test_predictions_sample.json

{
  "accuracy": 0.8110831234256927,
  "precision": 0.8290818892194408,
  "recall": 0.8110831234256927,
  "f1": 0.8133497816616648,
  "total_training_steps": 500,
  "early_stopped": false,
  "label_map": {
    "0": "contradiction",
    "1": "entailment",
    "2": "neutral"
  },
  "samples": [
    {
      "prediction": "entailment",
      "ground_truth": "entailment"
    },
    {
      "prediction": "entailment",
      "ground_truth": "entailment"
    },
    {
      "prediction": "neutral",
      "ground_truth": "entailment"
    },
    {
      "prediction": "contradiction",
      "ground_truth": "contradiction"
    },
    {
      "prediction": "neutral",
      "ground_truth": "neutral"
    },
    {
      "prediction": "entailment",
      "ground_truth": "entailment"
    },
    {
      "prediction": "contradiction",
      "ground_truth": "contradiction"
    },
    {
      "prediction": "entailment",
      "ground_truth": "entailment"
    },
    {
      "prediction": "neutral",
      "ground_truth": "neutral"
    },
    {
      "prediction": "entailment",
      "ground_truth": "neutral"
    }
  ]
}