|
--- |
|
library_name: transformers |
|
base_model: openai/clip-vit-base-patch32 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: clip-vit-base-patch32-finetuned-openai-clip-vit-base-patch32-emnist-letter |
|
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. --> |
|
|
|
# clip-vit-base-patch32-finetuned-openai-clip-vit-base-patch32-emnist-letter |
|
|
|
This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1524 |
|
- Accuracy: 0.9465 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 1.0859 | 0.9994 | 877 | 0.4055 | 0.8640 | |
|
| 0.927 | 2.0 | 1755 | 0.3652 | 0.8782 | |
|
| 0.83 | 2.9994 | 2632 | 0.2687 | 0.9066 | |
|
| 0.7747 | 4.0 | 3510 | 0.2356 | 0.9189 | |
|
| 0.7545 | 4.9994 | 4387 | 0.2147 | 0.9245 | |
|
| 0.6461 | 6.0 | 5265 | 0.1889 | 0.9320 | |
|
| 0.6457 | 6.9994 | 6142 | 0.1784 | 0.9354 | |
|
| 0.6796 | 8.0 | 7020 | 0.1659 | 0.9412 | |
|
| 0.5502 | 8.9994 | 7897 | 0.1548 | 0.9461 | |
|
| 0.5797 | 9.9943 | 8770 | 0.1524 | 0.9465 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
