trainer_state.json

{
  "best_metric": 0.6132865109901463,
  "best_model_checkpoint": "OS_OUT/harish/PT-UP-xlmR-ContextIncluded_IdiomExcluded-4_BEST/TrueFalse-0/0/checkpoint-10",
  "epoch": 5.0,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5054945349693298,
      "eval_f1": 0.4448186316904772,
      "eval_loss": 1.0858509540557861,
      "eval_runtime": 0.7803,
      "eval_samples_per_second": 349.868,
      "eval_steps_per_second": 44.855,
      "step": 2
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5457875728607178,
      "eval_f1": 0.5248267784316216,
      "eval_loss": 0.7876102924346924,
      "eval_runtime": 0.782,
      "eval_samples_per_second": 349.108,
      "eval_steps_per_second": 44.757,
      "step": 4
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5604395866394043,
      "eval_f1": 0.561999123336614,
      "eval_loss": 0.7128857970237732,
      "eval_runtime": 0.798,
      "eval_samples_per_second": 342.104,
      "eval_steps_per_second": 43.859,
      "step": 6
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6007326245307922,
      "eval_f1": 0.5950122936424307,
      "eval_loss": 0.7449135184288025,
      "eval_runtime": 0.7825,
      "eval_samples_per_second": 348.874,
      "eval_steps_per_second": 44.727,
      "step": 8
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6153846383094788,
      "eval_f1": 0.6132865109901463,
      "eval_loss": 0.7322821617126465,
      "eval_runtime": 0.8163,
      "eval_samples_per_second": 334.437,
      "eval_steps_per_second": 42.876,
      "step": 10
    }
  ],
  "max_steps": 18,
  "num_train_epochs": 9,
  "total_flos": 17431107417600.0,
  "trial_name": null,
  "trial_params": null
}