metadata
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: vit-base-patch16-224-in21k
results: []
vit-base-patch16-224-in21k
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8270
- F1: 0.9461
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: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 10 | 1.6377 | 0.6304 |
| No log | 2.0 | 20 | 1.4787 | 0.8389 |
| No log | 3.0 | 30 | 1.3397 | 0.8549 |
| No log | 4.0 | 40 | 1.2044 | 0.9127 |
| No log | 5.0 | 50 | 1.0852 | 0.9119 |
| No log | 6.0 | 60 | 0.9919 | 0.9125 |
| No log | 7.0 | 70 | 0.9203 | 0.9259 |
| No log | 8.0 | 80 | 0.8691 | 0.9393 |
| No log | 9.0 | 90 | 0.8390 | 0.9461 |
| No log | 10.0 | 100 | 0.8270 | 0.9461 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0