trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 14.962962962962964,
  "global_step": 195,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.67,
      "eval_loss": 5.965728282928467,
      "eval_runtime": 8.6392,
      "eval_samples_per_second": 22.919,
      "eval_steps_per_second": 2.894,
      "eval_wer": 1.0,
      "step": 100
    },
    {
      "epoch": 14.96,
      "step": 195,
      "total_flos": 8.135466484187405e+17,
      "train_loss": 11.425617237580129,
      "train_runtime": 412.0123,
      "train_samples_per_second": 15.327,
      "train_steps_per_second": 0.473
    }
  ],
  "max_steps": 195,
  "num_train_epochs": 15,
  "total_flos": 8.135466484187405e+17,
  "trial_name": null,
  "trial_params": null
}