You can deploy this model and start earning money today!

taiypeo/
bart-large-wiki-doc-nested-wasserstein-simultaneous-wiki-doc-alt

Name: bart-large-wiki-doc-nested-wasserstein-simultaneous-wiki-doc-alt
Availability: InStock

generated_from_trainer

taiypeo/bart-large-wiki-doc-full

finetune

apache-2.0

endpoints_compatible

Views

No views yet

bart-large-wiki-doc-nested-wasserstein-simultaneous-wiki-doc-alt

This model is a fine-tuned version of taiypeo/bart-large-wiki-doc-full on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 7.8984
Sari: 51.3085
Sari Add: 13.508
Sari Keep: 45.1811
Sari Del: 95.2364
Fkgl: 6.4281
Bleu: 21.6868
D Sari: 0.4692
D Sari Keep: 0.4057
D Sari Del: 0.813
D Sari Add: 0.189

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-06
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
label_smoothing_factor: 0.3

Training results

Training Loss	Epoch	Step	Validation Loss	Sari	Sari Add	Sari Keep	Sari Del	Fkgl	Bleu	D Sari	D Sari Keep	D Sari Del	D Sari Add
4.3009	0.0746	50	7.9193	51.3663	13.3048	45.4824	95.3117	6.425	21.3375	0.4644	0.4	0.8106	0.1827
4.3136	0.1491	100	7.8927	51.2678	13.3174	45.3112	95.1747	6.4464	22.2868	0.4636	0.4005	0.8069	0.1832
4.3129	0.2237	150	7.8575	51.2685	13.2887	45.2449	95.272	6.4419	21.3635	0.4644	0.4005	0.8093	0.1834
4.2768	0.2983	200	7.8656	51.1753	13.4353	44.8269	95.2638	6.4791	20.9212	0.4665	0.403	0.8108	0.1857
4.2974	0.3729	250	7.8889	51.2671	13.4539	44.9946	95.3528	6.3721	20.5645	0.4669	0.4023	0.8135	0.1848
4.2854	0.4474	300	7.8886	51.3469	13.5089	45.2271	95.3049	6.4563	21.1705	0.4669	0.4031	0.8113	0.1862
4.308	0.5220	350	7.8793	51.2555	13.4537	45.0781	95.2345	6.4398	21.6056	0.4666	0.4026	0.8101	0.1869
4.2915	0.5966	400	7.8731	51.2699	13.6447	45.0364	95.1285	6.5432	22.3748	0.466	0.4025	0.8084	0.1873
4.3032	0.6711	450	7.8705	51.1301	13.5016	44.7369	95.1519	6.5271	21.8921	0.4649	0.3999	0.8084	0.1864
4.321	0.7457	500	7.8405	51.2747	13.6095	45.036	95.1786	6.5003	22.0481	0.4667	0.4025	0.8109	0.1866
4.27	0.8203	550	7.8775	51.2038	13.4899	44.9277	95.194	6.4719	21.7804	0.466	0.4014	0.8107	0.186
4.3001	0.8949	600	7.8749	51.4288	13.6837	45.2686	95.3342	6.3461	21.1915	0.4682	0.4039	0.8134	0.1874
4.2789	0.9694	650	7.8757	51.1939	13.4916	44.8631	95.2271	6.4447	21.3401	0.4659	0.4001	0.812	0.1857
4.288	1.0433	700	7.8704	51.2322	13.4586	44.9789	95.2591	6.4477	21.2314	0.4675	0.4025	0.8121	0.1879
4.2849	1.1178	750	7.8801	51.2299	13.5116	44.9662	95.212	6.4476	21.667	0.4678	0.4035	0.8129	0.1869
4.2884	1.1924	800	7.8947	51.2458	13.4926	45.0101	95.2346	6.4869	21.4739	0.4675	0.4029	0.8123	0.1873
4.2501	1.2670	850	7.8984	51.3085	13.508	45.1811	95.2364	6.4281	21.6868	0.4692	0.4057	0.813	0.189
4.292	1.3415	900	7.8741	51.3351	13.5423	45.1421	95.3208	6.416	20.9965	0.4676	0.4024	0.8136	0.187
4.2731	1.4161	950	7.8988	51.3752	13.5315	45.2614	95.3325	6.4379	20.9597	0.4684	0.4037	0.8146	0.187
4.2662	1.4907	1000	7.9068	51.2609	13.5762	44.9776	95.2289	6.4671	21.5622	0.4666	0.4016	0.8112	0.1871
4.2969	1.5652	1050	7.9158	51.2633	13.519	45.0878	95.183	6.4803	22.0521	0.4663	0.4016	0.8115	0.1858
4.2783	1.6398	1100	7.8958	51.3313	13.5824	45.1692	95.2422	6.4844	21.6352	0.4677	0.403	0.8127	0.1874
4.2736	1.7144	1150	7.8924	51.3127	13.4844	45.2108	95.243	6.5017	21.6586	0.4667	0.4019	0.8121	0.1861
4.2942	1.7890	1200	7.9009	51.3457	13.5352	45.284	95.2179	6.4871	21.9577	0.4681	0.4037	0.8132	0.1873
4.2764	1.8635	1250	7.9296	51.3461	13.5385	45.2787	95.2209	6.4803	21.9348	0.4681	0.404	0.8134	0.187
4.2805	1.9381	1300	7.9229	51.2933	13.581	45.0083	95.2907	6.3472	21.1502	0.4677	0.4025	0.8144	0.1862
4.2659	2.0119	1350	7.9243	51.3446	13.5762	45.2433	95.2142	6.3795	22.0953	0.4689	0.4048	0.8142	0.1877

Framework versions

Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 3.6.0
Tokenizers 0.22.1

taiypeo/bart-large-wiki-doc-nested-wasserstein-simultaneous-wiki-doc-alt

bart-large-wiki-doc-nested-wasserstein-simultaneous-wiki-doc-alt

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

taiypeo/
bart-large-wiki-doc-nested-wasserstein-simultaneous-wiki-doc-alt