|
--- |
|
base_model: haryoaw/scenario-TCR-NER_data-univner_en |
|
library_name: transformers |
|
license: mit |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: scenario-non-kd-po-ner-full-xlmr_data-univner_en44 |
|
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. --> |
|
|
|
# scenario-non-kd-po-ner-full-xlmr_data-univner_en44 |
|
|
|
This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_en](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_en) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1427 |
|
- Precision: 0.7495 |
|
- Recall: 0.7774 |
|
- F1: 0.7632 |
|
- Accuracy: 0.9810 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 44 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0397 | 1.2755 | 500 | 0.0761 | 0.6856 | 0.7629 | 0.7222 | 0.9790 | |
|
| 0.0137 | 2.5510 | 1000 | 0.0903 | 0.7430 | 0.7391 | 0.7410 | 0.9804 | |
|
| 0.008 | 3.8265 | 1500 | 0.0999 | 0.7250 | 0.7723 | 0.7479 | 0.9802 | |
|
| 0.005 | 5.1020 | 2000 | 0.1024 | 0.7375 | 0.7650 | 0.7510 | 0.9808 | |
|
| 0.0033 | 6.3776 | 2500 | 0.1141 | 0.7329 | 0.7754 | 0.7535 | 0.9792 | |
|
| 0.0025 | 7.6531 | 3000 | 0.1259 | 0.7346 | 0.7536 | 0.7440 | 0.9800 | |
|
| 0.002 | 8.9286 | 3500 | 0.1351 | 0.7534 | 0.7495 | 0.7514 | 0.9799 | |
|
| 0.0022 | 10.2041 | 4000 | 0.1209 | 0.7444 | 0.7536 | 0.7490 | 0.9799 | |
|
| 0.0017 | 11.4796 | 4500 | 0.1340 | 0.7317 | 0.7567 | 0.7440 | 0.9796 | |
|
| 0.0012 | 12.7551 | 5000 | 0.1338 | 0.7455 | 0.7671 | 0.7561 | 0.9803 | |
|
| 0.0012 | 14.0306 | 5500 | 0.1365 | 0.7439 | 0.7609 | 0.7523 | 0.9794 | |
|
| 0.0011 | 15.3061 | 6000 | 0.1322 | 0.7324 | 0.7764 | 0.7538 | 0.9805 | |
|
| 0.0008 | 16.5816 | 6500 | 0.1314 | 0.7453 | 0.7816 | 0.7630 | 0.9810 | |
|
| 0.0009 | 17.8571 | 7000 | 0.1310 | 0.7495 | 0.7588 | 0.7541 | 0.9808 | |
|
| 0.0008 | 19.1327 | 7500 | 0.1396 | 0.7639 | 0.7536 | 0.7587 | 0.9815 | |
|
| 0.0005 | 20.4082 | 8000 | 0.1405 | 0.7579 | 0.7712 | 0.7645 | 0.9810 | |
|
| 0.0005 | 21.6837 | 8500 | 0.1397 | 0.7584 | 0.7702 | 0.7643 | 0.9814 | |
|
| 0.0004 | 22.9592 | 9000 | 0.1429 | 0.7452 | 0.7660 | 0.7555 | 0.9808 | |
|
| 0.0003 | 24.2347 | 9500 | 0.1437 | 0.7485 | 0.7702 | 0.7592 | 0.9806 | |
|
| 0.0004 | 25.5102 | 10000 | 0.1402 | 0.7618 | 0.7712 | 0.7665 | 0.9817 | |
|
| 0.0003 | 26.7857 | 10500 | 0.1420 | 0.7659 | 0.7723 | 0.7691 | 0.9815 | |
|
| 0.0003 | 28.0612 | 11000 | 0.1420 | 0.7533 | 0.7650 | 0.7591 | 0.9812 | |
|
| 0.0002 | 29.3367 | 11500 | 0.1427 | 0.7495 | 0.7774 | 0.7632 | 0.9810 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.19.1 |
|
|
