---
license: mit
tags:
- simplification
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mbart-large-50-clara-med
  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-clara-med

This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2719
- Rouge1: 47.3273
- Rouge2: 29.559
- Rougel: 42.4756
- Rougelsum: 42.6072

## 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: 5.6e-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: 30

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
| No log        | 1.0   | 190  | 8.8777          | 0.0     | 0.0     | 0.0     | 0.0       |
| No log        | 2.0   | 380  | 1.8823          | 42.9631 | 25.6911 | 38.0391 | 38.1538   |
| 4.9008        | 3.0   | 570  | 2.0013          | 35.1183 | 20.8995 | 31.4246 | 31.5244   |
| 4.9008        | 4.0   | 760  | 1.8788          | 40.5309 | 24.083  | 36.0682 | 36.1536   |
| 1.5674        | 5.0   | 950  | 1.9732          | 45.3455 | 26.8893 | 39.9257 | 40.0479   |
| 1.5674        | 6.0   | 1140 | 2.1709          | 45.7451 | 27.9563 | 40.7943 | 40.9558   |
| 1.5674        | 7.0   | 1330 | 2.3818          | 46.7204 | 28.2229 | 41.3356 | 41.4894   |
| 0.4273        | 8.0   | 1520 | 2.4915          | 45.2646 | 27.0017 | 40.0391 | 40.0651   |
| 0.4273        | 9.0   | 1710 | 2.6317          | 47.2481 | 29.1062 | 41.8523 | 42.0337   |
| 0.2256        | 10.0  | 1900 | 2.7477          | 47.0734 | 28.6713 | 41.6488 | 41.7768   |
| 0.2256        | 11.0  | 2090 | 2.7957          | 45.7955 | 27.9674 | 40.7893 | 40.9195   |
| 0.2256        | 12.0  | 2280 | 2.8360          | 46.4354 | 28.6781 | 41.3965 | 41.5133   |
| 0.1692        | 13.0  | 2470 | 2.8865          | 46.3897 | 28.1487 | 41.0427 | 41.1223   |
| 0.1692        | 14.0  | 2660 | 2.8814          | 47.4505 | 29.5163 | 42.4362 | 42.5386   |
| 0.1123        | 15.0  | 2850 | 2.9375          | 47.1197 | 29.315  | 42.1043 | 42.2586   |
| 0.1123        | 16.0  | 3040 | 3.0171          | 47.6975 | 29.342  | 42.654  | 42.7698   |
| 0.1123        | 17.0  | 3230 | 3.0271          | 47.1759 | 29.4071 | 42.337  | 42.4166   |
| 0.0508        | 18.0  | 3420 | 3.1101          | 46.0849 | 28.1961 | 41.174  | 41.3203   |
| 0.0508        | 19.0  | 3610 | 3.1070          | 46.6169 | 29.2838 | 41.8743 | 41.9666   |
| 0.0268        | 20.0  | 3800 | 3.1305          | 46.8893 | 29.0878 | 41.9831 | 42.1053   |
| 0.0268        | 21.0  | 3990 | 3.1861          | 47.1381 | 29.4249 | 42.0727 | 42.1941   |
| 0.0268        | 22.0  | 4180 | 3.1936          | 47.2897 | 29.3799 | 42.1783 | 42.3624   |
| 0.0146        | 23.0  | 4370 | 3.1948          | 47.1995 | 29.4603 | 42.0493 | 42.1786   |
| 0.0146        | 24.0  | 4560 | 3.2059          | 46.8882 | 29.4045 | 42.1013 | 42.2324   |
| 0.0098        | 25.0  | 4750 | 3.2399          | 47.4652 | 29.4997 | 42.4001 | 42.477    |
| 0.0098        | 26.0  | 4940 | 3.2327          | 47.8052 | 30.0034 | 42.9265 | 43.0563   |
| 0.0098        | 27.0  | 5130 | 3.2529          | 47.3934 | 29.7044 | 42.3686 | 42.4734   |
| 0.0065        | 28.0  | 5320 | 3.2535          | 47.2493 | 29.2719 | 42.3357 | 42.4759   |
| 0.0065        | 29.0  | 5510 | 3.2686          | 47.3168 | 29.4467 | 42.4364 | 42.5837   |
| 0.0047        | 30.0  | 5700 | 3.2719          | 47.3273 | 29.559  | 42.4756 | 42.6072   |


### Framework versions

- Transformers 4.25.1
- Pytorch 1.13.0
- Datasets 2.8.0
- Tokenizers 0.12.1