metadata
base_model: Fsoft-AIC/videberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ComOM-VIDeBERTa-1
results: []
ComOM-VIDeBERTa-1
This model is a fine-tuned version of Fsoft-AIC/videberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3821
- Accuracy: 0.8270
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 | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 126 | 0.5622 | 0.6899 |
| No log | 2.0 | 252 | 0.4775 | 0.7972 |
| No log | 3.0 | 378 | 0.4007 | 0.8131 |
| 0.512 | 4.0 | 504 | 0.3964 | 0.8171 |
| 0.512 | 5.0 | 630 | 0.3821 | 0.8270 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1