chessgpt-medium-s / README.md
dakwi's picture
End of training
487c4d3 verified
metadata
library_name: transformers
license: mit
base_model: gpt2-medium
tags:
  - generated_from_trainer
model-index:
  - name: chessgpt-medium-s
    results: []

chessgpt-medium-s

This model is a fine-tuned version of gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0974

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: 0.0003
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.2
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.9222 0.08 125 1.6441
1.5847 0.16 250 1.4532
1.4585 0.24 375 1.3629
1.3801 0.32 500 1.3059
1.3296 0.4 625 1.2550
1.2856 0.48 750 1.2185
1.2502 0.56 875 1.1902
1.2231 0.64 1000 1.1635
1.1978 0.72 1125 1.1451
1.1823 0.8 1250 1.1242
1.1688 0.88 1375 1.1113
1.1544 0.96 1500 1.1008

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1