metadata
license: apache-2.0
base_model: facebook/convnext-tiny-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: convnext-tiny-224-finetuned
results: []
convnext-tiny-224-finetuned
This model is a fine-tuned version of facebook/convnext-tiny-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0987
- Logloss: 1.0987
- 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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy |
|---|---|---|---|---|---|
| No log | 0.9412 | 8 | 1.1618 | 1.1618 | {'accuracy': 0.5882352941176471} |
| 0.9966 | 2.0 | 17 | 1.1464 | 1.1464 | {'accuracy': 0.5845588235294118} |
| 0.9619 | 2.9412 | 25 | 1.1380 | 1.1380 | {'accuracy': 0.5772058823529411} |
| 0.9133 | 4.0 | 34 | 1.1249 | 1.1249 | {'accuracy': 0.5735294117647058} |
| 0.8577 | 4.9412 | 42 | 1.1043 | 1.1043 | {'accuracy': 0.5882352941176471} |
| 0.8092 | 6.0 | 51 | 1.0899 | 1.0899 | {'accuracy': 0.5955882352941176} |
| 0.8092 | 6.9412 | 59 | 1.0927 | 1.0927 | {'accuracy': 0.5845588235294118} |
| 0.772 | 8.0 | 68 | 1.0834 | 1.0834 | {'accuracy': 0.5845588235294118} |
| 0.7128 | 8.9412 | 76 | 1.0730 | 1.0730 | {'accuracy': 0.5845588235294118} |
| 0.6902 | 10.0 | 85 | 1.0788 | 1.0788 | {'accuracy': 0.5882352941176471} |
| 0.645 | 10.9412 | 93 | 1.0649 | 1.0649 | {'accuracy': 0.5808823529411765} |
| 0.591 | 12.0 | 102 | 1.0631 | 1.0631 | {'accuracy': 0.5845588235294118} |
| 0.578 | 12.9412 | 110 | 1.0764 | 1.0764 | {'accuracy': 0.5845588235294118} |
| 0.578 | 14.0 | 119 | 1.0658 | 1.0658 | {'accuracy': 0.5808823529411765} |
| 0.5377 | 14.9412 | 127 | 1.0674 | 1.0674 | {'accuracy': 0.5808823529411765} |
| 0.516 | 16.0 | 136 | 1.0798 | 1.0798 | {'accuracy': 0.5808823529411765} |
| 0.4974 | 16.9412 | 144 | 1.0804 | 1.0804 | {'accuracy': 0.5808823529411765} |
| 0.4649 | 18.0 | 153 | 1.0818 | 1.0818 | {'accuracy': 0.5955882352941176} |
| 0.4422 | 18.9412 | 161 | 1.0742 | 1.0742 | {'accuracy': 0.5808823529411765} |
| 0.4222 | 20.0 | 170 | 1.0862 | 1.0862 | {'accuracy': 0.5735294117647058} |
| 0.4222 | 20.9412 | 178 | 1.0935 | 1.0935 | {'accuracy': 0.5772058823529411} |
| 0.4136 | 22.0 | 187 | 1.0907 | 1.0907 | {'accuracy': 0.5772058823529411} |
| 0.4006 | 22.9412 | 195 | 1.0967 | 1.0967 | {'accuracy': 0.5735294117647058} |
| 0.4032 | 24.0 | 204 | 1.0931 | 1.0931 | {'accuracy': 0.5772058823529411} |
| 0.3805 | 24.9412 | 212 | 1.1000 | 1.1000 | {'accuracy': 0.5845588235294118} |
| 0.3654 | 26.0 | 221 | 1.1078 | 1.1078 | {'accuracy': 0.5661764705882353} |
| 0.3654 | 26.9412 | 229 | 1.0959 | 1.0959 | {'accuracy': 0.5772058823529411} |
| 0.3678 | 28.0 | 238 | 1.0986 | 1.0986 | {'accuracy': 0.5808823529411765} |
| 0.3789 | 28.2353 | 240 | 1.0987 | 1.0987 | {'accuracy': 0.5808823529411765} |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1