|
--- |
|
license: cc-by-nc-4.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: facebook/nllb-200-1.3B |
|
metrics: |
|
- bleu |
|
- rouge |
|
model-index: |
|
- name: nllb-200-1.3B-ICFOSS-Malayalam_English_Translation1.3b |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# nllb-200-1.3B-ICFOSS-Malayalam_English_Translation1.3b |
|
|
|
This model is a fine-tuned version of [facebook/nllb-200-1.3B](https://huggingface.co/facebook/nllb-200-1.3B) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0536 |
|
- Bleu: 36.7256 |
|
- Rouge: {'rouge1': 0.6977825292445439, 'rouge2': 0.47317224666360513, 'rougeL': 0.6369586014923634, 'rougeLsum': 0.6367120144580565} |
|
- Chrf: {'score': 63.88643397225133, 'char_order': 6, 'word_order': 0, 'beta': 2} |
|
|
|
## 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: 0.0002 |
|
- 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: cosine |
|
- num_epochs: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge | Chrf | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:----------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------:| |
|
| 1.1683 | 1.0 | 5750 | 1.0774 | 35.9761 | {'rouge1': 0.6937855960659589, 'rouge2': 0.466938063654629, 'rougeL': 0.6325990208208303, 'rougeLsum': 0.6323899971616622} | {'score': 63.363704282940446, 'char_order': 6, 'word_order': 0, 'beta': 2} | |
|
| 1.1177 | 2.0 | 11500 | 1.0617 | 36.3486 | {'rouge1': 0.6957984629345982, 'rouge2': 0.47067647725021045, 'rougeL': 0.6351678391451753, 'rougeLsum': 0.6350175761315434} | {'score': 63.657728669261445, 'char_order': 6, 'word_order': 0, 'beta': 2} | |
|
| 1.102 | 3.0 | 17250 | 1.0559 | 36.7216 | {'rouge1': 0.6970801919668868, 'rouge2': 0.47279660574601357, 'rougeL': 0.6364385448189633, 'rougeLsum': 0.6362592345657716} | {'score': 63.89202343434442, 'char_order': 6, 'word_order': 0, 'beta': 2} | |
|
| 1.0967 | 4.0 | 23000 | 1.0545 | 36.7450 | {'rouge1': 0.6977900451765099, 'rouge2': 0.4734910607221403, 'rougeL': 0.6373405033951935, 'rougeLsum': 0.6371420919202282} | {'score': 63.918132836888965, 'char_order': 6, 'word_order': 0, 'beta': 2} | |
|
| 1.0935 | 5.0 | 28750 | 1.0538 | 36.7038 | {'rouge1': 0.6978511315129863, 'rouge2': 0.4733012047244315, 'rougeL': 0.6371351829239855, 'rougeLsum': 0.6369801889854168} | {'score': 63.87115369473548, 'char_order': 6, 'word_order': 0, 'beta': 2} | |
|
| 1.0928 | 6.0 | 34500 | 1.0536 | 36.7485 | {'rouge1': 0.6977169592049554, 'rouge2': 0.4734304167965041, 'rougeL': 0.636966108177003, 'rougeLsum': 0.6367749449397957} | {'score': 63.894445637643784, 'char_order': 6, 'word_order': 0, 'beta': 2} | |
|
| 1.0918 | 7.0 | 40250 | 1.0536 | 36.7256 | {'rouge1': 0.6977825292445439, 'rouge2': 0.47317224666360513, 'rougeL': 0.6369586014923634, 'rougeLsum': 0.6367120144580565} | {'score': 63.88643397225133, 'char_order': 6, 'word_order': 0, 'beta': 2} | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |