Edit model card

korca_bae-roberta-base-boolq-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of korca/bae-roberta-base-boolq on the tweet_eval dataset. It achieves the following results on the evaluation set:

  • accuracy: 0.6712

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: 0.0005
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 8

Training results

accuracy train_loss epoch
0.4942 None 0
0.5864 0.7118 0
0.5885 0.6780 1
0.6 0.6617 2
0.6230 0.6414 3
0.6513 0.6204 4
0.6335 0.6058 5
0.6461 0.5959 6
0.6712 0.5967 7

Framework versions

  • PEFT 0.8.2
  • Transformers 4.37.2
  • Pytorch 2.2.0
  • Datasets 2.16.1
  • Tokenizers 0.15.2
Downloads last month
1
Inference Examples
Inference API (serverless) does not yet support peft models for this pipeline type.

Adapter for

Dataset used to train TransferGraph/korca_bae-roberta-base-boolq-finetuned-lora-tweet_eval_irony

Evaluation results