pp-mod-subj-transformer-0
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9272
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: 0
- 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 |
|---|---|---|---|
| 4.2225 | 0.03 | 76319 | 4.2389 |
| 4.0185 | 0.03 | 152638 | 4.0713 |
| 3.9131 | 0.03 | 228957 | 3.9978 |
| 3.8409 | 0.03 | 305276 | 3.9590 |
| 3.788 | 0.03 | 381595 | 3.9349 |
| 3.7444 | 0.03 | 457914 | 3.9197 |
| 3.711 | 0.03 | 534233 | 3.9116 |
| 3.6829 | 0.03 | 610552 | 3.9048 |
| 3.6541 | 0.03 | 686871 | 3.9011 |
| 3.63 | 0.03 | 763190 | 3.8989 |
| 3.6103 | 1.03 | 839509 | 3.8982 |
| 3.5887 | 0.03 | 915829 | 3.8914 |
| 3.569 | 1.03 | 992149 | 3.8933 |
| 3.552 | 0.03 | 1068469 | 3.8944 |
| 3.535 | 1.03 | 1144789 | 3.8962 |
| 3.5188 | 0.03 | 1221109 | 3.8980 |
| 3.5028 | 1.03 | 1297429 | 3.9003 |
| 3.4894 | 0.03 | 1373749 | 3.9013 |
| 3.4769 | 1.03 | 1450069 | 3.9045 |
| 3.4689 | 0.03 | 1526389 | 3.9050 |
| 3.4588 | 0.03 | 1602709 | 3.9080 |
| 3.4454 | 1.03 | 1679029 | 3.9094 |
| 3.4345 | 0.03 | 1755349 | 3.9128 |
| 3.4239 | 0.03 | 1831669 | 3.9132 |
| 3.4088 | 1.03 | 1907989 | 3.9164 |
| 3.3977 | 0.03 | 1984309 | 3.9182 |
| 3.3864 | 1.03 | 2060629 | 3.9208 |
| 3.376 | 0.03 | 2136949 | 3.9220 |
| 3.3652 | 1.03 | 2213269 | 3.9247 |
| 3.3569 | 0.03 | 2289589 | 3.9260 |
| 3.3449 | 1.03 | 2365909 | 3.9271 |
| 3.3353 | 0.03 | 2442229 | 3.9283 |
| 3.3245 | 1.03 | 2518549 | 3.9300 |
| 3.3165 | 0.03 | 2594869 | 3.9304 |
| 3.3094 | 0.03 | 2671189 | 3.9313 |
| 3.3041 | 1.03 | 2747509 | 3.9317 |
| 3.2966 | 0.03 | 2823829 | 3.9312 |
| 3.2876 | 0.03 | 2900149 | 3.9298 |
| 3.2797 | 1.03 | 2976469 | 3.9291 |
| 3.2741 | 0.02 | 3052726 | 3.9272 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3