metadata
license: mit
base_model: microsoft/deberta-v3-xsmall
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: STS-Conventional-Fine-Tuning
results: []
STS-Conventional-Fine-Tuning
This model is a fine-tuned version of microsoft/deberta-v3-xsmall on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7499
- Accuracy: 0.2429
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: 0.03
- train_batch_size: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 180 | 1.7520 | 0.2429 |
| No log | 2.0 | 360 | 1.7483 | 0.2429 |
| 3.3637 | 3.0 | 540 | 1.7498 | 0.2429 |
| 3.3637 | 4.0 | 720 | 1.7525 | 0.2429 |
| 3.3637 | 5.0 | 900 | 1.7499 | 0.2429 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2