Text Classification
Transformers
PyTorch
TensorBoard
canine
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("vicl/canine-c-finetuned-cola")
model = AutoModelForSequenceClassification.from_pretrained("vicl/canine-c-finetuned-cola", device_map="auto")Quick Links
canine-c-finetuned-cola
This model is a fine-tuned version of google/canine-c on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.6246
- Matthews Correlation: 0.0990
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 | Matthews Correlation |
|---|---|---|---|---|
| 0.6142 | 1.0 | 535 | 0.6268 | 0.0 |
| 0.607 | 2.0 | 1070 | 0.6234 | 0.0 |
| 0.6104 | 3.0 | 1605 | 0.6226 | 0.0 |
| 0.5725 | 4.0 | 2140 | 0.6246 | 0.0990 |
| 0.5426 | 5.0 | 2675 | 0.6866 | 0.0495 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
- Downloads last month
- 21
Dataset used to train vicl/canine-c-finetuned-cola
Evaluation results
- Matthews Correlation on glueself-reported0.099
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="vicl/canine-c-finetuned-cola")