metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-base-ner-silvanus
results: []
xlm-roberta-base-ner-silvanus
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: 0.0885
- Precision: 0.9374
- Recall: 0.9485
- F1: 0.9429
- Accuracy: 0.9756
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: 6
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1123 | 1.0 | 1560 | 0.0853 | 0.9090 | 0.9388 | 0.9237 | 0.9705 |
0.0734 | 2.0 | 3121 | 0.0914 | 0.9303 | 0.9440 | 0.9371 | 0.9741 |
0.0494 | 3.0 | 4680 | 0.0885 | 0.9374 | 0.9485 | 0.9429 | 0.9756 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1