{
  "best_metric": 0.4175724387168884,
  "best_model_checkpoint": "/tmp/model/checkpoint-111",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 111,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 4.166666666666667e-06,
      "loss": 1.0986,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.0986,
      "step": 2
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.25e-05,
      "loss": 1.0984,
      "step": 3
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.0981,
      "step": 4
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 1.0961,
      "step": 5
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.5e-05,
      "loss": 1.0946,
      "step": 6
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.916666666666667e-05,
      "loss": 1.0942,
      "step": 7
    },
    {
      "epoch": 0.22,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.0938,
      "step": 8
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.0897,
      "step": 9
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.0914,
      "step": 10
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.0859,
      "step": 11
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 1.0782,
      "step": 12
    },
    {
      "epoch": 0.35,
      "learning_rate": 5e-05,
      "loss": 1.0988,
      "step": 13
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.94949494949495e-05,
      "loss": 1.0555,
      "step": 14
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.898989898989899e-05,
      "loss": 1.0476,
      "step": 15
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.848484848484849e-05,
      "loss": 1.0252,
      "step": 16
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.797979797979798e-05,
      "loss": 1.0211,
      "step": 17
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.7474747474747476e-05,
      "loss": 1.0334,
      "step": 18
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.696969696969697e-05,
      "loss": 1.0729,
      "step": 19
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.6464646464646464e-05,
      "loss": 0.9884,
      "step": 20
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.595959595959596e-05,
      "loss": 0.9349,
      "step": 21
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.9702,
      "step": 22
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.494949494949495e-05,
      "loss": 0.9057,
      "step": 23
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.0146,
      "step": 24
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.3939393939393944e-05,
      "loss": 0.9395,
      "step": 25
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.343434343434344e-05,
      "loss": 0.8846,
      "step": 26
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.292929292929293e-05,
      "loss": 0.887,
      "step": 27
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.242424242424243e-05,
      "loss": 0.859,
      "step": 28
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.191919191919192e-05,
      "loss": 0.8029,
      "step": 29
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.141414141414142e-05,
      "loss": 0.7816,
      "step": 30
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 0.9609,
      "step": 31
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.0404040404040405e-05,
      "loss": 0.7642,
      "step": 32
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.98989898989899e-05,
      "loss": 0.7118,
      "step": 33
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.939393939393939e-05,
      "loss": 0.8951,
      "step": 34
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.8017,
      "step": 35
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.838383838383838e-05,
      "loss": 0.8356,
      "step": 36
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.787878787878788e-05,
      "loss": 0.5413,
      "step": 37
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7808219178082192,
      "eval_f1_macro": 0.5618618618618618,
      "eval_f1_micro": 0.7808219178082192,
      "eval_f1_weighted": 0.7178082191780821,
      "eval_loss": 0.7590097784996033,
      "eval_precision_macro": 0.5192692692692692,
      "eval_precision_micro": 0.7808219178082192,
      "eval_precision_weighted": 0.6757990867579908,
      "eval_recall_macro": 0.6257507507507508,
      "eval_recall_micro": 0.7808219178082192,
      "eval_recall_weighted": 0.7808219178082192,
      "eval_runtime": 2.3148,
      "eval_samples_per_second": 31.536,
      "eval_steps_per_second": 2.16,
      "step": 37
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.7373737373737376e-05,
      "loss": 0.6457,
      "step": 38
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.686868686868687e-05,
      "loss": 0.8456,
      "step": 39
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.8503,
      "step": 40
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.5858585858585855e-05,
      "loss": 0.6334,
      "step": 41
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.535353535353535e-05,
      "loss": 0.7122,
      "step": 42
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.484848484848485e-05,
      "loss": 0.8674,
      "step": 43
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.434343434343435e-05,
      "loss": 0.586,
      "step": 44
    },
    {
      "epoch": 1.22,
      "learning_rate": 3.3838383838383844e-05,
      "loss": 0.712,
      "step": 45
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4884,
      "step": 46
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.282828282828283e-05,
      "loss": 0.8334,
      "step": 47
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.232323232323233e-05,
      "loss": 0.6581,
      "step": 48
    },
    {
      "epoch": 1.32,
      "learning_rate": 3.181818181818182e-05,
      "loss": 0.7907,
      "step": 49
    },
    {
      "epoch": 1.35,
      "learning_rate": 3.131313131313132e-05,
      "loss": 0.5002,
      "step": 50
    },
    {
      "epoch": 1.38,
      "learning_rate": 3.080808080808081e-05,
      "loss": 0.7007,
      "step": 51
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 0.7455,
      "step": 52
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.9797979797979796e-05,
      "loss": 0.4651,
      "step": 53
    },
    {
      "epoch": 1.46,
      "learning_rate": 2.9292929292929294e-05,
      "loss": 0.5418,
      "step": 54
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.878787878787879e-05,
      "loss": 0.5347,
      "step": 55
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.8282828282828282e-05,
      "loss": 0.5817,
      "step": 56
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.6389,
      "step": 57
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.9797,
      "step": 58
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.676767676767677e-05,
      "loss": 0.501,
      "step": 59
    },
    {
      "epoch": 1.62,
      "learning_rate": 2.6262626262626268e-05,
      "loss": 0.7068,
      "step": 60
    },
    {
      "epoch": 1.65,
      "learning_rate": 2.575757575757576e-05,
      "loss": 0.3491,
      "step": 61
    },
    {
      "epoch": 1.68,
      "learning_rate": 2.5252525252525256e-05,
      "loss": 0.4905,
      "step": 62
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.474747474747475e-05,
      "loss": 0.6119,
      "step": 63
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.4242424242424244e-05,
      "loss": 0.7567,
      "step": 64
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.3737373737373738e-05,
      "loss": 0.5284,
      "step": 65
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.3232323232323232e-05,
      "loss": 0.5752,
      "step": 66
    },
    {
      "epoch": 1.81,
      "learning_rate": 2.272727272727273e-05,
      "loss": 0.3456,
      "step": 67
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.5279,
      "step": 68
    },
    {
      "epoch": 1.86,
      "learning_rate": 2.171717171717172e-05,
      "loss": 0.367,
      "step": 69
    },
    {
      "epoch": 1.89,
      "learning_rate": 2.1212121212121215e-05,
      "loss": 0.56,
      "step": 70
    },
    {
      "epoch": 1.92,
      "learning_rate": 2.070707070707071e-05,
      "loss": 0.4395,
      "step": 71
    },
    {
      "epoch": 1.95,
      "learning_rate": 2.0202020202020203e-05,
      "loss": 0.4159,
      "step": 72
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.9696969696969697e-05,
      "loss": 0.5709,
      "step": 73
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.919191919191919e-05,
      "loss": 0.2119,
      "step": 74
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8493150684931506,
      "eval_f1_macro": 0.6951916592037325,
      "eval_f1_micro": 0.8493150684931505,
      "eval_f1_weighted": 0.8143444635933766,
      "eval_loss": 0.48367100954055786,
      "eval_precision_macro": 0.8952380952380953,
      "eval_precision_micro": 0.8493150684931506,
      "eval_precision_weighted": 0.8966731898238748,
      "eval_recall_macro": 0.7132132132132133,
      "eval_recall_micro": 0.8493150684931506,
      "eval_recall_weighted": 0.8493150684931506,
      "eval_runtime": 2.2697,
      "eval_samples_per_second": 32.163,
      "eval_steps_per_second": 2.203,
      "step": 74
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.8686868686868688e-05,
      "loss": 0.4983,
      "step": 75
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.5134,
      "step": 76
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.7676767676767676e-05,
      "loss": 0.728,
      "step": 77
    },
    {
      "epoch": 2.11,
      "learning_rate": 1.7171717171717173e-05,
      "loss": 0.6525,
      "step": 78
    },
    {
      "epoch": 2.14,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.3611,
      "step": 79
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.6161616161616165e-05,
      "loss": 0.4923,
      "step": 80
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.565656565656566e-05,
      "loss": 0.3824,
      "step": 81
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 0.549,
      "step": 82
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.4646464646464647e-05,
      "loss": 0.5291,
      "step": 83
    },
    {
      "epoch": 2.27,
      "learning_rate": 1.4141414141414141e-05,
      "loss": 0.4802,
      "step": 84
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 0.402,
      "step": 85
    },
    {
      "epoch": 2.32,
      "learning_rate": 1.3131313131313134e-05,
      "loss": 0.4655,
      "step": 86
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.2626262626262628e-05,
      "loss": 0.5878,
      "step": 87
    },
    {
      "epoch": 2.38,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 0.4826,
      "step": 88
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.1616161616161616e-05,
      "loss": 0.6002,
      "step": 89
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.3809,
      "step": 90
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.0606060606060607e-05,
      "loss": 0.2361,
      "step": 91
    },
    {
      "epoch": 2.49,
      "learning_rate": 1.0101010101010101e-05,
      "loss": 0.3682,
      "step": 92
    },
    {
      "epoch": 2.51,
      "learning_rate": 9.595959595959595e-06,
      "loss": 0.507,
      "step": 93
    },
    {
      "epoch": 2.54,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.2748,
      "step": 94
    },
    {
      "epoch": 2.57,
      "learning_rate": 8.585858585858587e-06,
      "loss": 0.275,
      "step": 95
    },
    {
      "epoch": 2.59,
      "learning_rate": 8.080808080808082e-06,
      "loss": 0.278,
      "step": 96
    },
    {
      "epoch": 2.62,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 0.5734,
      "step": 97
    },
    {
      "epoch": 2.65,
      "learning_rate": 7.0707070707070704e-06,
      "loss": 0.4405,
      "step": 98
    },
    {
      "epoch": 2.68,
      "learning_rate": 6.565656565656567e-06,
      "loss": 0.4318,
      "step": 99
    },
    {
      "epoch": 2.7,
      "learning_rate": 6.060606060606061e-06,
      "loss": 0.6203,
      "step": 100
    },
    {
      "epoch": 2.73,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.3329,
      "step": 101
    },
    {
      "epoch": 2.76,
      "learning_rate": 5.050505050505051e-06,
      "loss": 0.3477,
      "step": 102
    },
    {
      "epoch": 2.78,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.5386,
      "step": 103
    },
    {
      "epoch": 2.81,
      "learning_rate": 4.040404040404041e-06,
      "loss": 0.65,
      "step": 104
    },
    {
      "epoch": 2.84,
      "learning_rate": 3.5353535353535352e-06,
      "loss": 0.5258,
      "step": 105
    },
    {
      "epoch": 2.86,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.4519,
      "step": 106
    },
    {
      "epoch": 2.89,
      "learning_rate": 2.5252525252525253e-06,
      "loss": 0.3413,
      "step": 107
    },
    {
      "epoch": 2.92,
      "learning_rate": 2.0202020202020206e-06,
      "loss": 0.3542,
      "step": 108
    },
    {
      "epoch": 2.95,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 0.4562,
      "step": 109
    },
    {
      "epoch": 2.97,
      "learning_rate": 1.0101010101010103e-06,
      "loss": 0.2977,
      "step": 110
    },
    {
      "epoch": 3.0,
      "learning_rate": 5.050505050505052e-07,
      "loss": 0.1933,
      "step": 111
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8767123287671232,
      "eval_f1_macro": 0.7720961603314546,
      "eval_f1_micro": 0.8767123287671232,
      "eval_f1_weighted": 0.8574316899860817,
      "eval_loss": 0.4175724387168884,
      "eval_precision_macro": 0.8490555071200232,
      "eval_precision_micro": 0.8767123287671232,
      "eval_precision_weighted": 0.8791869200176757,
      "eval_recall_macro": 0.7687687687687688,
      "eval_recall_micro": 0.8767123287671232,
      "eval_recall_weighted": 0.8767123287671232,
      "eval_runtime": 2.2744,
      "eval_samples_per_second": 32.097,
      "eval_steps_per_second": 2.198,
      "step": 111
    }
  ],
  "logging_steps": 1,
  "max_steps": 111,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.3832354188224512e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}