|
--- |
|
base_model: openai/clip-vit-base-patch32 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: ktp-kk-crop |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: validation |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.967032967032967 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# ktp-kk-crop |
|
|
|
This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co./openai/clip-vit-base-patch32) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1497 |
|
- Accuracy: 0.9670 |
|
|
|
## 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-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 25 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
| No log | 0.9655 | 7 | 0.6506 | 0.5824 | |
|
| No log | 1.9310 | 14 | 0.3689 | 0.8352 | |
|
| 0.5439 | 2.8966 | 21 | 0.1940 | 0.9341 | |
|
| 0.5439 | 4.0 | 29 | 0.1185 | 0.9780 | |
|
| 0.0961 | 4.9655 | 36 | 0.1345 | 0.9780 | |
|
| 0.0961 | 5.9310 | 43 | 0.0828 | 0.9670 | |
|
| 0.114 | 6.8966 | 50 | 0.3337 | 0.9451 | |
|
| 0.114 | 8.0 | 58 | 0.1176 | 0.9670 | |
|
| 0.0106 | 8.9655 | 65 | 0.1484 | 0.9670 | |
|
| 0.0106 | 9.9310 | 72 | 0.0991 | 0.9780 | |
|
| 0.0609 | 10.8966 | 79 | 0.2071 | 0.9670 | |
|
| 0.0609 | 12.0 | 87 | 0.2575 | 0.9341 | |
|
| 0.0112 | 12.9655 | 94 | 0.1714 | 0.9451 | |
|
| 0.0112 | 13.9310 | 101 | 0.1918 | 0.9451 | |
|
| 0.0147 | 14.8966 | 108 | 0.1829 | 0.9670 | |
|
| 0.0147 | 16.0 | 116 | 0.3227 | 0.9341 | |
|
| 0.0025 | 16.9655 | 123 | 0.1287 | 0.9780 | |
|
| 0.0025 | 17.9310 | 130 | 0.1364 | 0.9780 | |
|
| 0.0 | 18.8966 | 137 | 0.1446 | 0.9670 | |
|
| 0.0 | 20.0 | 145 | 0.1487 | 0.9670 | |
|
| 0.0 | 20.9655 | 152 | 0.1499 | 0.9670 | |
|
| 0.0 | 21.9310 | 159 | 0.1501 | 0.9670 | |
|
| 0.0 | 22.8966 | 166 | 0.1498 | 0.9670 | |
|
| 0.0 | 24.0 | 174 | 0.1497 | 0.9670 | |
|
| 0.0 | 24.1379 | 175 | 0.1497 | 0.9670 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
