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": 7.408177408177407e-05,
      "loss": 0.6408,
      "step": 2138
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7329378128051758,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 22.7321,
      "eval_samples_per_second": 45.882,
      "eval_steps_per_second": 5.763,
      "step": 2138
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.704088704088704e-05,
      "loss": 0.6589,
      "step": 4276
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6311050057411194,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 22.7597,
      "eval_samples_per_second": 45.827,
      "eval_steps_per_second": 5.756,
      "step": 4276
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.6467,
      "step": 6414
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6554446816444397,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 22.7256,
      "eval_samples_per_second": 45.895,
      "eval_steps_per_second": 5.764,
      "step": 6414
    },
    {
      "epoch": 3.0,
      "step": 6414,
      "total_flos": 1.6048929796061184e+16,
      "train_loss": 0.0,
      "train_runtime": 0.0685,
      "train_samples_per_second": 374599.122,
      "train_steps_per_second": 93660.732
    }
  ],
  "max_steps": 6414,
  "num_train_epochs": 3,
  "total_flos": 1.6048929796061184e+16,
  "trial_name": null,
  "trial_params": null
}