tiny_bert_rand_50_v1_mnli

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

• Loss: 0.8632
• Accuracy: 0.6045

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
0.9908	1.0	1534	0.9352	0.5470
0.9036	2.0	3068	0.8886	0.5874
0.8527	3.0	4602	0.8672	0.6013
0.8101	4.0	6136	0.8601	0.6128
0.7693	5.0	7670	0.8588	0.6098
0.7296	6.0	9204	0.8737	0.6214
0.6889	7.0	10738	0.8843	0.6221
0.6504	8.0	12272	0.9532	0.6102
0.6127	9.0	13806	0.9572	0.6201
0.5741	10.0	15340	0.9934	0.6180

Framework versions

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