roberta-base-lora-1.18M-snli-model2

This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7906
• Accuracy: 0.717

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: 256
• eval_batch_size: 256
• seed: 93
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4855	1.0	2146	0.3867	0.8539
0.4522	2.0	4292	0.3551	0.8645
0.4454	3.0	6438	0.3493	0.8663

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0