Updated this model to include 50,000 games. 25,000 games for Bucket 1(400-1000) and 25,000 games for Bucket 2(1001-1200). 90% training and 10% validation array. Previously had 2,000 games each.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6799	1.0	1407	0.6864
0.6598	2.0	2814	0.6590
0.6445	3.0	4221	0.6500

Framework versions

Transformers 5.9.0
Pytorch 2.10.0+cu128
Datasets 4.8.5
Tokenizers 0.22.2

71-vueT10/chess-guesser-distilbert

chess-guesser-distilbert

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

71-vueT10/
chess-guesser-distilbert