metadata
license: apache-2.0
base_model: microsoft/resnet-50
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: msi-resnet-pretrain
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8862116991643454
msi-resnet-pretrain
This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3514
- Accuracy: 0.8862
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4387 | 1.0 | 1562 | 0.3894 | 0.8795 |
| 0.2626 | 2.0 | 3125 | 0.3142 | 0.9024 |
| 0.2134 | 3.0 | 4687 | 0.3767 | 0.8694 |
| 0.1452 | 4.0 | 6250 | 0.3211 | 0.8947 |
| 0.1773 | 5.0 | 7810 | 0.3514 | 0.8862 |
Framework versions
- Transformers 4.36.1
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0