metadata
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-base-finetuned-ner
results: []
xlm-roberta-base-finetuned-ner
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0666
- Precision: 0.9293
- Recall: 0.9362
- F1: 0.9327
- Accuracy: 0.9819
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 |
|---|---|---|---|---|---|---|---|
| 0.0724 | 1.0 | 54249 | 0.0649 | 0.9129 | 0.9185 | 0.9157 | 0.9784 |
| 0.0593 | 2.0 | 108498 | 0.0608 | 0.9292 | 0.9250 | 0.9271 | 0.9802 |
| 0.0483 | 3.0 | 162747 | 0.0595 | 0.9216 | 0.9324 | 0.9270 | 0.9812 |
| 0.041 | 4.0 | 216996 | 0.0627 | 0.9183 | 0.9361 | 0.9271 | 0.9817 |
| 0.0345 | 5.0 | 271245 | 0.0666 | 0.9293 | 0.9362 | 0.9327 | 0.9819 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1