|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: pp-mod-subj2-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-subj2-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: 4.0244 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.7935 | 0.03 | 76320 | 4.8062 | |
|
|
| 4.5109 | 1.03 | 152640 | 4.5276 | |
|
|
| 4.364 | 0.03 | 228960 | 4.3927 | |
|
|
| 4.2769 | 1.03 | 305280 | 4.3088 | |
|
|
| 4.218 | 2.03 | 381600 | 4.2524 | |
|
|
| 4.1632 | 0.03 | 457920 | 4.2110 | |
|
|
| 4.122 | 1.03 | 534240 | 4.1790 | |
|
|
| 4.0898 | 0.03 | 610560 | 4.1564 | |
|
|
| 4.061 | 1.03 | 686880 | 4.1367 | |
|
|
| 4.0412 | 0.03 | 763200 | 4.1209 | |
|
|
| 4.017 | 1.03 | 839520 | 4.1068 | |
|
|
| 4.0005 | 2.03 | 915840 | 4.0968 | |
|
|
| 3.9871 | 0.03 | 992160 | 4.0886 | |
|
|
| 3.9741 | 1.03 | 1068480 | 4.0804 | |
|
|
| 3.9581 | 0.03 | 1144800 | 4.0726 | |
|
|
| 3.9422 | 1.03 | 1221120 | 4.0674 | |
|
|
| 3.9348 | 2.03 | 1297440 | 4.0626 | |
|
|
| 3.9277 | 0.03 | 1373760 | 4.0584 | |
|
|
| 3.9161 | 1.03 | 1450080 | 4.0541 | |
|
|
| 3.9137 | 2.03 | 1526400 | 4.0513 | |
|
|
| 3.9114 | 0.03 | 1602720 | 4.0470 | |
|
|
| 3.9006 | 1.03 | 1679040 | 4.0451 | |
|
|
| 3.8935 | 2.03 | 1755360 | 4.0424 | |
|
|
| 3.8884 | 0.03 | 1831680 | 4.0403 | |
|
|
| 3.8812 | 1.03 | 1908000 | 4.0383 | |
|
|
| 3.8775 | 0.03 | 1984320 | 4.0364 | |
|
|
| 3.8699 | 1.03 | 2060640 | 4.0352 | |
|
|
| 3.8649 | 0.03 | 2136960 | 4.0336 | |
|
|
| 3.8632 | 1.03 | 2213280 | 4.0325 | |
|
|
| 3.8588 | 0.03 | 2289600 | 4.0305 | |
|
|
| 3.8516 | 1.03 | 2365920 | 4.0299 | |
|
|
| 3.8467 | 2.03 | 2442240 | 4.0294 | |
|
|
| 3.8464 | 0.03 | 2518560 | 4.0286 | |
|
|
| 3.8457 | 0.03 | 2594880 | 4.0275 | |
|
|
| 3.8392 | 1.03 | 2671200 | 4.0269 | |
|
|
| 3.841 | 0.03 | 2747520 | 4.0259 | |
|
|
| 3.8415 | 1.03 | 2823840 | 4.0257 | |
|
|
| 3.8387 | 0.03 | 2900160 | 4.0253 | |
|
|
| 3.8357 | 1.03 | 2976480 | 4.0248 | |
|
|
| 3.834 | 2.02 | 3052726 | 4.0244 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
