bert-finetuned

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

• Loss: 0.6753
• Accuracy: 0.6966

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• 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
0.9191	0.3333	30	0.8623	0.6180
0.9387	0.6667	60	0.8493	0.6180
0.8703	1.0	90	0.8300	0.6180
0.8821	1.3333	120	0.8125	0.6404
0.8534	1.6667	150	0.8569	0.6180
0.814	2.0	180	0.8207	0.6180
0.8321	2.3333	210	0.7345	0.6966
0.7997	2.6667	240	0.8491	0.4607
0.8799	3.0	270	0.6921	0.7303
0.8526	3.3333	300	0.6953	0.6854
0.7293	3.6667	330	0.7100	0.6517
0.783	4.0	360	0.6989	0.6854
0.7399	4.3333	390	0.7053	0.6966
0.6808	4.6667	420	0.7315	0.6517
0.6753	5.0	450	0.6753	0.6966

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0