chess-gpt2-ft_v0.1
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2815
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: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.0868 | 0.0885 | 100 | 1.7682 |
1.7195 | 0.1769 | 200 | 1.5783 |
1.5913 | 0.2654 | 300 | 1.4892 |
1.5263 | 0.3538 | 400 | 1.4391 |
1.4804 | 0.4423 | 500 | 1.3965 |
1.4476 | 0.5307 | 600 | 1.3645 |
1.4166 | 0.6192 | 700 | 1.3441 |
1.3967 | 0.7077 | 800 | 1.3226 |
1.3782 | 0.7961 | 900 | 1.3053 |
1.3627 | 0.8846 | 1000 | 1.2919 |
1.3523 | 0.9730 | 1100 | 1.2830 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for dakwi/chess-gpt2-ft_v0.1
Base model
openai-community/gpt2
Finetuned
this model