<!-- 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. -->
my_awesome_stocks_model
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.6460
- Loss: 0.8170
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: 0.05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Accuracy | Validation Loss |
---|---|---|---|---|
0.8669 | 1.0 | 3291 | 0.6353 | 0.8775 |
0.8695 | 2.0 | 6582 | 0.6405 | 0.8452 |
0.8281 | 3.0 | 9873 | 0.6427 | 0.8369 |
0.8442 | 4.0 | 13165 | 0.6436 | 0.8346 |
0.837 | 5.0 | 16456 | 0.6419 | 0.8377 |
0.7919 | 6.0 | 19747 | 0.6440 | 0.8274 |
0.8089 | 7.0 | 23038 | 0.6431 | 0.8254 |
0.8421 | 8.0 | 26330 | 0.6449 | 0.8210 |
0.8106 | 9.0 | 29621 | 0.6474 | 0.8184 |
0.8044 | 10.0 | 32910 | 0.6460 | 0.8170 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0
- Datasets 2.14.5
- Tokenizers 0.14.1