|
--- |
|
license: apache-2.0 |
|
base_model: facebook/convnextv2-base-1k-224 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: convnextv2-base-1k-224-for-pre_evaluation |
|
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. --> |
|
|
|
# convnextv2-base-1k-224-for-pre_evaluation |
|
|
|
This model is a fine-tuned version of [facebook/convnextv2-base-1k-224](https://huggingface.co/facebook/convnextv2-base-1k-224) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4479 |
|
- Accuracy: 0.4382 |
|
|
|
## 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 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.5952 | 0.93 | 10 | 1.5511 | 0.2960 | |
|
| 1.5238 | 1.95 | 21 | 1.5091 | 0.3427 | |
|
| 1.4881 | 2.98 | 32 | 1.4854 | 0.3450 | |
|
| 1.4708 | 4.0 | 43 | 1.4616 | 0.3473 | |
|
| 1.4361 | 4.93 | 53 | 1.4417 | 0.3450 | |
|
| 1.3764 | 5.95 | 64 | 1.4135 | 0.3753 | |
|
| 1.3333 | 6.98 | 75 | 1.3822 | 0.3986 | |
|
| 1.3296 | 8.0 | 86 | 1.4112 | 0.3636 | |
|
| 1.2798 | 8.93 | 96 | 1.4038 | 0.3893 | |
|
| 1.3129 | 9.95 | 107 | 1.4241 | 0.3776 | |
|
| 1.3014 | 10.98 | 118 | 1.3570 | 0.3893 | |
|
| 1.2332 | 12.0 | 129 | 1.4073 | 0.3893 | |
|
| 1.212 | 12.93 | 139 | 1.3770 | 0.4033 | |
|
| 1.1763 | 13.95 | 150 | 1.3891 | 0.3963 | |
|
| 1.124 | 14.98 | 161 | 1.3915 | 0.4126 | |
|
| 1.0963 | 16.0 | 172 | 1.4099 | 0.4149 | |
|
| 1.0547 | 16.93 | 182 | 1.4206 | 0.4033 | |
|
| 1.0631 | 17.95 | 193 | 1.4041 | 0.4196 | |
|
| 0.9911 | 18.98 | 204 | 1.4272 | 0.4149 | |
|
| 1.005 | 20.0 | 215 | 1.4211 | 0.4219 | |
|
| 0.9663 | 20.93 | 225 | 1.4662 | 0.4009 | |
|
| 0.9533 | 21.95 | 236 | 1.4286 | 0.4336 | |
|
| 0.9506 | 22.98 | 247 | 1.4135 | 0.4312 | |
|
| 0.8973 | 24.0 | 258 | 1.4428 | 0.4266 | |
|
| 0.8807 | 24.93 | 268 | 1.4479 | 0.4382 | |
|
| 0.8731 | 25.95 | 279 | 1.4429 | 0.4289 | |
|
| 0.8472 | 26.98 | 290 | 1.4461 | 0.4312 | |
|
| 0.8348 | 27.91 | 300 | 1.4531 | 0.4336 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
