Jeevesh8_6ep_bert_ft_cola-29-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of Jeevesh8/6ep_bert_ft_cola-29 on the tweet_eval dataset. It achieves the following results on the evaluation set:

• accuracy: 0.6429

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
0.5047	None	0
0.5236	0.8020	0
0.5298	0.6849	1
0.5654	0.6645	2
0.5948	0.6334	3
0.6157	0.5938	4
0.6241	0.5786	5
0.6314	0.5586	6
0.6429	0.5499	7

Framework versions

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