|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
base_model: dandelin/vilt-b32-mlm |
|
model-index: |
|
- name: vilt-b32-mlm-mami |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# vilt-b32-mlm-mami |
|
|
|
This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on the MAMI dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5796 |
|
- F1: 0.7899 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.6898 | 0.48 | 100 | 0.6631 | 0.6076 | |
|
| 0.5824 | 0.96 | 200 | 0.5055 | 0.7545 | |
|
| 0.4306 | 1.44 | 300 | 0.4586 | 0.7861 | |
|
| 0.4207 | 1.91 | 400 | 0.4439 | 0.7927 | |
|
| 0.3055 | 2.39 | 500 | 0.4912 | 0.7949 | |
|
| 0.2582 | 2.87 | 600 | 0.4921 | 0.7873 | |
|
| 0.1875 | 3.35 | 700 | 0.5796 | 0.7899 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
