mt5-small-finetuned-news_title_generation

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

• Loss: 1.8317
• Rouge1: 38.8271
• Rouge2: 15.9699
• Rougel: 37.4629
• Rougelsum: 37.4611

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: 8
• eval_batch_size: 8
• 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
2.9375	1.0	1715	2.1953	32.8581	12.0123	31.7428	31.7415
2.7861	2.0	3430	2.0516	34.7374	12.8384	33.5105	33.5139
2.5732	3.0	5145	1.9641	36.3304	14.2331	35.0356	35.0547
2.434	4.0	6860	1.9057	36.696	14.5408	35.4881	35.48
2.3377	5.0	8575	1.8784	37.5708	14.9623	36.232	36.2245
2.2665	6.0	10290	1.8506	38.0536	15.35	36.7089	36.6998
2.2281	7.0	12005	1.8379	38.6899	16.0013	37.3522	37.3469
2.2025	8.0	13720	1.8317	38.8271	15.9699	37.4629	37.4611

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1