|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: npi-sim-ques-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. --> |
|
|
|
|
|
# npi-sim-ques-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: 3.9709 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.806 | 0.03 | 76320 | 4.7637 | |
|
|
| 4.5179 | 1.03 | 152640 | 4.4810 | |
|
|
| 4.3786 | 0.03 | 228960 | 4.3461 | |
|
|
| 4.2891 | 1.03 | 305280 | 4.2627 | |
|
|
| 4.2257 | 0.03 | 381600 | 4.2058 | |
|
|
| 4.1775 | 1.03 | 457920 | 4.1652 | |
|
|
| 4.1404 | 0.03 | 534240 | 4.1341 | |
|
|
| 4.1056 | 1.03 | 610560 | 4.1093 | |
|
|
| 4.0786 | 0.03 | 686880 | 4.0893 | |
|
|
| 4.0545 | 1.03 | 763200 | 4.0733 | |
|
|
| 4.0336 | 0.03 | 839520 | 4.0604 | |
|
|
| 4.0179 | 1.03 | 915840 | 4.0494 | |
|
|
| 3.9965 | 0.03 | 992160 | 4.0393 | |
|
|
| 3.979 | 1.03 | 1068480 | 4.0310 | |
|
|
| 3.9668 | 0.03 | 1144800 | 4.0236 | |
|
|
| 3.9616 | 1.03 | 1221120 | 4.0182 | |
|
|
| 3.9493 | 0.03 | 1297440 | 4.0129 | |
|
|
| 3.9384 | 1.03 | 1373760 | 4.0078 | |
|
|
| 3.9327 | 0.03 | 1450080 | 4.0035 | |
|
|
| 3.924 | 1.03 | 1526400 | 4.0002 | |
|
|
| 3.9181 | 0.03 | 1602720 | 3.9966 | |
|
|
| 3.9132 | 1.03 | 1679040 | 3.9935 | |
|
|
| 3.9076 | 0.03 | 1755360 | 3.9911 | |
|
|
| 3.9016 | 1.03 | 1831680 | 3.9887 | |
|
|
| 3.8946 | 0.03 | 1908000 | 3.9864 | |
|
|
| 3.8885 | 1.03 | 1984320 | 3.9848 | |
|
|
| 3.8822 | 0.03 | 2060640 | 3.9832 | |
|
|
| 3.8791 | 0.03 | 2136960 | 3.9816 | |
|
|
| 3.8702 | 1.03 | 2213280 | 3.9803 | |
|
|
| 3.8615 | 0.03 | 2289600 | 3.9788 | |
|
|
| 3.8593 | 0.03 | 2365920 | 3.9775 | |
|
|
| 3.8616 | 1.03 | 2442240 | 3.9767 | |
|
|
| 3.8572 | 0.03 | 2518560 | 3.9757 | |
|
|
| 3.8525 | 1.03 | 2594880 | 3.9745 | |
|
|
| 3.8549 | 0.03 | 2671200 | 3.9739 | |
|
|
| 3.8517 | 1.03 | 2747520 | 3.9732 | |
|
|
| 3.85 | 0.03 | 2823840 | 3.9724 | |
|
|
| 3.8506 | 1.03 | 2900160 | 3.9718 | |
|
|
| 3.8519 | 0.03 | 2976480 | 3.9712 | |
|
|
| 3.8467 | 1.02 | 3052726 | 3.9709 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
