checkpoint-68223/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 68223,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.308,
      "step": 22741
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8924560969577047,
      "eval_combined_score": 0.8740405069726762,
      "eval_f1": 0.8556249169876479,
      "eval_loss": 0.2548316419124603,
      "eval_runtime": 413.8779,
      "eval_samples_per_second": 97.686,
      "eval_steps_per_second": 12.211,
      "step": 22741
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.201,
      "step": 45482
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9032401681919366,
      "eval_combined_score": 0.886515570715593,
      "eval_f1": 0.8697909732392491,
      "eval_loss": 0.2880714237689972,
      "eval_runtime": 412.3711,
      "eval_samples_per_second": 98.043,
      "eval_steps_per_second": 12.256,
      "step": 45482
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.1416,
      "step": 68223
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9083848627256987,
      "eval_combined_score": 0.8925741188794849,
      "eval_f1": 0.8767633750332712,
      "eval_loss": 0.37517139315605164,
      "eval_runtime": 412.699,
      "eval_samples_per_second": 97.965,
      "eval_steps_per_second": 12.246,
      "step": 68223
    }
  ],
  "max_steps": 68223,
  "num_train_epochs": 3,
  "total_flos": 2.8719571514554368e+17,
  "trial_name": null,
  "trial_params": null
}