|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: tmvar_0.0001_0404_ES6_strict_tok1 |
|
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. --> |
|
|
|
# tmvar_0.0001_0404_ES6_strict_tok1 |
|
|
|
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: 0.1472 |
|
- Precision: 0.0 |
|
- Recall: 0.0 |
|
- F1: 0.0 |
|
- Accuracy: 0.9561 |
|
|
|
## 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: 0.0001 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:| |
|
| 0.3183 | 0.49 | 25 | 0.2344 | 0.0 | 0.0 | 0.0 | 0.9555 | |
|
| 0.232 | 0.98 | 50 | 0.2467 | 0.0 | 0.0 | 0.0 | 0.9555 | |
|
| 0.2357 | 1.47 | 75 | 0.2341 | 0.0 | 0.0 | 0.0 | 0.9555 | |
|
| 0.2245 | 1.96 | 100 | 0.2373 | 0.0 | 0.0 | 0.0 | 0.9555 | |
|
| 0.1778 | 2.45 | 125 | 0.1339 | 0.0 | 0.0 | 0.0 | 0.9555 | |
|
| 0.137 | 2.94 | 150 | 0.1222 | 0.0 | 0.0 | 0.0 | 0.9582 | |
|
| 0.1146 | 3.43 | 175 | 0.1339 | 0.0 | 0.0 | 0.0 | 0.9625 | |
|
| 0.1215 | 3.92 | 200 | 0.1472 | 0.0 | 0.0 | 0.0 | 0.9561 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
