metadata
library_name: transformers
base_model: openai/clip-vit-large-patch14
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: >-
clip-vit-large-patch14-finetuned-openai-clip-vit-large-patch14-emnist-letter
results: []
clip-vit-large-patch14-finetuned-openai-clip-vit-large-patch14-emnist-letter
This model is a fine-tuned version of openai/clip-vit-large-patch14 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1347
- Accuracy: 0.9527
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 |
|---|---|---|---|---|
| 0.917 | 0.9994 | 877 | 0.3145 | 0.8863 |
| 0.7921 | 2.0 | 1755 | 0.2430 | 0.9152 |
| 0.7534 | 2.9994 | 2632 | 0.1897 | 0.9295 |
| 0.6294 | 4.0 | 3510 | 0.1720 | 0.9373 |
| 0.6219 | 4.9994 | 4387 | 0.1750 | 0.9390 |
| 0.5749 | 6.0 | 5265 | 0.1486 | 0.9486 |
| 0.5308 | 6.9994 | 6142 | 0.1431 | 0.9494 |
| 0.5505 | 8.0 | 7020 | 0.1429 | 0.9499 |
| 0.4938 | 8.9994 | 7897 | 0.1425 | 0.9496 |
| 0.5342 | 9.9943 | 8770 | 0.1347 | 0.9527 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1