metadata
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- biobert_json
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-finetuned-ner
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: 0.937991068905093
- name: Recall
type: recall
value: 0.9717163436200738
- name: F1
type: f1
value: 0.9545559134836631
- name: Accuracy
type: accuracy
value: 0.9784621223416512
xlm-roberta-finetuned-ner
This model is a fine-tuned version of xlm-roberta-base on the biobert_json dataset. It achieves the following results on the evaluation set:
- Loss: 0.0853
- Precision: 0.9380
- Recall: 0.9717
- F1: 0.9546
- Accuracy: 0.9785
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 306 | 0.1343 | 0.9035 | 0.9289 | 0.9160 | 0.9646 |
0.4365 | 2.0 | 612 | 0.0985 | 0.9254 | 0.9662 | 0.9453 | 0.9746 |
0.4365 | 3.0 | 918 | 0.0833 | 0.9413 | 0.9684 | 0.9547 | 0.9788 |
0.0949 | 4.0 | 1224 | 0.0853 | 0.9380 | 0.9717 | 0.9546 | 0.9785 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3