|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: npi-only-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-only-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: 3.8634 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.224 | 0.03 | 76320 | 4.1960 | |
|
|
| 4.021 | 1.03 | 152640 | 4.0259 | |
|
|
| 3.9128 | 0.03 | 228960 | 3.9511 | |
|
|
| 3.8414 | 1.03 | 305280 | 3.9098 | |
|
|
| 3.7915 | 0.03 | 381600 | 3.8843 | |
|
|
| 3.7489 | 1.03 | 457920 | 3.8684 | |
|
|
| 3.7172 | 0.03 | 534240 | 3.8578 | |
|
|
| 3.6886 | 1.03 | 610560 | 3.8503 | |
|
|
| 3.6592 | 0.03 | 686880 | 3.8463 | |
|
|
| 3.635 | 1.03 | 763200 | 3.8440 | |
|
|
| 3.6089 | 0.03 | 839520 | 3.8414 | |
|
|
| 3.5858 | 1.03 | 915840 | 3.8406 | |
|
|
| 3.5679 | 0.03 | 992160 | 3.8411 | |
|
|
| 3.5481 | 1.03 | 1068480 | 3.8400 | |
|
|
| 3.5304 | 0.03 | 1144800 | 3.8423 | |
|
|
| 3.5273 | 1.03 | 1221120 | 3.8431 | |
|
|
| 3.5084 | 0.03 | 1297440 | 3.8436 | |
|
|
| 3.4931 | 1.03 | 1373760 | 3.8460 | |
|
|
| 3.4817 | 0.03 | 1450080 | 3.8460 | |
|
|
| 3.4695 | 1.03 | 1526400 | 3.8482 | |
|
|
| 3.4604 | 0.03 | 1602720 | 3.8497 | |
|
|
| 3.451 | 0.03 | 1679040 | 3.8507 | |
|
|
| 3.4443 | 1.03 | 1755360 | 3.8523 | |
|
|
| 3.4359 | 0.03 | 1831680 | 3.8535 | |
|
|
| 3.4238 | 1.03 | 1908000 | 3.8556 | |
|
|
| 3.4097 | 0.03 | 1984320 | 3.8569 | |
|
|
| 3.3949 | 1.03 | 2060640 | 3.8573 | |
|
|
| 3.3833 | 0.03 | 2136960 | 3.8597 | |
|
|
| 3.373 | 1.03 | 2213280 | 3.8602 | |
|
|
| 3.3626 | 0.03 | 2289600 | 3.8611 | |
|
|
| 3.3495 | 1.03 | 2365920 | 3.8634 | |
|
|
| 3.3497 | 0.03 | 2442240 | 3.8635 | |
|
|
| 3.3351 | 1.03 | 2518560 | 3.8644 | |
|
|
| 3.3289 | 0.03 | 2594880 | 3.8649 | |
|
|
| 3.3182 | 1.03 | 2671200 | 3.8660 | |
|
|
| 3.3091 | 0.03 | 2747520 | 3.8667 | |
|
|
| 3.3031 | 1.03 | 2823840 | 3.8655 | |
|
|
| 3.2978 | 0.03 | 2900160 | 3.8657 | |
|
|
| 3.2938 | 0.03 | 2976480 | 3.8646 | |
|
|
| 3.2916 | 0.02 | 3052726 | 3.8634 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
