metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-de-1
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.de
split: validation
args: PAN-X.de
metrics:
- name: F1
type: f1
value: 0.8709714026327735
xlm-roberta-base-finetuned-panx-de-1
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: 0.1707
- F1: 0.8710
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: 5e-05
- train_batch_size: 96
- eval_batch_size: 96
- 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 | F1 |
|---|---|---|---|---|
| No log | 1.0 | 132 | 0.1593 | 0.8122 |
| No log | 2.0 | 264 | 0.1484 | 0.8427 |
| No log | 3.0 | 396 | 0.1399 | 0.8508 |
| 0.1703 | 4.0 | 528 | 0.1395 | 0.8560 |
| 0.1703 | 5.0 | 660 | 0.1409 | 0.8562 |
| 0.1703 | 6.0 | 792 | 0.1523 | 0.8648 |
| 0.1703 | 7.0 | 924 | 0.1554 | 0.8660 |
| 0.0448 | 8.0 | 1056 | 0.1633 | 0.8681 |
| 0.0448 | 9.0 | 1188 | 0.1664 | 0.8678 |
| 0.0448 | 10.0 | 1320 | 0.1707 | 0.8710 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2