|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- species_800 |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: electramed-small-SPECIES800-ner |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: species_800 |
|
type: species_800 |
|
config: species_800 |
|
split: train |
|
args: species_800 |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.6221498371335505 |
|
- name: Recall |
|
type: recall |
|
value: 0.7470664928292047 |
|
- name: F1 |
|
type: f1 |
|
value: 0.6789099526066352 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9831434110359828 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# electramed-small-SPECIES800-ner |
|
|
|
This model is a fine-tuned version of [giacomomiolo/electramed_small_scivocab](https://huggingface.co/giacomomiolo/electramed_small_scivocab) on the species_800 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0513 |
|
- Precision: 0.6221 |
|
- Recall: 0.7471 |
|
- F1: 0.6789 |
|
- Accuracy: 0.9831 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0536 | 1.0 | 359 | 0.0971 | 0.6138 | 0.5554 | 0.5832 | 0.9795 | |
|
| 0.0309 | 2.0 | 718 | 0.0692 | 0.6175 | 0.6063 | 0.6118 | 0.9808 | |
|
| 0.0563 | 3.0 | 1077 | 0.0582 | 0.6424 | 0.6910 | 0.6658 | 0.9819 | |
|
| 0.0442 | 4.0 | 1436 | 0.0553 | 0.5900 | 0.7523 | 0.6613 | 0.9814 | |
|
| 0.0069 | 5.0 | 1795 | 0.0511 | 0.6291 | 0.7497 | 0.6841 | 0.9827 | |
|
| 0.0141 | 6.0 | 2154 | 0.0505 | 0.6579 | 0.7471 | 0.6996 | 0.9837 | |
|
| 0.0052 | 7.0 | 2513 | 0.0513 | 0.5965 | 0.7458 | 0.6628 | 0.9826 | |
|
| 0.0573 | 8.0 | 2872 | 0.0509 | 0.6140 | 0.7445 | 0.6730 | 0.9828 | |
|
| 0.0203 | 9.0 | 3231 | 0.0516 | 0.6118 | 0.7458 | 0.6722 | 0.9830 | |
|
| 0.0101 | 10.0 | 3590 | 0.0513 | 0.6221 | 0.7471 | 0.6789 | 0.9831 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.1 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
