{
  "best_metric": 1.7833176851272583,
  "best_model_checkpoint": "./outputs/checkpoint-500",
  "epoch": 0.36429872495446264,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.1911,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.0239477157592773,
      "eval_runtime": 143.6069,
      "eval_samples_per_second": 43.689,
      "eval_steps_per_second": 5.466,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.9736,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 1.93068528175354,
      "eval_runtime": 143.6288,
      "eval_samples_per_second": 43.682,
      "eval_steps_per_second": 5.465,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.9,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 1.8703595399856567,
      "eval_runtime": 143.4955,
      "eval_samples_per_second": 43.723,
      "eval_steps_per_second": 5.471,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.8484,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 1.8250001668930054,
      "eval_runtime": 143.5707,
      "eval_samples_per_second": 43.7,
      "eval_steps_per_second": 5.468,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.7975,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 1.7833176851272583,
      "eval_runtime": 143.7076,
      "eval_samples_per_second": 43.658,
      "eval_steps_per_second": 5.462,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.983213629977395e+16,
  "trial_name": null,
  "trial_params": null
}