{
  "best_metric": 2.4924821853637695,
  "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": 2.7399,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.6418099403381348,
      "eval_runtime": 347.6157,
      "eval_samples_per_second": 18.049,
      "eval_steps_per_second": 2.258,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6052,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.5918312072753906,
      "eval_runtime": 333.731,
      "eval_samples_per_second": 18.8,
      "eval_steps_per_second": 2.352,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5622,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.551574468612671,
      "eval_runtime": 204.9306,
      "eval_samples_per_second": 30.615,
      "eval_steps_per_second": 3.831,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5366,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.517575263977051,
      "eval_runtime": 204.3925,
      "eval_samples_per_second": 30.696,
      "eval_steps_per_second": 3.841,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.4946,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.4924821853637695,
      "eval_runtime": 204.4035,
      "eval_samples_per_second": 30.694,
      "eval_steps_per_second": 3.84,
      "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
}