mt5-small-finetuned-13feb-6

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: 2.4645
• Rouge1: 18.09
• Rouge2: 5.09
• Rougel: 17.85

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: 5e-05
• train_batch_size: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel
7.2878	1.0	311	2.8276	8.04	2.25	7.88
3.6569	2.0	622	2.6625	15.73	4.67	15.52
3.3882	3.0	933	2.5924	16.9	5.12	16.63
3.2381	4.0	1244	2.5561	17.23	5.44	17.01
3.1386	5.0	1555	2.5301	16.92	5.16	16.69
3.0852	6.0	1866	2.5098	17.46	5.18	17.25
3.0244	7.0	2177	2.4873	17.48	5.05	17.23
2.9948	8.0	2488	2.4817	18.26	5.31	17.96
2.9542	9.0	2799	2.4892	17.97	5.5	17.68
2.9376	10.0	3110	2.4708	17.58	5.03	17.31
2.9197	11.0	3421	2.4697	18.05	5.05	17.75
2.9126	12.0	3732	2.4645	18.09	5.09	17.85

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2