jaesun_distilbert-base-uncased-finetuned-cola-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of jaesun/distilbert-base-uncased-finetuned-cola on the tweet_eval dataset. It achieves the following results on the evaluation set:

• accuracy: 0.6545

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
0.5194	None	0
0.5927	0.7373	0
0.5885	0.6589	1
0.6408	0.6278	2
0.6660	0.5924	3
0.6482	0.5733	4
0.6408	0.5544	5
0.6555	0.5394	6
0.6545	0.5331	7

Framework versions

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