metadata
base_model: FacebookAI/xlm-roberta-large
library_name: peft
license: mit
metrics:
- precision
- recall
- f1
- accuracy
tags:
- generated_from_trainer
model-index:
- name: xlm-roberta-large-finetuned-ner
results: []
xlm-roberta-large-finetuned-ner
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1297
- Precision: 0.9233
- Recall: 0.9608
- F1: 0.9416
- Accuracy: 0.9764
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2578 | 1.0 | 1167 | 0.1724 | 0.8145 | 0.8758 | 0.8440 | 0.9436 |
| 0.1792 | 2.0 | 2334 | 0.1305 | 0.8636 | 0.9089 | 0.8857 | 0.9603 |
| 0.1224 | 3.0 | 3501 | 0.1390 | 0.8714 | 0.9398 | 0.9043 | 0.9617 |
| 0.0894 | 4.0 | 4668 | 0.1201 | 0.8856 | 0.9444 | 0.9140 | 0.9646 |
| 0.0731 | 5.0 | 5835 | 0.1264 | 0.8848 | 0.9497 | 0.9161 | 0.9696 |
| 0.0597 | 6.0 | 7002 | 0.1247 | 0.9231 | 0.9516 | 0.9371 | 0.9751 |
| 0.044 | 7.0 | 8169 | 0.1141 | 0.9177 | 0.9468 | 0.9320 | 0.9749 |
| 0.0373 | 8.0 | 9336 | 0.1235 | 0.9126 | 0.9597 | 0.9355 | 0.9739 |
| 0.024 | 9.0 | 10503 | 0.1286 | 0.9226 | 0.9578 | 0.9399 | 0.9762 |
| 0.0209 | 10.0 | 11670 | 0.1297 | 0.9233 | 0.9608 | 0.9416 | 0.9764 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1