tiny_bert_rand_100_v1_wnli

This model is a fine-tuned version of Hartunka/tiny_bert_rand_100_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6914
• Accuracy: 0.5634

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
0.6941	1.0	3	0.6914	0.5634
0.6962	2.0	6	0.6954	0.5634
0.6966	3.0	9	0.7035	0.4366
0.6913	4.0	12	0.6997	0.4085
0.696	5.0	15	0.7007	0.4507
0.6928	6.0	18	0.7075	0.3521

Framework versions

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