gpt-expt-sp-v3-K-600-MA-Mac-actions-kmeans-v20
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0506
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.1868 | 0.18 | 5000 | 0.1545 |
0.112 | 0.36 | 10000 | 0.0991 |
0.0948 | 0.55 | 15000 | 0.0856 |
0.086 | 0.73 | 20000 | 0.0796 |
0.0805 | 0.91 | 25000 | 0.0742 |
0.0757 | 1.09 | 30000 | 0.0712 |
0.072 | 1.27 | 35000 | 0.0677 |
0.0685 | 1.46 | 40000 | 0.0645 |
0.0653 | 1.64 | 45000 | 0.0617 |
0.0623 | 1.82 | 50000 | 0.0592 |
0.0595 | 2.0 | 55000 | 0.0569 |
0.057 | 2.19 | 60000 | 0.0549 |
0.0549 | 2.37 | 65000 | 0.0532 |
0.0533 | 2.55 | 70000 | 0.0518 |
0.0523 | 2.73 | 75000 | 0.0509 |
0.0519 | 2.91 | 80000 | 0.0506 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.7
- Tokenizers 0.14.1
- Downloads last month
- 204