|
--- |
|
base_model: jsylee/scibert_scivocab_uncased-finetuned-ner |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: scibert-finetuned_ADEs_SonatafyAI |
|
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. --> |
|
|
|
# scibert-finetuned_ADEs_SonatafyAI |
|
|
|
This model is a fine-tuned version of [jsylee/scibert_scivocab_uncased-finetuned-ner](https://huggingface.co/jsylee/scibert_scivocab_uncased-finetuned-ner) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2004 |
|
- Precision: 0.6454 |
|
- Recall: 0.6962 |
|
- F1: 0.6698 |
|
- Accuracy: 0.9095 |
|
|
|
## 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-07 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2918 | 1.0 | 640 | 0.2240 | 0.6095 | 0.7148 | 0.6579 | 0.9029 | |
|
| 0.2305 | 2.0 | 1280 | 0.2064 | 0.6354 | 0.6896 | 0.6614 | 0.9079 | |
|
| 0.2223 | 3.0 | 1920 | 0.2031 | 0.636 | 0.6951 | 0.6642 | 0.9082 | |
|
| 0.2145 | 4.0 | 2560 | 0.2010 | 0.6419 | 0.6973 | 0.6684 | 0.9089 | |
|
| 0.2081 | 5.0 | 3200 | 0.2004 | 0.6454 | 0.6962 | 0.6698 | 0.9095 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|