{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.653500552592379,
  "eval_steps": 500,
  "global_step": 8500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "ep_loss": 4.4238,
      "epoch": 0.04,
      "learning_rate": 2.5e-05,
      "loss": 11.1467,
      "mlm_loss": 6.7229,
      "step": 500
    },
    {
      "ep_loss": 0.4305,
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 2.9841,
      "mlm_loss": 2.5537,
      "step": 1000
    },
    {
      "ep_loss": 0.3724,
      "epoch": 0.12,
      "learning_rate": 7.5e-05,
      "loss": 2.2371,
      "mlm_loss": 1.8647,
      "step": 1500
    },
    {
      "ep_loss": 0.364,
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 1.8477,
      "mlm_loss": 1.4837,
      "step": 2000
    },
    {
      "ep_loss": 0.3678,
      "epoch": 0.19,
      "learning_rate": 0.00012495,
      "loss": 1.5215,
      "mlm_loss": 1.1538,
      "step": 2500
    },
    {
      "ep_loss": 0.3617,
      "epoch": 0.23,
      "learning_rate": 0.00014995,
      "loss": 1.4119,
      "mlm_loss": 1.0501,
      "step": 3000
    },
    {
      "ep_loss": 0.3336,
      "epoch": 0.27,
      "learning_rate": 0.0001749,
      "loss": 1.3027,
      "mlm_loss": 0.9691,
      "step": 3500
    },
    {
      "ep_loss": 0.3348,
      "epoch": 0.31,
      "learning_rate": 0.0001999,
      "loss": 1.2441,
      "mlm_loss": 0.9093,
      "step": 4000
    },
    {
      "ep_loss": 0.3348,
      "epoch": 0.35,
      "learning_rate": 0.0002249,
      "loss": 1.1942,
      "mlm_loss": 0.8594,
      "step": 4500
    },
    {
      "ep_loss": 0.3331,
      "epoch": 0.38,
      "learning_rate": 0.0002499,
      "loss": 1.1466,
      "mlm_loss": 0.8135,
      "step": 5000
    },
    {
      "ep_loss": 0.3268,
      "epoch": 0.42,
      "learning_rate": 0.00027489999999999996,
      "loss": 1.1067,
      "mlm_loss": 0.7799,
      "step": 5500
    },
    {
      "ep_loss": 0.3378,
      "epoch": 0.46,
      "learning_rate": 0.00029985,
      "loss": 1.1007,
      "mlm_loss": 0.7629,
      "step": 6000
    },
    {
      "ep_loss": 0.3033,
      "epoch": 0.5,
      "learning_rate": 0.00032485,
      "loss": 1.028,
      "mlm_loss": 0.7246,
      "step": 6500
    },
    {
      "ep_loss": 0.2848,
      "epoch": 0.54,
      "learning_rate": 0.00034985,
      "loss": 0.9833,
      "mlm_loss": 0.6985,
      "step": 7000
    },
    {
      "ep_loss": 0.316,
      "epoch": 0.58,
      "learning_rate": 0.00037485000000000003,
      "loss": 1.0235,
      "mlm_loss": 0.7076,
      "step": 7500
    },
    {
      "ep_loss": 0.2885,
      "epoch": 0.62,
      "learning_rate": 0.00039975,
      "loss": 0.9673,
      "mlm_loss": 0.6789,
      "step": 8000
    },
    {
      "ep_loss": 0.274,
      "epoch": 0.65,
      "learning_rate": 0.00042475000000000005,
      "loss": 0.9266,
      "mlm_loss": 0.6525,
      "step": 8500
    }
  ],
  "logging_steps": 500,
  "max_steps": 520240,
  "num_train_epochs": 40,
  "save_steps": 500,
  "total_flos": 8.115946811576812e+18,
  "trial_name": null,
  "trial_params": null
}