mt5-small-finetuned-14feb-9

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: 2.3688
• Rouge1: 19.51
• Rouge2: 6.13
• Rougel: 19.33

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: 0.0001
• 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel
5.1754	1.0	311	2.6631	14.74	4.65	14.58
3.3235	2.0	622	2.5226	16.71	5.39	16.6
3.0994	3.0	933	2.4776	16.71	4.96	16.5
2.9608	4.0	1244	2.4551	17.92	5.15	17.7
2.8595	5.0	1555	2.4158	18.67	5.34	18.32
2.7933	6.0	1866	2.4059	18.35	5.33	18.14
2.7253	7.0	2177	2.4008	18.16	5.22	18.03
2.681	8.0	2488	2.3924	18.85	5.6	18.61
2.6286	9.0	2799	2.3811	18.99	5.44	18.8
2.6005	10.0	3110	2.3869	19.16	5.49	18.96
2.5682	11.0	3421	2.3796	19.59	5.7	19.27
2.546	12.0	3732	2.3623	18.75	5.78	18.56
2.5351	13.0	4043	2.3676	19.02	5.65	18.74
2.529	14.0	4354	2.3626	19.39	5.99	19.05
2.4941	15.0	4665	2.3688	19.51	6.13	19.33

Framework versions

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