mbart-large-50-finetuned-model-hu_1121

This model is a fine-tuned version of facebook/mbart-large-50 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.6534
• Rouge1: 35.6227
• Rouge2: 13.0189
• Rougel: 22.0402
• Rougelsum: 26.9175

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.9553	1.0	21353	2.5450	33.3195	12.2415	21.2029	25.3382
2.2811	2.0	42706	2.3570	33.6149	11.975	20.9943	25.726
1.9886	3.0	64059	2.3144	34.6221	12.2867	21.7798	26.1901
1.7463	4.0	85412	2.3198	35.2114	12.9183	22.215	27.1176
1.5245	5.0	106765	2.3774	35.1147	13.1621	22.3167	26.9264
1.3222	6.0	128118	2.4642	35.5719	13.1532	22.0023	26.8084
1.1456	7.0	149471	2.5673	35.9156	13.2115	22.2552	27.2581
1.0087	8.0	170824	2.6534	35.6227	13.0189	22.0402	26.9175

Framework versions

• Transformers 4.35.1
• Pytorch 2.1.1+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1