pp-mod-subj-transformer-4
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9241
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: 4
- 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 |
---|---|---|---|
4.2271 | 0.03 | 76319 | 4.2438 |
4.0211 | 0.03 | 152638 | 4.0736 |
3.9159 | 0.03 | 228957 | 4.0002 |
3.8439 | 0.03 | 305276 | 3.9584 |
3.7926 | 0.03 | 381595 | 3.9340 |
3.7493 | 0.03 | 457914 | 3.9186 |
3.7135 | 0.03 | 534233 | 3.9081 |
3.6846 | 0.03 | 610552 | 3.9026 |
3.6569 | 0.03 | 686871 | 3.8992 |
3.6319 | 1.03 | 763190 | 3.8971 |
3.6103 | 0.03 | 839510 | 3.8914 |
3.5908 | 1.03 | 915830 | 3.8907 |
3.5721 | 0.03 | 992150 | 3.8927 |
3.5536 | 1.03 | 1068470 | 3.8928 |
3.5359 | 0.03 | 1144790 | 3.8953 |
3.5224 | 1.03 | 1221110 | 3.8973 |
3.5034 | 0.03 | 1297430 | 3.8986 |
3.491 | 0.03 | 1373750 | 3.9005 |
3.4799 | 1.03 | 1450070 | 3.9023 |
3.4689 | 0.03 | 1526390 | 3.9049 |
3.4616 | 1.03 | 1602710 | 3.9054 |
3.4481 | 0.03 | 1679030 | 3.9090 |
3.4351 | 1.03 | 1755350 | 3.9108 |
3.4266 | 0.03 | 1831670 | 3.9123 |
3.4112 | 1.03 | 1907990 | 3.9139 |
3.4014 | 0.03 | 1984310 | 3.9171 |
3.3887 | 1.03 | 2060630 | 3.9187 |
3.377 | 0.03 | 2136950 | 3.9198 |
3.3682 | 1.03 | 2213270 | 3.9211 |
3.3572 | 0.03 | 2289590 | 3.9223 |
3.3464 | 1.03 | 2365910 | 3.9236 |
3.336 | 0.03 | 2442230 | 3.9254 |
3.3236 | 1.03 | 2518550 | 3.9257 |
3.3173 | 0.03 | 2594870 | 3.9269 |
3.3101 | 0.03 | 2671190 | 3.9266 |
3.3025 | 0.03 | 2747510 | 3.9266 |
3.2986 | 1.03 | 2823830 | 3.9265 |
3.2869 | 0.03 | 2900150 | 3.9270 |
3.2817 | 0.03 | 2976470 | 3.9255 |
3.2771 | 1.02 | 3052726 | 3.9241 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 1