adapter_dapt_reviews_small

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

• Loss: 1.5694

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: 0.0005
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 11
• total_train_batch_size: 352
• optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.06
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.7	0.2	500	1.5982
1.6873	0.41	1000	1.5850
1.6735	0.61	1500	1.5777
1.6686	0.82	2000	1.5726

Framework versions

• Transformers 4.36.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2