trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 6414,
  "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": 0.6195,
      "step": 2138
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6526795029640198,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 22.9461,
      "eval_samples_per_second": 45.454,
      "eval_steps_per_second": 5.709,
      "step": 2138
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.6168,
      "step": 4276
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6258916258811951,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 22.6853,
      "eval_samples_per_second": 45.977,
      "eval_steps_per_second": 5.775,
      "step": 4276
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.616,
      "step": 6414
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.624345064163208,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 22.6868,
      "eval_samples_per_second": 45.974,
      "eval_steps_per_second": 5.774,
      "step": 6414
    },
    {
      "epoch": 3.0,
      "step": 6414,
      "total_flos": 1.6048929796061184e+16,
      "train_loss": 0.0,
      "train_runtime": 0.1375,
      "train_samples_per_second": 186552.975,
      "train_steps_per_second": 46643.698
    }
  ],
  "max_steps": 6414,
  "num_train_epochs": 3,
  "total_flos": 1.6048929796061184e+16,
  "trial_name": null,
  "trial_params": null
}