summarise_v11

This model is a fine-tuned version of allenai/led-base-16384 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6322
• Rouge1 Precision: 0.6059
• Rouge1 Recall: 0.6233
• Rouge1 Fmeasure: 0.5895
• Rouge2 Precision: 0.4192
• Rouge2 Recall: 0.4512
• Rouge2 Fmeasure: 0.4176
• Rougel Precision: 0.4622
• Rougel Recall: 0.4946
• Rougel Fmeasure: 0.4566
• Rougelsum Precision: 0.4622
• Rougelsum Recall: 0.4946
• Rougelsum Fmeasure: 0.4566

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1 Precision	Rouge1 Recall	Rouge1 Fmeasure	Rouge2 Precision	Rouge2 Recall	Rouge2 Fmeasure	Rougel Precision	Rougel Recall	Rougel Fmeasure	Rougelsum Precision	Rougelsum Recall	Rougelsum Fmeasure
1.6201	0.45	10	1.4875	0.3203	0.64	0.3932	0.197	0.3839	0.2385	0.1952	0.4051	0.2454	0.1952	0.4051	0.2454
0.9172	0.91	20	1.4404	0.4917	0.5134	0.4699	0.288	0.3095	0.276	0.3371	0.3594	0.3277	0.3371	0.3594	0.3277
1.0923	1.36	30	1.3575	0.519	0.5505	0.4936	0.3114	0.3237	0.2958	0.3569	0.3702	0.3364	0.3569	0.3702	0.3364
1.1287	1.82	40	1.3269	0.4913	0.5997	0.5068	0.3108	0.3964	0.3269	0.3355	0.427	0.3521	0.3355	0.427	0.3521
0.9938	2.27	50	1.3189	0.5339	0.5781	0.4973	0.3555	0.3883	0.3345	0.3914	0.4289	0.3678	0.3914	0.4289	0.3678
0.8659	2.73	60	1.3241	0.525	0.638	0.5165	0.3556	0.4349	0.3535	0.3914	0.4793	0.3886	0.3914	0.4793	0.3886
0.6187	3.18	70	1.3360	0.5875	0.5864	0.5416	0.4005	0.4045	0.3701	0.4485	0.4556	0.414	0.4485	0.4556	0.414
0.3941	3.64	80	1.4176	0.5373	0.6415	0.5328	0.3576	0.446	0.3642	0.3787	0.4586	0.3781	0.3787	0.4586	0.3781
0.4145	4.09	90	1.3936	0.4127	0.6553	0.4568	0.2568	0.4498	0.2988	0.2918	0.4933	0.328	0.2918	0.4933	0.328
0.4203	4.55	100	1.4703	0.6545	0.601	0.5981	0.4789	0.4373	0.438	0.5251	0.4851	0.4818	0.5251	0.4851	0.4818
0.687	5.0	110	1.4304	0.5566	0.6357	0.5637	0.3734	0.4186	0.3748	0.4251	0.4825	0.4286	0.4251	0.4825	0.4286
0.4006	5.45	120	1.5399	0.5994	0.5794	0.5515	0.4215	0.4218	0.398	0.4359	0.4369	0.4084	0.4359	0.4369	0.4084
0.2536	5.91	130	1.5098	0.5074	0.6254	0.4874	0.3369	0.4189	0.3256	0.3802	0.4738	0.3664	0.3802	0.4738	0.3664
0.2218	6.36	140	1.5278	0.5713	0.6059	0.5688	0.3887	0.4233	0.3916	0.4414	0.4795	0.4457	0.4414	0.4795	0.4457
0.2577	6.82	150	1.5469	0.5148	0.5941	0.5175	0.3284	0.3856	0.3335	0.3616	0.4268	0.3681	0.3616	0.4268	0.3681
0.1548	7.27	160	1.5986	0.5983	0.657	0.5862	0.4322	0.4877	0.4287	0.4466	0.5167	0.4482	0.4466	0.5167	0.4482
0.1535	7.73	170	1.5796	0.5609	0.641	0.5616	0.3856	0.4428	0.3892	0.4238	0.4921	0.4263	0.4238	0.4921	0.4263
0.1568	8.18	180	1.6052	0.5669	0.617	0.5679	0.3911	0.4382	0.3969	0.4363	0.4877	0.4417	0.4363	0.4877	0.4417
0.2038	8.64	190	1.6191	0.5466	0.5973	0.5313	0.3543	0.4114	0.3531	0.4061	0.4666	0.404	0.4061	0.4666	0.404
0.1808	9.09	200	1.6165	0.5751	0.5919	0.5587	0.3831	0.4097	0.3817	0.4482	0.4728	0.4405	0.4482	0.4728	0.4405
0.1021	9.55	210	1.6316	0.5316	0.6315	0.535	0.3588	0.4563	0.3697	0.405	0.502	0.4126	0.405	0.502	0.4126
0.1407	10.0	220	1.6322	0.6059	0.6233	0.5895	0.4192	0.4512	0.4176	0.4622	0.4946	0.4566	0.4622	0.4946	0.4566

Framework versions

• Transformers 4.21.3
• Pytorch 1.12.1+cu113
• Datasets 1.2.1
• Tokenizers 0.12.1