hubert-agum960-amharic
This model is a fine-tuned version of facebook/hubert-large-ls960-ft on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3169
- Accuracy: 0.9395
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5275 | 0.6649 | 500 | 0.4740 | 0.8483 |
0.2923 | 1.3298 | 1000 | 0.3727 | 0.8999 |
0.2168 | 1.9947 | 1500 | 0.4175 | 0.9073 |
0.1442 | 2.6596 | 2000 | 0.3471 | 0.9312 |
0.1341 | 3.3245 | 2500 | 0.3641 | 0.9275 |
0.1136 | 3.9894 | 3000 | 0.3286 | 0.9432 |
0.1102 | 4.6543 | 3500 | 0.3169 | 0.9395 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 13
Model tree for Gizachew/hubert-agum960-amharic
Base model
facebook/hubert-large-ls960-ft