metadata
tags:
- generated_from_trainer
model-index:
- name: npi-only-transformer-1
results: []
npi-only-transformer-1
This model is a fine-tuned version of 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