bert_uncased_L-2_H-256_A-4_sst2

This model is a fine-tuned version of google/bert_uncased_L-2_H-256_A-4 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4074
• Accuracy: 0.8211

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4405	1.0	264	0.4195	0.8096
0.2935	2.0	528	0.4074	0.8211
0.2371	3.0	792	0.4241	0.8291
0.2044	4.0	1056	0.4573	0.8291
0.1805	5.0	1320	0.4635	0.8268
0.163	6.0	1584	0.4915	0.8326
0.1486	7.0	1848	0.5187	0.8326

Framework versions

• Transformers 4.46.3
• Pytorch 2.2.1+cu118
• Datasets 2.17.0
• Tokenizers 0.20.3