gpt2-kl_01_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: 0.5492
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 |
---|---|---|---|
73.6057 | 0.02 | 10 | 69.5688 |
46.1297 | 0.04 | 20 | 32.9398 |
13.6236 | 0.06 | 30 | 10.6408 |
6.8926 | 0.08 | 40 | 4.2341 |
3.624 | 0.1 | 50 | 2.0277 |
1.4923 | 0.12 | 60 | 1.0828 |
1.1113 | 0.14 | 70 | 0.8631 |
1.0637 | 0.16 | 80 | 0.8401 |
0.8052 | 0.18 | 90 | 0.7114 |
0.8037 | 0.2 | 100 | 0.6471 |
0.6838 | 0.22 | 110 | 0.5986 |
0.6964 | 0.24 | 120 | 0.5857 |
0.7026 | 0.26 | 130 | 0.5939 |
0.7504 | 0.28 | 140 | 0.5821 |
0.6942 | 0.3 | 150 | 0.5732 |
0.6843 | 0.32 | 160 | 0.5735 |
0.5917 | 0.34 | 170 | 0.5641 |
0.7147 | 0.36 | 180 | 0.5679 |
0.7191 | 0.38 | 190 | 0.5727 |
0.6479 | 0.4 | 200 | 0.5622 |
0.7827 | 0.42 | 210 | 0.5531 |
0.7211 | 0.44 | 220 | 0.5480 |
0.6038 | 0.46 | 230 | 0.5514 |
0.6323 | 0.48 | 240 | 0.5456 |
0.6168 | 0.5 | 250 | 0.5470 |
0.6322 | 0.52 | 260 | 0.5515 |
0.6365 | 0.54 | 270 | 0.5492 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 1.12.0a0+bd13bc6
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 13
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.