|
--- |
|
library_name: transformers |
|
base_model: IVN-RIN/bioBIT |
|
tags: |
|
- token-classification |
|
- generated_from_trainer |
|
datasets: |
|
- Rodrigo1771/drugtemist-it-fasttext-85-ner |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: output |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: Rodrigo1771/drugtemist-it-fasttext-85-ner |
|
type: Rodrigo1771/drugtemist-it-fasttext-85-ner |
|
config: DrugTEMIST Italian NER |
|
split: validation |
|
args: DrugTEMIST Italian NER |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9211538461538461 |
|
- name: Recall |
|
type: recall |
|
value: 0.9273959341723137 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9242643511818619 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9986302259153467 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# output |
|
|
|
This model is a fine-tuned version of [IVN-RIN/bioBIT](https://huggingface.co/IVN-RIN/bioBIT) on the Rodrigo1771/drugtemist-it-fasttext-85-ner dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0080 |
|
- Precision: 0.9212 |
|
- Recall: 0.9274 |
|
- F1: 0.9243 |
|
- Accuracy: 0.9986 |
|
|
|
## 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: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 0.9989 | 451 | 0.0051 | 0.9326 | 0.8703 | 0.9004 | 0.9984 | |
|
| 0.0116 | 2.0 | 903 | 0.0049 | 0.9066 | 0.9206 | 0.9135 | 0.9985 | |
|
| 0.0034 | 2.9989 | 1354 | 0.0056 | 0.8990 | 0.9216 | 0.9101 | 0.9984 | |
|
| 0.0018 | 4.0 | 1806 | 0.0066 | 0.9094 | 0.9235 | 0.9164 | 0.9985 | |
|
| 0.0011 | 4.9989 | 2257 | 0.0056 | 0.9082 | 0.9293 | 0.9187 | 0.9986 | |
|
| 0.0007 | 6.0 | 2709 | 0.0068 | 0.9145 | 0.9109 | 0.9127 | 0.9985 | |
|
| 0.0005 | 6.9989 | 3160 | 0.0076 | 0.8880 | 0.9284 | 0.9077 | 0.9984 | |
|
| 0.0003 | 8.0 | 3612 | 0.0080 | 0.9094 | 0.9235 | 0.9164 | 0.9986 | |
|
| 0.0002 | 8.9989 | 4063 | 0.0078 | 0.9162 | 0.9206 | 0.9184 | 0.9986 | |
|
| 0.0001 | 9.9889 | 4510 | 0.0080 | 0.9212 | 0.9274 | 0.9243 | 0.9986 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|