---
library_name: peft
tags:
- generated_from_trainer
base_model: facebook/mbart-large-50-many-to-many-mmt
metrics:
- bleu
- rouge
model-index:
- name: mbart-large-50-many-to-many-mmt-ICFOSS-Malayalam_English_Translation
  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. -->

# mbart-large-50-many-to-many-mmt-ICFOSS-Malayalam_English_Translation

This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3733
- Bleu: 28.9041
- Rouge: {'rouge1': 0.6211709615166336, 'rouge2': 0.3817538086155071, 'rougeL': 0.5654819931253774, 'rougeLsum': 0.5656455299372645}
- Chrf: {'score': 56.252579884228325, '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: 8

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Rouge                                                                                                                        | Chrf                                                                       |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:----------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------:|
| 1.5329        | 1.0   | 4700  | 1.4284          | 27.0756 | {'rouge1': 0.6054918604734425, 'rouge2': 0.36327221325964765, 'rougeL': 0.5490261054453232, 'rougeLsum': 0.5491186003413475} | {'score': 54.690919979551, 'char_order': 6, 'word_order': 0, 'beta': 2}    |
| 1.4295        | 2.0   | 9400  | 1.3924          | 28.2063 | {'rouge1': 0.614973366544844, 'rouge2': 0.373550100507563, 'rougeL': 0.5589026806041284, 'rougeLsum': 0.5589661976445393}    | {'score': 55.635529686949894, 'char_order': 6, 'word_order': 0, 'beta': 2} |
| 1.3942        | 3.0   | 14100 | 1.3792          | 28.5831 | {'rouge1': 0.6187502745206666, 'rouge2': 0.37919936984407143, 'rougeL': 0.5626864397042893, 'rougeLsum': 0.5627150169042504} | {'score': 56.019161628219024, 'char_order': 6, 'word_order': 0, 'beta': 2} |
| 1.3795        | 4.0   | 18800 | 1.3759          | 28.7523 | {'rouge1': 0.620515288235373, 'rouge2': 0.38072092563685545, 'rougeL': 0.5644953116677603, 'rougeLsum': 0.5646285495158272}  | {'score': 56.162861197192925, 'char_order': 6, 'word_order': 0, 'beta': 2} |
| 1.3723        | 5.0   | 23500 | 1.3735          | 28.8675 | {'rouge1': 0.6225302294049915, 'rouge2': 0.382440202243451, 'rougeL': 0.5664785907343486, 'rougeLsum': 0.5666347228887372}   | {'score': 56.30835530151895, 'char_order': 6, 'word_order': 0, 'beta': 2}  |
| 1.3684        | 6.0   | 28200 | 1.3731          | 28.8915 | {'rouge1': 0.6214787732761883, 'rouge2': 0.3815472818692578, 'rougeL': 0.5656767538045446, 'rougeLsum': 0.5657190870277087}  | {'score': 56.251600472693866, 'char_order': 6, 'word_order': 0, 'beta': 2} |
| 1.3685        | 7.0   | 32900 | 1.3732          | 28.8953 | {'rouge1': 0.6216361131555139, 'rouge2': 0.3821354228713412, 'rougeL': 0.5655300849639422, 'rougeLsum': 0.565595149126267}   | {'score': 56.26874870012928, 'char_order': 6, 'word_order': 0, 'beta': 2}  |
| 1.3678        | 8.0   | 37600 | 1.3733          | 28.9041 | {'rouge1': 0.6211709615166336, 'rouge2': 0.3817538086155071, 'rougeL': 0.5654819931253774, 'rougeLsum': 0.5656455299372645}  | {'score': 56.252579884228325, 'char_order': 6, 'word_order': 0, 'beta': 2} |


### Framework versions

- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0