metadata
library_name: transformers
license: apache-2.0
base_model: facebook/dinov2-small-imagenet1k-1-layer
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: dinov2-small-imagenet1k-1-layer-finetuned-noh
results: []
dinov2-small-imagenet1k-1-layer-finetuned-noh
This model is a fine-tuned version of facebook/dinov2-small-imagenet1k-1-layer on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3755
- Accuracy: 0.9080
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6331 | 1.0 | 23 | 0.5416 | 0.7652 |
| 0.4913 | 2.0 | 46 | 0.3755 | 0.9080 |
| 0.4642 | 3.0 | 69 | 0.7141 | 0.6141 |
| 0.4451 | 4.0 | 92 | 0.4348 | 0.8046 |
| 0.4095 | 5.0 | 115 | 0.5060 | 0.8030 |
| 0.3399 | 6.0 | 138 | 0.5464 | 0.7373 |
| 0.3304 | 7.0 | 161 | 0.3274 | 0.8883 |
| 0.3539 | 8.0 | 184 | 0.3893 | 0.8604 |
| 0.2849 | 9.0 | 207 | 0.3758 | 0.8637 |
| 0.2605 | 9.5778 | 220 | 0.3969 | 0.8489 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1
- Datasets 2.19.1
- Tokenizers 0.21.0