weeds_convnext_balanced
This model is a fine-tuned version of facebook/convnext-large-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1931
- Accuracy: 0.9333
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: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 2.0584 | 1.0 | 150 | 1.9386 | 0.6 |
| 0.7729 | 2.0 | 300 | 0.6873 | 0.8733 |
| 0.4394 | 3.0 | 450 | 0.4321 | 0.89 |
| 0.3337 | 4.0 | 600 | 0.3227 | 0.9 |
| 0.2489 | 5.0 | 750 | 0.2320 | 0.9267 |
| 0.1998 | 6.0 | 900 | 0.2556 | 0.9233 |
| 0.1994 | 7.0 | 1050 | 0.2538 | 0.92 |
| 0.1573 | 8.0 | 1200 | 0.2224 | 0.9333 |
| 0.143 | 9.0 | 1350 | 0.1495 | 0.96 |
| 0.0686 | 10.0 | 1500 | 0.1931 | 0.9333 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.11.0
- Downloads last month
- 22
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.