metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: datrix-image-classification-job_5472a213
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: 0.25660377358490566
datrix-image-classification-job_5472a213
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.7470
- Accuracy: 0.2566
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.5699 | 1.0 | 239 | 3.5545 | 0.0642 |
| 3.3479 | 2.0 | 478 | 3.3057 | 0.1170 |
| 3.2327 | 3.0 | 717 | 3.1975 | 0.1208 |
| 3.1248 | 4.0 | 956 | 3.0876 | 0.1434 |
| 3.0689 | 5.0 | 1195 | 2.9798 | 0.1736 |
| 2.9669 | 6.0 | 1434 | 2.9051 | 0.2038 |
| 2.9706 | 7.0 | 1673 | 2.8224 | 0.2151 |
| 2.9171 | 8.0 | 1912 | 2.7895 | 0.2528 |
| 2.8688 | 9.0 | 2151 | 2.7562 | 0.2528 |
| 2.8695 | 10.0 | 2390 | 2.7470 | 0.2566 |
Framework versions
- Transformers 5.9.0
- Pytorch 2.12.0+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2