|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
- precision |
|
|
model-index: |
|
|
- name: mvit_v2_rwf-2000 |
|
|
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. --> |
|
|
|
|
|
# mvit_v2_rwf-2000 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3786 |
|
|
- Accuracy: 0.8875 |
|
|
- F1: 0.8873 |
|
|
- Precision: 0.8907 |
|
|
|
|
|
## 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: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- training_steps: 1520 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:| |
|
|
| 0.4242 | 0.125 | 190 | 0.4227 | 0.8375 | 0.8366 | 0.8453 | |
|
|
| 0.3906 | 1.125 | 380 | 0.2933 | 0.9 | 0.8999 | 0.9010 | |
|
|
| 0.3199 | 2.125 | 570 | 0.3034 | 0.9313 | 0.9312 | 0.9313 | |
|
|
| 0.2239 | 3.125 | 760 | 0.3611 | 0.9125 | 0.9124 | 0.9135 | |
|
|
| 0.1747 | 4.125 | 950 | 0.3475 | 0.9313 | 0.9312 | 0.9313 | |
|
|
| 0.1702 | 5.125 | 1140 | 0.3667 | 0.9313 | 0.9312 | 0.9313 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.44.0 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 2.20.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
