pp-mod-subj-lstm-2
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.0209
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: 32
- eval_batch_size: 32
- seed: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 3052726
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.7854 | 0.03 | 76319 | 4.8028 |
4.4977 | 1.03 | 152638 | 4.5223 |
4.3587 | 0.03 | 228957 | 4.3889 |
4.2696 | 1.03 | 305276 | 4.3065 |
4.207 | 0.03 | 381595 | 4.2505 |
4.1571 | 1.03 | 457914 | 4.2098 |
4.121 | 0.03 | 534233 | 4.1792 |
4.0895 | 1.03 | 610552 | 4.1544 |
4.0629 | 0.03 | 686871 | 4.1348 |
4.0412 | 1.03 | 763190 | 4.1193 |
4.0214 | 0.03 | 839509 | 4.1071 |
4.0024 | 1.03 | 915828 | 4.0951 |
3.9814 | 0.03 | 992147 | 4.0868 |
3.9685 | 1.03 | 1068466 | 4.0790 |
3.9564 | 0.03 | 1144785 | 4.0722 |
3.9452 | 1.03 | 1221104 | 4.0665 |
3.9355 | 0.03 | 1297424 | 4.0602 |
3.9281 | 1.03 | 1373744 | 4.0566 |
3.917 | 0.03 | 1450064 | 4.0518 |
3.9124 | 1.03 | 1526384 | 4.0483 |
3.908 | 0.03 | 1602704 | 4.0445 |
3.9004 | 0.03 | 1679024 | 4.0419 |
3.893 | 1.03 | 1755344 | 4.0391 |
3.8861 | 0.03 | 1831664 | 4.0372 |
3.8812 | 1.03 | 1907984 | 4.0348 |
3.8753 | 0.03 | 1984304 | 4.0337 |
3.8713 | 0.03 | 2060624 | 4.0326 |
3.8646 | 1.03 | 2136944 | 4.0310 |
3.8633 | 0.03 | 2213264 | 4.0295 |
3.8573 | 1.03 | 2289584 | 4.0282 |
3.853 | 2.03 | 2365904 | 4.0275 |
3.8467 | 0.03 | 2442224 | 4.0265 |
3.8425 | 1.03 | 2518544 | 4.0254 |
3.843 | 2.03 | 2594864 | 4.0244 |
3.837 | 0.03 | 2671184 | 4.0234 |
3.8397 | 1.03 | 2747504 | 4.0227 |
3.8417 | 2.03 | 2823824 | 4.0220 |
3.8383 | 0.03 | 2900144 | 4.0215 |
3.8356 | 1.03 | 2976464 | 4.0212 |
3.8319 | 0.02 | 3052726 | 4.0209 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 10