opt-125m-pattern-based_finetuning_with_lora-mnli-d1_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: 0.7545
  • 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
0.7235 1.0 1 0.7545 0.5164
0.7313 2.0 2 0.7543 0.5160
0.7525 3.0 3 0.7541 0.5148
0.6582 4.0 4 0.7540 0.5149
0.666 5.0 5 0.7539 0.5149

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
Downloads last month
3
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for jeanlucmarsh/opt-125m-pattern-based_finetuning_with_lora-mnli-d1_fs2

Base model

facebook/opt-125m
Adapter
(45)
this model

Dataset used to train jeanlucmarsh/opt-125m-pattern-based_finetuning_with_lora-mnli-d1_fs2