opt-125m-pattern-based_finetuning_with_lora-mnli-d2_fs1

This model is a fine-tuned version of facebook/opt-125m on the glue dataset. It achieves the following results on the evaluation set:

• Loss: 0.7546
• Accuracy: 0.5164

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-06
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4477	1.0	1	0.7546	0.5164
0.6187	2.0	2	0.7544	0.5158
0.6611	3.0	3	0.7542	0.5155
0.5539	4.0	4	0.7541	0.5152
0.5898	5.0	5	0.7541	0.5151

Framework versions

• PEFT 0.7.1.dev0
• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0