<!-- 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_05_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: 0.5776
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 |
---|---|---|---|
73.8761 | 0.02 | 10 | 69.5761 |
46.4656 | 0.04 | 20 | 32.9595 |
13.7865 | 0.06 | 30 | 10.6413 |
6.1955 | 0.08 | 40 | 4.4713 |
3.2865 | 0.1 | 50 | 1.9343 |
1.7057 | 0.12 | 60 | 1.0630 |
1.4395 | 0.14 | 70 | 0.8938 |
1.3446 | 0.16 | 80 | 0.7473 |
1.0525 | 0.18 | 90 | 0.6359 |
1.0155 | 0.2 | 100 | 0.6422 |
0.9368 | 0.22 | 110 | 0.6149 |
0.909 | 0.24 | 120 | 0.5954 |
0.9592 | 0.26 | 130 | 0.5766 |
0.8922 | 0.28 | 140 | 0.5787 |
0.9056 | 0.3 | 150 | 0.5820 |
0.8984 | 0.32 | 160 | 0.5776 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.12.1