|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: plant-vit-model-1 |
|
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. --> |
|
|
|
# plant-vit-model-1 |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1560 |
|
- Accuracy: 0.9995 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.296 | 1.0 | 83 | 1.0361 | 0.9227 | |
|
| 0.4476 | 2.0 | 166 | 0.3646 | 0.9904 | |
|
| 0.2731 | 3.0 | 249 | 0.2174 | 0.9952 | |
|
| 0.2097 | 4.0 | 332 | 0.1560 | 0.9995 | |
|
| 0.1679 | 5.0 | 415 | 0.1288 | 0.9973 | |
|
| 0.135 | 6.0 | 498 | 0.1052 | 0.9984 | |
|
| 0.118 | 7.0 | 581 | 0.0918 | 0.9989 | |
|
| 0.1054 | 8.0 | 664 | 0.0826 | 0.9989 | |
|
| 0.1083 | 9.0 | 747 | 0.0777 | 0.9989 | |
|
| 0.0918 | 10.0 | 830 | 0.0756 | 0.9995 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
