ALLPegasusLargeModel

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: 4.9004
• Rouge1: 50.2858
• Rouge2: 17.3371
• Rougel: 34.9711
• Rougelsum: 45.9178
• Bertscore Precision: 80.3248
• Bertscore Recall: 83.1003
• Bertscore F1: 81.6841
• Bleu: 0.1287
• Gen Len: 213.7421

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
5.9374	0.1059	500	5.7310	43.8081	13.7728	29.7031	39.5834	77.3165	81.5184	79.3534	0.1021	213.7421
5.7002	0.2118	1000	5.4375	45.7599	14.6097	31.1826	41.4715	78.3108	81.9134	80.0646	0.1068	213.7421
5.5932	0.3178	1500	5.2635	46.7433	15.2361	32.2197	42.2622	78.8125	82.2397	80.4828	0.1115	213.7421
5.4417	0.4237	2000	5.1352	48.2636	15.9823	33.2082	43.9438	79.4905	82.5491	80.9852	0.1166	213.7421
5.3551	0.5296	2500	5.0519	49.16	16.5745	33.8127	44.6595	79.7321	82.7596	81.212	0.1213	213.7421
5.2625	0.6355	3000	4.9910	49.3156	16.7869	34.2642	45.012	80.0332	82.9083	81.4402	0.1240	213.7421
5.2208	0.7414	3500	4.9445	50.1565	17.1477	34.6991	45.7009	80.2185	83.0322	81.5962	0.1268	213.7421
5.2456	0.8473	4000	4.9126	50.0901	17.2522	34.8768	45.7267	80.2903	83.0784	81.6556	0.1282	213.7421
5.2835	0.9533	4500	4.9004	50.2858	17.3371	34.9711	45.9178	80.3248	83.1003	81.6841	0.1287	213.7421

Framework versions

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