|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: npi-only-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-only-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: 3.8616 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.2265 | 0.03 | 76320 | 4.1999 | |
|
| 4.0215 | 1.03 | 152640 | 4.0292 | |
|
| 3.9133 | 0.03 | 228960 | 3.9544 | |
|
| 3.8411 | 1.03 | 305280 | 3.9125 | |
|
| 3.7911 | 0.03 | 381600 | 3.8867 | |
|
| 3.7507 | 1.03 | 457920 | 3.8704 | |
|
| 3.7187 | 0.03 | 534240 | 3.8599 | |
|
| 3.6904 | 1.03 | 610560 | 3.8540 | |
|
| 3.6628 | 0.03 | 686880 | 3.8482 | |
|
| 3.6345 | 1.03 | 763200 | 3.8461 | |
|
| 3.6098 | 0.03 | 839520 | 3.8440 | |
|
| 3.5897 | 1.03 | 915840 | 3.8438 | |
|
| 3.572 | 0.03 | 992160 | 3.8438 | |
|
| 3.5528 | 1.03 | 1068480 | 3.8441 | |
|
| 3.5343 | 0.03 | 1144800 | 3.8445 | |
|
| 3.5293 | 1.03 | 1221120 | 3.8463 | |
|
| 3.5111 | 0.03 | 1297440 | 3.8466 | |
|
| 3.499 | 1.03 | 1373760 | 3.8482 | |
|
| 3.4854 | 0.03 | 1450080 | 3.8505 | |
|
| 3.4724 | 0.03 | 1526400 | 3.8520 | |
|
| 3.4654 | 1.03 | 1602720 | 3.8540 | |
|
| 3.455 | 0.03 | 1679040 | 3.8551 | |
|
| 3.4482 | 1.03 | 1755360 | 3.8560 | |
|
| 3.4398 | 0.03 | 1831680 | 3.8573 | |
|
| 3.4268 | 1.03 | 1908000 | 3.8586 | |
|
| 3.4123 | 0.03 | 1984320 | 3.8589 | |
|
| 3.3989 | 0.03 | 2060640 | 3.8610 | |
|
| 3.3867 | 1.03 | 2136960 | 3.8618 | |
|
| 3.3755 | 0.03 | 2213280 | 3.8635 | |
|
| 3.364 | 1.03 | 2289600 | 3.8636 | |
|
| 3.3533 | 0.03 | 2365920 | 3.8637 | |
|
| 3.3544 | 0.03 | 2442240 | 3.8637 | |
|
| 3.3405 | 1.03 | 2518560 | 3.8649 | |
|
| 3.3325 | 0.03 | 2594880 | 3.8654 | |
|
| 3.3219 | 1.03 | 2671200 | 3.8645 | |
|
| 3.3145 | 0.03 | 2747520 | 3.8646 | |
|
| 3.3084 | 1.03 | 2823840 | 3.8649 | |
|
| 3.3026 | 0.03 | 2900160 | 3.8641 | |
|
| 3.299 | 1.03 | 2976480 | 3.8632 | |
|
| 3.2939 | 0.02 | 3052726 | 3.8616 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|