metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-384
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: segmented-augmented
results: []
segmented-augmented
This model is a fine-tuned version of google/vit-base-patch16-384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5815
- Precision: 0.8308
- Recall: 0.9136
- F1: 0.8703
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.081 | 1.0 | 327 | 0.3693 | 0.8464 | 0.8970 | 0.8710 |
| 0.0151 | 2.0 | 654 | 0.4906 | 0.8171 | 0.8904 | 0.8521 |
| 0.0066 | 3.0 | 981 | 0.5194 | 0.8416 | 0.9003 | 0.8700 |
| 0.0029 | 4.0 | 1308 | 0.5671 | 0.8308 | 0.9136 | 0.8703 |
| 0.0026 | 5.0 | 1635 | 0.5815 | 0.8308 | 0.9136 | 0.8703 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1