metadata
library_name: transformers
license: apache-2.0
base_model: facebook/vit-msn-small
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-msn-small-wbc-classifier-mono-V-all
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9585338620875524
vit-msn-small-wbc-classifier-mono-V-all
This model is a fine-tuned version of facebook/vit-msn-small on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1140
- Accuracy: 0.9585
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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 |
|---|---|---|---|---|
| 0.1974 | 1.0 | 208 | 0.1642 | 0.9372 |
| 0.1589 | 2.0 | 416 | 0.1334 | 0.9508 |
| 0.134 | 3.0 | 624 | 0.1466 | 0.9431 |
| 0.1488 | 4.0 | 832 | 0.1155 | 0.9566 |
| 0.1169 | 5.0 | 1040 | 0.1140 | 0.9585 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1