You can deploy this model and start earning money today!

taiypeo/
bart-base-gigaword-rouge-3-loss-differentiable-100-cnt-supervised-sequential

Name: bart-base-gigaword-rouge-3-loss-differentiable-100-cnt-supervised-sequential
Availability: InStock

Views

No views yet

bart-base-gigaword-rouge-3-loss-differentiable-100-cnt-supervised-sequential

This model is a fine-tuned version of taiypeo/bart-base-gigaword-sentence-paraphrased-100-cnt-supervised-basic on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

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 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: 1

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.9789	0.0032	10	2.6820	0.403	0.1862	0.3757	0.376
0.9564	0.0064	20	2.7074	0.4027	0.185	0.3757	0.3759
0.964	0.0096	30	2.7558	0.4043	0.1866	0.376	0.3764
0.971	0.0128	40	2.8240	0.4032	0.1855	0.3752	0.3755
0.9286	0.0160	50	2.9063	0.4044	0.1855	0.375	0.3754
0.8988	0.0192	60	3.0028	0.4049	0.185	0.3746	0.3748
0.905	0.0224	70	3.0851	0.41	0.1879	0.3796	0.3799
0.8848	0.0257	80	3.2184	0.4073	0.1831	0.3774	0.3776
0.8967	0.0289	90	3.3391	0.4056	0.1789	0.3738	0.3739
0.8736	0.0321	100	3.4328	0.404	0.1767	0.3724	0.3724
0.8713	0.0353	110	3.5631	0.396	0.1691	0.3655	0.3655
0.9068	0.0385	120	3.7952	0.3881	0.1601	0.3587	0.3589
0.8873	0.0417	130	4.1277	0.3781	0.15	0.3484	0.3487
0.8977	0.0449	140	4.5336	0.3627	0.1377	0.3336	0.3339