eval/results/avgs/llama-2_avg_scores.json

{
    "gpt_score": {
        "precision": 0.6980871624324851,
        "recall": 0.7127254131153953,
        "f1_score": 0.704834289367951
    },
    "pubmedbert_score": {
        "precision": 0.7064137150843938,
        "recall": 0.7759113654494285,
        "f1_score": 0.7389454205873335
    },
    "rouge": {
        "rouge1": 0.3659305177603431,
        "rouge2": 0.020672486922408015,
        "rougeL": 0.36848071670658417,
        "rougeLsum": 0.36707879084117795
    },
    "bert_score": {
        "precision": 0.7786839826146094,
        "recall": 0.8027321054412081,
        "f1_score": 0.7896073062115788
    },
    "bleu": {
        "bleu": 0.0,
        "precisions": [
            0.0018199233716475096,
            0.0002824858757062147,
            0.0001633986928104575,
            0.0
        ],
        "brevity_penalty": 0.008333333333333333,
        "length_ratio": 0.015425531914893617,
        "translation_length": 0.725,
        "reference_length": 0.39166666666666666
    },
    "meteor": 0.0019263250791459903,
    "mauve": {}
}