mt5-small-text-sum-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: 2.3694
• Rouge1: 20.18
• Rouge2: 6.52
• Rougel: 19.84

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: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel
4.4337	1.93	500	2.5989	15.94	4.85	15.78
3.0621	3.86	1000	2.4750	19.09	5.95	18.82
2.8411	5.79	1500	2.4011	18.39	5.69	18.22
2.6947	7.72	2000	2.3851	19.27	5.79	19.01
2.5872	9.65	2500	2.3918	19.09	6.02	18.81
2.4996	11.58	3000	2.3689	18.84	5.84	18.46
2.4192	13.51	3500	2.3604	19.89	5.97	19.5
2.3524	15.44	4000	2.3694	20.18	6.52	19.84
2.3012	17.37	4500	2.3637	19.24	5.51	18.9
2.2408	19.31	5000	2.3374	19.78	6.27	19.43
2.2004	21.24	5500	2.3400	19.74	6.06	19.37
2.1631	23.17	6000	2.3584	19.95	6.08	19.53
2.123	25.1	6500	2.3527	19.64	5.9	19.36

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2