metadata
library_name: transformers
base_model: castorini/afriberta_base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: afriberta-stl-base-sentiment
results: []
afriberta-stl-base-sentiment
This model is a fine-tuned version of castorini/afriberta_base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8213
- Sentiment Precision: 0.7191
- Sentiment Recall: 0.7099
- F1: 0.7111
- Sentiment Acc: 0.7161
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: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Sentiment Precision | Sentiment Recall | F1 | Sentiment Acc |
|---|---|---|---|---|---|---|---|
| 0.7579 | 1.0 | 402 | 0.7556 | 0.6904 | 0.6818 | 0.6729 | 0.6845 |
| 0.6418 | 2.0 | 804 | 0.7293 | 0.6981 | 0.6946 | 0.6945 | 0.7032 |
| 0.4884 | 3.0 | 1206 | 0.7908 | 0.6974 | 0.6863 | 0.6763 | 0.6933 |
| 0.3494 | 4.0 | 1608 | 0.8595 | 0.7064 | 0.6959 | 0.6971 | 0.7032 |
| 0.3035 | 5.0 | 2010 | 0.9201 | 0.7120 | 0.7062 | 0.7074 | 0.7120 |
| 0.2468 | 6.0 | 2412 | 0.9231 | 0.7012 | 0.6990 | 0.6996 | 0.7057 |
Framework versions
- Transformers 5.15.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2