metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/nllb-200-distilled-600M
tags:
- generated_from_trainer
model-index:
- name: qcri_test
results: []
qcri_test
This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the TEDx dataset. It achieves the following results on the evaluation set:
- Loss: 0.5696
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8109 | 1.0 | 537 | 0.8636 |
| 0.7152 | 2.0 | 1074 | 0.7924 |
| 0.6361 | 3.0 | 1611 | 0.7339 |
| 0.6227 | 4.0 | 2148 | 0.6863 |
| 0.599 | 5.0 | 2685 | 0.6502 |
| 0.551 | 6.0 | 3222 | 0.6199 |
| 0.5277 | 7.0 | 3759 | 0.5982 |
| 0.4916 | 8.0 | 4296 | 0.5823 |
| 0.4766 | 9.0 | 4833 | 0.5734 |
| 0.4581 | 10.0 | 5370 | 0.5696 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1