BERT-base

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

• Loss: 1.6524
• Accuracy: 0.4265

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	22	1.8763	0.2549
No log	2.0	44	1.8652	0.25
No log	3.0	66	1.7901	0.3088
No log	4.0	88	1.7617	0.3235
No log	5.0	110	1.7064	0.3676
No log	6.0	132	1.6792	0.4167
No log	7.0	154	1.6574	0.4216
No log	8.0	176	1.6524	0.4265

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0+cpu
• Datasets 2.21.0
• Tokenizers 0.19.1