metadata
tags:
- generated_from_trainer
model-index:
- name: npi-only-transformer-2
results: []
npi-only-transformer-2
This model is a fine-tuned version of 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