trainer_state.json

{
  "best_metric": 0.6666666666666667,
  "best_model_checkpoint": "NLP/trained_models/256_5e-06_90/checkpoint-140",
  "epoch": 70.0,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5647058823529412,
      "eval_f1": 0.0,
      "eval_loss": 0.6881718635559082,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 2.0353,
      "eval_samples_per_second": 41.763,
      "eval_steps_per_second": 0.491,
      "step": 10
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.5647058823529412,
      "eval_f1": 0.0,
      "eval_loss": 0.6862292885780334,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 3.3692,
      "eval_samples_per_second": 25.229,
      "eval_steps_per_second": 0.297,
      "step": 20
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.5764705882352941,
      "eval_f1": 0.1,
      "eval_loss": 0.6834429502487183,
      "eval_precision": 0.6666666666666666,
      "eval_recall": 0.05405405405405406,
      "eval_runtime": 1.8134,
      "eval_samples_per_second": 46.873,
      "eval_steps_per_second": 0.551,
      "step": 30
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.6235294117647059,
      "eval_f1": 0.3846153846153846,
      "eval_loss": 0.6755977272987366,
      "eval_precision": 0.6666666666666666,
      "eval_recall": 0.2702702702702703,
      "eval_runtime": 2.1098,
      "eval_samples_per_second": 40.288,
      "eval_steps_per_second": 0.474,
      "step": 40
    },
    {
      "epoch": 25.0,
      "eval_accuracy": 0.611764705882353,
      "eval_f1": 0.47619047619047616,
      "eval_loss": 0.6568019390106201,
      "eval_precision": 0.5769230769230769,
      "eval_recall": 0.40540540540540543,
      "eval_runtime": 2.4655,
      "eval_samples_per_second": 34.475,
      "eval_steps_per_second": 0.406,
      "step": 50
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.6588235294117647,
      "eval_f1": 0.5797101449275363,
      "eval_loss": 0.6438259482383728,
      "eval_precision": 0.625,
      "eval_recall": 0.5405405405405406,
      "eval_runtime": 1.8313,
      "eval_samples_per_second": 46.416,
      "eval_steps_per_second": 0.546,
      "step": 60
    },
    {
      "epoch": 35.0,
      "eval_accuracy": 0.6588235294117647,
      "eval_f1": 0.6133333333333333,
      "eval_loss": 0.6628918647766113,
      "eval_precision": 0.6052631578947368,
      "eval_recall": 0.6216216216216216,
      "eval_runtime": 1.8199,
      "eval_samples_per_second": 46.706,
      "eval_steps_per_second": 0.549,
      "step": 70
    },
    {
      "epoch": 40.0,
      "eval_accuracy": 0.6588235294117647,
      "eval_f1": 0.6133333333333333,
      "eval_loss": 0.6717644333839417,
      "eval_precision": 0.6052631578947368,
      "eval_recall": 0.6216216216216216,
      "eval_runtime": 6.0426,
      "eval_samples_per_second": 14.067,
      "eval_steps_per_second": 0.165,
      "step": 80
    },
    {
      "epoch": 45.0,
      "eval_accuracy": 0.6823529411764706,
      "eval_f1": 0.6666666666666666,
      "eval_loss": 0.7056936025619507,
      "eval_precision": 0.6136363636363636,
      "eval_recall": 0.7297297297297297,
      "eval_runtime": 4.3129,
      "eval_samples_per_second": 19.708,
      "eval_steps_per_second": 0.232,
      "step": 90
    },
    {
      "epoch": 50.0,
      "eval_accuracy": 0.6705882352941176,
      "eval_f1": 0.6410256410256411,
      "eval_loss": 0.7082163095474243,
      "eval_precision": 0.6097560975609756,
      "eval_recall": 0.6756756756756757,
      "eval_runtime": 2.7778,
      "eval_samples_per_second": 30.6,
      "eval_steps_per_second": 0.36,
      "step": 100
    },
    {
      "epoch": 55.0,
      "eval_accuracy": 0.6705882352941176,
      "eval_f1": 0.6499999999999999,
      "eval_loss": 0.7371630668640137,
      "eval_precision": 0.6046511627906976,
      "eval_recall": 0.7027027027027027,
      "eval_runtime": 2.1835,
      "eval_samples_per_second": 38.928,
      "eval_steps_per_second": 0.458,
      "step": 110
    },
    {
      "epoch": 60.0,
      "eval_accuracy": 0.6823529411764706,
      "eval_f1": 0.6582278481012659,
      "eval_loss": 0.7530251145362854,
      "eval_precision": 0.6190476190476191,
      "eval_recall": 0.7027027027027027,
      "eval_runtime": 2.1705,
      "eval_samples_per_second": 39.161,
      "eval_steps_per_second": 0.461,
      "step": 120
    },
    {
      "epoch": 65.0,
      "eval_accuracy": 0.6823529411764706,
      "eval_f1": 0.6582278481012659,
      "eval_loss": 0.7745981812477112,
      "eval_precision": 0.6190476190476191,
      "eval_recall": 0.7027027027027027,
      "eval_runtime": 2.8635,
      "eval_samples_per_second": 29.684,
      "eval_steps_per_second": 0.349,
      "step": 130
    },
    {
      "epoch": 70.0,
      "eval_accuracy": 0.6941176470588235,
      "eval_f1": 0.6666666666666667,
      "eval_loss": 0.7838086485862732,
      "eval_precision": 0.6341463414634146,
      "eval_recall": 0.7027027027027027,
      "eval_runtime": 1.9223,
      "eval_samples_per_second": 44.219,
      "eval_steps_per_second": 0.52,
      "step": 140
    }
  ],
  "max_steps": 180,
  "num_train_epochs": 90,
  "total_flos": 116488518693120.0,
  "trial_name": null,
  "trial_params": null
}