|
--- |
|
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-pre-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-pre-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: 0.1413 |
|
- Precision: 0.7900 |
|
- Recall: 0.8023 |
|
- F1: 0.7961 |
|
- Accuracy: 0.9836 |
|
|
|
## 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 | |
|
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0035 | 1.2755 | 500 | 0.1065 | 0.7916 | 0.8023 | 0.7969 | 0.9842 | |
|
| 0.0036 | 2.5510 | 1000 | 0.1246 | 0.7914 | 0.7619 | 0.7764 | 0.9821 | |
|
| 0.0027 | 3.8265 | 1500 | 0.1191 | 0.7819 | 0.8054 | 0.7935 | 0.9837 | |
|
| 0.002 | 5.1020 | 2000 | 0.1324 | 0.7907 | 0.7940 | 0.7924 | 0.9831 | |
|
| 0.0023 | 6.3776 | 2500 | 0.1197 | 0.7826 | 0.8085 | 0.7953 | 0.9836 | |
|
| 0.0017 | 7.6531 | 3000 | 0.1390 | 0.7673 | 0.8054 | 0.7859 | 0.9819 | |
|
| 0.0012 | 8.9286 | 3500 | 0.1371 | 0.7827 | 0.7609 | 0.7717 | 0.9815 | |
|
| 0.0013 | 10.2041 | 4000 | 0.1459 | 0.7426 | 0.8002 | 0.7703 | 0.9809 | |
|
| 0.0017 | 11.4796 | 4500 | 0.1345 | 0.7771 | 0.7723 | 0.7747 | 0.9819 | |
|
| 0.0011 | 12.7551 | 5000 | 0.1327 | 0.7824 | 0.7930 | 0.7877 | 0.9831 | |
|
| 0.001 | 14.0306 | 5500 | 0.1422 | 0.7591 | 0.7961 | 0.7772 | 0.9813 | |
|
| 0.0009 | 15.3061 | 6000 | 0.1383 | 0.7715 | 0.7899 | 0.7806 | 0.9819 | |
|
| 0.0006 | 16.5816 | 6500 | 0.1360 | 0.7827 | 0.8054 | 0.7939 | 0.9831 | |
|
| 0.0006 | 17.8571 | 7000 | 0.1429 | 0.7889 | 0.7930 | 0.7909 | 0.9834 | |
|
| 0.0006 | 19.1327 | 7500 | 0.1409 | 0.7933 | 0.7826 | 0.7879 | 0.9827 | |
|
| 0.0005 | 20.4082 | 8000 | 0.1415 | 0.7886 | 0.7992 | 0.7938 | 0.9835 | |
|
| 0.0005 | 21.6837 | 8500 | 0.1361 | 0.7913 | 0.7930 | 0.7921 | 0.9832 | |
|
| 0.0004 | 22.9592 | 9000 | 0.1393 | 0.8069 | 0.8002 | 0.8035 | 0.9839 | |
|
| 0.0004 | 24.2347 | 9500 | 0.1376 | 0.7784 | 0.8147 | 0.7962 | 0.9835 | |
|
| 0.0003 | 25.5102 | 10000 | 0.1421 | 0.7862 | 0.7919 | 0.7891 | 0.9833 | |
|
| 0.0002 | 26.7857 | 10500 | 0.1417 | 0.7882 | 0.8054 | 0.7967 | 0.9834 | |
|
| 0.0002 | 28.0612 | 11000 | 0.1399 | 0.7900 | 0.7981 | 0.7940 | 0.9835 | |
|
| 0.0001 | 29.3367 | 11500 | 0.1413 | 0.7900 | 0.8023 | 0.7961 | 0.9836 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.19.1 |
|
|
