Token Classification
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("Osquery/1a5e2b8e")
model = AutoModelForTokenClassification.from_pretrained("Osquery/1a5e2b8e")Quick Links
1a5e2b8e
This model is a fine-tuned version of xlm-roberta-base on the udpos28 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3219
- Precision: 0.8943
- Recall: 0.8577
- F1: 0.8681
- Accuracy: 0.9471
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0423 | 7.58 | 1000 | 0.3219 | 0.8943 | 0.8577 | 0.8681 | 0.9471 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 3
Model tree for Osquery/1a5e2b8e
Base model
FacebookAI/xlm-roberta-baseEvaluation results
- Precision on udpos28validation set self-reported0.894
- Recall on udpos28validation set self-reported0.858
- F1 on udpos28validation set self-reported0.868
- Accuracy on udpos28validation set self-reported0.947
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Osquery/1a5e2b8e")