|
--- |
|
library_name: transformers |
|
base_model: openai/clip-vit-large-patch14-336 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: clip-finetuned-csu-p14-336-e4l58-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-e4l58-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: 0.8656 |
|
|
|
## 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-08 |
|
- 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: 4.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 0.3758 | 0.0921 | 500 | 1.4185 | |
|
| 0.4103 | 0.1842 | 1000 | 1.3501 | |
|
| 0.433 | 0.2763 | 1500 | 1.2885 | |
|
| 0.3424 | 0.3685 | 2000 | 1.2391 | |
|
| 0.3645 | 0.4606 | 2500 | 1.1902 | |
|
| 0.3172 | 0.5527 | 3000 | 1.1506 | |
|
| 0.2751 | 0.6448 | 3500 | 1.1169 | |
|
| 0.2919 | 0.7369 | 4000 | 1.0921 | |
|
| 0.2583 | 0.8290 | 4500 | 1.0721 | |
|
| 0.2679 | 0.9211 | 5000 | 1.0519 | |
|
| 0.2472 | 1.0133 | 5500 | 1.0356 | |
|
| 0.26 | 1.1054 | 6000 | 1.0177 | |
|
| 0.2153 | 1.1975 | 6500 | 1.0045 | |
|
| 0.1791 | 1.2896 | 7000 | 0.9927 | |
|
| 0.2082 | 1.3817 | 7500 | 0.9804 | |
|
| 0.196 | 1.4738 | 8000 | 0.9712 | |
|
| 0.1946 | 1.5660 | 8500 | 0.9621 | |
|
| 0.2422 | 1.6581 | 9000 | 0.9537 | |
|
| 0.2106 | 1.7502 | 9500 | 0.9458 | |
|
| 0.1801 | 1.8423 | 10000 | 0.9393 | |
|
| 0.2117 | 1.9344 | 10500 | 0.9308 | |
|
| 0.2061 | 2.0265 | 11000 | 0.9237 | |
|
| 0.1878 | 2.1186 | 11500 | 0.9167 | |
|
| 0.1655 | 2.2108 | 12000 | 0.9109 | |
|
| 0.1946 | 2.3029 | 12500 | 0.9071 | |
|
| 0.1882 | 2.3950 | 13000 | 0.9021 | |
|
| 0.1871 | 2.4871 | 13500 | 0.8960 | |
|
| 0.1419 | 2.5792 | 14000 | 0.8913 | |
|
| 0.1431 | 2.6713 | 14500 | 0.8879 | |
|
| 0.1811 | 2.7634 | 15000 | 0.8848 | |
|
| 0.1694 | 2.8556 | 15500 | 0.8827 | |
|
| 0.1718 | 2.9477 | 16000 | 0.8798 | |
|
| 0.153 | 3.0398 | 16500 | 0.8777 | |
|
| 0.1715 | 3.1319 | 17000 | 0.8759 | |
|
| 0.1558 | 3.2240 | 17500 | 0.8742 | |
|
| 0.1384 | 3.3161 | 18000 | 0.8715 | |
|
| 0.1788 | 3.4083 | 18500 | 0.8695 | |
|
| 0.1668 | 3.5004 | 19000 | 0.8685 | |
|
| 0.1697 | 3.5925 | 19500 | 0.8674 | |
|
| 0.1764 | 3.6846 | 20000 | 0.8666 | |
|
| 0.1417 | 3.7767 | 20500 | 0.8660 | |
|
| 0.1556 | 3.8688 | 21000 | 0.8657 | |
|
| 0.1605 | 3.9609 | 21500 | 0.8656 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.0.dev0 |
|
- Pytorch 1.12.1 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
