|
--- |
|
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: 0.7743 |
|
|
|
## 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: 1.2009578191195431e-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 | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 0.4588 | 0.0921 | 500 | 1.4195 | |
|
| 0.4255 | 0.1842 | 1000 | 1.3417 | |
|
| 0.3724 | 0.2763 | 1500 | 1.2873 | |
|
| 0.3251 | 0.3684 | 2000 | 1.2349 | |
|
| 0.3308 | 0.4605 | 2500 | 1.1945 | |
|
| 0.3017 | 0.5526 | 3000 | 1.1593 | |
|
| 0.2962 | 0.6447 | 3500 | 1.1259 | |
|
| 0.2919 | 0.7368 | 4000 | 1.0954 | |
|
| 0.307 | 0.8289 | 4500 | 1.0729 | |
|
| 0.2764 | 0.9210 | 5000 | 1.0524 | |
|
| 0.2456 | 1.0131 | 5500 | 1.0375 | |
|
| 0.2642 | 1.1052 | 6000 | 1.0233 | |
|
| 0.2066 | 1.1973 | 6500 | 1.0104 | |
|
| 0.2376 | 1.2894 | 7000 | 0.9984 | |
|
| 0.1931 | 1.3815 | 7500 | 0.9887 | |
|
| 0.2163 | 1.4736 | 8000 | 0.9767 | |
|
| 0.1903 | 1.5657 | 8500 | 0.9665 | |
|
| 0.2069 | 1.6578 | 9000 | 0.9572 | |
|
| 0.2093 | 1.7499 | 9500 | 0.9497 | |
|
| 0.2523 | 1.8420 | 10000 | 0.9420 | |
|
| 0.2127 | 1.9341 | 10500 | 0.9329 | |
|
| 0.1968 | 2.0262 | 11000 | 0.9270 | |
|
| 0.1879 | 2.1183 | 11500 | 0.9231 | |
|
| 0.1981 | 2.2104 | 12000 | 0.9184 | |
|
| 0.1964 | 2.3024 | 12500 | 0.9135 | |
|
| 0.1697 | 2.3945 | 13000 | 0.9100 | |
|
| 0.2015 | 2.4866 | 13500 | 0.9052 | |
|
| 0.1827 | 2.5787 | 14000 | 0.9026 | |
|
| 0.1435 | 2.6708 | 14500 | 0.8998 | |
|
| 0.1541 | 2.7629 | 15000 | 0.8963 | |
|
| 0.1716 | 2.8550 | 15500 | 0.8935 | |
|
| 0.2056 | 2.9471 | 16000 | 0.8905 | |
|
| 0.1843 | 3.0392 | 16500 | 0.8875 | |
|
| 0.1611 | 3.1313 | 17000 | 0.8858 | |
|
| 0.1568 | 3.2240 | 17500 | 0.7821 | |
|
| 0.1395 | 3.3161 | 18000 | 0.7794 | |
|
| 0.1804 | 3.4083 | 18500 | 0.7778 | |
|
| 0.1728 | 3.5004 | 19000 | 0.7769 | |
|
| 0.179 | 3.5925 | 19500 | 0.7758 | |
|
| 0.179 | 3.6846 | 20000 | 0.7752 | |
|
| 0.1454 | 3.7767 | 20500 | 0.7747 | |
|
| 0.1568 | 3.8688 | 21000 | 0.7744 | |
|
| 0.1663 | 3.9609 | 21500 | 0.7743 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.0.dev0 |
|
- Pytorch 1.12.1 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
