|
--- |
|
base_model: clip_roberta |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
model-index: |
|
- name: Chest-X-Ray-Roco-Clip |
|
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. --> |
|
|
|
# Chest-X-Ray-Roco-Clip |
|
|
|
This model is a fine-tuned version of [clip_roberta](https://huggingface.co/clip_roberta) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3863 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 2 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 5 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.3868 | 0.4619 | 100 | 1.3863 | |
|
| 1.3867 | 0.9238 | 200 | 1.3863 | |
|
| 1.3862 | 1.3857 | 300 | 1.3863 | |
|
| 1.3872 | 1.8476 | 400 | 1.3863 | |
|
| 1.3869 | 2.3095 | 500 | 1.3863 | |
|
| 1.3861 | 2.7714 | 600 | 1.3863 | |
|
| 1.3862 | 3.2333 | 700 | 1.3863 | |
|
| 1.3863 | 3.6952 | 800 | 1.3863 | |
|
| 1.3865 | 4.1570 | 900 | 1.3863 | |
|
| 1.3864 | 4.6189 | 1000 | 1.3863 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|