pp-mod-subj-transformer-1
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9216
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: 1
- 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 |
|---|---|---|---|
| 4.2284 | 0.03 | 76319 | 4.2464 |
| 4.022 | 0.03 | 152638 | 4.0756 |
| 3.9165 | 0.03 | 228957 | 4.0014 |
| 3.845 | 0.03 | 305276 | 3.9610 |
| 3.7923 | 0.03 | 381595 | 3.9358 |
| 3.7472 | 0.03 | 457914 | 3.9196 |
| 3.7144 | 0.03 | 534233 | 3.9107 |
| 3.6831 | 0.03 | 610552 | 3.9037 |
| 3.6555 | 0.03 | 686871 | 3.8989 |
| 3.6296 | 1.03 | 763190 | 3.8978 |
| 3.6102 | 0.03 | 839510 | 3.8908 |
| 3.5875 | 1.03 | 915830 | 3.8914 |
| 3.5688 | 0.03 | 992150 | 3.8931 |
| 3.5513 | 1.03 | 1068470 | 3.8935 |
| 3.5348 | 0.03 | 1144790 | 3.8949 |
| 3.5189 | 1.03 | 1221110 | 3.8979 |
| 3.5035 | 0.03 | 1297430 | 3.8983 |
| 3.4886 | 1.03 | 1373750 | 3.9014 |
| 3.4778 | 0.03 | 1450070 | 3.9015 |
| 3.4697 | 1.03 | 1526390 | 3.9047 |
| 3.4615 | 0.03 | 1602710 | 3.9072 |
| 3.4463 | 0.03 | 1679030 | 3.9081 |
| 3.4369 | 1.03 | 1755350 | 3.9108 |
| 3.4268 | 0.03 | 1831670 | 3.9115 |
| 3.4106 | 1.03 | 1907990 | 3.9129 |
| 3.4009 | 0.03 | 1984310 | 3.9149 |
| 3.3873 | 1.03 | 2060630 | 3.9166 |
| 3.3776 | 0.03 | 2136950 | 3.9181 |
| 3.3661 | 1.03 | 2213270 | 3.9200 |
| 3.3553 | 0.03 | 2289590 | 3.9216 |
| 3.3454 | 0.03 | 2365910 | 3.9219 |
| 3.3375 | 0.03 | 2442230 | 3.9231 |
| 3.3268 | 0.03 | 2518550 | 3.9243 |
| 3.3174 | 1.03 | 2594870 | 3.9252 |
| 3.3094 | 0.03 | 2671190 | 3.9248 |
| 3.3041 | 1.03 | 2747510 | 3.9247 |
| 3.2986 | 0.03 | 2823830 | 3.9247 |
| 3.2883 | 0.03 | 2900150 | 3.9242 |
| 3.281 | 1.03 | 2976470 | 3.9231 |
| 3.2775 | 0.02 | 3052726 | 3.9216 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3