---
library_name: transformers
license: mit
base_model: uhhlt/am-roberta
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: STL-amroberta-sentiment
  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. -->

# STL-amroberta-sentiment

This model is a fine-tuned version of [uhhlt/am-roberta](https://huggingface.co/uhhlt/am-roberta) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0446
- Sentiment Precision: 0.6743
- Sentiment Recall: 0.6767
- F1: 0.6739
- Sentiment Acc: 0.6833

## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 300
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Sentiment Precision | Sentiment Recall | F1     | Sentiment Acc |
|:-------------:|:-----:|:----:|:---------------:|:-------------------:|:----------------:|:------:|:-------------:|
| 0.8072        | 1.0   | 377  | 0.7511          | 0.6336              | 0.6336           | 0.6278 | 0.6372        |
| 0.6882        | 2.0   | 754  | 0.7255          | 0.6647              | 0.6636           | 0.6556 | 0.6671        |
| 0.4904        | 3.0   | 1131 | 0.7734          | 0.6831              | 0.6805           | 0.6726 | 0.6833        |
| 0.3859        | 4.0   | 1508 | 0.7936          | 0.6880              | 0.6827           | 0.6836 | 0.6858        |
| 0.3540        | 5.0   | 1885 | 0.8578          | 0.6825              | 0.6820           | 0.6805 | 0.6870        |
| 0.2477        | 6.0   | 2262 | 0.9558          | 0.6763              | 0.6774           | 0.6751 | 0.6833        |
| 0.2105        | 7.0   | 2639 | 1.0446          | 0.6743              | 0.6767           | 0.6739 | 0.6833        |


### Framework versions

- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.23.1