bias_model_1

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

• Loss: 1.5496
• Accuracy: 0.5667

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	12	0.6961	0.4667
No log	2.0	24	0.7091	0.4333
No log	3.0	36	0.6954	0.3833
No log	4.0	48	0.6720	0.65
No log	5.0	60	0.6877	0.5833
No log	6.0	72	0.7910	0.4667
No log	7.0	84	0.7422	0.5833
No log	8.0	96	0.7865	0.55
No log	9.0	108	0.8997	0.5833
No log	10.0	120	1.0164	0.55
No log	11.0	132	1.1668	0.5167
No log	12.0	144	1.2486	0.5833
No log	13.0	156	1.3424	0.5167
No log	14.0	168	1.4065	0.5167
No log	15.0	180	1.4477	0.5833
No log	16.0	192	1.4737	0.5833
No log	17.0	204	1.5120	0.55
No log	18.0	216	1.5484	0.5333
No log	19.0	228	1.5479	0.5667
No log	20.0	240	1.5496	0.5667

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2