|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: npi-sim-ques-transformer-1 |
|
|
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-transformer-1 |
|
|
|
|
|
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: 3.8619 |
|
|
|
|
|
## 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: 1 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2375 | 0.03 | 76320 | 4.1971 | |
|
|
| 4.0282 | 1.03 | 152640 | 4.0283 | |
|
|
| 3.9236 | 0.03 | 228960 | 3.9527 | |
|
|
| 3.8528 | 1.03 | 305280 | 3.9116 | |
|
|
| 3.7989 | 0.03 | 381600 | 3.8860 | |
|
|
| 3.7596 | 0.03 | 457920 | 3.8695 | |
|
|
| 3.725 | 1.03 | 534240 | 3.8590 | |
|
|
| 3.6914 | 0.03 | 610560 | 3.8515 | |
|
|
| 3.663 | 1.03 | 686880 | 3.8472 | |
|
|
| 3.6364 | 0.03 | 763200 | 3.8443 | |
|
|
| 3.6133 | 1.03 | 839520 | 3.8424 | |
|
|
| 3.5958 | 0.03 | 915840 | 3.8413 | |
|
|
| 3.5717 | 1.03 | 992160 | 3.8403 | |
|
|
| 3.5508 | 0.03 | 1068480 | 3.8411 | |
|
|
| 3.5374 | 1.03 | 1144800 | 3.8404 | |
|
|
| 3.5307 | 0.03 | 1221120 | 3.8424 | |
|
|
| 3.5136 | 1.03 | 1297440 | 3.8437 | |
|
|
| 3.5008 | 0.03 | 1373760 | 3.8459 | |
|
|
| 3.4902 | 1.03 | 1450080 | 3.8467 | |
|
|
| 3.4789 | 0.03 | 1526400 | 3.8487 | |
|
|
| 3.469 | 1.03 | 1602720 | 3.8494 | |
|
|
| 3.46 | 0.03 | 1679040 | 3.8510 | |
|
|
| 3.4508 | 1.03 | 1755360 | 3.8526 | |
|
|
| 3.437 | 0.03 | 1831680 | 3.8534 | |
|
|
| 3.4233 | 1.03 | 1908000 | 3.8546 | |
|
|
| 3.4119 | 0.03 | 1984320 | 3.8562 | |
|
|
| 3.3993 | 1.03 | 2060640 | 3.8578 | |
|
|
| 3.3929 | 0.03 | 2136960 | 3.8581 | |
|
|
| 3.3765 | 1.03 | 2213280 | 3.8606 | |
|
|
| 3.3611 | 0.03 | 2289600 | 3.8612 | |
|
|
| 3.3543 | 1.03 | 2365920 | 3.8624 | |
|
|
| 3.3543 | 0.03 | 2442240 | 3.8624 | |
|
|
| 3.3435 | 1.03 | 2518560 | 3.8634 | |
|
|
| 3.3332 | 0.03 | 2594880 | 3.8640 | |
|
|
| 3.3239 | 1.03 | 2671200 | 3.8647 | |
|
|
| 3.318 | 0.03 | 2747520 | 3.8650 | |
|
|
| 3.3101 | 1.03 | 2823840 | 3.8644 | |
|
|
| 3.3052 | 0.03 | 2900160 | 3.8643 | |
|
|
| 3.3 | 1.03 | 2976480 | 3.8636 | |
|
|
| 3.2909 | 0.02 | 3052726 | 3.8619 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
