Jeevesh8_bert_ft_qqp-39-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of Jeevesh8/bert_ft_qqp-39 on the tweet_eval dataset. It achieves the following results on the evaluation set:

• accuracy: 0.6283

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
0.5225	None	0
0.5707	0.8689	0
0.5518	0.6801	1
0.5696	0.6507	2
0.5937	0.6308	3
0.6073	0.6114	4
0.5958	0.5907	5
0.6230	0.5773	6
0.6283	0.5678	7

Framework versions

• PEFT 0.8.2
• Transformers 4.37.2
• Pytorch 2.2.0
• Datasets 2.16.1
• Tokenizers 0.15.2