metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta-v3-base__sst2__all-train
results: []
deberta-v3-base__sst2__all-train
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6964
- Accuracy: 0.49
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: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 7 | 0.6964 | 0.49 |
| No log | 2.0 | 14 | 0.7010 | 0.49 |
| No log | 3.0 | 21 | 0.7031 | 0.49 |
| No log | 4.0 | 28 | 0.7054 | 0.49 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2
- Tokenizers 0.10.3