---
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: 0.5308

## 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 |
|:-------------:|:------:|:-----:|:---------------:|
| 0.2705        | 0.0921 | 500   | 1.0681          |
| 0.2545        | 0.1842 | 1000  | 0.9444          |
| 0.234         | 0.2763 | 1500  | 0.8769          |
| 0.1539        | 0.3685 | 2000  | 0.8415          |
| 0.1766        | 0.4606 | 2500  | 0.7660          |
| 0.1679        | 0.5527 | 3000  | 0.7269          |
| 0.1104        | 0.6448 | 3500  | 0.7098          |
| 0.1367        | 0.7369 | 4000  | 0.6969          |
| 0.1129        | 0.8290 | 4500  | 0.6777          |
| 0.1125        | 0.9211 | 5000  | 0.6658          |
| 0.1071        | 1.0133 | 5500  | 0.6465          |
| 0.0553        | 1.1054 | 6000  | 0.6357          |
| 0.0729        | 1.1975 | 6500  | 0.6284          |
| 0.0476        | 1.2896 | 7000  | 0.6260          |
| 0.0756        | 1.3817 | 7500  | 0.6102          |
| 0.0797        | 1.4738 | 8000  | 0.6023          |
| 0.0536        | 1.5660 | 8500  | 0.5879          |
| 0.0784        | 1.6581 | 9000  | 0.5880          |
| 0.0703        | 1.7502 | 9500  | 0.5665          |
| 0.0551        | 1.8423 | 10000 | 0.5671          |
| 0.0852        | 1.9344 | 10500 | 0.5695          |
| 0.0546        | 2.0265 | 11000 | 0.5558          |
| 0.0369        | 2.1186 | 11500 | 0.5533          |
| 0.0205        | 2.2108 | 12000 | 0.5498          |
| 0.0673        | 2.3029 | 12500 | 0.5446          |
| 0.0509        | 2.3950 | 13000 | 0.5434          |
| 0.0447        | 2.4871 | 13500 | 0.5404          |
| 0.0246        | 2.5792 | 14000 | 0.5360          |
| 0.0395        | 2.6713 | 14500 | 0.5335          |
| 0.0436        | 2.7634 | 15000 | 0.5332          |
| 0.0398        | 2.8556 | 15500 | 0.5320          |
| 0.0427        | 2.9477 | 16000 | 0.5308          |


### Framework versions

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