|
--- |
|
library_name: transformers |
|
base_model: openai/clip-vit-large-patch14-336 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: clip-finetuned-csu-p14-336-e3l56-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-e3l56-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: 0.6863 |
|
|
|
## 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-06 |
|
- 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 | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 0.2253 | 0.0921 | 500 | 1.4694 | |
|
| 0.2544 | 0.1842 | 1000 | 1.5421 | |
|
| 0.3236 | 0.2763 | 1500 | 1.4643 | |
|
| 0.1888 | 0.3685 | 2000 | 1.3194 | |
|
| 0.2563 | 0.4606 | 2500 | 1.3764 | |
|
| 0.2794 | 0.5527 | 3000 | 1.3007 | |
|
| 0.1749 | 0.6448 | 3500 | 1.3361 | |
|
| 0.2672 | 0.7369 | 4000 | 1.2684 | |
|
| 0.218 | 0.8290 | 4500 | 1.1065 | |
|
| 0.1665 | 0.9211 | 5000 | 1.0620 | |
|
| 0.1842 | 1.0133 | 5500 | 0.9443 | |
|
| 0.1183 | 1.1054 | 6000 | 0.9431 | |
|
| 0.1066 | 1.1975 | 6500 | 1.0051 | |
|
| 0.0901 | 1.2896 | 7000 | 1.0017 | |
|
| 0.112 | 1.3817 | 7500 | 1.0030 | |
|
| 0.1265 | 1.4738 | 8000 | 0.9463 | |
|
| 0.1193 | 1.5660 | 8500 | 1.0378 | |
|
| 0.1318 | 1.6581 | 9000 | 0.9299 | |
|
| 0.1262 | 1.7502 | 9500 | 0.9714 | |
|
| 0.101 | 1.8423 | 10000 | 0.8754 | |
|
| 0.1158 | 1.9344 | 10500 | 0.8075 | |
|
| 0.0656 | 2.0265 | 11000 | 0.8281 | |
|
| 0.0854 | 2.1186 | 11500 | 0.7756 | |
|
| 0.0574 | 2.2108 | 12000 | 0.7431 | |
|
| 0.0643 | 2.3029 | 12500 | 0.7556 | |
|
| 0.0657 | 2.3950 | 13000 | 0.7819 | |
|
| 0.0372 | 2.4871 | 13500 | 0.7689 | |
|
| 0.0286 | 2.5792 | 14000 | 0.7623 | |
|
| 0.0581 | 2.6713 | 14500 | 0.7251 | |
|
| 0.0578 | 2.7634 | 15000 | 0.6913 | |
|
| 0.0442 | 2.8556 | 15500 | 0.6863 | |
|
| 0.0304 | 2.9477 | 16000 | 0.6906 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.0.dev0 |
|
- Pytorch 1.12.1 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
