|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/resnet-50 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: resnet-50-finetuned-cifar10 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: train |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.5076 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# resnet-50-finetuned-cifar10 |
|
|
|
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9060 |
|
- Accuracy: 0.5076 |
|
|
|
## 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: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 2.3058 | 0.03 | 10 | 2.3106 | 0.0794 | |
|
| 2.3033 | 0.06 | 20 | 2.3026 | 0.0892 | |
|
| 2.3012 | 0.09 | 30 | 2.2971 | 0.1042 | |
|
| 2.2914 | 0.11 | 40 | 2.2890 | 0.1254 | |
|
| 2.2869 | 0.14 | 50 | 2.2816 | 0.16 | |
|
| 2.2785 | 0.17 | 60 | 2.2700 | 0.1902 | |
|
| 2.2712 | 0.2 | 70 | 2.2602 | 0.2354 | |
|
| 2.2619 | 0.23 | 80 | 2.2501 | 0.2688 | |
|
| 2.2509 | 0.26 | 90 | 2.2383 | 0.3022 | |
|
| 2.2382 | 0.28 | 100 | 2.2229 | 0.3268 | |
|
| 2.2255 | 0.31 | 110 | 2.2084 | 0.353 | |
|
| 2.2164 | 0.34 | 120 | 2.1939 | 0.3608 | |
|
| 2.2028 | 0.37 | 130 | 2.1829 | 0.3668 | |
|
| 2.1977 | 0.4 | 140 | 2.1646 | 0.401 | |
|
| 2.1844 | 0.43 | 150 | 2.1441 | 0.4244 | |
|
| 2.1689 | 0.45 | 160 | 2.1323 | 0.437 | |
|
| 2.1555 | 0.48 | 170 | 2.1159 | 0.4462 | |
|
| 2.1448 | 0.51 | 180 | 2.0992 | 0.45 | |
|
| 2.1313 | 0.54 | 190 | 2.0810 | 0.4642 | |
|
| 2.1189 | 0.57 | 200 | 2.0589 | 0.4708 | |
|
| 2.1111 | 0.6 | 210 | 2.0430 | 0.4828 | |
|
| 2.0905 | 0.63 | 220 | 2.0288 | 0.4938 | |
|
| 2.082 | 0.65 | 230 | 2.0089 | 0.4938 | |
|
| 2.0646 | 0.68 | 240 | 1.9970 | 0.5014 | |
|
| 2.0636 | 0.71 | 250 | 1.9778 | 0.4946 | |
|
| 2.0579 | 0.74 | 260 | 1.9609 | 0.49 | |
|
| 2.028 | 0.77 | 270 | 1.9602 | 0.4862 | |
|
| 2.0447 | 0.8 | 280 | 1.9460 | 0.4934 | |
|
| 2.0168 | 0.82 | 290 | 1.9369 | 0.505 | |
|
| 2.0126 | 0.85 | 300 | 1.9317 | 0.4926 | |
|
| 2.0099 | 0.88 | 310 | 1.9235 | 0.4952 | |
|
| 1.9978 | 0.91 | 320 | 1.9174 | 0.4972 | |
|
| 1.9951 | 0.94 | 330 | 1.9119 | 0.507 | |
|
| 1.9823 | 0.97 | 340 | 1.9120 | 0.4992 | |
|
| 1.985 | 1.0 | 350 | 1.9064 | 0.5022 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.1 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
