trainer_state.json

{
  "best_metric": 0.5536774704373721,
  "best_model_checkpoint": "R2-OUTPUT/xlm-roberta-base/ContextIncluded_IdiomExcluded/4/checkpoint-185",
  "epoch": 5.0,
  "global_step": 185,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5641025900840759,
      "eval_f1": 0.4068936527952921,
      "eval_loss": 0.6858616471290588,
      "eval_runtime": 0.8041,
      "eval_samples_per_second": 339.518,
      "eval_steps_per_second": 43.528,
      "step": 37
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5641025900840759,
      "eval_f1": 0.4068936527952921,
      "eval_loss": 0.7174506187438965,
      "eval_runtime": 0.8048,
      "eval_samples_per_second": 339.219,
      "eval_steps_per_second": 43.49,
      "step": 74
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5641025900840759,
      "eval_f1": 0.4068936527952921,
      "eval_loss": 0.8625497817993164,
      "eval_runtime": 0.804,
      "eval_samples_per_second": 339.572,
      "eval_steps_per_second": 43.535,
      "step": 111
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5274725556373596,
      "eval_f1": 0.5077237216898057,
      "eval_loss": 0.8788116574287415,
      "eval_runtime": 0.8029,
      "eval_samples_per_second": 340.023,
      "eval_steps_per_second": 43.593,
      "step": 148
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5604395866394043,
      "eval_f1": 0.5536774704373721,
      "eval_loss": 1.1304702758789062,
      "eval_runtime": 0.8023,
      "eval_samples_per_second": 340.278,
      "eval_steps_per_second": 43.625,
      "step": 185
    }
  ],
  "max_steps": 333,
  "num_train_epochs": 9,
  "total_flos": 1242795250575360.0,
  "trial_name": null,
  "trial_params": null
}