|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: bert-base-greek-uncased-v2-finetuned-polylex |
|
|
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. --> |
|
|
|
|
|
# bert-base-greek-uncased-v2-finetuned-polylex |
|
|
|
|
|
This model is a fine-tuned version of [nlpaueb/bert-base-greek-uncased-v1](https://huggingface.co/nlpaueb/bert-base-greek-uncased-v1) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.7748 |
|
|
|
|
|
## 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: 2e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 50 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.9392 | 1.0 | 12 | 2.6722 | |
|
|
| 0.8066 | 2.0 | 24 | 2.5322 | |
|
|
| 0.6438 | 3.0 | 36 | 2.2449 | |
|
|
| 0.5654 | 4.0 | 48 | 2.2614 | |
|
|
| 0.6796 | 5.0 | 60 | 2.7160 | |
|
|
| 0.6361 | 6.0 | 72 | 3.0292 | |
|
|
| 0.6515 | 7.0 | 84 | 3.2517 | |
|
|
| 0.6073 | 8.0 | 96 | 2.7854 | |
|
|
| 0.5889 | 9.0 | 108 | 2.4421 | |
|
|
| 0.7134 | 10.0 | 120 | 2.6351 | |
|
|
| 0.3772 | 11.0 | 132 | 2.6377 | |
|
|
| 0.5095 | 12.0 | 144 | 2.5834 | |
|
|
| 0.3965 | 13.0 | 156 | 2.8454 | |
|
|
| 0.4555 | 14.0 | 168 | 2.2274 | |
|
|
| 0.4788 | 15.0 | 180 | 2.2452 | |
|
|
| 0.543 | 16.0 | 192 | 2.4528 | |
|
|
| 0.4249 | 17.0 | 204 | 3.1464 | |
|
|
| 0.5451 | 18.0 | 216 | 2.9913 | |
|
|
| 0.4661 | 19.0 | 228 | 2.6519 | |
|
|
| 0.3383 | 20.0 | 240 | 2.9366 | |
|
|
| 0.3598 | 21.0 | 252 | 3.2501 | |
|
|
| 0.5232 | 22.0 | 264 | 2.3395 | |
|
|
| 0.3792 | 23.0 | 276 | 2.8389 | |
|
|
| 0.4436 | 24.0 | 288 | 2.7843 | |
|
|
| 0.3975 | 25.0 | 300 | 2.3773 | |
|
|
| 0.3268 | 26.0 | 312 | 4.0139 | |
|
|
| 0.4764 | 27.0 | 324 | 3.7974 | |
|
|
| 0.3743 | 28.0 | 336 | 2.0727 | |
|
|
| 0.4574 | 29.0 | 348 | 2.5576 | |
|
|
| 0.5219 | 30.0 | 360 | 3.3557 | |
|
|
| 0.3854 | 31.0 | 372 | 2.4598 | |
|
|
| 0.4107 | 32.0 | 384 | 2.8564 | |
|
|
| 0.3899 | 33.0 | 396 | 2.4589 | |
|
|
| 0.3655 | 34.0 | 408 | 2.6613 | |
|
|
| 0.4607 | 35.0 | 420 | 2.7836 | |
|
|
| 0.3703 | 36.0 | 432 | 2.9499 | |
|
|
| 0.455 | 37.0 | 444 | 2.9653 | |
|
|
| 0.4234 | 38.0 | 456 | 1.7769 | |
|
|
| 0.4161 | 39.0 | 468 | 2.9451 | |
|
|
| 0.3983 | 40.0 | 480 | 2.6283 | |
|
|
| 0.5074 | 41.0 | 492 | 2.8233 | |
|
|
| 0.4793 | 42.0 | 504 | 2.4598 | |
|
|
| 0.5614 | 43.0 | 516 | 3.3149 | |
|
|
| 0.4965 | 44.0 | 528 | 2.0932 | |
|
|
| 0.5946 | 45.0 | 540 | 2.6992 | |
|
|
| 0.5001 | 46.0 | 552 | 2.7653 | |
|
|
| 0.6891 | 47.0 | 564 | 2.6126 | |
|
|
| 0.8634 | 48.0 | 576 | 1.9130 | |
|
|
| 0.639 | 49.0 | 588 | 2.7710 | |
|
|
| 0.572 | 50.0 | 600 | 3.3767 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.30.2 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 2.13.1 |
|
|
- Tokenizers 0.13.3 |
|
|
|
