metadata
library_name: transformers
license: apache-2.0
base_model: google/siglip2-so400m-patch16-naflex
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: train_dit02_initials_3cat_cls_3.5k_naflex-r2
results: []
train_dit02_initials_3cat_cls_3.5k_naflex-r2
This model is a fine-tuned version of google/siglip2-so400m-patch16-naflex on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6956
- Accuracy: 0.6418
- Precision: 0.6396
- Recall: 0.6418
- F1: 0.6307
- Roc Auc: 0.7587
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-06
- train_batch_size: 96
- eval_batch_size: 96
- seed: 1337
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Roc Auc |
|---|---|---|---|---|---|---|---|---|
| 0.184 | 3.125 | 100 | 0.3170 | 0.6754 | 0.6694 | 0.6754 | 0.6569 | 0.7862 |
| 0.038 | 6.25 | 200 | 0.5170 | 0.6474 | 0.6700 | 0.6474 | 0.6422 | 0.7691 |
| 0.013 | 9.375 | 300 | 0.6968 | 0.6474 | 0.6423 | 0.6474 | 0.6346 | 0.7590 |
Framework versions
- Transformers 4.56.2
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1