{
  "best_metric": 1.9101046323776245,
  "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": 2.315,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.160651922225952,
      "eval_runtime": 144.1197,
      "eval_samples_per_second": 43.533,
      "eval_steps_per_second": 5.447,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.1091,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.0636215209960938,
      "eval_runtime": 143.9553,
      "eval_samples_per_second": 43.583,
      "eval_steps_per_second": 5.453,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.0344,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.0027897357940674,
      "eval_runtime": 144.1134,
      "eval_samples_per_second": 43.535,
      "eval_steps_per_second": 5.447,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.9806,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 1.9537049531936646,
      "eval_runtime": 144.1171,
      "eval_samples_per_second": 43.534,
      "eval_steps_per_second": 5.447,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.9262,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 1.9101046323776245,
      "eval_runtime": 143.9719,
      "eval_samples_per_second": 43.578,
      "eval_steps_per_second": 5.452,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.9805494916120576e+16,
  "trial_name": null,
  "trial_params": null
}