Giyaseddin_distilroberta-base-finetuned-short-answer-assessment-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of Giyaseddin/distilroberta-base-finetuned-short-answer-assessment on the tweet_eval dataset. It achieves the following results on the evaluation set:

• accuracy: 0.7016

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
0.4743	None	0
0.6188	0.7149	0
0.6262	0.6574	1
0.6660	0.6179	2
0.6932	0.5705	3
0.6859	0.5397	4
0.6796	0.5244	5
0.6953	0.5155	6
0.7016	0.4939	7

Framework versions

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