mt5-small-text-sum-7

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: 2.3801
• Rouge1: 20.58
• Rouge2: 6.51
• Rougel: 20.26

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: 13
• eval_batch_size: 13
• 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
4.4436	2.09	500	2.5528	17.73	5.9	17.55
3.0439	4.18	1000	2.4974	18.76	5.73	18.64
2.822	6.28	1500	2.4043	17.82	5.09	17.68
2.6799	8.37	2000	2.3938	18.9	5.73	18.62
2.5687	10.46	2500	2.3617	19.0	5.76	18.73
2.4701	12.55	3000	2.3455	19.82	6.14	19.54
2.3917	14.64	3500	2.3801	20.58	6.51	20.26
2.3427	16.74	4000	2.3407	19.52	6.49	19.23
2.2811	18.83	4500	2.3544	18.82	5.75	18.43
2.2347	20.92	5000	2.3503	20.17	6.08	19.76
2.1884	23.01	5500	2.3586	20.25	6.06	19.9
2.1414	25.1	6000	2.3507	19.94	6.31	19.61

Framework versions

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