imdb-lora-0.01

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: 0.7073
• Accuracy: 0.4867
• F1: 0.4106

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: 5e-06
• train_batch_size: 80
• eval_batch_size: 80
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	4	0.7085	0.4858	0.4038
No log	2.0	8	0.7079	0.4859	0.4066
No log	3.0	12	0.7073	0.4867	0.4106
No log	4.0	16	0.7068	0.4862	0.4133
No log	5.0	20	0.7064	0.4864	0.4163
No log	6.0	24	0.7061	0.4866	0.4183
No log	7.0	28	0.7059	0.4862	0.4190
No log	8.0	32	0.7058	0.4864	0.4196
No log	9.0	36	0.7057	0.4864	0.4200
No log	10.0	40	0.7057	0.4864	0.4201

Framework versions

• PEFT 0.18.0
• Transformers 4.57.3
• Pytorch 2.9.1+cu128
• Datasets 4.4.2
• Tokenizers 0.22.1