{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0475020475020473,
  "eval_steps": 500,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 4.8293748293748295e-05,
      "loss": 4.3223,
      "step": 500
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.658749658749659e-05,
      "loss": 4.2808,
      "step": 1000
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.4881244881244886e-05,
      "loss": 4.2576,
      "step": 1500
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.317499317499318e-05,
      "loss": 4.1952,
      "step": 2000
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.146874146874147e-05,
      "loss": 4.133,
      "step": 2500
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.976248976248976e-05,
      "loss": 4.0789,
      "step": 3000
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.8056238056238055e-05,
      "loss": 4.0146,
      "step": 3500
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.6349986349986354e-05,
      "loss": 3.9639,
      "step": 4000
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.4643734643734647e-05,
      "loss": 3.9444,
      "step": 4500
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.293748293748294e-05,
      "loss": 3.8477,
      "step": 5000
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.123123123123123e-05,
      "loss": 3.7137,
      "step": 5500
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.952497952497953e-05,
      "loss": 3.6799,
      "step": 6000
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.781872781872782e-05,
      "loss": 3.674,
      "step": 6500
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.6112476112476115e-05,
      "loss": 3.6476,
      "step": 7000
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.4406224406224407e-05,
      "loss": 3.6145,
      "step": 7500
    },
    {
      "epoch": 1.64,
      "learning_rate": 2.2699972699972703e-05,
      "loss": 3.5609,
      "step": 8000
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.0993720993720995e-05,
      "loss": 3.5179,
      "step": 8500
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.928746928746929e-05,
      "loss": 3.5089,
      "step": 9000
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.7581217581217583e-05,
      "loss": 3.5192,
      "step": 9500
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.5874965874965875e-05,
      "loss": 3.39,
      "step": 10000
    }
  ],
  "logging_steps": 500,
  "max_steps": 14652,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10000,
  "total_flos": 1.0451158695936e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}