metadata
base_model: google/vit-base-patch16-224-in21k
library_name: peft
license: apache-2.0
metrics:
- accuracy
- f1
- precision
- recall
tags:
- generated_from_trainer
model-index:
- name: vit-base-patch16-224-in21k-finetuned-tekno23
results: []
vit-base-patch16-224-in21k-finetuned-tekno23
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2583
- Accuracy: 0.4014
- F1: 0.3092
- Precision: 0.3870
- Recall: 0.4014
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.3662 | 1.0 | 421 | 1.3619 | 0.3190 | 0.1618 | 0.2852 | 0.3190 |
| 1.3095 | 2.0 | 842 | 1.2970 | 0.3962 | 0.2933 | 0.4359 | 0.3962 |
| 1.2683 | 3.0 | 1263 | 1.2687 | 0.4020 | 0.3081 | 0.3550 | 0.4020 |
| 1.2524 | 4.0 | 1684 | 1.2576 | 0.4057 | 0.3098 | 0.3951 | 0.4057 |
| 1.2781 | 5.0 | 2105 | 1.2583 | 0.4014 | 0.3092 | 0.3870 | 0.4014 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1