HealthPrincipalMainPegasus

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: 5.0343
• Rouge1: 51.1056
• Rouge2: 17.2499
• Rougel: 33.8193
• Rougelsum: 47.8453
• Bertscore Precision: 80.2471
• Bertscore Recall: 82.3517
• Bertscore F1: 81.2824
• Bleu: 0.1256
• Gen Len: 233.9958

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
6.5043	0.0835	100	6.1043	39.8446	11.121	25.4982	36.4742	76.5079	80.1477	78.2789	0.0801	233.9958
5.9911	0.1671	200	5.7625	44.9139	13.8953	29.2395	41.9312	78.5034	81.0686	79.7606	0.0984	233.9958
5.8802	0.2506	300	5.5925	45.7626	14.8524	30.2239	42.6984	78.7715	81.3496	80.0356	0.1063	233.9958
5.708	0.3342	400	5.4492	47.5481	15.4828	31.1939	44.4724	79.2119	81.535	80.3531	0.1099	233.9958
5.4908	0.4177	500	5.3144	49.3891	16.3343	32.4471	46.2974	79.6037	81.8018	80.6843	0.1159	233.9958
5.5082	0.5013	600	5.2235	49.2315	16.3591	32.6255	46.1221	79.5967	81.9095	80.733	0.1184	233.9958
5.4192	0.5848	700	5.1577	50.8099	16.929	33.2596	47.5073	79.9416	82.1638	81.0339	0.1226	233.9958
5.4327	0.6684	800	5.1134	51.0419	17.0275	33.4839	47.8258	80.0834	82.1836	81.1165	0.1228	233.9958
5.3311	0.7519	900	5.0760	50.6545	17.1249	33.5043	47.4752	80.0946	82.2579	81.1584	0.1242	233.9958
5.3244	0.8355	1000	5.0510	51.2619	17.2114	33.7881	47.9991	80.254	82.3319	81.2763	0.1247	233.9958
5.2486	0.9190	1100	5.0343	51.1056	17.2499	33.8193	47.8453	80.2471	82.3517	81.2824	0.1256	233.9958

Framework versions

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