trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0767754318618041,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27,
      "learning_rate": 3.5e-05,
      "loss": 0.0793,
      "step": 35
    },
    {
      "epoch": 0.27,
      "eval_loss": 0.2476252019405365,
      "eval_runtime": 215.5237,
      "eval_samples_per_second": 17.237,
      "eval_steps_per_second": 2.158,
      "eval_wer": 0.22721730371626994,
      "step": 35
    },
    {
      "epoch": 0.54,
      "learning_rate": 7e-05,
      "loss": 0.0421,
      "step": 70
    },
    {
      "epoch": 0.54,
      "eval_loss": 0.22333967685699463,
      "eval_runtime": 146.1566,
      "eval_samples_per_second": 25.418,
      "eval_steps_per_second": 3.182,
      "eval_wer": 0.20049833006414675,
      "step": 70
    },
    {
      "epoch": 0.81,
      "learning_rate": 9.999615088529639e-05,
      "loss": 0.0367,
      "step": 105
    },
    {
      "epoch": 0.81,
      "eval_loss": 0.22262878715991974,
      "eval_runtime": 146.9473,
      "eval_samples_per_second": 25.281,
      "eval_steps_per_second": 3.164,
      "eval_wer": 0.19588612627895882,
      "step": 105
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.996920708237106e-05,
      "loss": 0.0344,
      "step": 140
    },
    {
      "epoch": 1.08,
      "eval_loss": 0.22949478030204773,
      "eval_runtime": 150.3329,
      "eval_samples_per_second": 24.712,
      "eval_steps_per_second": 3.093,
      "eval_wer": 0.19413666967078408,
      "step": 140
    }
  ],
  "max_steps": 130000,
  "num_train_epochs": 1000,
  "total_flos": 3.2610548660980367e+18,
  "trial_name": null,
  "trial_params": null
}