---
base_model: alsgyu/sentiment-analysis-fine-tuned-model
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: kcbert-interview-sentiment-ex1
  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. -->

# kcbert-interview-sentiment-ex1

This model is a fine-tuned version of [alsgyu/sentiment-analysis-fine-tuned-model](https://huggingface.co/alsgyu/sentiment-analysis-fine-tuned-model) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8484
- Accuracy: 0.8331
- Macro F1: 0.7797
- Weighted F1: 0.8382

## 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
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|
| 0.2373        | 1.0   | 999  | 0.6532          | 0.8247   | 0.7701   | 0.8299      |
| 0.1028        | 2.0   | 1998 | 0.7480          | 0.8347   | 0.7729   | 0.8391      |
| 0.045         | 3.0   | 2997 | 0.8484          | 0.8331   | 0.7797   | 0.8382      |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.8.0+cu128
- Datasets 2.19.0
- Tokenizers 0.19.1