{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1060,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 9.95e-05,
      "loss": 6.3597,
      "step": 212
    },
    {
      "epoch": 1.0,
      "eval_loss": 5.853069305419922,
      "eval_runtime": 3.5937,
      "eval_samples_per_second": 188.106,
      "eval_steps_per_second": 23.652,
      "step": 212
    },
    {
      "epoch": 2.0,
      "learning_rate": 9.900000000000001e-05,
      "loss": 5.5629,
      "step": 424
    },
    {
      "epoch": 2.0,
      "eval_loss": 4.915834903717041,
      "eval_runtime": 3.704,
      "eval_samples_per_second": 182.506,
      "eval_steps_per_second": 22.948,
      "step": 424
    },
    {
      "epoch": 3.0,
      "learning_rate": 9.850000000000001e-05,
      "loss": 4.8228,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_loss": 4.177055835723877,
      "eval_runtime": 3.7104,
      "eval_samples_per_second": 182.193,
      "eval_steps_per_second": 22.909,
      "step": 636
    },
    {
      "epoch": 4.0,
      "learning_rate": 9.8e-05,
      "loss": 4.1035,
      "step": 848
    },
    {
      "epoch": 4.0,
      "eval_loss": 3.462527275085449,
      "eval_runtime": 3.1205,
      "eval_samples_per_second": 216.633,
      "eval_steps_per_second": 27.239,
      "step": 848
    },
    {
      "epoch": 5.0,
      "learning_rate": 9.75e-05,
      "loss": 3.467,
      "step": 1060
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.8398332595825195,
      "eval_runtime": 3.3235,
      "eval_samples_per_second": 203.402,
      "eval_steps_per_second": 25.576,
      "step": 1060
    }
  ],
  "logging_steps": 500,
  "max_steps": 42400,
  "num_train_epochs": 200,
  "save_steps": 500,
  "total_flos": 1333912528679340.0,
  "trial_name": null,
  "trial_params": null
}