metadata
license: apache-2.0
base_model: dandelin/vilt-b32-mlm
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: vilt_finetuned_200
results: []
vilt_finetuned_200
This model is a fine-tuned version of dandelin/vilt-b32-mlm on the None dataset. It achieves the following results on the evaluation set:
- Loss: 21.0818
- Accuracy: 0.02
- F1: 0.02
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 4.1329 | 1.0 | 2678 | 9.9163 | 0.0 | 0.0 |
| 3.7352 | 2.0 | 5356 | 10.4438 | 0.0 | 0.0 |
| 2.1774 | 3.0 | 8034 | 11.5371 | 0.0 | 0.0 |
| 1.1338 | 4.0 | 10712 | 12.9686 | 0.0 | 0.0 |
| 0.6816 | 5.0 | 13390 | 15.4396 | 0.0 | 0.0 |
| 0.3725 | 6.0 | 16068 | 17.1792 | 0.01 | 0.01 |
| 0.1133 | 7.0 | 18746 | 18.8999 | 0.01 | 0.01 |
| 0.0494 | 8.0 | 21424 | 19.9610 | 0.01 | 0.01 |
| 0.0905 | 9.0 | 24102 | 20.6784 | 0.02 | 0.02 |
| 0.0749 | 10.0 | 26780 | 21.0818 | 0.02 | 0.02 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1