metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2chess_scratch
results: []
gpt2chess_scratch
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6902
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3139 | 0.7 | 5000 | 0.9635 |
| 0.9239 | 1.4 | 10000 | 0.8407 |
| 0.8367 | 2.1 | 15000 | 0.7807 |
| 0.7813 | 2.8 | 20000 | 0.7415 |
| 0.7373 | 3.5 | 25000 | 0.7127 |
| 0.7073 | 4.2 | 30000 | 0.6955 |
| 0.6853 | 4.9 | 35000 | 0.6902 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3