precision    recall  f1-score   support

medical          0.87      0.81      0.84        83
environmental    0.77      0.91      0.84        93
administration   0.58      0.32      0.41        22
communication    0.85      0.82      0.84        50
condition        0.42      0.52      0.46        29
treatment        0.90      0.78      0.83        68
food             0.92      0.94      0.93        36
clean            0.65      0.83      0.73        18
bathroom         0.64      0.64      0.64        14
discharge        0.83      0.83      0.83        24
wait             0.96      1.00      0.98        24
financial        0.44      1.00      0.62         4
extra_nice       0.20      0.13      0.16        23
rude             1.00      0.64      0.78        11
nurse            0.92      0.98      0.95       110
doctor           0.96      0.84      0.90        57

micro avg        0.81      0.81      0.81       666
macro avg        0.75      0.75      0.73       666
weighted avg     0.82      0.81      0.81       666
samples avg      0.64      0.64      0.62       666

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("joniponi/multilabel_inpatient_comments_16labels")
model = AutoModel.from_pretrained("joniponi/multilabel_inpatient_comments_16labels")