trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 468,
  "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": 0.6829,
      "step": 156
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5703971119133574,
      "eval_loss": 0.6657100915908813,
      "eval_runtime": 2.0131,
      "eval_samples_per_second": 137.6,
      "eval_steps_per_second": 17.386,
      "step": 156
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.6174,
      "step": 312
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6101083032490975,
      "eval_loss": 0.6784032583236694,
      "eval_runtime": 2.013,
      "eval_samples_per_second": 137.609,
      "eval_steps_per_second": 17.387,
      "step": 312
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.5141,
      "step": 468
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.628158844765343,
      "eval_loss": 0.6978281736373901,
      "eval_runtime": 2.0128,
      "eval_samples_per_second": 137.616,
      "eval_steps_per_second": 17.388,
      "step": 468
    },
    {
      "epoch": 3.0,
      "step": 468,
      "total_flos": 1328457479639040.0,
      "train_loss": 0.6048059545011601,
      "train_runtime": 204.1282,
      "train_samples_per_second": 36.595,
      "train_steps_per_second": 2.293
    }
  ],
  "max_steps": 468,
  "num_train_epochs": 3,
  "total_flos": 1328457479639040.0,
  "trial_name": null,
  "trial_params": null
}