<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
gpt2-kl_1_03-hs_cn
This model is a fine-tuned version of gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5831
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: 4
- seed: 21
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 73.6964 | 0.02 | 10 | 69.5849 |
| 46.2529 | 0.04 | 20 | 32.9743 |
| 13.6872 | 0.06 | 30 | 10.6434 |
| 6.9606 | 0.08 | 40 | 4.2609 |
| 3.0304 | 0.1 | 50 | 2.0214 |
| 1.5531 | 0.12 | 60 | 1.0653 |
| 1.2219 | 0.14 | 70 | 0.9094 |
| 1.123 | 0.16 | 80 | 0.8057 |
| 0.9086 | 0.18 | 90 | 0.6375 |
| 0.8539 | 0.2 | 100 | 0.6410 |
| 0.7491 | 0.22 | 110 | 0.5954 |
| 0.7632 | 0.24 | 120 | 0.5803 |
| 0.7792 | 0.26 | 130 | 0.5807 |
| 0.774 | 0.28 | 140 | 0.5821 |
| 0.7971 | 0.3 | 150 | 0.5831 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.12.1
