opt-125m-pattern-based_finetuning_with_lora-mnli-mm-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: 0.8122
• Accuracy: 0.5104

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
0.6446	1.0	1	0.8122	0.5104
0.6665	2.0	2	0.8126	0.5104
0.6007	3.0	3	0.8130	0.5099
0.6147	4.0	4	0.8132	0.5101
0.6054	5.0	5	0.8133	0.5101

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