Social_Principal_PegasusLargeModel

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

• Loss: 5.7293
• Rouge1: 42.5669
• Rouge2: 11.7234
• Rougel: 27.7786
• Rougelsum: 39.618
• Bertscore Precision: 77.477
• Bertscore Recall: 80.953
• Bertscore F1: 79.1718
• Bleu: 0.0783
• Gen Len: 193.5630

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bertscore Precision	Bertscore Recall	Bertscore F1	Bleu	Gen Len
6.8026	0.1314	100	6.4616	31.6892	6.7933	21.4758	29.2175	74.4637	79.3128	76.8049	0.0458	193.5630
6.3765	0.2628	200	6.1464	36.2413	9.2779	25.1904	33.7712	75.7773	80.0271	77.837	0.0618	193.5630
6.2227	0.3943	300	6.0317	39.5034	10.6245	26.455	36.7119	76.6932	80.4692	78.5301	0.0712	193.5630
6.125	0.5257	400	5.9252	39.3613	10.6879	26.5658	36.6574	76.7781	80.5732	78.6239	0.0723	193.5630
5.9687	0.6571	500	5.8381	40.3723	10.95	26.9783	37.6384	76.8811	80.6213	78.7007	0.0733	193.5630
5.9196	0.7885	600	5.7625	41.4841	11.4949	27.417	38.6113	77.0166	80.822	78.8674	0.0773	193.5630
5.898	0.9199	700	5.7293	42.5669	11.7234	27.7786	39.618	77.477	80.953	79.1718	0.0783	193.5630

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.2.1
• Tokenizers 0.19.1