|
|
--- |
|
|
library_name: transformers |
|
|
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: 1.0311 |
|
|
- Logloss: 1.0311 |
|
|
- Accuracy: {'accuracy': 0.5626423690205011} |
|
|
|
|
|
## 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: 30 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:-------:|:---------------------------------:| |
|
|
| 1.6135 | 0.9455 | 13 | 1.5881 | 1.5881 | {'accuracy': 0.22323462414578588} | |
|
|
| 1.5823 | 1.9636 | 27 | 1.5302 | 1.5302 | {'accuracy': 0.35990888382687924} | |
|
|
| 1.4988 | 2.9818 | 41 | 1.4480 | 1.4480 | {'accuracy': 0.4874715261958998} | |
|
|
| 1.4303 | 4.0 | 55 | 1.3424 | 1.3424 | {'accuracy': 0.5034168564920274} | |
|
|
| 1.3653 | 4.9455 | 68 | 1.2544 | 1.2544 | {'accuracy': 0.5239179954441914} | |
|
|
| 1.2232 | 5.9636 | 82 | 1.1867 | 1.1867 | {'accuracy': 0.5239179954441914} | |
|
|
| 1.1734 | 6.9818 | 96 | 1.1330 | 1.1330 | {'accuracy': 0.5466970387243736} | |
|
|
| 1.0747 | 8.0 | 110 | 1.1197 | 1.1197 | {'accuracy': 0.5626423690205011} | |
|
|
| 1.0405 | 8.9455 | 123 | 1.0871 | 1.0871 | {'accuracy': 0.5535307517084282} | |
|
|
| 1.0313 | 9.9636 | 137 | 1.0900 | 1.0900 | {'accuracy': 0.5671981776765376} | |
|
|
| 0.959 | 10.9818 | 151 | 1.0766 | 1.0766 | {'accuracy': 0.5603644646924829} | |
|
|
| 0.9314 | 12.0 | 165 | 1.0608 | 1.0608 | {'accuracy': 0.5603644646924829} | |
|
|
| 0.9102 | 12.9455 | 178 | 1.0388 | 1.0388 | {'accuracy': 0.5649202733485194} | |
|
|
| 0.8437 | 13.9636 | 192 | 1.0332 | 1.0332 | {'accuracy': 0.5785876993166287} | |
|
|
| 0.8234 | 14.9818 | 206 | 1.0302 | 1.0302 | {'accuracy': 0.5763097949886105} | |
|
|
| 0.7883 | 16.0 | 220 | 1.0276 | 1.0276 | {'accuracy': 0.5649202733485194} | |
|
|
| 0.7364 | 16.9455 | 233 | 1.0278 | 1.0278 | {'accuracy': 0.5649202733485194} | |
|
|
| 0.7561 | 17.9636 | 247 | 1.0258 | 1.0258 | {'accuracy': 0.5649202733485194} | |
|
|
| 0.7062 | 18.9818 | 261 | 1.0196 | 1.0196 | {'accuracy': 0.5694760820045558} | |
|
|
| 0.6897 | 20.0 | 275 | 1.0308 | 1.0308 | {'accuracy': 0.5558086560364465} | |
|
|
| 0.6511 | 20.9455 | 288 | 1.0247 | 1.0247 | {'accuracy': 0.5626423690205011} | |
|
|
| 0.6338 | 21.9636 | 302 | 1.0310 | 1.0310 | {'accuracy': 0.5603644646924829} | |
|
|
| 0.619 | 22.9818 | 316 | 1.0258 | 1.0258 | {'accuracy': 0.5671981776765376} | |
|
|
| 0.6008 | 24.0 | 330 | 1.0299 | 1.0299 | {'accuracy': 0.5626423690205011} | |
|
|
| 0.601 | 24.9455 | 343 | 1.0329 | 1.0329 | {'accuracy': 0.5671981776765376} | |
|
|
| 0.595 | 25.9636 | 357 | 1.0277 | 1.0277 | {'accuracy': 0.5694760820045558} | |
|
|
| 0.598 | 26.9818 | 371 | 1.0288 | 1.0288 | {'accuracy': 0.5671981776765376} | |
|
|
| 0.5771 | 28.0 | 385 | 1.0311 | 1.0311 | {'accuracy': 0.5603644646924829} | |
|
|
| 0.5829 | 28.3636 | 390 | 1.0311 | 1.0311 | {'accuracy': 0.5626423690205011} | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.44.2 |
|
|
- Pytorch 2.4.0+cu121 |
|
|
- Datasets 2.21.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
