gpt2-lichess-uci-2016-01_11

This model is a fine-tuned version of austindavis/gpt2-lichess-uci-201601 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0379

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: 0.0001715755714441261
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.0634	1.0	266171	1.0379

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0
• Datasets 2.19.1
• Tokenizers 0.19.1