mt5-small-finetuned_samsum_summarization_model

This model is a fine-tuned version of google/mt5-small on the samsum dataset. It achieves the following results on the evaluation set:

• Loss: 1.9328
• Rouge1: 39.9323
• Rouge2: 18.0293
• Rougel: 34.3611
• Rougelsum: 37.3087

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: 14
• eval_batch_size: 14
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
4.5012	1.0	1050	2.1992	34.6608	14.0886	29.8674	32.1737
2.6852	2.0	2100	2.1014	38.1793	16.0747	32.5426	35.4332
2.4933	3.0	3150	2.0319	38.4414	16.4993	32.6973	35.8539
2.3933	4.0	4200	1.9910	39.2966	17.1718	33.5556	36.802
2.3273	5.0	5250	1.9764	39.7619	17.7287	33.9838	37.1345
2.2783	6.0	6300	1.9503	39.9351	17.8312	34.2641	37.2625
2.2543	7.0	7350	1.9350	39.9551	17.918	34.3361	37.2039
2.2383	8.0	8400	1.9328	39.9323	18.0293	34.3611	37.3087

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0