bert_base_km_5_v2_stsb – AI Model by Hartunka | AlphaNeural AI

You can deploy this model and start earning money today!

Hartunka/
bert_base_km_5_v2_stsb

like

0

text-classification

generated_from_trainer

Hartunka/bert_base_km_5_v2

autotrain_compatible

endpoints_compatible

Views

No views yet

bert_base_km_5_v2_stsb

This model is a fine-tuned version of Hartunka/bert_base_km_5_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:

Loss: 1.8177
Pearson: 0.4729
Spearmanr: 0.4647
Combined Score: 0.4688

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-05
train_batch_size: 256
eval_batch_size: 256
seed: 10
optimizer: Use 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr	Combined Score
2.6459	1.0	23	2.4966	0.1835	0.1715	0.1775
1.8235	2.0	46	2.2914	0.3594	0.3550	0.3572
1.4306	3.0	69	2.0514	0.4242	0.4267	0.4254
1.0154	4.0	92	1.8177	0.4729	0.4647	0.4688
0.6595	5.0	115	2.1356	0.4311	0.4288	0.4299
0.5214	6.0	138	2.0065	0.4628	0.4615	0.4621
0.3787	7.0	161	2.2221	0.4495	0.4408	0.4451
0.3169	8.0	184	2.1129	0.4652	0.4569	0.4611
0.2679	9.0	207	2.1071	0.4559	0.4422	0.4491

Framework versions

Transformers 4.50.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.21.1