|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pp-mod-subj-lstm-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-lstm-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: 4.0209 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.7854 | 0.03 | 76319 | 4.8028 | |
|
| 4.4977 | 1.03 | 152638 | 4.5223 | |
|
| 4.3587 | 0.03 | 228957 | 4.3889 | |
|
| 4.2696 | 1.03 | 305276 | 4.3065 | |
|
| 4.207 | 0.03 | 381595 | 4.2505 | |
|
| 4.1571 | 1.03 | 457914 | 4.2098 | |
|
| 4.121 | 0.03 | 534233 | 4.1792 | |
|
| 4.0895 | 1.03 | 610552 | 4.1544 | |
|
| 4.0629 | 0.03 | 686871 | 4.1348 | |
|
| 4.0412 | 1.03 | 763190 | 4.1193 | |
|
| 4.0214 | 0.03 | 839509 | 4.1071 | |
|
| 4.0024 | 1.03 | 915828 | 4.0951 | |
|
| 3.9814 | 0.03 | 992147 | 4.0868 | |
|
| 3.9685 | 1.03 | 1068466 | 4.0790 | |
|
| 3.9564 | 0.03 | 1144785 | 4.0722 | |
|
| 3.9452 | 1.03 | 1221104 | 4.0665 | |
|
| 3.9355 | 0.03 | 1297424 | 4.0602 | |
|
| 3.9281 | 1.03 | 1373744 | 4.0566 | |
|
| 3.917 | 0.03 | 1450064 | 4.0518 | |
|
| 3.9124 | 1.03 | 1526384 | 4.0483 | |
|
| 3.908 | 0.03 | 1602704 | 4.0445 | |
|
| 3.9004 | 0.03 | 1679024 | 4.0419 | |
|
| 3.893 | 1.03 | 1755344 | 4.0391 | |
|
| 3.8861 | 0.03 | 1831664 | 4.0372 | |
|
| 3.8812 | 1.03 | 1907984 | 4.0348 | |
|
| 3.8753 | 0.03 | 1984304 | 4.0337 | |
|
| 3.8713 | 0.03 | 2060624 | 4.0326 | |
|
| 3.8646 | 1.03 | 2136944 | 4.0310 | |
|
| 3.8633 | 0.03 | 2213264 | 4.0295 | |
|
| 3.8573 | 1.03 | 2289584 | 4.0282 | |
|
| 3.853 | 2.03 | 2365904 | 4.0275 | |
|
| 3.8467 | 0.03 | 2442224 | 4.0265 | |
|
| 3.8425 | 1.03 | 2518544 | 4.0254 | |
|
| 3.843 | 2.03 | 2594864 | 4.0244 | |
|
| 3.837 | 0.03 | 2671184 | 4.0234 | |
|
| 3.8397 | 1.03 | 2747504 | 4.0227 | |
|
| 3.8417 | 2.03 | 2823824 | 4.0220 | |
|
| 3.8383 | 0.03 | 2900144 | 4.0215 | |
|
| 3.8356 | 1.03 | 2976464 | 4.0212 | |
|
| 3.8319 | 0.02 | 3052726 | 4.0209 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
