You can deploy this model and start earning money today!

mhr2004/
roberta-large-nsp-1000000-1e-06-32-stsb-lr2e-05-bs32

Name: roberta-large-nsp-1000000-1e-06-32-stsb-lr2e-05-bs32
Availability: InStock

Views

No views yet

roberta-large-nsp-1000000-1e-06-32-stsb-lr2e-05-bs32

This model is a fine-tuned version of mhr2004/roberta-large-nsp-1000000-1e-06-32 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: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearman
0.0378	1.0	180	0.0204	0.8831	0.8870
0.0309	2.0	360	0.0175	0.9099	0.9075
0.0272	3.0	540	0.0195	0.9053	0.9077
0.0207	4.0	720	0.0184	0.9118	0.9097
0.0188	5.0	900	0.0167	0.9094	0.9114
0.0168	6.0	1080	0.0205	0.9157	0.9175
0.0134	7.0	1260	0.0141	0.9192	0.9184
0.0127	8.0	1440	0.0249	0.9148	0.9130
0.0117	9.0	1620	0.0167	0.9206	0.9202
0.011	10.0	1800	0.0146	0.9173	0.9186
0.0098	11.0	1980	0.0152	0.9176	0.9177
0.0097	12.0	2160	0.0199	0.9207	0.9211
0.0085	13.0	2340	0.0147	0.9210	0.9204
0.0082	14.0	2520	0.0158	0.9210	0.9200
0.0078	15.0	2700	0.0175	0.9197	0.9199