<!-- 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-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: 0.5400
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 |
|---|---|---|---|
| 74.3984 | 0.02 | 10 | 69.5824 |
| 46.8803 | 0.04 | 20 | 32.9798 |
| 14.3833 | 0.06 | 30 | 10.6415 |
| 7.575 | 0.08 | 40 | 4.6376 |
| 3.743 | 0.1 | 50 | 2.0118 |
| 2.2075 | 0.12 | 60 | 1.0526 |
| 1.7704 | 0.14 | 70 | 0.9221 |
| 1.6742 | 0.16 | 80 | 0.7326 |
| 1.6277 | 0.18 | 90 | 0.6323 |
| 1.5239 | 0.2 | 100 | 0.6305 |
| 1.4315 | 0.22 | 110 | 0.6303 |
| 1.4175 | 0.24 | 120 | 0.6087 |
| 1.4311 | 0.26 | 130 | 0.6332 |
| 1.551 | 0.28 | 140 | 0.5729 |
| 1.594 | 0.3 | 150 | 0.5792 |
| 1.4637 | 0.32 | 160 | 0.5718 |
| 1.3139 | 0.34 | 170 | 0.5715 |
| 1.5152 | 0.36 | 180 | 0.5667 |
| 1.5807 | 0.38 | 190 | 0.5628 |
| 1.3656 | 0.4 | 200 | 0.5642 |
| 1.622 | 0.42 | 210 | 0.5629 |
| 1.5337 | 0.44 | 220 | 0.5561 |
| 1.3122 | 0.46 | 230 | 0.5596 |
| 1.4214 | 0.48 | 240 | 0.5549 |
| 1.3091 | 0.5 | 250 | 0.5594 |
| 1.408 | 0.52 | 260 | 0.5501 |
| 1.3621 | 0.54 | 270 | 0.5445 |
| 1.472 | 0.56 | 280 | 0.5457 |
| 1.3257 | 0.58 | 290 | 0.5445 |
| 1.2563 | 0.6 | 300 | 0.5443 |
| 1.451 | 0.62 | 310 | 0.5410 |
| 1.5655 | 0.64 | 320 | 0.5384 |
| 1.3168 | 0.66 | 330 | 0.5416 |
| 1.3216 | 0.68 | 340 | 0.5391 |
| 1.3135 | 0.7 | 350 | 0.5400 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.12.1
