metadata
library_name: transformers
base_model: openai/clip-vit-base-patch16
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: clip-vit-base-patch16-finetuned-openai-clip-vit-base-patch16-emnist-letter
results: []
clip-vit-base-patch16-finetuned-openai-clip-vit-base-patch16-emnist-letter
This model is a fine-tuned version of openai/clip-vit-base-patch16 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1460
- Accuracy: 0.9468
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- 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 |
|---|---|---|---|---|
| 1.0535 | 0.9994 | 877 | 0.3616 | 0.8803 |
| 0.9258 | 2.0 | 1755 | 0.2692 | 0.9015 |
| 0.7331 | 2.9994 | 2632 | 0.2283 | 0.9207 |
| 0.7137 | 4.0 | 3510 | 0.1815 | 0.9353 |
| 0.6585 | 4.9994 | 4387 | 0.1889 | 0.9324 |
| 0.6366 | 6.0 | 5265 | 0.1688 | 0.9376 |
| 0.6284 | 6.9994 | 6142 | 0.1565 | 0.9424 |
| 0.5834 | 8.0 | 7020 | 0.1541 | 0.9433 |
| 0.5159 | 8.9994 | 7897 | 0.1425 | 0.9485 |
| 0.5233 | 9.9943 | 8770 | 0.1460 | 0.9468 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1