tiny_bert_rand_50_v1_sst2

This model is a fine-tuned version of Hartunka/tiny_bert_rand_50_v1 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4549
• Accuracy: 0.8028

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4234	1.0	264	0.4549	0.8028
0.2388	2.0	528	0.5081	0.7936
0.1892	3.0	792	0.5134	0.8039
0.1562	4.0	1056	0.5727	0.8062
0.1309	5.0	1320	0.6913	0.7924
0.1098	6.0	1584	0.7671	0.7993

Framework versions

• Transformers 4.40.0
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.19.1