---
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: 0.2831

## 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: 256
- 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 |
|:-------------:|:------:|:-----:|:---------------:|
| 0.3448        | 0.0921 | 500   | 1.0839          |
| 0.2708        | 0.1842 | 1000  | 0.8948          |
| 0.177         | 0.2763 | 1500  | 0.8396          |
| 0.1831        | 0.3685 | 2000  | 0.7721          |
| 0.2038        | 0.4606 | 2500  | 0.7446          |
| 0.1309        | 0.5527 | 3000  | 0.7235          |
| 0.1431        | 0.6448 | 3500  | 0.6691          |
| 0.1411        | 0.7369 | 4000  | 0.6437          |
| 0.0849        | 0.8290 | 4500  | 0.4805          |
| 0.1026        | 0.9211 | 5000  | 0.4800          |
| 0.1201        | 1.0133 | 5500  | 0.4810          |
| 0.0757        | 1.1054 | 6000  | 0.4692          |
| 0.0696        | 1.1975 | 6500  | 0.4764          |
| 0.0911        | 1.2896 | 7000  | 0.4601          |
| 0.0806        | 1.3817 | 7500  | 0.4590          |
| 0.088         | 1.4738 | 8000  | 0.4654          |
| 0.0878        | 1.5660 | 8500  | 0.4769          |
| 0.0369        | 1.6581 | 9000  | 0.4684          |
| 0.1034        | 1.7502 | 9500  | 0.4716          |
| 0.0852        | 1.8423 | 10000 | 0.4720          |
| 0.0493        | 1.9344 | 10500 | 0.4714          |
| 0.0603        | 2.0265 | 11000 | 0.4661          |
| 0.0547        | 2.1186 | 11500 | 0.4669          |
| 0.0793        | 2.2108 | 12000 | 0.4664          |
| 0.0415        | 2.3024 | 12500 | 0.2888          |
| 0.0565        | 2.3945 | 13000 | 0.2910          |
| 0.0629        | 2.4866 | 13500 | 0.2889          |
| 0.0584        | 2.5787 | 14000 | 0.2874          |
| 0.0582        | 2.6708 | 14500 | 0.2863          |
| 0.052         | 2.7629 | 15000 | 0.2846          |
| 0.0402        | 2.8550 | 15500 | 0.2835          |
| 0.0518        | 2.9471 | 16000 | 0.2831          |


### Framework versions

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