bert-base-uncased-finetuned-set_5

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3627
• Accuracy: 0.8690
• Qwk: 0.8044

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Qwk
No log	1.0	92	0.4092	0.8542	0.6368
No log	2.0	184	0.3892	0.8452	0.7958
No log	3.0	276	0.3484	0.8512	0.7103
No log	4.0	368	0.3624	0.8452	0.7737
No log	5.0	460	0.3627	0.8690	0.8044

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0