tiny_bert_km_50_v1_wnli

This model is a fine-tuned version of Hartunka/tiny_bert_km_50_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.7139
• Accuracy: 0.3803

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
0.7038	1.0	3	0.7232	0.3803
0.6955	2.0	6	0.7139	0.3803
0.692	3.0	9	0.7201	0.3662
0.6926	4.0	12	0.7316	0.3521
0.689	5.0	15	0.7488	0.2817
0.6869	6.0	18	0.7665	0.2817
0.6912	7.0	21	0.7717	0.2394

Framework versions

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