---
base_model: OFA-Sys/chinese-clip-vit-base-patch16
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: aoi_clip_high_resolution
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/shark_meow_team/huggingface/runs/p4n09c36)
# aoi_clip_high_resolution

This model is a fine-tuned version of [OFA-Sys/chinese-clip-vit-base-patch16](https://huggingface.co/OFA-Sys/chinese-clip-vit-base-patch16) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.7487
- Accuracy: 0.0334

## 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: 1e-05
- train_batch_size: 40
- eval_batch_size: 40
- seed: 42
- gradient_accumulation_steps: 5
- total_train_batch_size: 200
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss | Accuracy |
|:-------------:|:-------:|:-----:|:---------------:|:--------:|
| 2.4298        | 5.9923  | 1866  | 3.7282          | 0.0434   |
| 2.246         | 11.9846 | 3732  | 3.9666          | 0.0379   |
| 2.1293        | 17.9769 | 5598  | 4.1019          | 0.0360   |
| 2.0539        | 23.9692 | 7464  | 4.2821          | 0.0352   |
| 2.0135        | 29.9615 | 9330  | 4.3318          | 0.0345   |
| 1.9879        | 35.9538 | 11196 | 4.3700          | 0.0341   |
| 1.9648        | 41.9461 | 13062 | 4.4619          | 0.0341   |
| 1.9495        | 47.9383 | 14928 | 4.5999          | 0.0341   |
| 1.9391        | 53.9306 | 16794 | 4.6806          | 0.0339   |
| 1.9372        | 59.9229 | 18660 | 4.7487          | 0.0336   |


### Framework versions

- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1