bert2gpt2SUMM-finetuned-mlsum

Chemsseddine/bert2gpt2SUMM-finetuned-mlsum

bert2gpt2SUMM-finetuned-mlsum is a machine learning model from Chemsseddine. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

<img src="https://huggingface.co/Chemsseddine/bert2gpt2medmlorangesumm-finetunedmedsumnew-finetunedmedsumnew/resolve/main/logobert2gpt2.png" alt="Map of positive probabilities per country." width="200"/

Downloads · 30 days

1% of all-time downloads

All-time downloads

1.3K

Public

Repo size

5.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.1 GB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: encoder-decoder
Access: Public
Created: Jun 14, 2022
Updated: Jun 30, 2022
SHA: 21c2f20b

Spaces

Model card

From the Hugging Face model README

bert2gpt2SUMM-finetuned-mlsum

This model is used for french summarization

Problem type: Summarization
Model ID: 980832493
CO2 Emissions (in grams): 0.10685501288084795

This model is a fine-tuned version of Chemsseddine/bert2gpt2SUMM on the None dataset. It achieves the following results on the evaluation set:

Loss: 4.03749418258667
Rouge1: 28.8384
Rouge2: 10.7511
RougeL: 27.0842
RougeLsum: 27.5118
Gen Len: 22.0625

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
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	33199	4.03749	28.8384	10.7511	27.0842	27.5118	22.0625

Library: transformers
Type: encoder-decoder
License: apache-2.0
Languages: fr
Created: Jun 14, 2022
Updated: Jun 30, 2022