|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: finetuned-fer2013-balanced |
|
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. --> |
|
|
|
# finetuned-fer2013-balanced |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0183 |
|
- Accuracy: 0.6362 |
|
- Precision: 0.6312 |
|
- Recall: 0.6362 |
|
- F1: 0.6310 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 17 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- 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 | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 1.3969 | 1.0 | 267 | 1.3735 | 0.4996 | 0.4776 | 0.4996 | 0.4436 | |
|
| 1.2341 | 2.0 | 534 | 1.2239 | 0.5442 | 0.5430 | 0.5442 | 0.5108 | |
|
| 1.1363 | 3.0 | 801 | 1.1585 | 0.5758 | 0.5715 | 0.5758 | 0.5638 | |
|
| 1.0894 | 4.0 | 1068 | 1.1087 | 0.5912 | 0.5827 | 0.5912 | 0.5706 | |
|
| 1.0666 | 5.0 | 1335 | 1.0655 | 0.6184 | 0.6111 | 0.6184 | 0.6082 | |
|
| 0.9219 | 6.0 | 1602 | 1.0520 | 0.6233 | 0.6153 | 0.6233 | 0.6136 | |
|
| 0.943 | 7.0 | 1869 | 1.0331 | 0.6299 | 0.6238 | 0.6299 | 0.6231 | |
|
| 0.8906 | 8.0 | 2136 | 1.0238 | 0.6318 | 0.6252 | 0.6318 | 0.6239 | |
|
| 0.8854 | 9.0 | 2403 | 1.0196 | 0.6341 | 0.6313 | 0.6341 | 0.6298 | |
|
| 0.8991 | 10.0 | 2670 | 1.0183 | 0.6362 | 0.6312 | 0.6362 | 0.6310 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.0.dev0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
|
