|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: rel-cl-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. --> |
|
|
|
# rel-cl-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: 3.9785 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.8008 | 0.03 | 76319 | 4.7627 | |
|
| 4.5151 | 0.03 | 152638 | 4.4816 | |
|
| 4.374 | 0.03 | 228957 | 4.3478 | |
|
| 4.2862 | 1.03 | 305276 | 4.2645 | |
|
| 4.2226 | 0.03 | 381595 | 4.2082 | |
|
| 4.1691 | 1.03 | 457914 | 4.1669 | |
|
| 4.1333 | 0.03 | 534233 | 4.1361 | |
|
| 4.1034 | 1.03 | 610552 | 4.1115 | |
|
| 4.0735 | 0.03 | 686871 | 4.0929 | |
|
| 4.051 | 1.03 | 763190 | 4.0768 | |
|
| 4.0334 | 0.03 | 839509 | 4.0648 | |
|
| 4.0153 | 1.03 | 915828 | 4.0532 | |
|
| 3.9936 | 0.03 | 992147 | 4.0440 | |
|
| 3.9834 | 0.03 | 1068466 | 4.0364 | |
|
| 3.9681 | 1.03 | 1144785 | 4.0294 | |
|
| 3.9586 | 0.03 | 1221105 | 4.0229 | |
|
| 3.9442 | 1.03 | 1297425 | 4.0173 | |
|
| 3.9351 | 0.03 | 1373745 | 4.0124 | |
|
| 3.9238 | 1.03 | 1450065 | 4.0085 | |
|
| 3.9209 | 0.03 | 1526385 | 4.0051 | |
|
| 3.9142 | 1.03 | 1602705 | 4.0024 | |
|
| 3.9116 | 0.03 | 1679025 | 3.9996 | |
|
| 3.9073 | 1.03 | 1755345 | 3.9973 | |
|
| 3.9009 | 0.03 | 1831665 | 3.9954 | |
|
| 3.8922 | 1.03 | 1907985 | 3.9933 | |
|
| 3.8829 | 0.03 | 1984305 | 3.9910 | |
|
| 3.8762 | 1.03 | 2060625 | 3.9890 | |
|
| 3.8746 | 0.03 | 2136945 | 3.9878 | |
|
| 3.8673 | 1.03 | 2213265 | 3.9862 | |
|
| 3.8607 | 0.03 | 2289585 | 3.9850 | |
|
| 3.8607 | 0.03 | 2365905 | 3.9843 | |
|
| 3.8592 | 0.03 | 2442225 | 3.9831 | |
|
| 3.8521 | 1.03 | 2518545 | 3.9822 | |
|
| 3.8487 | 0.03 | 2594865 | 3.9816 | |
|
| 3.8455 | 1.03 | 2671185 | 3.9811 | |
|
| 3.846 | 0.03 | 2747505 | 3.9803 | |
|
| 3.846 | 1.03 | 2823825 | 3.9796 | |
|
| 3.846 | 0.03 | 2900145 | 3.9794 | |
|
| 3.8496 | 0.03 | 2976465 | 3.9789 | |
|
| 3.8456 | 1.02 | 3052726 | 3.9785 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
