{
  "best_metric": 2.4934604167938232,
  "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": 2.7406,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.6424405574798584,
      "eval_runtime": 206.8728,
      "eval_samples_per_second": 30.328,
      "eval_steps_per_second": 3.795,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6056,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.591430187225342,
      "eval_runtime": 206.9647,
      "eval_samples_per_second": 30.314,
      "eval_steps_per_second": 3.793,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5631,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.5565075874328613,
      "eval_runtime": 206.6263,
      "eval_samples_per_second": 30.364,
      "eval_steps_per_second": 3.799,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5363,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.5222103595733643,
      "eval_runtime": 234.7988,
      "eval_samples_per_second": 26.721,
      "eval_steps_per_second": 3.343,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.4935,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.4934604167938232,
      "eval_runtime": 206.7039,
      "eval_samples_per_second": 30.353,
      "eval_steps_per_second": 3.798,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 1.459702746464256e+16,
  "trial_name": null,
  "trial_params": null
}