Downloads · 30 days
9
3% of all-time downloads
mt5-bambara-phase0-pro
Fatoumataa/mt5-bambara-phase0-pro
mt5-bambara-phase0-pro is a machine learning model from Fatoumataa. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
339
Public
Parameters
556M
68 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
- apache-2.0
- Model type
- mt5
- Access
- Public
- Created
- Jan 3, 2026
- Updated
- Feb 9, 2026
- SHA
- 2170eece
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. -->
mt5-bambara-phase0-pro
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.3777
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 63.6409 | 0.1038 | 100 | 24.1875 |
| 51.0854 | 0.2077 | 200 | 16.4790 |
| 37.1135 | 0.3115 | 300 | 13.2133 |
| 25.3601 | 0.4154 | 400 | 9.3961 |
| 17.9259 | 0.5192 | 500 | 6.6792 |
| 14.3323 | 0.6231 | 600 | 5.8368 |
| 12.8457 | 0.7269 | 700 | 5.4056 |
| 11.9870 | 0.8307 | 800 | 5.2790 |
| 11.4545 | 0.9346 | 900 | 5.0855 |
| 11.0667 | 1.0384 | 1000 | 4.8737 |
| 10.7920 | 1.1423 | 1100 | 4.8623 |
| 10.5198 | 1.2461 | 1200 | 4.7579 |
| 10.3654 | 1.3499 | 1300 | 4.7318 |
| 10.2133 | 1.4538 | 1400 | 4.6913 |
| 10.1077 | 1.5576 | 1500 | 4.6596 |
| 10.0039 | 1.6615 | 1600 | 4.6280 |
| 9.9163 | 1.7653 | 1700 | 4.5885 |
| 9.8522 | 1.8692 | 1800 | 4.5634 |
| 9.7571 | 1.9730 | 1900 | 4.5099 |
| 9.7045 | 2.0768 | 2000 | 4.4752 |
| 9.6377 | 2.1807 | 2100 | 4.4573 |
| 9.6112 | 2.2845 | 2200 | 4.4544 |
| 9.5404 | 2.3884 | 2300 | 4.4300 |
| 9.5338 | 2.4922 | 2400 | 4.3980 |
| 9.4867 | 2.5961 | 2500 | 4.3867 |
| 9.4811 | 2.6999 | 2600 | 4.3802 |
| 9.5017 | 2.8037 | 2700 | 4.3676 |
| 9.4564 | 2.9076 | 2800 | 4.3777 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2
- Library
- transformers
- Type
- mt5
- License
- apache-2.0
- Created
- Jan 3, 2026
- Updated
- Feb 9, 2026