<!-- 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_07_hscnspecial-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: 0.5555
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 |
---|---|---|---|
74.2708 | 0.02 | 10 | 69.5779 |
46.8995 | 0.04 | 20 | 32.9904 |
14.1147 | 0.06 | 30 | 10.6462 |
7.5603 | 0.08 | 40 | 4.2364 |
4.2656 | 0.1 | 50 | 2.0342 |
2.0155 | 0.12 | 60 | 1.0776 |
1.7338 | 0.14 | 70 | 0.8626 |
1.6131 | 0.16 | 80 | 0.7370 |
1.4307 | 0.18 | 90 | 0.6911 |
1.3948 | 0.2 | 100 | 0.6827 |
1.2695 | 0.22 | 110 | 0.6138 |
1.2576 | 0.24 | 120 | 0.6027 |
1.3685 | 0.26 | 130 | 0.5944 |
1.24 | 0.28 | 140 | 0.5742 |
1.2747 | 0.3 | 150 | 0.5767 |
1.2222 | 0.32 | 160 | 0.5743 |
1.1463 | 0.34 | 170 | 0.5736 |
1.3169 | 0.36 | 180 | 0.5661 |
1.3233 | 0.38 | 190 | 0.5588 |
1.2432 | 0.4 | 200 | 0.5581 |
1.3868 | 0.42 | 210 | 0.5552 |
1.3661 | 0.44 | 220 | 0.5524 |
1.1409 | 0.46 | 230 | 0.5557 |
1.2373 | 0.48 | 240 | 0.5539 |
1.2253 | 0.5 | 250 | 0.5555 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.12.1