tiny-bert-sst2-distilled

This model was trained from scratch on the glue dataset. It achieves the following results on the evaluation set:

• Loss: 0.6749
• Accuracy: 0.8200

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: 6e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 33
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 7
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1125	1.0	3	0.6731	0.8177
0.0984	2.0	6	0.6756	0.8188
0.1273	3.0	9	0.6754	0.8177
0.0758	4.0	12	0.6751	0.8188
0.1188	5.0	15	0.6754	0.8188
0.0936	6.0	18	0.6749	0.8200
0.0781	7.0	21	0.6748	0.8200

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0