opt-125m-pattern-based_finetuning_with_lora-mnli-d3_fs2

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: 0.7558
• Accuracy: 0.5166

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
0.6236	1.0	1	0.7554	0.5160
0.6717	2.0	2	0.7556	0.5163
0.7121	3.0	3	0.7558	0.5166
0.7589	4.0	4	0.7559	0.5164
0.6858	5.0	5	0.7559	0.5163

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