|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: pp-mod-subj2-lstm-3 |
|
|
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-3 |
|
|
|
|
|
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: 4.0236 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.7998 | 0.03 | 76320 | 4.8120 | |
|
|
| 4.5096 | 1.03 | 152640 | 4.5251 | |
|
|
| 4.3616 | 0.03 | 228960 | 4.3905 | |
|
|
| 4.2752 | 1.03 | 305280 | 4.3081 | |
|
|
| 4.2147 | 0.03 | 381600 | 4.2510 | |
|
|
| 4.1606 | 1.03 | 457920 | 4.2100 | |
|
|
| 4.121 | 2.03 | 534240 | 4.1801 | |
|
|
| 4.0874 | 0.03 | 610560 | 4.1569 | |
|
|
| 4.0594 | 1.03 | 686880 | 4.1368 | |
|
|
| 4.0388 | 0.03 | 763200 | 4.1216 | |
|
|
| 4.016 | 1.03 | 839520 | 4.1087 | |
|
|
| 4.0008 | 2.03 | 915840 | 4.0984 | |
|
|
| 3.9863 | 0.03 | 992160 | 4.0888 | |
|
|
| 3.9719 | 1.03 | 1068480 | 4.0808 | |
|
|
| 3.9568 | 2.03 | 1144800 | 4.0741 | |
|
|
| 3.9403 | 0.03 | 1221120 | 4.0691 | |
|
|
| 3.9322 | 1.03 | 1297440 | 4.0641 | |
|
|
| 3.9259 | 2.03 | 1373760 | 4.0599 | |
|
|
| 3.9149 | 0.03 | 1450080 | 4.0563 | |
|
|
| 3.9133 | 1.03 | 1526400 | 4.0523 | |
|
|
| 3.9093 | 2.03 | 1602720 | 4.0500 | |
|
|
| 3.8988 | 0.03 | 1679040 | 4.0472 | |
|
|
| 3.8926 | 1.03 | 1755360 | 4.0448 | |
|
|
| 3.8832 | 2.03 | 1831680 | 4.0416 | |
|
|
| 3.8768 | 0.03 | 1908000 | 4.0403 | |
|
|
| 3.8735 | 1.03 | 1984320 | 4.0384 | |
|
|
| 3.8645 | 2.03 | 2060640 | 4.0364 | |
|
|
| 3.8607 | 0.03 | 2136960 | 4.0340 | |
|
|
| 3.8578 | 1.03 | 2213280 | 4.0319 | |
|
|
| 3.8554 | 0.03 | 2289600 | 4.0308 | |
|
|
| 3.848 | 1.03 | 2365920 | 4.0301 | |
|
|
| 3.843 | 0.03 | 2442240 | 4.0291 | |
|
|
| 3.8407 | 0.03 | 2518560 | 4.0285 | |
|
|
| 3.839 | 1.03 | 2594880 | 4.0277 | |
|
|
| 3.8342 | 0.03 | 2671200 | 4.0266 | |
|
|
| 3.8362 | 1.03 | 2747520 | 4.0257 | |
|
|
| 3.8409 | 0.03 | 2823840 | 4.0250 | |
|
|
| 3.8346 | 1.03 | 2900160 | 4.0244 | |
|
|
| 3.8314 | 0.03 | 2976480 | 4.0241 | |
|
|
| 3.8276 | 1.02 | 3052726 | 4.0236 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
