gpt2-scratch
This model is a fine-tuned version of Harshatheeswar/gpt2-scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.1380
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.2094 | 1.0 | 1390 | 4.1380 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 30
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Harshatheeswar/gpt2-scratch
Unable to build the model tree, the base model loops to the model itself. Learn more.