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

# BertDiscussionComp

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7725
- Accuracy: 0.7743
- Precision: 0.4149
- Recall: 0.4305
- F1: 0.4196
- Top3: 0.9389
- Top3macro: 0.6172

## 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: 4

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Top3   | Top3macro |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|:---------:|
| 1.4786        | 1.0   | 1640 | 1.2465          | 0.6157   | 0.2343    | 0.2236 | 0.2018 | 0.8509 | 0.4342    |
| 0.9172        | 2.0   | 3280 | 0.8520          | 0.7493   | 0.3946    | 0.3700 | 0.3751 | 0.9250 | 0.5534    |
| 0.6639        | 3.0   | 4920 | 0.8068          | 0.7597   | 0.3980    | 0.4112 | 0.4006 | 0.9299 | 0.5995    |
| 0.5251        | 4.0   | 6560 | 0.8011          | 0.7658   | 0.4043    | 0.4194 | 0.4110 | 0.9375 | 0.6070    |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.2.1
- Tokenizers 0.19.1