Text Classification
Transformers
PyTorch
TensorBoard
data2vec-text
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("mrm8488/data2vec-text-base-finetuned-mnli")
model = AutoModelForSequenceClassification.from_pretrained("mrm8488/data2vec-text-base-finetuned-mnli")Quick Links
data2vec-text-base-finetuned-mnli
This model is a fine-tuned version of facebook/data2vec-text-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5521
- Accuracy: 0.7862
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.099 | 1.0 | 24544 | 1.0987 | 0.3182 |
| 1.0993 | 2.0 | 49088 | 1.0979 | 0.3545 |
| 0.7481 | 3.0 | 73632 | 0.7197 | 0.7046 |
| 0.5671 | 4.0 | 98176 | 0.5862 | 0.7728 |
| 0.5505 | 5.0 | 122720 | 0.5521 | 0.7862 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 7
Dataset used to train mrm8488/data2vec-text-base-finetuned-mnli
Evaluation results
- Accuracy on glueself-reported0.786
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mrm8488/data2vec-text-base-finetuned-mnli")