<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
ViT-BERT-Chess-V4
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3213
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: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.705 | 1.0 | 3895 | 3.5686 |
| 3.5139 | 2.0 | 7790 | 3.4288 |
| 3.4156 | 3.0 | 11685 | 3.3663 |
| 3.3661 | 4.0 | 15580 | 3.3331 |
| 3.3352 | 5.0 | 19475 | 3.3213 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu116
- Datasets 2.3.2
- Tokenizers 0.12.1
