Physical_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: 5.5512
• Rouge1: 42.7556
• Rouge2: 11.8875
• Rougel: 28.895
• Rougelsum: 39.3949
• Bertscore Precision: 78.8849
• Bertscore Recall: 81.4458
• Bertscore F1: 80.1383
• Bleu: 0.0723
• Gen Len: 195.6218

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
6.8945	0.0620	100	6.5742	31.5625	6.7644	21.3466	29.564	75.9351	79.1872	77.5195	0.0377	195.6218
6.3686	0.1239	200	6.2216	36.3235	9.5662	25.3803	33.4451	76.783	80.08	78.3873	0.0551	195.6218
6.1776	0.1859	300	6.0881	38.1424	10.5393	26.1916	35.0327	77.3676	80.4951	78.892	0.0625	195.6218
6.1663	0.2478	400	5.9817	39.7408	10.7982	26.9356	36.7781	77.9473	80.6841	79.2852	0.0636	195.6218
6.0978	0.3098	500	5.8917	39.3921	10.6543	26.9539	36.4703	77.9172	80.7242	79.289	0.0631	195.6218
5.9824	0.3717	600	5.8200	42.4464	11.3324	27.8739	39.2401	78.5855	81.0563	79.7957	0.0669	195.6218
5.9387	0.4337	700	5.7582	41.98	11.3435	28.0672	38.7014	78.4184	81.1429	79.7509	0.0688	195.6218
5.8692	0.4957	800	5.7002	41.8091	11.4629	28.0863	38.4041	78.2676	81.1789	79.6896	0.0691	195.6218
5.8287	0.5576	900	5.6638	42.0986	11.4605	28.3743	38.792	78.3915	81.233	79.7799	0.0691	195.6218
5.8113	0.6196	1000	5.6285	41.7907	11.4896	28.4144	38.688	78.6019	81.2325	79.889	0.0691	195.6218
5.788	0.6815	1100	5.6124	42.7557	11.8057	28.7632	39.4786	78.7952	81.3582	80.0499	0.0709	195.6218
5.7594	0.7435	1200	5.5892	42.8952	11.8442	28.8255	39.5519	78.7779	81.3894	80.0556	0.0716	195.6218
5.7829	0.8055	1300	5.5713	42.9309	11.8742	28.8596	39.5816	78.8398	81.4053	80.0955	0.0719	195.6218
5.7359	0.8674	1400	5.5603	42.5415	11.7179	28.8073	39.2871	78.8019	81.37	80.0586	0.0710	195.6218
5.7216	0.9294	1500	5.5546	43.1987	12.0116	29.0028	39.8203	78.9462	81.474	80.1838	0.0728	195.6218
5.6968	0.9913	1600	5.5512	42.7556	11.8875	28.895	39.3949	78.8849	81.4458	80.1383	0.0723	195.6218

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1