{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 18.0,
  "eval_steps": 5,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "learning_rate": 2.9999177540482684e-05,
      "loss": 2.7246,
      "step": 2
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.9996710252122685e-05,
      "loss": 2.1484,
      "step": 4
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.9992598405485974e-05,
      "loss": 1.883,
      "step": 6
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.9986842451482876e-05,
      "loss": 1.6115,
      "step": 8
    },
    {
      "epoch": 2.5,
      "learning_rate": 2.9979443021318607e-05,
      "loss": 1.4423,
      "step": 10
    },
    {
      "epoch": 3.0,
      "learning_rate": 2.9970400926424075e-05,
      "loss": 1.2197,
      "step": 12
    },
    {
      "epoch": 3.5,
      "learning_rate": 2.995971715836687e-05,
      "loss": 1.179,
      "step": 14
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.9947392888742566e-05,
      "loss": 1.1804,
      "step": 16
    },
    {
      "epoch": 4.5,
      "learning_rate": 2.9933429469046202e-05,
      "loss": 1.0764,
      "step": 18
    },
    {
      "epoch": 5.0,
      "learning_rate": 2.99178284305241e-05,
      "loss": 1.0158,
      "step": 20
    },
    {
      "epoch": 5.5,
      "learning_rate": 2.9900591484005944e-05,
      "loss": 1.0207,
      "step": 22
    },
    {
      "epoch": 6.0,
      "learning_rate": 2.988172051971717e-05,
      "loss": 0.9368,
      "step": 24
    },
    {
      "epoch": 6.5,
      "learning_rate": 2.9861217607071655e-05,
      "loss": 0.9267,
      "step": 26
    },
    {
      "epoch": 7.0,
      "learning_rate": 2.983908499444483e-05,
      "loss": 0.918,
      "step": 28
    },
    {
      "epoch": 7.5,
      "learning_rate": 2.981532510892707e-05,
      "loss": 0.8598,
      "step": 30
    },
    {
      "epoch": 8.0,
      "learning_rate": 2.9789940556057574e-05,
      "loss": 0.8009,
      "step": 32
    },
    {
      "epoch": 8.5,
      "learning_rate": 2.9762934119538628e-05,
      "loss": 0.7998,
      "step": 34
    },
    {
      "epoch": 9.0,
      "learning_rate": 2.9734308760930333e-05,
      "loss": 0.8224,
      "step": 36
    },
    {
      "epoch": 9.5,
      "learning_rate": 2.9704067619325828e-05,
      "loss": 0.7715,
      "step": 38
    },
    {
      "epoch": 10.0,
      "learning_rate": 2.9672214011007087e-05,
      "loss": 0.7385,
      "step": 40
    },
    {
      "epoch": 10.5,
      "learning_rate": 2.9638751429081213e-05,
      "loss": 0.7225,
      "step": 42
    },
    {
      "epoch": 11.0,
      "learning_rate": 2.9603683543097406e-05,
      "loss": 0.7344,
      "step": 44
    },
    {
      "epoch": 11.5,
      "learning_rate": 2.9567014198644542e-05,
      "loss": 0.694,
      "step": 46
    },
    {
      "epoch": 12.0,
      "learning_rate": 2.9528747416929467e-05,
      "loss": 0.6524,
      "step": 48
    },
    {
      "epoch": 12.5,
      "learning_rate": 2.9488887394336025e-05,
      "loss": 0.6711,
      "step": 50
    },
    {
      "epoch": 13.0,
      "learning_rate": 2.9447438501964873e-05,
      "loss": 0.658,
      "step": 52
    },
    {
      "epoch": 13.5,
      "learning_rate": 2.9404405285154146e-05,
      "loss": 0.6104,
      "step": 54
    },
    {
      "epoch": 14.0,
      "learning_rate": 2.9359792462981007e-05,
      "loss": 0.7061,
      "step": 56
    },
    {
      "epoch": 14.5,
      "learning_rate": 2.9313604927744153e-05,
      "loss": 0.614,
      "step": 58
    },
    {
      "epoch": 15.0,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 0.56,
      "step": 60
    },
    {
      "epoch": 15.5,
      "learning_rate": 2.9216526150143788e-05,
      "loss": 0.5688,
      "step": 62
    },
    {
      "epoch": 16.0,
      "learning_rate": 2.9165645553562215e-05,
      "loss": 0.5619,
      "step": 64
    },
    {
      "epoch": 16.5,
      "learning_rate": 2.9113211534313385e-05,
      "loss": 0.5505,
      "step": 66
    },
    {
      "epoch": 17.0,
      "learning_rate": 2.9059229842378373e-05,
      "loss": 0.5268,
      "step": 68
    },
    {
      "epoch": 17.5,
      "learning_rate": 2.9003706397458025e-05,
      "loss": 0.5121,
      "step": 70
    },
    {
      "epoch": 18.0,
      "learning_rate": 2.894664728832377e-05,
      "loss": 0.5214,
      "step": 72
    }
  ],
  "logging_steps": 2,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 150,
  "save_steps": 500,
  "total_flos": 3085327254159360.0,
  "train_batch_size": 52,
  "trial_name": null,
  "trial_params": null
}