dhimskyy_wiki-bert-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of dhimskyy/wiki-bert on the tweet_eval dataset. It achieves the following results on the evaluation set:

  • accuracy: 0.5749

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
0.5215 None 0
0.5476 0.6930 0
0.5738 0.6883 1
0.5759 0.6802 2
0.5613 0.6658 3
0.5749 0.6548 4
0.5487 0.6509 5
0.5853 0.6418 6
0.5749 0.6377 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
0
Inference Examples
Inference API (serverless) does not yet support peft models for this pipeline type.

Model tree for TransferGraph/dhimskyy_wiki-bert-finetuned-lora-tweet_eval_irony

Base model

dhimskyy/wiki-bert
Adapter
(4)
this model

Dataset used to train TransferGraph/dhimskyy_wiki-bert-finetuned-lora-tweet_eval_irony

Evaluation results