---
library_name: transformers
base_model: openai/clip-vit-large-patch14-336
tags:
- generated_from_trainer
model-index:
- name: clip-finetuned-csu-p14-336-e3l57-l
  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-finetuned-csu-p14-336-e3l57-l

This model is a fine-tuned version of [openai/clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5312

## 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-07
- train_batch_size: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 0.2708        | 0.0921 | 500   | 1.0631          |
| 0.251         | 0.1842 | 1000  | 0.9428          |
| 0.235         | 0.2763 | 1500  | 0.8717          |
| 0.1529        | 0.3685 | 2000  | 0.8318          |
| 0.1781        | 0.4606 | 2500  | 0.7549          |
| 0.1681        | 0.5527 | 3000  | 0.7218          |
| 0.1064        | 0.6448 | 3500  | 0.7048          |
| 0.1357        | 0.7369 | 4000  | 0.6962          |
| 0.1098        | 0.8290 | 4500  | 0.6778          |
| 0.1142        | 0.9211 | 5000  | 0.6657          |
| 0.1113        | 1.0133 | 5500  | 0.6431          |
| 0.0572        | 1.1054 | 6000  | 0.6367          |
| 0.0746        | 1.1975 | 6500  | 0.6261          |
| 0.0494        | 1.2896 | 7000  | 0.6245          |
| 0.0788        | 1.3817 | 7500  | 0.6120          |
| 0.0808        | 1.4738 | 8000  | 0.6011          |
| 0.0536        | 1.5660 | 8500  | 0.5893          |
| 0.0869        | 1.6581 | 9000  | 0.5916          |
| 0.0752        | 1.7502 | 9500  | 0.5707          |
| 0.0577        | 1.8423 | 10000 | 0.5678          |
| 0.0891        | 1.9344 | 10500 | 0.5631          |
| 0.0559        | 2.0265 | 11000 | 0.5548          |
| 0.0385        | 2.1186 | 11500 | 0.5536          |
| 0.0185        | 2.2108 | 12000 | 0.5519          |
| 0.0642        | 2.3029 | 12500 | 0.5505          |
| 0.0456        | 2.3950 | 13000 | 0.5444          |
| 0.0476        | 2.4871 | 13500 | 0.5395          |
| 0.027         | 2.5792 | 14000 | 0.5361          |
| 0.042         | 2.6713 | 14500 | 0.5356          |
| 0.0469        | 2.7634 | 15000 | 0.5343          |
| 0.0438        | 2.8556 | 15500 | 0.5332          |
| 0.0481        | 2.9477 | 16000 | 0.5312          |


### Framework versions

- Transformers 4.45.0.dev0
- Pytorch 1.12.1
- Datasets 2.21.0
- Tokenizers 0.19.1