LoRA-SemEval

This model is a fine-tuned version of bert-base-uncased on the tweet_eval dataset. It achieves the following results on the evaluation set:

• Loss: 0.7185
• Accuracy: 0.6830
• Precision: 0.6857
• Recall: 0.6830
• Micro-avg-recall: 0.6830
• Micro-avg-precision: 0.6830

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	Micro-avg-recall	Micro-avg-precision
0.8156	1.0	2851	0.7505	0.6628	0.6653	0.6628	0.6628	0.6628
0.6812	2.0	5702	0.7254	0.6789	0.6819	0.6789	0.6789	0.6789
0.661	3.0	8553	0.7185	0.6830	0.6857	0.6830	0.6830	0.6830

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.15.0