cointegrated_roberta-base-formality-finetuned-lora-tweet_eval_irony

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

• accuracy: 0.7120

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
0.5529	None	0
0.6084	0.7289	0
0.6230	0.6485	1
0.6743	0.6205	2
0.7005	0.5887	3
0.7047	0.5693	4
0.6817	0.5384	5
0.7110	0.5272	6
0.7120	0.5182	7

Framework versions

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