|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: npi-only-transformer-3 |
|
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-3 |
|
|
|
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: 3.8598 |
|
|
|
## 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: 3 |
|
- 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.2223 | 0.03 | 76320 | 4.1964 | |
|
| 4.0204 | 1.03 | 152640 | 4.0268 | |
|
| 3.912 | 0.03 | 228960 | 3.9523 | |
|
| 3.8408 | 1.03 | 305280 | 3.9111 | |
|
| 3.7917 | 0.03 | 381600 | 3.8861 | |
|
| 3.7492 | 1.03 | 457920 | 3.8700 | |
|
| 3.7159 | 0.03 | 534240 | 3.8608 | |
|
| 3.6895 | 1.03 | 610560 | 3.8526 | |
|
| 3.6619 | 0.03 | 686880 | 3.8481 | |
|
| 3.6343 | 1.03 | 763200 | 3.8460 | |
|
| 3.61 | 0.03 | 839520 | 3.8443 | |
|
| 3.5902 | 1.03 | 915840 | 3.8437 | |
|
| 3.571 | 0.03 | 992160 | 3.8429 | |
|
| 3.5525 | 1.03 | 1068480 | 3.8434 | |
|
| 3.5337 | 0.03 | 1144800 | 3.8455 | |
|
| 3.5324 | 1.03 | 1221120 | 3.8451 | |
|
| 3.5107 | 0.03 | 1297440 | 3.8464 | |
|
| 3.4996 | 1.03 | 1373760 | 3.8468 | |
|
| 3.4875 | 0.03 | 1450080 | 3.8484 | |
|
| 3.475 | 1.03 | 1526400 | 3.8496 | |
|
| 3.4666 | 0.03 | 1602720 | 3.8495 | |
|
| 3.4571 | 1.03 | 1679040 | 3.8516 | |
|
| 3.4483 | 0.03 | 1755360 | 3.8525 | |
|
| 3.4417 | 1.03 | 1831680 | 3.8534 | |
|
| 3.4295 | 0.03 | 1908000 | 3.8552 | |
|
| 3.4152 | 1.03 | 1984320 | 3.8558 | |
|
| 3.3995 | 0.03 | 2060640 | 3.8572 | |
|
| 3.3901 | 1.03 | 2136960 | 3.8578 | |
|
| 3.3801 | 0.03 | 2213280 | 3.8582 | |
|
| 3.367 | 1.03 | 2289600 | 3.8592 | |
|
| 3.3558 | 0.03 | 2365920 | 3.8611 | |
|
| 3.3561 | 1.03 | 2442240 | 3.8599 | |
|
| 3.3408 | 0.03 | 2518560 | 3.8615 | |
|
| 3.334 | 1.03 | 2594880 | 3.8621 | |
|
| 3.3245 | 0.03 | 2671200 | 3.8619 | |
|
| 3.317 | 0.03 | 2747520 | 3.8619 | |
|
| 3.3107 | 1.03 | 2823840 | 3.8615 | |
|
| 3.3063 | 0.03 | 2900160 | 3.8617 | |
|
| 3.3022 | 1.03 | 2976480 | 3.8610 | |
|
| 3.2972 | 0.02 | 3052726 | 3.8598 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|