<!-- 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. -->
10E-affecthq-fer-balanced-w0.1-jitter-jiggle
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0926
- Accuracy: 0.6094
- Precision: 0.5984
- Recall: 0.6094
- F1: 0.5985
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: 32
- seed: 17
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.7434 | 1.0 | 133 | 1.7100 | 0.3920 | 0.5334 | 0.3920 | 0.2829 |
| 1.3586 | 2.0 | 266 | 1.3433 | 0.5115 | 0.4915 | 0.5115 | 0.4535 |
| 1.2118 | 3.0 | 399 | 1.2464 | 0.5457 | 0.5288 | 0.5457 | 0.5084 |
| 1.1762 | 4.0 | 532 | 1.1858 | 0.5724 | 0.5615 | 0.5724 | 0.5435 |
| 1.1222 | 5.0 | 665 | 1.1502 | 0.5850 | 0.5704 | 0.5850 | 0.5601 |
| 1.074 | 6.0 | 798 | 1.1300 | 0.5963 | 0.5841 | 0.5963 | 0.5800 |
| 1.0299 | 7.0 | 931 | 1.1119 | 0.6014 | 0.5922 | 0.6014 | 0.5880 |
| 0.9919 | 8.0 | 1064 | 1.1001 | 0.6028 | 0.5907 | 0.6028 | 0.5890 |
| 0.9761 | 9.0 | 1197 | 1.0943 | 0.6075 | 0.5966 | 0.6075 | 0.5950 |
| 0.9769 | 10.0 | 1330 | 1.0926 | 0.6094 | 0.5984 | 0.6094 | 0.5985 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
