SST-2-GLoRA-p30-seed63

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

• Loss: 0.2018
• Accuracy: 0.9335

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3798	0.0950	200	0.2151	0.9186
0.2903	0.1900	400	0.1979	0.9220
0.2661	0.2850	600	0.1986	0.9197
0.2509	0.3800	800	0.2018	0.9335
0.2433	0.4751	1000	0.2158	0.9255
0.2302	0.5701	1200	0.2079	0.9266
0.229	0.6651	1400	0.1874	0.9289
0.2303	0.7601	1600	0.1907	0.9335
0.2275	0.8551	1800	0.1804	0.9335
0.2131	0.9501	2000	0.1898	0.9323

Framework versions

• PEFT 0.16.0
• Transformers 4.54.1
• Pytorch 2.5.1+cu121
• Datasets 4.0.0
• Tokenizers 0.21.4