "dharma_loss": 2.3925395412445067,
      "epoch": 0.91,
      "step": 325
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002990262836986059,
      "loss": 0.358,
      "step": 326
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002990151994639048,
      "loss": 0.5683,
      "step": 327
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000299004052705194,
      "loss": 0.4744,
      "step": 328
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00029899284342715054,
      "loss": 0.6101,
      "step": 329
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00029898157163447763,
      "loss": 0.5381,
      "step": 330
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002989702373319047,
      "loss": 0.5269,
      "step": 331
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00029895884052418735,
      "loss": 0.4993,
      "step": 332
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00029894738121610755,
      "loss": 0.5623,
      "step": 333
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002989358594124733,
      "loss": 0.5988,
      "step": 334
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002989242751181191,
      "loss": 0.5623,
      "step": 335
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002989126283379054,
      "loss": 0.4471,
      "step": 336
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000298900919076719,
      "loss": 0.489,
      "step": 337
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00029888914733947275,
      "loss": 0.5404,
      "step": 338
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00029887731313110613,
      "loss": 0.5639,
      "step": 339
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002988654164565843,
      "loss": 0.6034,
      "step": 340
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00029885345732089905,
      "loss": 0.5529,
      "step": 341
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002988414357290681,
      "loss": 0.6584,
      "step": 342
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002988293516861356,
      "loss": 0.5119,
      "step": 343
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002988172051971717,
      "loss": 0.4797,
      "step": 344
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002988049962672728,
      "loss": 0.619,
      "step": 345
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002987927249015616,
      "loss": 0.621,
      "step": 346
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00029878039110518704,
      "loss": 0.6019,
      "step": 347
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000298767994883324,
      "loss": 0.5099,
      "step": 348
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00029875553624117375,
      "loss": 0.3973,
      "step": 349
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00029874301518396376,
      "loss": 0.6068,
      "step": 350
    },
    {
      "epoch": 0.98,
      "eval_loss": 0.517635703086853,
      "eval_runtime": 26.3545,
      "eval_samples_per_second": 7.589,
      "eval_steps_per_second": 1.897,
      "step": 350
    },
    {
      "dharma_eval_accuracy": 0.36985182212251455,
      "dharma_eval_accuracy_ARC-Challenge": 0.37037037037037035,
      "dharma_eval_accuracy_ARC-Easy": 0.4444444444444444,
      "dharma_eval_accuracy_BoolQ": 0.6851851851851852,
      "dharma_eval_accuracy_MMLU": 0.2962962962962963,
      "dharma_eval_accuracy_agieval": 0.23728813559322035,
      "dharma_eval_accuracy_bigbench": 0.29508196721311475,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.35185185185185186,
      "dharma_eval_accuracy_winogrande": 0.5555555555555556,
      "dharma_loss": 2.8203083801269533,
      "epoch": 0.98,
      "step": 350
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00029873043171694755,
      "loss": 0.5346,
      "step": 351
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002987177858454049,
      "loss": 0.3792,
      "step": 352
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00029870507757464193,
      "loss": 0.5227,
      "step": 353
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002986923069099906,
      "loss": 0.4218,
      "step": 354
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00029867947385680936,
      "loss": 0.4866,
      "step": 355
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00029866657842048274,
      "loss": 0.4593,
      "step": 356
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00029865362060642136,
      "loss": 0.6367,
      "step": 357
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002986406004200621,
      "loss": 0.5064,
      "step": 358
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00029862751786686797,
      "loss": 0.4206,
      "step": 359
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002986143729523282,
      "loss": 0.6043,
      "step": 360
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002986011656819582,
      "loss": 0.6889,
      "step": 361
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002985878960612993,
      "loss": 0.6266,
      "step": 362
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002985745640959194,
      "loss": 0.6016,
      "step": 363
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00029856116979141224,
      "loss": 0.387,
      "step": 364
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00029854771315339785,
      "loss": 0.4954,
      "step": 365
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002985341941875224,
      "loss": 0.5165,
      "step": 366
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002985206128994581,
      "loss": 0.459,
      "step": 367
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002985069692949036,
      "loss": 0.5966,
      "step": 368
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002984932633795833,
      "loss": 0.4271,
      "step": 369
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00029847949515924806,
      "loss": 0.4243,
      "step": 370
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00029846566463967477,
      "loss": 0.4879,
      "step": 371
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002984517718266664,
      "loss": 0.4225,
      "step": 372
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00029843781672605216,
      "loss": 0.385,
      "step": 373
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00029842379934368735,
      "loss": 0.5161,
      "step": 374
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002984097196854534,
      "loss": 0.5034,
      "step": 375
    },
    {
      "epoch": 1.05,
      "eval_loss": 0.5201339721679688,
      "eval_runtime": 26.3832,
      "eval_samples_per_second": 7.581,
      "eval_steps_per_second": 1.895,
      "step": 375
    },
    {
      "dharma_eval_accuracy": 0.40587691825690037,
      "dharma_eval_accuracy_ARC-Challenge": 0.24074074074074073,
      "dharma_eval_accuracy_ARC-Easy": 0.2962962962962963,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.2037037037037037,
      "dharma_eval_accuracy_agieval": 0.23728813559322035,
      "dharma_eval_accuracy_bigbench": 0.5081967213114754,
      "dharma_eval_accuracy_openbookqa": 0.24074074074074073,
      "dharma_eval_accuracy_truthful_qa": 0.7037037037037037,
      "dharma_eval_accuracy_winogrande": 0.5185185185185185,
      "dharma_loss": 2.7163280713558198,
      "epoch": 1.05,
      "step": 375
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002983955777572578,
      "loss": 0.6131,
      "step": 376
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002983813735650344,
      "loss": 0.546,
      "step": 377
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00029836710711474287,
      "loss": 0.3439,
      "step": 378
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002983527784123692,
      "loss": 0.6843,
      "step": 379
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002983383874639254,
      "loss": 0.4989,
      "step": 380
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002983239342754498,
      "loss": 0.4311,
      "step": 381
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002983094188530065,
      "loss": 0.6035,
      "step": 382
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.000298294841202686,
      "loss": 0.3606,
      "step": 383
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002982802013306048,
      "loss": 0.3556,
      "step": 384
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00029826549924290557,
      "loss": 0.4458,
      "step": 385
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002982507349457569,
      "loss": 0.4737,
      "step": 386
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00029823590844535366,
      "loss": 0.5703,
      "step": 387
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002982210197479169,
      "loss": 0.3601,
      "step": 388
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00029820606885969347,
      "loss": 0.337,
      "step": 389
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00029819105578695655,
      "loss": 0.4757,
      "step": 390
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002981759805360054,
      "loss": 0.5072,
      "step": 391
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002981608431131653,
      "loss": 0.4409,
      "step": 392
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00029814564352478753,
      "loss": 0.5252,
      "step": 393
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00029813038177724965,
      "loss": 0.5016,
      "step": 394
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00029811505787695524,
      "loss": 0.3186,
      "step": 395
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002980996718303338,
      "loss": 0.5822,
      "step": 396
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00029808422364384113,
      "loss": 0.54,
      "step": 397
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00029806871332395895,
      "loss": 0.4582,
      "step": 398
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002980531408771951,
      "loss": 0.5073,
      "step": 399
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00029803750631008356,
      "loss": 0.5227,
      "step": 400
    },
    {
      "epoch": 1.12,
      "eval_loss": 0.5233827829360962,
      "eval_runtime": 26.3434,
      "eval_samples_per_second": 7.592,
      "eval_steps_per_second": 1.898,
      "step": 400
    },
    {
      "dharma_eval_accuracy": 0.3770703338947604,
      "dharma_eval_accuracy_ARC-Challenge": 0.24074074074074073,
      "dharma_eval_accuracy_ARC-Easy": 0.3148148148148148,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.2037037037037037,
      "dharma_eval_accuracy_agieval": 0.23728813559322035,
      "dharma_eval_accuracy_bigbench": 0.5081967213114754,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.5555555555555556,
      "dharma_eval_accuracy_winogrande": 0.5370370370370371,
      "dharma_loss": 2.5418553066253664,
      "epoch": 1.12,
      "step": 400
    }
  ],
  "max_steps": 5000,
  "num_train_epochs": 15,
  "total_flos": 1.2906498742913434e+17,
  "trial_name": null,
  "trial_params": null
}