bert_cm

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: 0.4443
• Accuracy: 0.9210

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	132	0.2634	0.8951
No log	2.0	264	0.2139	0.9195
No log	3.0	396	0.3145	0.9195
0.2227	4.0	528	0.3342	0.9286
0.2227	5.0	660	0.3804	0.9316
0.2227	6.0	792	0.3942	0.9362
0.2227	7.0	924	0.4372	0.9195
0.0101	8.0	1056	0.4211	0.9255
0.0101	9.0	1188	0.4334	0.9240
0.0101	10.0	1320	0.4443	0.9210

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1