---
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: SciBERT_BC5CDR_NER_new
  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_BC5CDR_NER_new

This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0868
- Precision: 0.9785
- Recall: 0.9771
- F1: 0.9778
- Accuracy: 0.9755

## 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: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.0   | 286  | 0.0907          | 0.9766    | 0.9681 | 0.9724 | 0.9687   |
| 0.1007        | 2.0   | 572  | 0.0834          | 0.9784    | 0.9737 | 0.9761 | 0.9735   |
| 0.1007        | 3.0   | 858  | 0.0868          | 0.9785    | 0.9771 | 0.9778 | 0.9755   |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0