pp-mod-subj-transformer-3
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9286
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: 3
- 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 |
---|---|---|---|
4.2242 | 0.03 | 76319 | 4.2409 |
4.02 | 0.03 | 152638 | 4.0727 |
3.9131 | 0.03 | 228957 | 3.9988 |
3.8422 | 0.03 | 305276 | 3.9591 |
3.7903 | 0.03 | 381595 | 3.9357 |
3.7462 | 1.03 | 457914 | 3.9199 |
3.7113 | 0.03 | 534233 | 3.9105 |
3.6838 | 0.03 | 610552 | 3.9045 |
3.6564 | 1.03 | 686871 | 3.8994 |
3.63 | 0.03 | 763190 | 3.8980 |
3.6086 | 0.03 | 839509 | 3.8966 |
3.5902 | 1.03 | 915828 | 3.8978 |
3.5709 | 0.03 | 992148 | 3.8916 |
3.5523 | 1.03 | 1068468 | 3.8932 |
3.5349 | 0.03 | 1144788 | 3.8944 |
3.518 | 1.03 | 1221108 | 3.8979 |
3.504 | 0.03 | 1297428 | 3.8994 |
3.4889 | 1.03 | 1373748 | 3.9016 |
3.4773 | 0.03 | 1450068 | 3.9037 |
3.4686 | 0.03 | 1526388 | 3.9062 |
3.4615 | 1.03 | 1602708 | 3.9090 |
3.449 | 0.03 | 1679028 | 3.9111 |
3.4364 | 1.03 | 1755348 | 3.9123 |
3.4251 | 0.03 | 1831668 | 3.9152 |
3.4097 | 1.03 | 1907988 | 3.9180 |
3.3987 | 0.03 | 1984308 | 3.9189 |
3.3864 | 0.03 | 2060628 | 3.9229 |
3.375 | 0.03 | 2136948 | 3.9232 |
3.3676 | 1.03 | 2213268 | 3.9248 |
3.3576 | 0.03 | 2289588 | 3.9265 |
3.3447 | 1.03 | 2365908 | 3.9277 |
3.3337 | 0.03 | 2442228 | 3.9294 |
3.3247 | 1.03 | 2518548 | 3.9311 |
3.3156 | 0.03 | 2594868 | 3.9312 |
3.3073 | 0.03 | 2671188 | 3.9313 |
3.3017 | 0.03 | 2747508 | 3.9313 |
3.2986 | 0.03 | 2823828 | 3.9318 |
3.2881 | 1.03 | 2900148 | 3.9311 |
3.2809 | 0.03 | 2976468 | 3.9301 |
3.2725 | 1.02 | 3052726 | 3.9286 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 1