checkpoint-10/trainer_state.json

{
  "best_metric": 10.801591873168945,
  "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/2023-11-20/16-19-50/checkpoints/checkpoint-10",
  "epoch": 0.08,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 4.600000000000001e-05,
      "loss": 10.8117,
      "step": 10
    },
    {
      "epoch": 0.08,
      "eval_loss": 10.801591873168945,
      "eval_runtime": 2.6865,
      "eval_samples_per_second": 372.226,
      "eval_steps_per_second": 46.528,
      "step": 10
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 703388819520.0,
  "trial_name": null,
  "trial_params": null
}