{
  "best_metric": 1.4523780345916748,
  "best_model_checkpoint": "./results/checkpoint-64",
  "epoch": 0.05200081251269551,
  "eval_steps": 8,
  "global_step": 64,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.604,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.5865,
      "step": 8
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.58369779586792,
      "eval_runtime": 33.9799,
      "eval_samples_per_second": 15.244,
      "eval_steps_per_second": 1.913,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.4024,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.3627,
      "step": 16
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.503720998764038,
      "eval_runtime": 34.2342,
      "eval_samples_per_second": 15.131,
      "eval_steps_per_second": 1.899,
      "step": 16
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.3242,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.2733,
      "step": 24
    },
    {
      "epoch": 0.02,
      "eval_loss": 1.4826295375823975,
      "eval_runtime": 34.4234,
      "eval_samples_per_second": 15.048,
      "eval_steps_per_second": 1.888,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.507,
      "step": 28
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.472,
      "step": 32
    },
    {
      "epoch": 0.03,
      "eval_loss": 1.4713466167449951,
      "eval_runtime": 34.5227,
      "eval_samples_per_second": 15.005,
      "eval_steps_per_second": 1.883,
      "step": 32
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.4269,
      "step": 36
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.6282,
      "step": 40
    },
    {
      "epoch": 0.03,
      "eval_loss": 1.4705039262771606,
      "eval_runtime": 34.5472,
      "eval_samples_per_second": 14.994,
      "eval_steps_per_second": 1.881,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.6744,
      "step": 44
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.789,
      "step": 48
    },
    {
      "epoch": 0.04,
      "eval_loss": 1.4801452159881592,
      "eval_runtime": 34.5611,
      "eval_samples_per_second": 14.988,
      "eval_steps_per_second": 1.881,
      "step": 48
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.7547,
      "step": 52
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.3081,
      "step": 56
    },
    {
      "epoch": 0.05,
      "eval_loss": 1.465359091758728,
      "eval_runtime": 34.5837,
      "eval_samples_per_second": 14.978,
      "eval_steps_per_second": 1.88,
      "step": 56
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.2313,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.4273,
      "step": 64
    },
    {
      "epoch": 0.05,
      "eval_loss": 1.4523780345916748,
      "eval_runtime": 34.6395,
      "eval_samples_per_second": 14.954,
      "eval_steps_per_second": 1.876,
      "step": 64
    }
  ],
  "logging_steps": 4,
  "max_steps": 64,
  "num_train_epochs": 1,
  "save_steps": 8,
  "total_flos": 7578875318034432.0,
  "trial_name": null,
  "trial_params": null
}