metadata
license: apache-2.0
base_model: facebook/convnextv2-large-1k-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: convnextv2_large_food101
results: []
convnextv2_large_food101
This model is a fine-tuned version of facebook/convnextv2-large-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6622
- Accuracy: 0.908
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.9463 | 0.99 | 62 | 2.6321 | 0.764 |
| 1.516 | 2.0 | 125 | 1.3564 | 0.8605 |
| 1.0163 | 2.99 | 187 | 0.9408 | 0.8855 |
| 0.7411 | 4.0 | 250 | 0.7443 | 0.9075 |
| 0.6397 | 4.99 | 312 | 0.6746 | 0.9085 |
| 0.583 | 5.95 | 372 | 0.6622 | 0.908 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.1
- Datasets 2.17.1
- Tokenizers 0.15.2