---
library_name: transformers
license: mit
base_model: EthioNLP/EthioLLM-b-250K
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: STL-ethiollm-b-250K-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-ethiollm-b-250K-sentiment

This model is a fine-tuned version of [EthioNLP/EthioLLM-b-250K](https://huggingface.co/EthioNLP/EthioLLM-b-250K) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9272
- Sentiment Precision: 0.6650
- Sentiment Recall: 0.6514
- F1: 0.6451
- Sentiment Acc: 0.6484

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-------------------:|:----------------:|:------:|:-------------:|
| 0.9908        | 1.0   | 377  | 0.8728          | 0.6072              | 0.6070           | 0.6071 | 0.6110        |
| 0.8654        | 2.0   | 754  | 0.8423          | 0.6625              | 0.6281           | 0.6123 | 0.6222        |
| 0.7344        | 3.0   | 1131 | 0.7865          | 0.6662              | 0.6595           | 0.6568 | 0.6584        |
| 0.6174        | 4.0   | 1508 | 0.7960          | 0.6592              | 0.6565           | 0.6532 | 0.6571        |
| 0.5512        | 5.0   | 1885 | 0.8839          | 0.6608              | 0.6438           | 0.6313 | 0.6434        |
| 0.4653        | 6.0   | 2262 | 0.9272          | 0.6650              | 0.6514           | 0.6451 | 0.6484        |


### Framework versions

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