metadata
tags:
- generated_from_trainer
model-index:
- name: npi-only-transformer-4
results: []
npi-only-transformer-4
This model is a fine-tuned version of 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: 4
- 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 |
---|---|---|---|
4.2235 | 0.03 | 76320 | 4.1957 |
4.019 | 1.03 | 152640 | 4.0271 |
3.9115 | 0.03 | 228960 | 3.9505 |
3.8389 | 1.03 | 305280 | 3.9099 |
3.7889 | 0.03 | 381600 | 3.8846 |
3.749 | 1.03 | 457920 | 3.8686 |
3.7151 | 0.03 | 534240 | 3.8581 |
3.6879 | 1.03 | 610560 | 3.8510 |
3.6587 | 0.03 | 686880 | 3.8468 |
3.6325 | 1.03 | 763200 | 3.8441 |
3.6082 | 0.03 | 839520 | 3.8417 |
3.5868 | 1.03 | 915840 | 3.8415 |
3.5695 | 0.03 | 992160 | 3.8415 |
3.5516 | 1.03 | 1068480 | 3.8433 |
3.5316 | 0.03 | 1144800 | 3.8432 |
3.5291 | 1.03 | 1221120 | 3.8443 |
3.5091 | 0.03 | 1297440 | 3.8459 |
3.4953 | 1.03 | 1373760 | 3.8458 |
3.4831 | 0.03 | 1450080 | 3.8475 |
3.4707 | 1.03 | 1526400 | 3.8479 |
3.4629 | 0.03 | 1602720 | 3.8500 |
3.4549 | 0.03 | 1679040 | 3.8510 |
3.4461 | 1.03 | 1755360 | 3.8524 |
3.4385 | 0.03 | 1831680 | 3.8544 |
3.426 | 1.03 | 1908000 | 3.8561 |
3.4132 | 0.03 | 1984320 | 3.8569 |
3.399 | 1.03 | 2060640 | 3.8577 |
3.3863 | 0.03 | 2136960 | 3.8583 |
3.376 | 1.03 | 2213280 | 3.8598 |
3.3638 | 0.03 | 2289600 | 3.8609 |
3.3519 | 1.03 | 2365920 | 3.8610 |
3.3527 | 0.03 | 2442240 | 3.8618 |
3.338 | 1.03 | 2518560 | 3.8625 |
3.3299 | 0.03 | 2594880 | 3.8628 |
3.3204 | 0.03 | 2671200 | 3.8632 |
3.3114 | 1.03 | 2747520 | 3.8629 |
3.3075 | 0.03 | 2823840 | 3.8630 |
3.3027 | 1.03 | 2900160 | 3.8619 |
3.2984 | 0.03 | 2976480 | 3.8611 |
3.2935 | 1.02 | 3052726 | 3.8598 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3