metadata

library_name: transformers
base_model: raulgdp/xml-roberta-large-finetuned-ner
tags:
  - generated_from_trainer
datasets:
  - biobert_json
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: NER-finetuning-XMLR-CM-V1
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: biobert_json
          type: biobert_json
          config: Biobert_json
          split: validation
          args: Biobert_json
        metrics:
          - name: Precision
            type: precision
            value: 0.9336523819882532
          - name: Recall
            type: recall
            value: 0.9595349877040018
          - name: F1
            type: f1
            value: 0.9464167585446528
          - name: Accuracy
            type: accuracy
            value: 0.9819591471596839

NER-finetuning-XMLR-CM-V1

This model is a fine-tuned version of raulgdp/xml-roberta-large-finetuned-ner on the biobert_json dataset. It achieves the following results on the evaluation set:

Loss: 0.0849
Precision: 0.9337
Recall: 0.9595
F1: 0.9464
Accuracy: 0.9820

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.2697	1.0	612	0.0995	0.9022	0.9392	0.9203	0.9726
0.0954	2.0	1224	0.0909	0.9171	0.9586	0.9374	0.9778
0.0661	3.0	1836	0.0789	0.9337	0.9581	0.9457	0.9816
0.0533	4.0	2448	0.0853	0.9317	0.9594	0.9454	0.9811
0.035	5.0	3060	0.0849	0.9337	0.9595	0.9464	0.9820

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.1.0
Tokenizers 0.19.1