trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "global_step": 320,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8748680042238648,
      "eval_f1": 0.0,
      "eval_loss": 0.616299569606781,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.1116,
      "eval_samples_per_second": 815.287,
      "step": 32
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8785638859556494,
      "eval_f1": 0.0,
      "eval_loss": 0.4105246365070343,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.1118,
      "eval_samples_per_second": 814.082,
      "step": 64
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.883843717001056,
      "eval_f1": 0.3583333333333333,
      "eval_loss": 0.328654408454895,
      "eval_precision": 0.4387755102040816,
      "eval_recall": 0.3028169014084507,
      "eval_runtime": 0.1118,
      "eval_samples_per_second": 814.03,
      "step": 96
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8912354804646251,
      "eval_f1": 0.36909871244635195,
      "eval_loss": 0.31546750664711,
      "eval_precision": 0.4725274725274725,
      "eval_recall": 0.3028169014084507,
      "eval_runtime": 0.1118,
      "eval_samples_per_second": 813.707,
      "step": 128
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8933474128827877,
      "eval_f1": 0.41538461538461535,
      "eval_loss": 0.3068830370903015,
      "eval_precision": 0.4576271186440678,
      "eval_recall": 0.38028169014084506,
      "eval_runtime": 0.1247,
      "eval_samples_per_second": 730.008,
      "step": 160
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8912354804646251,
      "eval_f1": 0.48135593220338985,
      "eval_loss": 0.330695241689682,
      "eval_precision": 0.46405228758169936,
      "eval_recall": 0.5,
      "eval_runtime": 0.1127,
      "eval_samples_per_second": 807.78,
      "step": 192
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.895987328405491,
      "eval_f1": 0.4470588235294118,
      "eval_loss": 0.3800097107887268,
      "eval_precision": 0.504424778761062,
      "eval_recall": 0.4014084507042254,
      "eval_runtime": 0.1125,
      "eval_samples_per_second": 808.798,
      "step": 224
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.899155227032735,
      "eval_f1": 0.49295774647887325,
      "eval_loss": 0.4225572347640991,
      "eval_precision": 0.49295774647887325,
      "eval_recall": 0.49295774647887325,
      "eval_runtime": 0.1126,
      "eval_samples_per_second": 808.356,
      "step": 256
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8922914466737064,
      "eval_f1": 0.4901960784313726,
      "eval_loss": 0.4346790611743927,
      "eval_precision": 0.4573170731707317,
      "eval_recall": 0.528169014084507,
      "eval_runtime": 0.1123,
      "eval_samples_per_second": 810.599,
      "step": 288
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8870116156282999,
      "eval_f1": 0.47647058823529415,
      "eval_loss": 0.48350322246551514,
      "eval_precision": 0.4090909090909091,
      "eval_recall": 0.5704225352112676,
      "eval_runtime": 0.1129,
      "eval_samples_per_second": 805.916,
      "step": 320
    },
    {
      "epoch": 10.0,
      "step": 320,
      "total_flos": 201896658999468.0,
      "train_runtime": 25.0952,
      "train_samples_per_second": 12.751
    }
  ],
  "max_steps": 320,
  "num_train_epochs": 10,
  "total_flos": 201896658999468.0,
  "trial_name": null,
  "trial_params": null
}