robertou2_roberta-base-bne-finetuned-amazon_reviews_multi-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of robertou2/roberta-base-bne-finetuned-amazon_reviews_multi on the tweet_eval dataset. It achieves the following results on the evaluation set:

• accuracy: 0.6670

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
0.5403	None	0
0.5948	0.7041	0
0.6	0.6361	1
0.6251	0.5760	2
0.6545	0.5366	3
0.6628	0.4968	4
0.6545	0.4455	5
0.6764	0.4160	6
0.6670	0.3901	7

Framework versions

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