|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: pp-mod-subj-transformer-2 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# pp-mod-subj-transformer-2 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.9189 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2295 | 0.03 | 76319 | 4.2460 | |
|
|
| 4.0231 | 0.03 | 152638 | 4.0758 | |
|
|
| 3.9178 | 0.03 | 228957 | 4.0001 | |
|
|
| 3.8454 | 0.03 | 305276 | 3.9592 | |
|
|
| 3.7934 | 0.03 | 381595 | 3.9336 | |
|
|
| 3.7503 | 0.03 | 457914 | 3.9190 | |
|
|
| 3.7152 | 0.03 | 534233 | 3.9088 | |
|
|
| 3.6863 | 0.03 | 610552 | 3.9023 | |
|
|
| 3.6576 | 0.03 | 686871 | 3.8977 | |
|
|
| 3.6331 | 1.03 | 763190 | 3.8957 | |
|
|
| 3.6109 | 0.03 | 839510 | 3.8893 | |
|
|
| 3.5889 | 1.03 | 915830 | 3.8901 | |
|
|
| 3.571 | 0.03 | 992150 | 3.8901 | |
|
|
| 3.5544 | 1.03 | 1068470 | 3.8913 | |
|
|
| 3.5353 | 0.03 | 1144790 | 3.8925 | |
|
|
| 3.5236 | 1.03 | 1221110 | 3.8951 | |
|
|
| 3.5072 | 0.03 | 1297430 | 3.8966 | |
|
|
| 3.4951 | 1.03 | 1373750 | 3.8979 | |
|
|
| 3.4837 | 0.03 | 1450070 | 3.8999 | |
|
|
| 3.4736 | 0.03 | 1526390 | 3.9007 | |
|
|
| 3.4667 | 1.03 | 1602710 | 3.9031 | |
|
|
| 3.4513 | 0.03 | 1679030 | 3.9036 | |
|
|
| 3.4392 | 0.03 | 1755350 | 3.9068 | |
|
|
| 3.4296 | 1.03 | 1831670 | 3.9090 | |
|
|
| 3.4146 | 0.03 | 1907990 | 3.9102 | |
|
|
| 3.4042 | 0.03 | 1984310 | 3.9112 | |
|
|
| 3.3929 | 1.03 | 2060630 | 3.9125 | |
|
|
| 3.3825 | 0.03 | 2136950 | 3.9158 | |
|
|
| 3.3718 | 1.03 | 2213270 | 3.9160 | |
|
|
| 3.3648 | 0.03 | 2289590 | 3.9177 | |
|
|
| 3.3522 | 0.03 | 2365910 | 3.9185 | |
|
|
| 3.3433 | 1.03 | 2442230 | 3.9193 | |
|
|
| 3.3302 | 0.03 | 2518550 | 3.9203 | |
|
|
| 3.3225 | 0.03 | 2594870 | 3.9205 | |
|
|
| 3.3142 | 1.03 | 2671190 | 3.9214 | |
|
|
| 3.3087 | 0.03 | 2747510 | 3.9222 | |
|
|
| 3.3031 | 0.03 | 2823830 | 3.9223 | |
|
|
| 3.2928 | 0.03 | 2900150 | 3.9217 | |
|
|
| 3.2847 | 1.03 | 2976470 | 3.9198 | |
|
|
| 3.2821 | 0.02 | 3052726 | 3.9189 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
