metadata
base_model: openai/clip-vit-base-patch32
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: ktp-not-ktp-clip
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: 0.9900990099009901
ktp-not-ktp-clip
This model is a fine-tuned version of openai/clip-vit-base-patch32 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0159
- Accuracy: 0.9901
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.9231 | 3 | 0.0256 | 0.9901 |
| No log | 1.8462 | 6 | 0.0514 | 0.9802 |
| No log | 2.7692 | 9 | 0.1041 | 0.9604 |
| 0.1234 | 4.0 | 13 | 0.0597 | 0.9802 |
| 0.1234 | 4.9231 | 16 | 0.0736 | 0.9802 |
| 0.1234 | 5.8462 | 19 | 0.1338 | 0.9802 |
| 0.0335 | 6.7692 | 22 | 0.1006 | 0.9802 |
| 0.0335 | 8.0 | 26 | 0.0856 | 0.9802 |
| 0.0335 | 8.9231 | 29 | 0.0410 | 0.9703 |
| 0.1078 | 9.8462 | 32 | 0.1247 | 0.9802 |
| 0.1078 | 10.7692 | 35 | 0.1851 | 0.9703 |
| 0.1078 | 12.0 | 39 | 0.0078 | 1.0 |
| 0.0526 | 12.9231 | 42 | 0.0127 | 0.9901 |
| 0.0526 | 13.8462 | 45 | 0.0159 | 0.9901 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1