|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: 20240327180321_slow_hinton |
|
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. --> |
|
|
|
# 20240327180321_slow_hinton |
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0488 |
|
- Precision: 0.9507 |
|
- Recall: 0.9581 |
|
- F1: 0.9544 |
|
- Accuracy: 0.9830 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 69 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 350 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.095 | 0.09 | 300 | 0.0845 | 0.9071 | 0.9202 | 0.9136 | 0.9668 | |
|
| 0.0884 | 0.18 | 600 | 0.0782 | 0.9112 | 0.9274 | 0.9192 | 0.9689 | |
|
| 0.0861 | 0.26 | 900 | 0.0761 | 0.9139 | 0.9294 | 0.9215 | 0.9698 | |
|
| 0.082 | 0.35 | 1200 | 0.0742 | 0.9171 | 0.9322 | 0.9246 | 0.9711 | |
|
| 0.0794 | 0.44 | 1500 | 0.0708 | 0.9229 | 0.9330 | 0.9279 | 0.9725 | |
|
| 0.0788 | 0.53 | 1800 | 0.0699 | 0.9239 | 0.9339 | 0.9289 | 0.9729 | |
|
| 0.078 | 0.62 | 2100 | 0.0701 | 0.9224 | 0.9339 | 0.9281 | 0.9726 | |
|
| 0.0785 | 0.71 | 2400 | 0.0698 | 0.9278 | 0.9286 | 0.9282 | 0.9727 | |
|
| 0.0768 | 0.79 | 2700 | 0.0686 | 0.9285 | 0.9326 | 0.9306 | 0.9736 | |
|
| 0.0764 | 0.88 | 3000 | 0.0694 | 0.9166 | 0.9418 | 0.9290 | 0.9727 | |
|
| 0.0754 | 0.97 | 3300 | 0.0674 | 0.9289 | 0.9341 | 0.9315 | 0.9740 | |
|
| 0.0687 | 1.06 | 3600 | 0.0665 | 0.9304 | 0.9359 | 0.9332 | 0.9746 | |
|
| 0.0697 | 1.15 | 3900 | 0.0664 | 0.9256 | 0.9410 | 0.9332 | 0.9744 | |
|
| 0.0682 | 1.24 | 4200 | 0.0651 | 0.9258 | 0.9418 | 0.9337 | 0.9746 | |
|
| 0.0679 | 1.32 | 4500 | 0.0637 | 0.9296 | 0.9425 | 0.9360 | 0.9757 | |
|
| 0.0685 | 1.41 | 4800 | 0.0640 | 0.9288 | 0.9428 | 0.9357 | 0.9755 | |
|
| 0.0662 | 1.5 | 5100 | 0.0627 | 0.9336 | 0.9394 | 0.9365 | 0.9760 | |
|
| 0.0655 | 1.59 | 5400 | 0.0617 | 0.9334 | 0.9422 | 0.9378 | 0.9764 | |
|
| 0.0656 | 1.68 | 5700 | 0.0621 | 0.9298 | 0.9458 | 0.9377 | 0.9763 | |
|
| 0.065 | 1.77 | 6000 | 0.0610 | 0.9352 | 0.9419 | 0.9386 | 0.9768 | |
|
| 0.0647 | 1.85 | 6300 | 0.0597 | 0.9341 | 0.9465 | 0.9403 | 0.9774 | |
|
| 0.0629 | 1.94 | 6600 | 0.0591 | 0.9342 | 0.9457 | 0.9399 | 0.9772 | |
|
| 0.0557 | 2.03 | 6900 | 0.0592 | 0.9375 | 0.9455 | 0.9415 | 0.9779 | |
|
| 0.0563 | 2.12 | 7200 | 0.0598 | 0.9355 | 0.9454 | 0.9404 | 0.9774 | |
|
| 0.0564 | 2.21 | 7500 | 0.0573 | 0.9375 | 0.9483 | 0.9428 | 0.9783 | |
|
| 0.0574 | 2.3 | 7800 | 0.0571 | 0.9368 | 0.9490 | 0.9429 | 0.9783 | |
|
| 0.0564 | 2.38 | 8100 | 0.0578 | 0.9375 | 0.9482 | 0.9428 | 0.9783 | |
|
| 0.0553 | 2.47 | 8400 | 0.0574 | 0.9387 | 0.9472 | 0.9429 | 0.9785 | |
|
| 0.0557 | 2.56 | 8700 | 0.0564 | 0.9378 | 0.9505 | 0.9441 | 0.9788 | |
|
| 0.0554 | 2.65 | 9000 | 0.0557 | 0.9410 | 0.9472 | 0.9441 | 0.9789 | |
|
| 0.0542 | 2.74 | 9300 | 0.0545 | 0.9409 | 0.9516 | 0.9462 | 0.9796 | |
|
| 0.0533 | 2.83 | 9600 | 0.0540 | 0.9430 | 0.9501 | 0.9465 | 0.9799 | |
|
| 0.0523 | 2.91 | 9900 | 0.0538 | 0.9388 | 0.9523 | 0.9455 | 0.9794 | |
|
| 0.0509 | 3.0 | 10200 | 0.0547 | 0.9430 | 0.9503 | 0.9466 | 0.9798 | |
|
| 0.0459 | 3.09 | 10500 | 0.0538 | 0.9428 | 0.9512 | 0.9470 | 0.9801 | |
|
| 0.0443 | 3.18 | 10800 | 0.0549 | 0.9438 | 0.9496 | 0.9467 | 0.9800 | |
|
| 0.0458 | 3.27 | 11100 | 0.0536 | 0.9440 | 0.9516 | 0.9478 | 0.9804 | |
|
| 0.0445 | 3.36 | 11400 | 0.0523 | 0.9451 | 0.9509 | 0.9480 | 0.9805 | |
|
| 0.0449 | 3.44 | 11700 | 0.0513 | 0.9453 | 0.9527 | 0.9490 | 0.9808 | |
|
| 0.0442 | 3.53 | 12000 | 0.0518 | 0.9477 | 0.9513 | 0.9495 | 0.9811 | |
|
| 0.0441 | 3.62 | 12300 | 0.0511 | 0.9447 | 0.9551 | 0.9499 | 0.9811 | |
|
| 0.0439 | 3.71 | 12600 | 0.0503 | 0.9465 | 0.9556 | 0.9510 | 0.9815 | |
|
| 0.0442 | 3.8 | 12900 | 0.0502 | 0.9466 | 0.9538 | 0.9502 | 0.9813 | |
|
| 0.0431 | 3.88 | 13200 | 0.0503 | 0.9473 | 0.9549 | 0.9511 | 0.9817 | |
|
| 0.0429 | 3.97 | 13500 | 0.0491 | 0.9473 | 0.9559 | 0.9516 | 0.9819 | |
|
| 0.0356 | 4.06 | 13800 | 0.0522 | 0.9465 | 0.9566 | 0.9515 | 0.9818 | |
|
| 0.0354 | 4.15 | 14100 | 0.0518 | 0.9489 | 0.9560 | 0.9524 | 0.9822 | |
|
| 0.0357 | 4.24 | 14400 | 0.0509 | 0.9485 | 0.9565 | 0.9525 | 0.9822 | |
|
| 0.0353 | 4.33 | 14700 | 0.0507 | 0.9492 | 0.9563 | 0.9527 | 0.9823 | |
|
| 0.0352 | 4.41 | 15000 | 0.0498 | 0.9497 | 0.9572 | 0.9534 | 0.9826 | |
|
| 0.0352 | 4.5 | 15300 | 0.0492 | 0.9496 | 0.9577 | 0.9536 | 0.9826 | |
|
| 0.0341 | 4.59 | 15600 | 0.0493 | 0.9494 | 0.9583 | 0.9538 | 0.9827 | |
|
| 0.034 | 4.68 | 15900 | 0.0495 | 0.9504 | 0.9576 | 0.9540 | 0.9828 | |
|
| 0.0334 | 4.77 | 16200 | 0.0493 | 0.9501 | 0.9584 | 0.9542 | 0.9829 | |
|
| 0.0335 | 4.86 | 16500 | 0.0493 | 0.9509 | 0.9574 | 0.9541 | 0.9828 | |
|
| 0.0338 | 4.94 | 16800 | 0.0488 | 0.9507 | 0.9581 | 0.9544 | 0.9830 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.1 |
|
- Pytorch 2.2.0a0+6a974be |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|