ViT-BERT-Chess-V2 / README.md
Migga's picture
update model card README.md
3192e80
metadata
tags:
  - generated_from_trainer
model-index:
  - name: ViT-BERT-Chess-V2
    results: []

ViT-BERT-Chess-V2

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.7128

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: 10
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
4.0385 1.0 2770 3.9132
3.7453 2.0 5540 3.7552
3.6513 3.0 8310 3.7128

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.11.0
  • Datasets 2.1.0
  • Tokenizers 0.12.1