Downloads · 30 days
0
MTL-rasyosef-bert-medium-amharic
tadiecool29/MTL-rasyosef-bert-medium-amharic
MTL-rasyosef-bert-medium-amharic is a machine learning model from tadiecool29. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Aug 30, 2026
Parameters
40.4M
485 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors162 MB · 100%
At a glance
- Library
- transformers
- Access
- Public
- Created
- Aug 27, 2026
- Updated
- Aug 30, 2026
- SHA
- e5b06e4c
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
MTL-rasyosef-bert-medium-amharic
This model is a fine-tuned version of rasyosef/bert-medium-amharic on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4138
- Stance F1: 0.7144
- Sentiment F1: 0.7214
- F1: 0.7179
- Stance Acc: 0.7060
- Sentiment Acc: 0.7259
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 | Stance F1 | Sentiment F1 | F1 | Stance Acc | Sentiment Acc |
|---|---|---|---|---|---|---|---|---|
| 2.0029 | 1.0 | 377 | 1.7809 | 0.5873 | 0.6299 | 0.6086 | 0.5823 | 0.6409 |
| 1.5356 | 2.0 | 754 | 1.5354 | 0.6668 | 0.6514 | 0.6591 | 0.6608 | 0.6671 |
| 1.3620 | 3.0 | 1131 | 1.4593 | 0.7094 | 0.6738 | 0.6916 | 0.6995 | 0.6870 |
| 1.2352 | 4.0 | 1508 | 1.4215 | 0.7214 | 0.6987 | 0.7100 | 0.7132 | 0.7057 |
| 1.1922 | 5.0 | 1885 | 1.4386 | 0.7173 | 0.6900 | 0.7037 | 0.7107 | 0.6983 |
| 1.1215 | 6.0 | 2262 | 1.4498 | 0.7259 | 0.6873 | 0.7066 | 0.7182 | 0.6945 |
| 1.0760 | 7.0 | 2639 | 1.4267 | 0.7360 | 0.6939 | 0.7149 | 0.7269 | 0.7020 |
| 1.0670 | 8.0 | 3016 | 1.4342 | 0.7282 | 0.6968 | 0.7125 | 0.7207 | 0.7032 |
| 1.0332 | 9.0 | 3393 | 1.4352 | 0.7300 | 0.7007 | 0.7153 | 0.7219 | 0.7070 |
| 1.0303 | 10.0 | 3770 | 1.4377 | 0.7268 | 0.7005 | 0.7136 | 0.7195 | 0.7070 |
Framework versions
- Transformers 5.15.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Library
- transformers
- Created
- Aug 27, 2026
- Updated
- Aug 30, 2026