{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6298815822625347,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 9.5e-05,
      "loss": 57.2732,
      "step": 500
    },
    {
      "epoch": 0.06,
      "eval_loss": 51.029930114746094,
      "eval_runtime": 3.1759,
      "eval_samples_per_second": 31.487,
      "eval_steps_per_second": 4.093,
      "step": 500
    },
    {
      "epoch": 0.13,
      "learning_rate": 9e-05,
      "loss": 56.0705,
      "step": 1000
    },
    {
      "epoch": 0.13,
      "eval_loss": 49.898155212402344,
      "eval_runtime": 4.4269,
      "eval_samples_per_second": 22.589,
      "eval_steps_per_second": 2.937,
      "step": 1000
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.5e-05,
      "loss": 55.3144,
      "step": 1500
    },
    {
      "epoch": 0.19,
      "eval_loss": 49.3874397277832,
      "eval_runtime": 4.228,
      "eval_samples_per_second": 23.652,
      "eval_steps_per_second": 3.075,
      "step": 1500
    },
    {
      "epoch": 0.25,
      "learning_rate": 8e-05,
      "loss": 54.301,
      "step": 2000
    },
    {
      "epoch": 0.25,
      "eval_loss": 48.694358825683594,
      "eval_runtime": 3.1949,
      "eval_samples_per_second": 31.299,
      "eval_steps_per_second": 4.069,
      "step": 2000
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.500000000000001e-05,
      "loss": 54.8258,
      "step": 2500
    },
    {
      "epoch": 0.31,
      "eval_loss": 49.120418548583984,
      "eval_runtime": 4.0702,
      "eval_samples_per_second": 24.569,
      "eval_steps_per_second": 3.194,
      "step": 2500
    },
    {
      "epoch": 0.38,
      "learning_rate": 7e-05,
      "loss": 55.0078,
      "step": 3000
    },
    {
      "epoch": 0.38,
      "eval_loss": 48.479034423828125,
      "eval_runtime": 3.9143,
      "eval_samples_per_second": 25.547,
      "eval_steps_per_second": 3.321,
      "step": 3000
    },
    {
      "epoch": 0.44,
      "learning_rate": 6.500000000000001e-05,
      "loss": 55.0228,
      "step": 3500
    },
    {
      "epoch": 0.44,
      "eval_loss": 48.023162841796875,
      "eval_runtime": 3.9112,
      "eval_samples_per_second": 25.568,
      "eval_steps_per_second": 3.324,
      "step": 3500
    },
    {
      "epoch": 0.5,
      "learning_rate": 6e-05,
      "loss": 53.2773,
      "step": 4000
    },
    {
      "epoch": 0.5,
      "eval_loss": 47.419307708740234,
      "eval_runtime": 4.7859,
      "eval_samples_per_second": 20.895,
      "eval_steps_per_second": 2.716,
      "step": 4000
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.500000000000001e-05,
      "loss": 54.9082,
      "step": 4500
    },
    {
      "epoch": 0.57,
      "eval_loss": 46.841548919677734,
      "eval_runtime": 4.8111,
      "eval_samples_per_second": 20.785,
      "eval_steps_per_second": 2.702,
      "step": 4500
    },
    {
      "epoch": 0.63,
      "learning_rate": 5e-05,
      "loss": 53.3684,
      "step": 5000
    },
    {
      "epoch": 0.63,
      "eval_loss": 46.429256439208984,
      "eval_runtime": 4.525,
      "eval_samples_per_second": 22.099,
      "eval_steps_per_second": 2.873,
      "step": 5000
    }
  ],
  "logging_steps": 500,
  "max_steps": 10000,
  "num_train_epochs": 2,
  "save_steps": 5000,
  "total_flos": 6.84757352448e+16,
  "trial_name": null,
  "trial_params": null
}