metadata
license: apache-2.0
base_model: tigeryi/imagenet1k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: imagenet-tiger
results: []
imagenet-tiger
This model is a fine-tuned version of tigeryi/imagenet1k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0970
- Accuracy: 0.99
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 1
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8141 | 1.0 | 25 | 0.2320 | 0.95 |
| 0.7293 | 2.0 | 50 | 0.0970 | 0.99 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1