{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09628114093152004,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6869,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.8396,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 0.7489,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7252,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 0.6548,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-05,
      "loss": 0.8022,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.6524,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.6981,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-05,
      "loss": 0.7488,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 0.6368,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6891,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-05,
      "loss": 0.7968,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.6912,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.8452,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 0.6989,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.6685,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.5469,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.2e-05,
      "loss": 0.7915,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.6e-05,
      "loss": 0.7744,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 0.6804,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.4e-05,
      "loss": 0.7796,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.706,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.6798,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.6e-05,
      "loss": 0.6333,
      "step": 24
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 0.6012,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.52,
      "step": 26
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.6583,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.7354,
      "step": 28
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000116,
      "loss": 0.6296,
      "step": 29
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012,
      "loss": 0.6352,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000124,
      "loss": 0.6007,
      "step": 31
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.5659,
      "step": 32
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000132,
      "loss": 0.5138,
      "step": 33
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.6639,
      "step": 34
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014,
      "loss": 0.5934,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000144,
      "loss": 0.5233,
      "step": 36
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000148,
      "loss": 0.5307,
      "step": 37
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000152,
      "loss": 0.5928,
      "step": 38
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.5908,
      "step": 39
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00016,
      "loss": 0.6366,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000164,
      "loss": 0.5972,
      "step": 41
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000168,
      "loss": 0.4825,
      "step": 42
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000172,
      "loss": 0.6783,
      "step": 43
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.6082,
      "step": 44
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018,
      "loss": 0.7633,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.5988,
      "step": 46
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000188,
      "loss": 0.6658,
      "step": 47
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000192,
      "loss": 0.5945,
      "step": 48
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000196,
      "loss": 0.5984,
      "step": 49
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6778,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 1557,
  "num_train_epochs": 3,
  "save_steps": 50,
  "total_flos": 6.525202843946189e+16,
  "trial_name": null,
  "trial_params": null
}