ADL_HW2_GPT2
This model is a fine-tuned version of ckiplab/gpt2-tiny-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4578
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: 5.6e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.02 | 1.0 | 543 | 3.6837 |
| 3.8249 | 2.0 | 1086 | 3.5804 |
| 3.7431 | 3.0 | 1629 | 3.5336 |
| 3.6958 | 4.0 | 2172 | 3.5036 |
| 3.6633 | 5.0 | 2715 | 3.4815 |
| 3.639 | 6.0 | 3258 | 3.4722 |
| 3.622 | 7.0 | 3801 | 3.4597 |
| 3.6095 | 8.0 | 4344 | 3.4578 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 59
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for b09501048/ADL_HW2_GPT2
Base model
ckiplab/gpt2-tiny-chinese