|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: SETH_1e-05_0404_ES6_strict_tok |
|
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. --> |
|
|
|
# SETH_1e-05_0404_ES6_strict_tok |
|
|
|
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1042 |
|
- Precision: 0.6583 |
|
- Recall: 0.8623 |
|
- F1: 0.7466 |
|
- Accuracy: 0.9675 |
|
|
|
## 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: 1e-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 |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.9667 | 0.96 | 25 | 0.3537 | 0.0 | 0.0 | 0.0 | 0.9293 | |
|
| 0.2692 | 1.92 | 50 | 0.1917 | 0.0 | 0.0 | 0.0 | 0.9308 | |
|
| 0.148 | 2.88 | 75 | 0.1300 | 0.5833 | 0.0843 | 0.1474 | 0.9504 | |
|
| 0.1085 | 3.85 | 100 | 0.1147 | 0.6699 | 0.4819 | 0.5606 | 0.9578 | |
|
| 0.0998 | 4.81 | 125 | 0.1047 | 0.6534 | 0.6231 | 0.6379 | 0.9607 | |
|
| 0.0745 | 5.77 | 150 | 0.0901 | 0.6798 | 0.7711 | 0.7226 | 0.9677 | |
|
| 0.0709 | 6.73 | 175 | 0.0889 | 0.6657 | 0.8296 | 0.7387 | 0.9676 | |
|
| 0.0614 | 7.69 | 200 | 0.0867 | 0.6753 | 0.8485 | 0.7521 | 0.9681 | |
|
| 0.0532 | 8.65 | 225 | 0.0851 | 0.6830 | 0.8158 | 0.7435 | 0.9685 | |
|
| 0.0496 | 9.62 | 250 | 0.0956 | 0.6585 | 0.8296 | 0.7342 | 0.9668 | |
|
| 0.0429 | 10.58 | 275 | 0.1042 | 0.6583 | 0.8623 | 0.7466 | 0.9675 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
