{
  "best_metric": 0.9024694561958313,
  "best_model_checkpoint": "models/checkpoints/checkpoint-2000",
  "epoch": 2.0986358866736623,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.52,
      "learning_rate": 1.9475341028331587e-05,
      "loss": 1.2025,
      "step": 500
    },
    {
      "epoch": 0.52,
      "eval_loss": 0.9926990270614624,
      "eval_runtime": 325.2407,
      "eval_samples_per_second": 43.454,
      "eval_steps_per_second": 0.341,
      "step": 500
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.895068205666317e-05,
      "loss": 1.0125,
      "step": 1000
    },
    {
      "epoch": 1.05,
      "eval_loss": 0.948229968547821,
      "eval_runtime": 325.6473,
      "eval_samples_per_second": 43.4,
      "eval_steps_per_second": 0.341,
      "step": 1000
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.8426023084994754e-05,
      "loss": 0.9408,
      "step": 1500
    },
    {
      "epoch": 1.57,
      "eval_loss": 0.9487974047660828,
      "eval_runtime": 410.664,
      "eval_samples_per_second": 34.415,
      "eval_steps_per_second": 0.27,
      "step": 1500
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.790136411332634e-05,
      "loss": 0.9073,
      "step": 2000
    },
    {
      "epoch": 2.1,
      "eval_loss": 0.9024694561958313,
      "eval_runtime": 409.1112,
      "eval_samples_per_second": 34.546,
      "eval_steps_per_second": 0.271,
      "step": 2000
    }
  ],
  "max_steps": 19060,
  "num_train_epochs": 20,
  "total_flos": 1.3535851069855128e+16,
  "trial_name": null,
  "trial_params": null
}