w11wo_sundanese-bert-base-emotion-classifier-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of w11wo/sundanese-bert-base-emotion-classifier on the tweet_eval dataset. It achieves the following results on the evaluation set:

• accuracy: 0.5864

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
0.4974	None	0
0.5361	0.7013	0
0.5298	0.6854	1
0.5529	0.6635	2
0.5644	0.6476	3
0.5560	0.6263	4
0.5738	0.6143	5
0.5812	0.6073	6
0.5864	0.6047	7

Framework versions

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