---
library_name: transformers
license: mit
base_model: mateiaassAI/teacher_sst2
tags:
- generated_from_trainer
datasets:
- laroseda
metrics:
- f1
- accuracy
- precision
- recall
model-index:
- name: teacher_sst2_laroseda
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: laroseda
      type: laroseda
      config: laroseda
      split: train
      args: laroseda
    metrics:
    - name: F1
      type: f1
      value: 0.9489953582155384
    - name: Accuracy
      type: accuracy
      value: 0.949
    - name: Precision
      type: precision
      value: 0.9490837535014006
    - name: Recall
      type: recall
      value: 0.949
---

<!-- 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. -->

# teacher_sst2_laroseda

This model is a fine-tuned version of [mateiaassAI/teacher_sst2](https://huggingface.co/mateiaassAI/teacher_sst2) on the laroseda dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1906
- F1: 0.9490
- Roc Auc: 0.9490
- Accuracy: 0.949
- Precision: 0.9491
- Recall: 0.949

## 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: 1.7e-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 | F1     | Roc Auc | Accuracy | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|:---------:|:------:|
| 0.1799        | 1.0   | 688  | 0.1426          | 0.9435 | 0.9434  | 0.943    | 0.9441    | 0.943  |
| 0.1071        | 2.0   | 1376 | 0.1906          | 0.9490 | 0.9490  | 0.949    | 0.9491    | 0.949  |


### Framework versions

- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0