tiny_bert_rand_5_v1_stsb – AI Model by Hartunka | AlphaNeural AI

You can deploy this model and start earning money today!

Hartunka/
tiny_bert_rand_5_v1_stsb

like

0

text-classification

generated_from_trainer

Hartunka/tiny_bert_rand_5_v1

autotrain_compatible

endpoints_compatible

Views

No views yet

tiny_bert_rand_5_v1_stsb

This model is a fine-tuned version of Hartunka/tiny_bert_rand_5_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:

Loss: 2.3876
Pearson: 0.2931
Spearmanr: 0.2855
Combined Score: 0.2893

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
3.4897	1.0	23	2.4595	0.0690	0.0582	0.0636
2.0096	2.0	46	2.6146	0.1248	0.1084	0.1166
1.8479	3.0	69	2.3951	0.1948	0.1792	0.1870
1.6023	4.0	92	2.3876	0.2931	0.2855	0.2893
1.3085	5.0	115	2.4778	0.2811	0.2712	0.2761
1.0396	6.0	138	2.4495	0.3129	0.3111	0.3120
0.8308	7.0	161	2.4751	0.3386	0.3393	0.3390
0.6749	8.0	184	2.5454	0.3256	0.3217	0.3237
0.574	9.0	207	2.6687	0.3171	0.3124	0.3148

Framework versions

Transformers 4.50.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.21.1