metadata
library_name: transformers
base_model: openai/clip-vit-large-patch14-336
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: >-
clip-vit-large-patch14-336-finetuned-openai-clip-vit-large-patch14-336-mnist
results: []
clip-vit-large-patch14-336-finetuned-openai-clip-vit-large-patch14-336-mnist
This model is a fine-tuned version of openai/clip-vit-large-patch14-336 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0173
- Accuracy: 0.9945
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 |
|---|---|---|---|---|
| 0.4739 | 1.0 | 422 | 0.1506 | 0.9578 |
| 0.4608 | 2.0 | 844 | 0.0464 | 0.9857 |
| 0.3125 | 3.0 | 1266 | 0.0406 | 0.9878 |
| 0.3281 | 4.0 | 1688 | 0.0328 | 0.9895 |
| 0.3068 | 5.0 | 2110 | 0.0230 | 0.9933 |
| 0.3187 | 6.0 | 2532 | 0.0254 | 0.9918 |
| 0.2928 | 7.0 | 2954 | 0.0286 | 0.99 |
| 0.2336 | 8.0 | 3376 | 0.0296 | 0.9908 |
| 0.2472 | 9.0 | 3798 | 0.0217 | 0.994 |
| 0.2356 | 10.0 | 4220 | 0.0173 | 0.9945 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1