|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: passive-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. --> |
|
|
|
|
|
# passive-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: 3.9742 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.7721 | 0.03 | 76320 | 4.7403 | |
|
|
| 4.4938 | 1.03 | 152640 | 4.4686 | |
|
|
| 4.3497 | 0.03 | 228960 | 4.3374 | |
|
|
| 4.2699 | 0.03 | 305280 | 4.2560 | |
|
|
| 4.2042 | 1.03 | 381600 | 4.2005 | |
|
|
| 4.1597 | 0.03 | 457920 | 4.1602 | |
|
|
| 4.1213 | 0.03 | 534240 | 4.1284 | |
|
|
| 4.0881 | 1.03 | 610560 | 4.1051 | |
|
|
| 4.058 | 0.03 | 686880 | 4.0860 | |
|
|
| 4.0344 | 1.03 | 763200 | 4.0706 | |
|
|
| 4.0105 | 0.03 | 839520 | 4.0573 | |
|
|
| 3.9935 | 1.03 | 915840 | 4.0466 | |
|
|
| 3.9739 | 0.03 | 992160 | 4.0379 | |
|
|
| 3.9532 | 1.03 | 1068480 | 4.0302 | |
|
|
| 3.9432 | 0.03 | 1144800 | 4.0231 | |
|
|
| 3.939 | 1.03 | 1221120 | 4.0177 | |
|
|
| 3.9282 | 0.03 | 1297440 | 4.0131 | |
|
|
| 3.9195 | 1.03 | 1373760 | 4.0090 | |
|
|
| 3.9069 | 0.03 | 1450080 | 4.0045 | |
|
|
| 3.9075 | 1.03 | 1526400 | 4.0009 | |
|
|
| 3.8977 | 0.03 | 1602720 | 3.9981 | |
|
|
| 3.8977 | 1.03 | 1679040 | 3.9952 | |
|
|
| 3.892 | 0.03 | 1755360 | 3.9930 | |
|
|
| 3.8848 | 1.03 | 1831680 | 3.9905 | |
|
|
| 3.8757 | 0.03 | 1908000 | 3.9878 | |
|
|
| 3.8689 | 1.03 | 1984320 | 3.9858 | |
|
|
| 3.8612 | 0.03 | 2060640 | 3.9842 | |
|
|
| 3.8576 | 1.03 | 2136960 | 3.9836 | |
|
|
| 3.8501 | 0.03 | 2213280 | 3.9823 | |
|
|
| 3.8404 | 1.03 | 2289600 | 3.9811 | |
|
|
| 3.8371 | 0.03 | 2365920 | 3.9803 | |
|
|
| 3.8437 | 1.03 | 2442240 | 3.9792 | |
|
|
| 3.8388 | 0.03 | 2518560 | 3.9781 | |
|
|
| 3.8353 | 0.03 | 2594880 | 3.9776 | |
|
|
| 3.8294 | 0.03 | 2671200 | 3.9766 | |
|
|
| 3.8363 | 1.03 | 2747520 | 3.9760 | |
|
|
| 3.8327 | 0.03 | 2823840 | 3.9755 | |
|
|
| 3.8355 | 0.03 | 2900160 | 3.9750 | |
|
|
| 3.8333 | 1.03 | 2976480 | 3.9745 | |
|
|
| 3.8312 | 0.02 | 3052726 | 3.9742 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
