nbaresult
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7787
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.4842 | 1.5209 | 100 | 1.5785 |
1.3561 | 3.0418 | 200 | 1.0734 |
0.9769 | 4.5627 | 300 | 0.8836 |
0.8586 | 6.0837 | 400 | 0.8362 |
0.8166 | 7.6046 | 500 | 0.8127 |
0.7922 | 9.1255 | 600 | 0.8015 |
0.7708 | 10.6464 | 700 | 0.7941 |
0.7467 | 12.1673 | 800 | 0.7889 |
0.728 | 13.6882 | 900 | 0.7820 |
0.7138 | 15.2091 | 1000 | 0.7795 |
0.7043 | 16.7300 | 1100 | 0.7780 |
0.7007 | 18.2510 | 1200 | 0.7783 |
0.6964 | 19.7719 | 1300 | 0.7787 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Model tree for jhebmds/nbaresult
Base model
openai-community/gpt2