mt5-small-finetuned-no-email-summary

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2815
• Rouge1: 44.0759
• Rouge2: 29.0229
• Rougel: 41.8945
• Rougelsum: 41.801

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
10.2054	1.0	417	2.3095	19.097	8.5001	17.7548	17.7829
3.1624	2.0	834	1.6965	30.9222	16.6468	28.3312	28.3229
2.4529	3.0	1251	1.5142	34.9498	20.327	32.1027	32.0904
2.19	4.0	1668	1.4286	40.0996	25.4238	38.1114	38.0192
2.0096	5.0	2085	1.3853	42.2543	27.8126	40.5722	40.4353
1.8849	6.0	2502	1.3377	42.9442	28.4625	41.1796	41.132
1.8099	7.0	2919	1.3008	43.2106	28.327	41.3598	41.3596
1.7495	8.0	3336	1.2961	43.1156	27.8989	40.9504	40.8745
1.7354	9.0	3753	1.2817	44.3051	29.1231	42.13	42.0315
1.6907	10.0	4170	1.2815	44.0759	29.0229	41.8945	41.801

Framework versions

• Transformers 4.28.1
• Pytorch 1.13.1
• Datasets 2.11.0
• Tokenizers 0.13.0.dev0