ALLPrincipalPegasusLargeModel

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: 5.0232
• Rouge1: 47.6658
• Rouge2: 14.3424
• Rougel: 32.0036
• Rougelsum: 44.3129
• Bertscore Precision: 80.0039
• Bertscore Recall: 82.2832
• Bertscore F1: 81.1232
• Bleu: 0.0968
• Gen Len: 215.5775

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
6.0475	0.1059	500	5.8195	40.9165	11.2781	27.4543	38.2464	77.6812	80.818	79.2126	0.0750	215.5775
5.7557	0.2118	1000	5.5171	44.1505	12.4929	29.115	41.1231	78.4631	81.3235	79.8626	0.0826	215.5775
5.5723	0.3178	1500	5.3613	45.368	13.0491	30.0119	42.2834	79.0906	81.6243	80.3329	0.0866	215.5775
5.5134	0.4237	2000	5.2571	45.8933	13.254	30.5132	42.7279	79.3615	81.82	80.5674	0.0886	215.5775
5.3793	0.5296	2500	5.1767	46.8804	13.7974	31.0723	43.5411	79.5774	82.0228	80.7769	0.0926	215.5775
5.4004	0.6355	3000	5.1101	46.7592	13.9082	31.3732	43.5105	79.7564	82.1032	80.9084	0.0934	215.5775
5.2125	0.7414	3500	5.0666	47.6221	14.2392	31.788	44.2768	79.9394	82.2162	81.0575	0.0954	215.5775
5.2604	0.8473	4000	5.0372	47.5699	14.3045	31.92	44.208	80.008	82.2777	81.1227	0.0967	215.5775
5.2959	0.9533	4500	5.0232	47.6658	14.3424	32.0036	44.3129	80.0039	82.2832	81.1232	0.0968	215.5775

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.1+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1