Downloads · 30 days
0
MTL-roberta-large-amharic-finetuned
tadiecool29/MTL-roberta-large-amharic-finetuned
MTL-roberta-large-amharic-finetuned 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. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Aug 29, 2026
Parameters
560M
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.2 GB · 99%
At a glance
- Library
- transformers
- License
- mit
- Access
- Public
- Created
- Aug 29, 2026
- Updated
- Aug 29, 2026
- SHA
- 603e84f3
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-roberta-large-amharic-finetuned
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8056
- Stance F1: 0.7606
- Sentiment F1: 0.7332
- F1: 0.7469
- Stance Acc: 0.7506
- Sentiment Acc: 0.7382
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 |
|---|---|---|---|---|---|---|---|---|
| 1.6626 | 1.0 | 377 | 1.6084 | 0.6191 | 0.7006 | 0.6599 | 0.6234 | 0.7082 |
| 1.3896 | 2.0 | 754 | 1.3907 | 0.7085 | 0.7205 | 0.7145 | 0.6995 | 0.7269 |
| 1.1795 | 3.0 | 1131 | 1.3255 | 0.7462 | 0.7189 | 0.7326 | 0.7357 | 0.7319 |
| 0.9617 | 4.0 | 1508 | 1.4237 | 0.7271 | 0.7468 | 0.7370 | 0.7207 | 0.7519 |
| 0.8033 | 5.0 | 1885 | 1.4437 | 0.7390 | 0.7428 | 0.7409 | 0.7307 | 0.7456 |
| 0.5729 | 6.0 | 2262 | 1.5006 | 0.7580 | 0.7309 | 0.7445 | 0.7481 | 0.7357 |
| 0.5035 | 7.0 | 2639 | 1.6484 | 0.7632 | 0.7298 | 0.7465 | 0.7531 | 0.7357 |
| 0.3721 | 8.0 | 3016 | 1.7511 | 0.7659 | 0.7413 | 0.7536 | 0.7569 | 0.7481 |
| 0.3395 | 9.0 | 3393 | 1.8006 | 0.7642 | 0.7324 | 0.7483 | 0.7544 | 0.7382 |
| 0.3343 | 10.0 | 3770 | 1.8056 | 0.7606 | 0.7332 | 0.7469 | 0.7506 | 0.7382 |
Framework versions
- Transformers 5.15.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Library
- transformers
- License
- mit
- Created
- Aug 29, 2026
- Updated
- Aug 29, 2026