|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: facebook/convnext-tiny-224 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: convnext-tiny-224-finetuned |
|
|
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-finetuned |
|
|
|
|
|
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: 1.1657 |
|
|
- Logloss: 1.1657 |
|
|
- Accuracy: {'accuracy': 0.5808823529411765} |
|
|
|
|
|
## 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: 20 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:-------:|:---------------------------------:| |
|
|
| No log | 0.9412 | 8 | 1.6072 | 1.6072 | {'accuracy': 0.18382352941176472} | |
|
|
| 1.6101 | 2.0 | 17 | 1.5668 | 1.5668 | {'accuracy': 0.31985294117647056} | |
|
|
| 1.5645 | 2.9412 | 25 | 1.5246 | 1.5246 | {'accuracy': 0.33455882352941174} | |
|
|
| 1.4902 | 4.0 | 34 | 1.4774 | 1.4774 | {'accuracy': 0.4007352941176471} | |
|
|
| 1.4243 | 4.9412 | 42 | 1.4283 | 1.4283 | {'accuracy': 0.44485294117647056} | |
|
|
| 1.3502 | 6.0 | 51 | 1.3747 | 1.3747 | {'accuracy': 0.48161764705882354} | |
|
|
| 1.3502 | 6.9412 | 59 | 1.3332 | 1.3332 | {'accuracy': 0.48161764705882354} | |
|
|
| 1.2906 | 8.0 | 68 | 1.2978 | 1.2978 | {'accuracy': 0.5036764705882353} | |
|
|
| 1.2371 | 8.9412 | 76 | 1.2702 | 1.2702 | {'accuracy': 0.5147058823529411} | |
|
|
| 1.1856 | 10.0 | 85 | 1.2434 | 1.2434 | {'accuracy': 0.5404411764705882} | |
|
|
| 1.1506 | 10.9412 | 93 | 1.2300 | 1.2300 | {'accuracy': 0.5477941176470589} | |
|
|
| 1.0987 | 12.0 | 102 | 1.2088 | 1.2088 | {'accuracy': 0.5588235294117647} | |
|
|
| 1.0758 | 12.9412 | 110 | 1.1949 | 1.1949 | {'accuracy': 0.5514705882352942} | |
|
|
| 1.0758 | 14.0 | 119 | 1.1896 | 1.1896 | {'accuracy': 0.5588235294117647} | |
|
|
| 1.0483 | 14.9412 | 127 | 1.1773 | 1.1773 | {'accuracy': 0.5698529411764706} | |
|
|
| 1.0346 | 16.0 | 136 | 1.1719 | 1.1719 | {'accuracy': 0.5735294117647058} | |
|
|
| 1.0215 | 16.9412 | 144 | 1.1702 | 1.1702 | {'accuracy': 0.5698529411764706} | |
|
|
| 1.0177 | 18.0 | 153 | 1.1666 | 1.1666 | {'accuracy': 0.5772058823529411} | |
|
|
| 0.9956 | 18.8235 | 160 | 1.1657 | 1.1657 | {'accuracy': 0.5808823529411765} | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.42.4 |
|
|
- Pytorch 2.3.1+cu121 |
|
|
- Datasets 2.21.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
