|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pp-mod-subj-lstm-4 |
|
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-lstm-4 |
|
|
|
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: 4.0228 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.7906 | 0.03 | 76319 | 4.8075 | |
|
| 4.5003 | 1.03 | 152638 | 4.5249 | |
|
| 4.3616 | 0.03 | 228957 | 4.3904 | |
|
| 4.2704 | 1.03 | 305276 | 4.3082 | |
|
| 4.2086 | 0.03 | 381595 | 4.2515 | |
|
| 4.1599 | 1.03 | 457914 | 4.2106 | |
|
| 4.1234 | 0.03 | 534233 | 4.1798 | |
|
| 4.0919 | 1.03 | 610552 | 4.1544 | |
|
| 4.0655 | 0.03 | 686871 | 4.1360 | |
|
| 4.0406 | 1.03 | 763190 | 4.1198 | |
|
| 4.0219 | 0.03 | 839509 | 4.1069 | |
|
| 4.0045 | 1.03 | 915828 | 4.0971 | |
|
| 3.9834 | 0.03 | 992147 | 4.0878 | |
|
| 3.9687 | 0.03 | 1068466 | 4.0806 | |
|
| 3.956 | 1.03 | 1144785 | 4.0738 | |
|
| 3.952 | 0.03 | 1221105 | 4.0657 | |
|
| 3.9407 | 1.03 | 1297425 | 4.0606 | |
|
| 3.9296 | 0.03 | 1373745 | 4.0566 | |
|
| 3.917 | 1.03 | 1450065 | 4.0529 | |
|
| 3.9143 | 2.03 | 1526385 | 4.0498 | |
|
| 3.909 | 0.03 | 1602705 | 4.0460 | |
|
| 3.9 | 1.03 | 1679025 | 4.0440 | |
|
| 3.8943 | 2.03 | 1755345 | 4.0411 | |
|
| 3.888 | 0.03 | 1831665 | 4.0389 | |
|
| 3.8795 | 1.03 | 1907985 | 4.0365 | |
|
| 3.8727 | 2.03 | 1984305 | 4.0343 | |
|
| 3.8701 | 0.03 | 2060625 | 4.0330 | |
|
| 3.8647 | 1.03 | 2136945 | 4.0315 | |
|
| 3.8625 | 2.03 | 2213265 | 4.0301 | |
|
| 3.8572 | 0.03 | 2289585 | 4.0286 | |
|
| 3.8561 | 0.03 | 2365905 | 4.0274 | |
|
| 3.8493 | 1.03 | 2442225 | 4.0270 | |
|
| 3.8418 | 2.03 | 2518545 | 4.0264 | |
|
| 3.8425 | 0.03 | 2594865 | 4.0256 | |
|
| 3.839 | 1.03 | 2671185 | 4.0251 | |
|
| 3.8411 | 2.03 | 2747505 | 4.0247 | |
|
| 3.8431 | 0.03 | 2823825 | 4.0241 | |
|
| 3.8379 | 0.03 | 2900145 | 4.0237 | |
|
| 3.8353 | 1.03 | 2976465 | 4.0233 | |
|
| 3.8331 | 0.02 | 3052726 | 4.0228 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
