You can deploy this model and start earning money today!

taiypeo/
bart-large-gigaword-rouge-3-loss-differentiable-10-cnt-supervised-sequential

Name: bart-large-gigaword-rouge-3-loss-differentiable-10-cnt-supervised-sequential
Availability: InStock

generated_from_trainer

taiypeo/bart-large-gigaword-sentence-paraphrased-10-cnt-supervised-basic

finetune

endpoints_compatible

Views

No views yet

bart-large-gigaword-rouge-3-loss-differentiable-10-cnt-supervised-sequential

This model is a fine-tuned version of taiypeo/bart-large-gigaword-sentence-paraphrased-10-cnt-supervised-basic on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.8113
Rouge1: 0.409
Rouge2: 0.1908
Rougel: 0.3745
Rougelsum: 0.3746

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: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.06
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.9081	0.0006	2	2.7011	0.4039	0.1875	0.3709	0.3705
0.9935	0.0013	4	2.7013	0.4039	0.1873	0.3707	0.3704
0.9384	0.0019	6	2.7017	0.4034	0.187	0.3703	0.37
0.9419	0.0026	8	2.7022	0.4033	0.1869	0.3699	0.3698
0.9851	0.0032	10	2.7029	0.4034	0.1866	0.37	0.3699
0.9882	0.0038	12	2.7039	0.404	0.1872	0.3705	0.3706
1.2981	0.0045	14	2.7050	0.404	0.1873	0.3705	0.3705
0.9815	0.0051	16	2.7063	0.4037	0.1872	0.3704	0.3701
0.8786	0.0058	18	2.7076	0.4034	0.1866	0.3699	0.3697
0.9345	0.0064	20	2.7094	0.4042	0.1871	0.3707	0.3705
0.9753	0.0070	22	2.7112	0.4041	0.1872	0.3707	0.3704
1.0457	0.0077	24	2.7131	0.4049	0.1873	0.3712	0.3711
0.971	0.0083	26	2.7153	0.4054	0.1878	0.3717	0.3716
0.9451	0.0090	28	2.7176	0.4043	0.1868	0.3712	0.3711
0.9366	0.0096	30	2.7200	0.4043	0.1867	0.3712	0.3712
0.8957	0.0102	32	2.7223	0.4046	0.1868	0.3713	0.3713
0.935	0.0109	34	2.7251	0.4056	0.1879	0.3725	0.3725
0.9241	0.0115	36	2.7284	0.4057	0.1883	0.3727	0.3727
0.9231	0.0122	38	2.7321	0.4052	0.1877	0.3722	0.3722
0.8891	0.0128	40	2.7363	0.4046	0.1873	0.3716	0.3716
0.9335	0.0134	42	2.7406	0.4039	0.1861	0.3709	0.371
0.9874	0.0141	44	2.7448	0.405	0.1872	0.3718	0.3719
1.0861	0.0147	46	2.7495	0.4045	0.1868	0.3714	0.3714
0.9618	0.0154	48	2.7551	0.4048	0.1874	0.372	0.3721
0.9918	0.0160	50	2.7613	0.4052	0.1877	0.3721	0.3721
0.9371	0.0166	52	2.7677	0.4059	0.1884	0.3729	0.3729
0.9301	0.0173	54	2.7747	0.4062	0.1887	0.3728	0.3727
0.9394	0.0179	56	2.7811	0.4066	0.1885	0.3726	0.3727
0.907	0.0186	58	2.7879	0.4071	0.1889	0.3731	0.373
0.9463	0.0192	60	2.7950	0.4071	0.1892	0.3729	0.3732
0.8816	0.0198	62	2.8030	0.4074	0.1891	0.3728	0.3728
0.962	0.0205	64	2.8113	0.409	0.1908	0.3745	0.3746
0.935	0.0211	66	2.8204	0.4085	0.1898	0.3735	0.3736
0.9083	0.0218	68	2.8309	0.4091	0.1904	0.3742	0.3743
0.8682	0.0224	70	2.8413	0.4081	0.1897	0.3736	0.3736
0.9037	0.0230	72	2.8521	0.4078	0.1894	0.3731	0.3731
0.873	0.0237	74	2.8642	0.407	0.1892	0.3723	0.372
0.9156	0.0243	76	2.8762	0.4061	0.1888	0.3713	0.3712
0.9198	0.0250	78	2.8887	0.4054	0.1882	0.3706	0.3704
0.9395	0.0256	80	2.9027	0.4071	0.1894	0.3723	0.3721
0.8747	0.0262	82	2.9161	0.4075	0.1893	0.3723	0.3723
0.8831	0.0269	84	2.9312	0.406	0.1882	0.371	0.371

Framework versions

Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 3.6.0
Tokenizers 0.22.1

taiypeo/bart-large-gigaword-rouge-3-loss-differentiable-10-cnt-supervised-sequential

bart-large-gigaword-rouge-3-loss-differentiable-10-cnt-supervised-sequential

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

taiypeo/
bart-large-gigaword-rouge-3-loss-differentiable-10-cnt-supervised-sequential