metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta-v3-base-zeroshot-v1.1-none
results: []
deberta-v3-base-zeroshot-v1.1-none
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: 0.1987
- F1 Macro: 0.6760
- F1 Micro: 0.7335
- Accuracy Balanced: 0.7247
- Accuracy: 0.7335
- Precision Macro: 0.6872
- Recall Macro: 0.7247
- Precision Micro: 0.7335
- Recall Micro: 0.7335
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: 32
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Micro | Accuracy Balanced | Accuracy | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2135 | 1.0 | 30790 | 0.3591 | 0.8469 | 0.8620 | 0.8432 | 0.8620 | 0.8511 | 0.8432 | 0.8620 | 0.8620 |
| 0.1573 | 2.0 | 61580 | 0.3712 | 0.8517 | 0.8664 | 0.8478 | 0.8664 | 0.8562 | 0.8478 | 0.8664 | 0.8664 |
| 0.1038 | 3.0 | 92370 | 0.4572 | 0.8569 | 0.8701 | 0.8556 | 0.8701 | 0.8583 | 0.8556 | 0.8701 | 0.8701 |
Framework versions
- Transformers 4.33.3
- Pytorch 1.11.0+cu113
- Datasets 2.14.6
- Tokenizers 0.12.1