utku-model-part1_latest

This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:

Validation Loss: 0.988973 Matthews Correlation: 0.568543

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: 8.80887270242613e-06
• train_batch_size: 4
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Epoch	Training Loss	Validation Loss	Mcc
1	0.272100	0.702248	0.516378
2	0.451200	0.745428	0.580507
3	0.244100	0.859209	0.580807
4	0.160700	0.988973	0.568543

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3