# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("lijingxin/xlm-roberta-base-finetuned-panx-en")
model = AutoModelForTokenClassification.from_pretrained("lijingxin/xlm-roberta-base-finetuned-panx-en", device_map="auto")Quick Links
xlm-roberta-base-finetuned-panx-en
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: 0.3814
- F1: 0.7043
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: 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 |
|---|---|---|---|---|
| 1.1472 | 1.0 | 50 | 0.5820 | 0.4600 |
| 0.5186 | 2.0 | 100 | 0.4105 | 0.6645 |
| 0.3599 | 3.0 | 150 | 0.3814 | 0.7043 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.9.1
- Datasets 1.16.1
- Tokenizers 0.10.3
- Downloads last month
- 1
Dataset used to train lijingxin/xlm-roberta-base-finetuned-panx-en
Evaluation results
- F1 on xtremeself-reported0.704
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="lijingxin/xlm-roberta-base-finetuned-panx-en")