|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: michiyasunaga/BioLinkBERT-base |
|
tags: |
|
- token-classification |
|
- generated_from_trainer |
|
datasets: |
|
- Rodrigo1771/drugtemist-en-85-ner |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: output |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: Rodrigo1771/drugtemist-en-85-ner |
|
type: Rodrigo1771/drugtemist-en-85-ner |
|
config: DrugTEMIST English NER |
|
split: validation |
|
args: DrugTEMIST English NER |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9302325581395349 |
|
- name: Recall |
|
type: recall |
|
value: 0.9319664492078286 |
|
- name: F1 |
|
type: f1 |
|
value: 0.931098696461825 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9986534758462869 |
|
--- |
|
|
|
<!-- 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 [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on the Rodrigo1771/drugtemist-en-85-ner dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0083 |
|
- Precision: 0.9302 |
|
- Recall: 0.9320 |
|
- F1: 0.9311 |
|
- Accuracy: 0.9987 |
|
|
|
## 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 | 457 | 0.0056 | 0.8730 | 0.9292 | 0.9002 | 0.9983 | |
|
| 0.0158 | 2.0 | 915 | 0.0066 | 0.8625 | 0.9357 | 0.8976 | 0.9981 | |
|
| 0.0037 | 2.9989 | 1372 | 0.0056 | 0.9247 | 0.9161 | 0.9204 | 0.9986 | |
|
| 0.0025 | 4.0 | 1830 | 0.0064 | 0.9234 | 0.9096 | 0.9164 | 0.9985 | |
|
| 0.0015 | 4.9989 | 2287 | 0.0061 | 0.9193 | 0.9236 | 0.9214 | 0.9985 | |
|
| 0.0008 | 6.0 | 2745 | 0.0074 | 0.9282 | 0.9273 | 0.9277 | 0.9986 | |
|
| 0.0006 | 6.9989 | 3202 | 0.0077 | 0.9305 | 0.9226 | 0.9265 | 0.9986 | |
|
| 0.0003 | 8.0 | 3660 | 0.0082 | 0.9282 | 0.9282 | 0.9282 | 0.9986 | |
|
| 0.0004 | 8.9989 | 4117 | 0.0083 | 0.9290 | 0.9264 | 0.9277 | 0.9986 | |
|
| 0.0002 | 9.9891 | 4570 | 0.0083 | 0.9302 | 0.9320 | 0.9311 | 0.9987 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
