tiny_bert_km_100_v1_wnli

This model is a fine-tuned version of Hartunka/tiny_bert_km_100_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6931
• Accuracy: 0.5211

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
0.7061	1.0	3	0.6931	0.5211
0.6931	2.0	6	0.6976	0.4930
0.6991	3.0	9	0.7136	0.3803
0.692	4.0	12	0.7199	0.3803
0.6907	5.0	15	0.7243	0.3662
0.6884	6.0	18	0.7314	0.3803

Framework versions

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