---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: filtered_cause_extraction_bert_because
  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. -->

# filtered_cause_extraction_bert_because

This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4768
- Precision: 0.25
- Recall: 0.3878
- F1: 0.304
- Accuracy: 0.8087
- Cause P: 0.25
- Cause R: 0.3878
- Cause F1: 0.304

## 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: 4e-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: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy | Cause P | Cause R | Cause F1 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------:|:-------:|:--------:|
| 0.7298        | 0.41  | 20   | 0.5714          | 0.0843    | 0.3010 | 0.1317 | 0.6191   | 0.0843  | 0.3010  | 0.1317   |
| 0.7298        | 0.82  | 40   | 0.4815          | 0.1528    | 0.3010 | 0.2027 | 0.7796   | 0.1528  | 0.3010  | 0.2027   |
| 0.7298        | 1.22  | 60   | 0.4449          | 0.2061    | 0.3776 | 0.2667 | 0.7979   | 0.2061  | 0.3776  | 0.2667   |
| 0.7298        | 1.63  | 80   | 0.4607          | 0.2444    | 0.3929 | 0.3014 | 0.8052   | 0.2444  | 0.3929  | 0.3014   |


### Framework versions

- Transformers 4.37.2
- Pytorch 2.3.1.post100
- Datasets 2.20.0
- Tokenizers 0.15.1