{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9273570324574961,
  "eval_steps": 500,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.9999999999999997e-06,
      "loss": 1.8153,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.999999999999999e-06,
      "loss": 1.7198,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.999999999999999e-06,
      "loss": 1.8138,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.1999999999999999e-05,
      "loss": 1.91,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 1.8071,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.7999999999999997e-05,
      "loss": 1.8472,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.1e-05,
      "loss": 1.8289,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.3999999999999997e-05,
      "loss": 1.9348,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.6999999999999996e-05,
      "loss": 1.9788,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.8609,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.2999999999999996e-05,
      "loss": 1.8541,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.5999999999999994e-05,
      "loss": 1.759,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.9e-05,
      "loss": 1.7788,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.2e-05,
      "loss": 1.8238,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 1.851,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.7999999999999994e-05,
      "loss": 1.6828,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.1e-05,
      "loss": 1.5966,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.399999999999999e-05,
      "loss": 1.77,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 1.798,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.7845,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.299999999999999e-05,
      "loss": 1.625,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.599999999999999e-05,
      "loss": 1.6687,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.9e-05,
      "loss": 1.6592,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.199999999999999e-05,
      "loss": 1.6339,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.5e-05,
      "loss": 1.5621,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.8e-05,
      "loss": 1.51,
      "step": 26
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.1e-05,
      "loss": 1.5743,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.4e-05,
      "loss": 1.4974,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.699999999999999e-05,
      "loss": 1.513,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.4505,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.3e-05,
      "loss": 1.4374,
      "step": 31
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.599999999999999e-05,
      "loss": 1.4201,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.9e-05,
      "loss": 1.3513,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000102,
      "loss": 1.3564,
      "step": 34
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00010499999999999999,
      "loss": 1.2858,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00010799999999999998,
      "loss": 1.2458,
      "step": 36
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011099999999999999,
      "loss": 1.2151,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.1821,
      "step": 38
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000117,
      "loss": 1.164,
      "step": 39
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.1299,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00012299999999999998,
      "loss": 1.1514,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00012599999999999997,
      "loss": 1.0846,
      "step": 42
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000129,
      "loss": 1.0845,
      "step": 43
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00013199999999999998,
      "loss": 1.0378,
      "step": 44
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000135,
      "loss": 1.0215,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000138,
      "loss": 1.0468,
      "step": 46
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00014099999999999998,
      "loss": 1.0085,
      "step": 47
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00014399999999999998,
      "loss": 1.0042,
      "step": 48
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000147,
      "loss": 0.9914,
      "step": 49
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015,
      "loss": 1.0245,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00015299999999999998,
      "loss": 0.9608,
      "step": 51
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000156,
      "loss": 0.9765,
      "step": 52
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000159,
      "loss": 0.9647,
      "step": 53
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000162,
      "loss": 0.9637,
      "step": 54
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000165,
      "loss": 0.9745,
      "step": 55
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000168,
      "loss": 0.968,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017099999999999998,
      "loss": 1.0064,
      "step": 57
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017399999999999997,
      "loss": 0.9273,
      "step": 58
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00017699999999999997,
      "loss": 0.9038,
      "step": 59
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.8971,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00018299999999999998,
      "loss": 0.8887,
      "step": 61
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000186,
      "loss": 0.8992,
      "step": 62
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018899999999999999,
      "loss": 0.8799,
      "step": 63
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019199999999999998,
      "loss": 0.8914,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000195,
      "loss": 0.8953,
      "step": 65
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000198,
      "loss": 0.8819,
      "step": 66
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000201,
      "loss": 0.8911,
      "step": 67
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000204,
      "loss": 0.9396,
      "step": 68
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00020699999999999996,
      "loss": 0.8563,
      "step": 69
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.8911,
      "step": 70
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00021299999999999997,
      "loss": 0.89,
      "step": 71
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00021599999999999996,
      "loss": 0.8253,
      "step": 72
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00021899999999999998,
      "loss": 0.8842,
      "step": 73
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00022199999999999998,
      "loss": 0.8779,
      "step": 74
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000225,
      "loss": 0.8851,
      "step": 75
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00022799999999999999,
      "loss": 0.8743,
      "step": 76
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00023099999999999998,
      "loss": 0.8802,
      "step": 77
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000234,
      "loss": 0.8775,
      "step": 78
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000237,
      "loss": 0.865,
      "step": 79
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.8602,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000243,
      "loss": 0.8278,
      "step": 81
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00024599999999999996,
      "loss": 0.8699,
      "step": 82
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000249,
      "loss": 0.871,
      "step": 83
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00025199999999999995,
      "loss": 0.8603,
      "step": 84
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00025499999999999996,
      "loss": 0.8488,
      "step": 85
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000258,
      "loss": 0.885,
      "step": 86
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000261,
      "loss": 0.8583,
      "step": 87
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00026399999999999997,
      "loss": 0.8771,
      "step": 88
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000267,
      "loss": 0.8723,
      "step": 89
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00027,
      "loss": 0.8741,
      "step": 90
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00027299999999999997,
      "loss": 0.8475,
      "step": 91
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000276,
      "loss": 0.8693,
      "step": 92
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000279,
      "loss": 0.891,
      "step": 93
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00028199999999999997,
      "loss": 0.8563,
      "step": 94
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000285,
      "loss": 0.844,
      "step": 95
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00028799999999999995,
      "loss": 0.8566,
      "step": 96
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00029099999999999997,
      "loss": 0.8621,
      "step": 97
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000294,
      "loss": 0.8403,
      "step": 98
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00029699999999999996,
      "loss": 0.8866,
      "step": 99
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.8684,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00029999199041570257,
      "loss": 0.8769,
      "step": 101
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00029996796251818966,
      "loss": 0.8124,
      "step": 102
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00029992791887350736,
      "loss": 0.841,
      "step": 103
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002998718637580951,
      "loss": 0.8653,
      "step": 104
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002997998031583285,
      "loss": 0.8434,
      "step": 105
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002997117447698802,
      "loss": 0.8748,
      "step": 106
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00029960769799689793,
      "loss": 0.8647,
      "step": 107
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.8731,
      "step": 108
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002993516854500905,
      "loss": 0.8323,
      "step": 109
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00029919974701698635,
      "loss": 0.8492,
      "step": 110
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00029903187487787046,
      "loss": 0.8608,
      "step": 111
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002988480869605567,
      "loss": 0.8776,
      "step": 112
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002986484028925761,
      "loss": 0.8521,
      "step": 113
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002984328439990804,
      "loss": 0.822,
      "step": 114
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002982014333005645,
      "loss": 0.7943,
      "step": 115
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.8497,
      "step": 116
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00029769115703223763,
      "loss": 0.8067,
      "step": 117
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002974123459571039,
      "loss": 0.8534,
      "step": 118
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00029711779206048454,
      "loss": 0.8412,
      "step": 119
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00029680752679910315,
      "loss": 0.8596,
      "step": 120
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00029648158330756986,
      "loss": 0.8492,
      "step": 121
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002961399963948431,
      "loss": 0.8469,
      "step": 122
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002957828025405117,
      "loss": 0.8642,
      "step": 123
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.8423,
      "step": 124
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00029502174825499146,
      "loss": 0.8727,
      "step": 125
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000294617969100182,
      "loss": 0.8712,
      "step": 126
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00029419874554784695,
      "loss": 0.8377,
      "step": 127
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002937641223687379,
      "loss": 0.8405,
      "step": 128
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00029331414597820145,
      "loss": 0.8378,
      "step": 129
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00029284886443122214,
      "loss": 0.8302,
      "step": 130
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00029236832741729016,
      "loss": 0.9031,
      "step": 131
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.8793,
      "step": 132
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002913616938870455,
      "loss": 0.7985,
      "step": 133
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002908357048736144,
      "loss": 0.8195,
      "step": 134
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00029029467538751303,
      "loss": 0.859,
      "step": 135
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00028973866320769183,
      "loss": 0.8469,
      "step": 136
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00028916772771316973,
      "loss": 0.813,
      "step": 137
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000288581929876693,
      "loss": 0.8844,
      "step": 138
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002879813322582237,
      "loss": 0.8435,
      "step": 139
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.8526,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002867359958109792,
      "loss": 0.8495,
      "step": 141
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00028609138997723397,
      "loss": 0.8697,
      "step": 142
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00028543225033735313,
      "loss": 0.8201,
      "step": 143
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002847586472837968,
      "loss": 0.8113,
      "step": 144
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00028407065275363753,
      "loss": 0.8414,
      "step": 145
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002833683402208777,
      "loss": 0.8668,
      "step": 146
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002826517846886033,
      "loss": 0.8236,
      "step": 147
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.8743,
      "step": 148
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002811762522350481,
      "loss": 0.8138,
      "step": 149
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000280417432892455,
      "loss": 0.8432,
      "step": 150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002796446856908939,
      "loss": 0.826,
      "step": 151
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002788580931554828,
      "loss": 0.8556,
      "step": 152
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002780577392899446,
      "loss": 0.8358,
      "step": 153
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00027724370956763603,
      "loss": 0.8656,
      "step": 154
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002764160909224196,
      "loss": 0.8393,
      "step": 155
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.8464,
      "step": 156
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002747204418453818,
      "loss": 0.8046,
      "step": 157
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00027385259249948333,
      "loss": 0.8221,
      "step": 158
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000272971516383184,
      "loss": 0.8424,
      "step": 159
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00027207730759052924,
      "loss": 0.8172,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002711700616180619,
      "loss": 0.8373,
      "step": 161
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002702498753546232,
      "loss": 0.8903,
      "step": 162
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00026931684707100586,
      "loss": 0.8203,
      "step": 163
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.8212,
      "step": 164
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00026741266437304716,
      "loss": 0.8103,
      "step": 165
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002664417133148636,
      "loss": 0.8475,
      "step": 166
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00026545832692709964,
      "loss": 0.8714,
      "step": 167
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00026446261022997097,
      "loss": 0.871,
      "step": 168
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00026345466956050176,
      "loss": 0.8585,
      "step": 169
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002624346125611689,
      "loss": 0.8292,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000261402548168406,
      "loss": 0.8579,
      "step": 171
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.8106,
      "step": 172
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002593028393481692,
      "loss": 0.8582,
      "step": 173
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002582354191579593,
      "loss": 0.8508,
      "step": 174
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00025715644002489996,
      "loss": 0.8388,
      "step": 175
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00025606601717798207,
      "loss": 0.8449,
      "step": 176
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00025496426706832193,
      "loss": 0.8649,
      "step": 177
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002538513073567244,
      "loss": 0.8672,
      "step": 178
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00025272725690111806,
      "loss": 0.8367,
      "step": 179
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.8433,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00025044636509892227,
      "loss": 0.7995,
      "step": 181
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00024928976733893494,
      "loss": 0.8302,
      "step": 182
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002481225659821294,
      "loss": 0.8565,
      "step": 183
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00024694488567914106,
      "loss": 0.8723,
      "step": 184
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002457568521996988,
      "loss": 0.8731,
      "step": 185
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00024455859241919326,
      "loss": 0.856,
      "step": 186
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002433502343051274,
      "loss": 0.8385,
      "step": 187
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.8431,
      "step": 188
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00024090374032477533,
      "loss": 0.865,
      "step": 189
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002396658657304861,
      "loss": 0.8676,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00023841841531872798,
      "loss": 0.8143,
      "step": 191
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00023716152231029072,
      "loss": 0.8507,
      "step": 192
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000235895320934381,
      "loss": 0.8582,
      "step": 193
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00023461994641428766,
      "loss": 0.8621,
      "step": 194
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002333355349529403,
      "loss": 0.8503,
      "step": 195
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.8339,
      "step": 196
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00023074015082903015,
      "loss": 0.86,
      "step": 197
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002294294553391063,
      "loss": 0.798,
      "step": 198
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00022811027722360598,
      "loss": 0.8391,
      "step": 199
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00022678275736344014,
      "loss": 0.7992,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00022544703753037178,
      "loss": 0.8329,
      "step": 201
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00022410326037187558,
      "loss": 0.8191,
      "step": 202
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00022275156939590392,
      "loss": 0.8405,
      "step": 203
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.8587,
      "step": 204
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00022002502423368678,
      "loss": 0.8691,
      "step": 205
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002186504612273522,
      "loss": 0.8381,
      "step": 206
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002172685667322676,
      "loss": 0.8781,
      "step": 207
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00021587948832710554,
      "loss": 0.8304,
      "step": 208
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002144833743577405,
      "loss": 0.824,
      "step": 209
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002130803739214061,
      "loss": 0.8309,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00021167063685077262,
      "loss": 0.7997,
      "step": 211
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.8495,
      "step": 212
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00020883155571838692,
      "loss": 0.834,
      "step": 213
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00020740251485476345,
      "loss": 0.897,
      "step": 214
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00020596734372071852,
      "loss": 0.8345,
      "step": 215
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00020452619558457446,
      "loss": 0.8458,
      "step": 216
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00020307922435296443,
      "loss": 0.8221,
      "step": 217
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002016265845543958,
      "loss": 0.8335,
      "step": 218
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00020016843132274746,
      "loss": 0.8065,
      "step": 219
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.8264,
      "step": 220
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019723620802311774,
      "loss": 0.8727,
      "step": 221
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019576245110033231,
      "loss": 0.843,
      "step": 222
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019428380700141698,
      "loss": 0.8805,
      "step": 223
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019280043363736579,
      "loss": 0.8282,
      "step": 224
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001913124894242322,
      "loss": 0.8405,
      "step": 225
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018982013326621083,
      "loss": 0.8305,
      "step": 226
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018832352453866777,
      "loss": 0.8385,
      "step": 227
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.8179,
      "step": 228
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018531818913016584,
      "loss": 0.8599,
      "step": 229
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018380978340237092,
      "loss": 0.8344,
      "step": 230
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018229776697710617,
      "loss": 0.8516,
      "step": 231
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018078230132934512,
      "loss": 0.8463,
      "step": 232
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00017926354830241924,
      "loss": 0.8366,
      "step": 233
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00017774167009073377,
      "loss": 0.833,
      "step": 234
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00017621682922244633,
      "loss": 0.8045,
      "step": 235
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.8242,
      "step": 236
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001731589111932823,
      "loss": 0.8476,
      "step": 237
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000171626160601102,
      "loss": 0.8633,
      "step": 238
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001700911004548369,
      "loss": 0.8443,
      "step": 239
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016855389469040217,
      "loss": 0.8813,
      "step": 240
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016701470747285317,
      "loss": 0.8224,
      "step": 241
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016547370317885354,
      "loss": 0.8262,
      "step": 242
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001639310463791205,
      "loss": 0.836,
      "step": 243
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016238690182084986,
      "loss": 0.8262,
      "step": 244
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00016084143441012156,
      "loss": 0.8434,
      "step": 245
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001592948091942892,
      "loss": 0.8431,
      "step": 246
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001577471913443532,
      "loss": 0.8592,
      "step": 247
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015619874613732196,
      "loss": 0.8309,
      "step": 248
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001546496389385611,
      "loss": 0.8255,
      "step": 249
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015310003518413315,
      "loss": 0.7773,
      "step": 250
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015155010036313008,
      "loss": 0.8441,
      "step": 251
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015,
      "loss": 0.8472,
      "step": 252
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00014844989963686992,
      "loss": 0.8443,
      "step": 253
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00014689996481586688,
      "loss": 0.841,
      "step": 254
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00014535036106143892,
      "loss": 0.835,
      "step": 255
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000143801253862678,
      "loss": 0.8462,
      "step": 256
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001422528086556468,
      "loss": 0.8092,
      "step": 257
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001407051908057108,
      "loss": 0.8208,
      "step": 258
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001391585655898784,
      "loss": 0.8446,
      "step": 259
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00013761309817915014,
      "loss": 0.7963,
      "step": 260
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00013606895362087949,
      "loss": 0.8162,
      "step": 261
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00013452629682114646,
      "loss": 0.8829,
      "step": 262
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00013298529252714684,
      "loss": 0.8289,
      "step": 263
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00013144610530959784,
      "loss": 0.848,
      "step": 264
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001299088995451631,
      "loss": 0.7897,
      "step": 265
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00012837383939889798,
      "loss": 0.8196,
      "step": 266
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00012684108880671772,
      "loss": 0.7939,
      "step": 267
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00012531081145788987,
      "loss": 0.8232,
      "step": 268
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00012378317077755362,
      "loss": 0.8411,
      "step": 269
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00012225832990926623,
      "loss": 0.8726,
      "step": 270
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00012073645169758076,
      "loss": 0.7977,
      "step": 271
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00011921769867065485,
      "loss": 0.8042,
      "step": 272
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00011770223302289385,
      "loss": 0.7933,
      "step": 273
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001161902165976291,
      "loss": 0.8396,
      "step": 274
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00011468181086983412,
      "loss": 0.8328,
      "step": 275
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00011317717692888012,
      "loss": 0.8353,
      "step": 276
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001116764754613322,
      "loss": 0.801,
      "step": 277
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00011017986673378918,
      "loss": 0.842,
      "step": 278
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00010868751057576782,
      "loss": 0.8578,
      "step": 279
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00010719956636263423,
      "loss": 0.8259,
      "step": 280
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00010571619299858303,
      "loss": 0.8238,
      "step": 281
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00010423754889966769,
      "loss": 0.8322,
      "step": 282
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00010276379197688222,
      "loss": 0.8194,
      "step": 283
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00010129507961929748,
      "loss": 0.8031,
      "step": 284
    },
    {
      "epoch": 0.7,
      "learning_rate": 9.983156867725255e-05,
      "loss": 0.8259,
      "step": 285
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.837341544560423e-05,
      "loss": 0.8215,
      "step": 286
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.692077564703555e-05,
      "loss": 0.8282,
      "step": 287
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.547380441542549e-05,
      "loss": 0.85,
      "step": 288
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.403265627928147e-05,
      "loss": 0.8034,
      "step": 289
    },
    {
      "epoch": 0.72,
      "learning_rate": 9.259748514523653e-05,
      "loss": 0.8197,
      "step": 290
    },
    {
      "epoch": 0.72,
      "learning_rate": 9.116844428161309e-05,
      "loss": 0.776,
      "step": 291
    },
    {
      "epoch": 0.72,
      "learning_rate": 8.97456863020546e-05,
      "loss": 0.8112,
      "step": 292
    },
    {
      "epoch": 0.72,
      "learning_rate": 8.83293631492274e-05,
      "loss": 0.827,
      "step": 293
    },
    {
      "epoch": 0.73,
      "learning_rate": 8.691962607859386e-05,
      "loss": 0.8157,
      "step": 294
    },
    {
      "epoch": 0.73,
      "learning_rate": 8.55166256422595e-05,
      "loss": 0.8386,
      "step": 295
    },
    {
      "epoch": 0.73,
      "learning_rate": 8.412051167289446e-05,
      "loss": 0.8088,
      "step": 296
    },
    {
      "epoch": 0.73,
      "learning_rate": 8.27314332677324e-05,
      "loss": 0.8409,
      "step": 297
    },
    {
      "epoch": 0.74,
      "learning_rate": 8.134953877264778e-05,
      "loss": 0.81,
      "step": 298
    },
    {
      "epoch": 0.74,
      "learning_rate": 7.997497576631323e-05,
      "loss": 0.8396,
      "step": 299
    },
    {
      "epoch": 0.74,
      "learning_rate": 7.860789104443896e-05,
      "loss": 0.8428,
      "step": 300
    },
    {
      "epoch": 0.74,
      "learning_rate": 7.724843060409606e-05,
      "loss": 0.8172,
      "step": 301
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.589673962812442e-05,
      "loss": 0.8108,
      "step": 302
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.455296246962823e-05,
      "loss": 0.8459,
      "step": 303
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.321724263655988e-05,
      "loss": 0.8168,
      "step": 304
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.188972277639405e-05,
      "loss": 0.817,
      "step": 305
    },
    {
      "epoch": 0.76,
      "learning_rate": 7.057054466089371e-05,
      "loss": 0.8435,
      "step": 306
    },
    {
      "epoch": 0.76,
      "learning_rate": 6.925984917096985e-05,
      "loss": 0.8272,
      "step": 307
    },
    {
      "epoch": 0.76,
      "learning_rate": 6.795777628163599e-05,
      "loss": 0.8508,
      "step": 308
    },
    {
      "epoch": 0.76,
      "learning_rate": 6.66644650470597e-05,
      "loss": 0.8529,
      "step": 309
    },
    {
      "epoch": 0.77,
      "learning_rate": 6.538005358571234e-05,
      "loss": 0.8434,
      "step": 310
    },
    {
      "epoch": 0.77,
      "learning_rate": 6.410467906561896e-05,
      "loss": 0.8311,
      "step": 311
    },
    {
      "epoch": 0.77,
      "learning_rate": 6.283847768970926e-05,
      "loss": 0.789,
      "step": 312
    },
    {
      "epoch": 0.77,
      "learning_rate": 6.158158468127196e-05,
      "loss": 0.824,
      "step": 313
    },
    {
      "epoch": 0.78,
      "learning_rate": 6.0334134269513865e-05,
      "loss": 0.8425,
      "step": 314
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.9096259675224647e-05,
      "loss": 0.8228,
      "step": 315
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.786809309654982e-05,
      "loss": 0.8333,
      "step": 316
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.664976569487263e-05,
      "loss": 0.8656,
      "step": 317
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.5441407580806745e-05,
      "loss": 0.8228,
      "step": 318
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.4243147800301134e-05,
      "loss": 0.7834,
      "step": 319
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.305511432085884e-05,
      "loss": 0.7926,
      "step": 320
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.187743401787054e-05,
      "loss": 0.8453,
      "step": 321
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.071023266106502e-05,
      "loss": 0.848,
      "step": 322
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.955363490107777e-05,
      "loss": 0.8579,
      "step": 323
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.840776425613886e-05,
      "loss": 0.826,
      "step": 324
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.727274309888191e-05,
      "loss": 0.8296,
      "step": 325
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.614869264327553e-05,
      "loss": 0.8263,
      "step": 326
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.503573293167805e-05,
      "loss": 0.8345,
      "step": 327
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.3933982822017876e-05,
      "loss": 0.8175,
      "step": 328
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.284355997510003e-05,
      "loss": 0.8081,
      "step": 329
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.17645808420407e-05,
      "loss": 0.8121,
      "step": 330
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.0697160651830814e-05,
      "loss": 0.8072,
      "step": 331
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.964141339903026e-05,
      "loss": 0.8569,
      "step": 332
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.8597451831594014e-05,
      "loss": 0.8123,
      "step": 333
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.756538743883111e-05,
      "loss": 0.8379,
      "step": 334
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.654533043949823e-05,
      "loss": 0.805,
      "step": 335
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.5537389770029046e-05,
      "loss": 0.8434,
      "step": 336
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.454167307290036e-05,
      "loss": 0.8017,
      "step": 337
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.3558286685136384e-05,
      "loss": 0.8328,
      "step": 338
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.258733562695283e-05,
      "loss": 0.8238,
      "step": 339
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.162892359054098e-05,
      "loss": 0.8477,
      "step": 340
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.0683152928994105e-05,
      "loss": 0.8162,
      "step": 341
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.9750124645376755e-05,
      "loss": 0.8293,
      "step": 342
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.8829938381938117e-05,
      "loss": 0.8393,
      "step": 343
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.792269240947076e-05,
      "loss": 0.8461,
      "step": 344
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.702848361681605e-05,
      "loss": 0.8294,
      "step": 345
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.6147407500516643e-05,
      "loss": 0.8482,
      "step": 346
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.5279558154618197e-05,
      "loss": 0.8296,
      "step": 347
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.4425028260620715e-05,
      "loss": 0.8322,
      "step": 348
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.35839090775804e-05,
      "loss": 0.8226,
      "step": 349
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.2756290432363957e-05,
      "loss": 0.8192,
      "step": 350
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.1942260710055386e-05,
      "loss": 0.8226,
      "step": 351
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.1141906844517203e-05,
      "loss": 0.8049,
      "step": 352
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.0355314309106097e-05,
      "loss": 0.8261,
      "step": 353
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.9582567107544962e-05,
      "loss": 0.8317,
      "step": 354
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.882374776495187e-05,
      "loss": 0.8421,
      "step": 355
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.8078937319026654e-05,
      "loss": 0.834,
      "step": 356
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.734821531139667e-05,
      "loss": 0.8752,
      "step": 357
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.663165977912221e-05,
      "loss": 0.8185,
      "step": 358
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.5929347246362452e-05,
      "loss": 0.8115,
      "step": 359
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.524135271620317e-05,
      "loss": 0.8062,
      "step": 360
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.456774966264685e-05,
      "loss": 0.8766,
      "step": 361
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.390861002276602e-05,
      "loss": 0.818,
      "step": 362
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.3264004189020777e-05,
      "loss": 0.7928,
      "step": 363
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.2634001001741373e-05,
      "loss": 0.8159,
      "step": 364
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.2018667741776266e-05,
      "loss": 0.8423,
      "step": 365
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.1418070123306989e-05,
      "loss": 0.8281,
      "step": 366
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.0832272286830285e-05,
      "loss": 0.8235,
      "step": 367
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.0261336792308167e-05,
      "loss": 0.8432,
      "step": 368
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.705324612486936e-06,
      "loss": 0.8614,
      "step": 369
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.164295126385562e-06,
      "loss": 0.8353,
      "step": 370
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.638306112954452e-06,
      "loss": 0.8301,
      "step": 371
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.127413744904804e-06,
      "loss": 0.7989,
      "step": 372
    },
    {
      "epoch": 0.92,
      "learning_rate": 7.631672582709808e-06,
      "loss": 0.8164,
      "step": 373
    },
    {
      "epoch": 0.92,
      "learning_rate": 7.151135568777838e-06,
      "loss": 0.8253,
      "step": 374
    },
    {
      "epoch": 0.93,
      "learning_rate": 6.685854021798509e-06,
      "loss": 0.8161,
      "step": 375
    }
  ],
  "logging_steps": 1,
  "max_steps": 404,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 4.214459938342994e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}