You can deploy this model and start earning money today!

NasimB/
bert-finetune-simcse-truncate

Name: bert-finetune-simcse-truncate
Availability: InStock

Views

No views yet

bert-finetune-simcse-truncate

This model is a fine-tuned version of princeton-nlp/unsup-simcse-bert-base-uncased on the generator 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:

Training Loss	Epoch	Step	Validation Loss
4.5987	0.06	1000	4.1297
4.8781	0.13	2000	4.3769
4.9067	0.19	3000	4.3046
4.786	0.25	4000	4.1983
4.6378	0.32	5000	4.0821
4.4742	0.38	6000	3.9498
4.3019	0.44	7000	3.8138
4.1554	0.5	8000	3.7022
4.0328	0.57	9000	3.6072
3.9307	0.63	10000	3.5121
3.7965	0.69	11000	3.4289
3.6985	0.76	12000	3.3583
3.6315	0.82	13000	3.3108
3.5727	0.88	14000	3.2817
3.5468	0.95	15000	3.2668