{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.552397868561279,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 2.61,
      "step": 100
    },
    {
      "epoch": 0.36,
      "learning_rate": 2e-05,
      "loss": 2.239,
      "step": 200
    },
    {
      "epoch": 0.53,
      "learning_rate": 3e-05,
      "loss": 2.1544,
      "step": 300
    },
    {
      "epoch": 0.71,
      "learning_rate": 4e-05,
      "loss": 2.1588,
      "step": 400
    },
    {
      "epoch": 0.89,
      "learning_rate": 5e-05,
      "loss": 2.1616,
      "step": 500
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.714611872146119e-05,
      "loss": 2.1307,
      "step": 600
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.4292237442922375e-05,
      "loss": 2.099,
      "step": 700
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.143835616438356e-05,
      "loss": 2.0643,
      "step": 800
    },
    {
      "epoch": 1.6,
      "learning_rate": 3.8584474885844754e-05,
      "loss": 1.9641,
      "step": 900
    },
    {
      "epoch": 1.78,
      "learning_rate": 3.573059360730594e-05,
      "loss": 2.02,
      "step": 1000
    },
    {
      "epoch": 1.95,
      "learning_rate": 3.287671232876712e-05,
      "loss": 1.9874,
      "step": 1100
    },
    {
      "epoch": 2.13,
      "learning_rate": 3.0022831050228313e-05,
      "loss": 1.9012,
      "step": 1200
    },
    {
      "epoch": 2.31,
      "learning_rate": 2.71689497716895e-05,
      "loss": 1.8334,
      "step": 1300
    },
    {
      "epoch": 2.49,
      "learning_rate": 2.4315068493150686e-05,
      "loss": 1.8206,
      "step": 1400
    },
    {
      "epoch": 2.66,
      "learning_rate": 2.1461187214611872e-05,
      "loss": 1.8217,
      "step": 1500
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.8607305936073062e-05,
      "loss": 1.7761,
      "step": 1600
    },
    {
      "epoch": 3.02,
      "learning_rate": 1.5753424657534248e-05,
      "loss": 1.7351,
      "step": 1700
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.2899543378995434e-05,
      "loss": 1.6358,
      "step": 1800
    },
    {
      "epoch": 3.37,
      "learning_rate": 1.004566210045662e-05,
      "loss": 1.5685,
      "step": 1900
    },
    {
      "epoch": 3.55,
      "learning_rate": 7.191780821917809e-06,
      "loss": 1.6077,
      "step": 2000
    }
  ],
  "max_steps": 2252,
  "num_train_epochs": 4,
  "total_flos": 3412844614972800.0,
  "trial_name": null,
  "trial_params": null
}