metadata
base_model: TannerGladson/chess-roberta
tags:
- generated_from_trainer
datasets:
- TannerGladson/chess-roberta-whole-move-tuning
metrics:
- accuracy
model-index:
- name: 2024.07.20-19.49
results:
- task:
name: Masked Language Modeling
type: fill-mask
dataset:
name: TannerGladson/chess-roberta-whole-move-tuning
type: TannerGladson/chess-roberta-whole-move-tuning
metrics:
- name: Accuracy
type: accuracy
value: 0.902359997194343
2024.07.20-19.49
This model is a fine-tuned version of TannerGladson/chess-roberta on the TannerGladson/chess-roberta-whole-move-tuning dataset. It achieves the following results on the evaluation set:
- Loss: 0.2611
- Accuracy: 0.9024
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5262 | 0.2485 | 1000 | 0.4272 | 0.8519 |
| 0.413 | 0.4970 | 2000 | 0.3650 | 0.8711 |
| 0.3505 | 0.7455 | 3000 | 0.3138 | 0.8852 |
| 0.3111 | 0.9939 | 4000 | 0.2829 | 0.8950 |
| 0.2817 | 1.2424 | 5000 | 0.2596 | 0.9025 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.0.1+cu117
- Datasets 2.17.1
- Tokenizers 0.19.1