|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: npi-sim-ques-transformer-0 |
|
|
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-0 |
|
|
|
|
|
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: 3.8645 |
|
|
|
|
|
## 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: 0 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2355 | 0.03 | 76320 | 4.1957 | |
|
|
| 4.0283 | 1.03 | 152640 | 4.0271 | |
|
|
| 3.9226 | 0.03 | 228960 | 3.9523 | |
|
|
| 3.8525 | 1.03 | 305280 | 3.9112 | |
|
|
| 3.7987 | 0.03 | 381600 | 3.8874 | |
|
|
| 3.7585 | 0.03 | 457920 | 3.8707 | |
|
|
| 3.7256 | 1.03 | 534240 | 3.8600 | |
|
|
| 3.6925 | 0.03 | 610560 | 3.8526 | |
|
|
| 3.6629 | 1.03 | 686880 | 3.8489 | |
|
|
| 3.638 | 0.03 | 763200 | 3.8461 | |
|
|
| 3.6149 | 1.03 | 839520 | 3.8438 | |
|
|
| 3.5961 | 0.03 | 915840 | 3.8432 | |
|
|
| 3.5736 | 1.03 | 992160 | 3.8439 | |
|
|
| 3.5512 | 0.03 | 1068480 | 3.8437 | |
|
|
| 3.5368 | 1.03 | 1144800 | 3.8446 | |
|
|
| 3.5316 | 0.03 | 1221120 | 3.8466 | |
|
|
| 3.5167 | 1.03 | 1297440 | 3.8475 | |
|
|
| 3.5006 | 0.03 | 1373760 | 3.8494 | |
|
|
| 3.4911 | 1.03 | 1450080 | 3.8496 | |
|
|
| 3.4783 | 0.03 | 1526400 | 3.8520 | |
|
|
| 3.4688 | 1.03 | 1602720 | 3.8533 | |
|
|
| 3.4614 | 0.03 | 1679040 | 3.8556 | |
|
|
| 3.4521 | 0.03 | 1755360 | 3.8569 | |
|
|
| 3.439 | 1.03 | 1831680 | 3.8583 | |
|
|
| 3.4277 | 0.03 | 1908000 | 3.8584 | |
|
|
| 3.4129 | 1.03 | 1984320 | 3.8603 | |
|
|
| 3.4039 | 0.03 | 2060640 | 3.8618 | |
|
|
| 3.3952 | 1.03 | 2136960 | 3.8636 | |
|
|
| 3.38 | 0.03 | 2213280 | 3.8643 | |
|
|
| 3.3646 | 1.03 | 2289600 | 3.8643 | |
|
|
| 3.358 | 0.03 | 2365920 | 3.8663 | |
|
|
| 3.3554 | 1.03 | 2442240 | 3.8673 | |
|
|
| 3.3451 | 0.03 | 2518560 | 3.8676 | |
|
|
| 3.3336 | 1.03 | 2594880 | 3.8677 | |
|
|
| 3.3289 | 0.03 | 2671200 | 3.8682 | |
|
|
| 3.3191 | 1.03 | 2747520 | 3.8673 | |
|
|
| 3.3109 | 0.03 | 2823840 | 3.8671 | |
|
|
| 3.3068 | 1.03 | 2900160 | 3.8667 | |
|
|
| 3.3028 | 0.03 | 2976480 | 3.8658 | |
|
|
| 3.2929 | 0.02 | 3052726 | 3.8645 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
