metadata
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: DebertaV2-Base-100M_fwedu-A__cola
results: []
DebertaV2-Base-100M_fwedu-A__cola
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9455
- Accuracy: 0.6667
- F1: 0.7825
- Mcc: 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: 3e-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: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Mcc |
|---|---|---|---|---|---|---|
| 0.6091 | 1.0 | 535 | 0.6046 | 0.6992 | 0.8230 | 0.0 |
| 0.5609 | 2.0 | 1070 | 0.6194 | 0.6686 | 0.7835 | 0.1064 |
| 0.4563 | 3.0 | 1605 | 0.7374 | 0.6686 | 0.7835 | 0.1064 |
| 0.3459 | 4.0 | 2140 | 0.9455 | 0.6667 | 0.7825 | 0.0990 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1