|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: convnext-tiny-224_album_vitVMMRdb_make_model_album_pred |
|
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. --> |
|
|
|
# convnext-tiny-224_album_vitVMMRdb_make_model_album_pred |
|
|
|
This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4384 |
|
- Accuracy: 0.8814 |
|
- Precision: 0.8793 |
|
- Recall: 0.8814 |
|
- F1: 0.8772 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 25 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 4.8445 | 1.0 | 944 | 4.7488 | 0.0919 | 0.0214 | 0.0919 | 0.0266 | |
|
| 3.8243 | 2.0 | 1888 | 3.6914 | 0.2379 | 0.1520 | 0.2379 | 0.1447 | |
|
| 2.8783 | 3.0 | 2832 | 2.7011 | 0.4105 | 0.3433 | 0.4105 | 0.3235 | |
|
| 2.1348 | 4.0 | 3776 | 1.9752 | 0.5652 | 0.5279 | 0.5652 | 0.5069 | |
|
| 1.6456 | 5.0 | 4720 | 1.5225 | 0.6529 | 0.6274 | 0.6529 | 0.6134 | |
|
| 1.3835 | 6.0 | 5664 | 1.2167 | 0.7106 | 0.6996 | 0.7106 | 0.6845 | |
|
| 1.1258 | 7.0 | 6608 | 1.0067 | 0.7491 | 0.7394 | 0.7491 | 0.7272 | |
|
| 1.0181 | 8.0 | 7552 | 0.8722 | 0.7819 | 0.7755 | 0.7819 | 0.7678 | |
|
| 0.7829 | 9.0 | 8496 | 0.7752 | 0.8018 | 0.7987 | 0.8018 | 0.7899 | |
|
| 0.7503 | 10.0 | 9440 | 0.6983 | 0.8202 | 0.8189 | 0.8202 | 0.8121 | |
|
| 0.6534 | 11.0 | 10384 | 0.6392 | 0.8301 | 0.8280 | 0.8301 | 0.8220 | |
|
| 0.6108 | 12.0 | 11328 | 0.5941 | 0.8422 | 0.8384 | 0.8422 | 0.8343 | |
|
| 0.5087 | 13.0 | 12272 | 0.5659 | 0.8487 | 0.8462 | 0.8487 | 0.8416 | |
|
| 0.528 | 14.0 | 13216 | 0.5379 | 0.8554 | 0.8536 | 0.8554 | 0.8495 | |
|
| 0.4489 | 15.0 | 14160 | 0.5189 | 0.8589 | 0.8566 | 0.8589 | 0.8528 | |
|
| 0.4252 | 16.0 | 15104 | 0.5072 | 0.8626 | 0.8610 | 0.8626 | 0.8579 | |
|
| 0.4239 | 17.0 | 16048 | 0.4857 | 0.8686 | 0.8678 | 0.8686 | 0.8645 | |
|
| 0.3951 | 18.0 | 16992 | 0.4796 | 0.8695 | 0.8675 | 0.8695 | 0.8645 | |
|
| 0.3679 | 19.0 | 17936 | 0.4685 | 0.8739 | 0.8724 | 0.8739 | 0.8695 | |
|
| 0.3694 | 20.0 | 18880 | 0.4604 | 0.8751 | 0.8720 | 0.8751 | 0.8697 | |
|
| 0.3435 | 21.0 | 19824 | 0.4555 | 0.8777 | 0.8755 | 0.8777 | 0.8739 | |
|
| 0.3204 | 22.0 | 20768 | 0.4479 | 0.8783 | 0.8763 | 0.8783 | 0.8744 | |
|
| 0.3475 | 23.0 | 21712 | 0.4433 | 0.8794 | 0.8773 | 0.8794 | 0.8753 | |
|
| 0.338 | 24.0 | 22656 | 0.4408 | 0.8809 | 0.8785 | 0.8809 | 0.8767 | |
|
| 0.3437 | 25.0 | 23600 | 0.4384 | 0.8814 | 0.8793 | 0.8814 | 0.8772 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.7.1 |
|
- Tokenizers 0.13.2 |
|
|
