|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: npi-sim-ques-transformer-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-transformer-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: 3.8596 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.236 | 0.03 | 76320 | 4.1966 | |
|
|
| 4.0278 | 1.03 | 152640 | 4.0278 | |
|
|
| 3.9233 | 0.03 | 228960 | 3.9528 | |
|
|
| 3.8525 | 1.03 | 305280 | 3.9101 | |
|
|
| 3.7996 | 0.03 | 381600 | 3.8852 | |
|
|
| 3.76 | 0.03 | 457920 | 3.8693 | |
|
|
| 3.7243 | 1.03 | 534240 | 3.8584 | |
|
|
| 3.6919 | 0.03 | 610560 | 3.8520 | |
|
|
| 3.6631 | 1.03 | 686880 | 3.8469 | |
|
|
| 3.6379 | 0.03 | 763200 | 3.8443 | |
|
|
| 3.6153 | 1.03 | 839520 | 3.8424 | |
|
|
| 3.5968 | 0.03 | 915840 | 3.8410 | |
|
|
| 3.5729 | 1.03 | 992160 | 3.8428 | |
|
|
| 3.5536 | 0.03 | 1068480 | 3.8435 | |
|
|
| 3.5392 | 1.03 | 1144800 | 3.8427 | |
|
|
| 3.5331 | 0.03 | 1221120 | 3.8431 | |
|
|
| 3.519 | 1.03 | 1297440 | 3.8451 | |
|
|
| 3.5032 | 0.03 | 1373760 | 3.8465 | |
|
|
| 3.4931 | 1.03 | 1450080 | 3.8464 | |
|
|
| 3.4808 | 0.03 | 1526400 | 3.8482 | |
|
|
| 3.471 | 1.03 | 1602720 | 3.8491 | |
|
|
| 3.4641 | 0.03 | 1679040 | 3.8513 | |
|
|
| 3.454 | 0.03 | 1755360 | 3.8520 | |
|
|
| 3.4402 | 1.03 | 1831680 | 3.8531 | |
|
|
| 3.4275 | 0.03 | 1908000 | 3.8550 | |
|
|
| 3.4157 | 1.03 | 1984320 | 3.8553 | |
|
|
| 3.406 | 0.03 | 2060640 | 3.8571 | |
|
|
| 3.395 | 1.03 | 2136960 | 3.8574 | |
|
|
| 3.3784 | 0.03 | 2213280 | 3.8600 | |
|
|
| 3.3662 | 1.03 | 2289600 | 3.8591 | |
|
|
| 3.3576 | 0.03 | 2365920 | 3.8592 | |
|
|
| 3.355 | 1.03 | 2442240 | 3.8609 | |
|
|
| 3.3466 | 0.03 | 2518560 | 3.8618 | |
|
|
| 3.3352 | 1.03 | 2594880 | 3.8626 | |
|
|
| 3.3291 | 0.03 | 2671200 | 3.8615 | |
|
|
| 3.3208 | 1.03 | 2747520 | 3.8622 | |
|
|
| 3.3146 | 0.03 | 2823840 | 3.8622 | |
|
|
| 3.3096 | 0.03 | 2900160 | 3.8620 | |
|
|
| 3.3031 | 0.03 | 2976480 | 3.8603 | |
|
|
| 3.2941 | 1.02 | 3052726 | 3.8596 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
