metadata
license: mit
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-it
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.it
split: validation
args: PAN-X.it
metrics:
- name: F1
type: f1
value: 0.835038886614818
xlm-roberta-base-finetuned-panx-it
This model is a fine-tuned version of xlm-roberta-base on the xtreme dataset. It achieves the following results on the evaluation set:
- Loss: 0.2401
- F1: 0.8350
Model description
More information needed
Intended uses & limitations
This is a simple test from the O'Reilly's book "Natural Language Processing with Transformers". Not to use for anything but testing purposes.
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- 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 | F1 |
---|---|---|---|---|
0.8197 | 1.0 | 70 | 0.3529 | 0.7242 |
0.2844 | 2.0 | 140 | 0.2484 | 0.8016 |
0.1861 | 3.0 | 210 | 0.2401 | 0.8350 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3