{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.324459234608985,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.0008,
      "step": 10
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.9939,
      "step": 20
    },
    {
      "epoch": 0.8,
      "learning_rate": 6e-06,
      "loss": 2.0215,
      "step": 30
    },
    {
      "epoch": 1.06,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.9508,
      "step": 40
    },
    {
      "epoch": 1.33,
      "learning_rate": 1e-05,
      "loss": 1.9897,
      "step": 50
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.2e-05,
      "loss": 1.961,
      "step": 60
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.904,
      "step": 70
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.8214,
      "step": 80
    },
    {
      "epoch": 2.4,
      "learning_rate": 1.8e-05,
      "loss": 1.8104,
      "step": 90
    },
    {
      "epoch": 2.66,
      "learning_rate": 2e-05,
      "loss": 1.709,
      "step": 100
    },
    {
      "epoch": 2.93,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.618,
      "step": 110
    },
    {
      "epoch": 3.19,
      "learning_rate": 2.4e-05,
      "loss": 1.5314,
      "step": 120
    },
    {
      "epoch": 3.46,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.5163,
      "step": 130
    },
    {
      "epoch": 3.73,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.4742,
      "step": 140
    },
    {
      "epoch": 3.99,
      "learning_rate": 3e-05,
      "loss": 1.4783,
      "step": 150
    },
    {
      "epoch": 4.26,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.43,
      "step": 160
    },
    {
      "epoch": 4.53,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.4322,
      "step": 170
    },
    {
      "epoch": 4.79,
      "learning_rate": 3.6e-05,
      "loss": 1.3991,
      "step": 180
    },
    {
      "epoch": 5.06,
      "learning_rate": 3.8e-05,
      "loss": 1.3835,
      "step": 190
    },
    {
      "epoch": 5.32,
      "learning_rate": 4e-05,
      "loss": 1.3465,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 296,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 100,
  "total_flos": 5.19952498950144e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}