Jeevesh8_feather_berts_46-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of Jeevesh8/feather_berts_46 on the tweet_eval dataset. It achieves the following results on the evaluation set:

• accuracy: 0.7026

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
0.4775	None	0
0.5895	0.6862	0
0.6408	0.6491	1
0.6513	0.6070	2
0.6702	0.5783	3
0.6754	0.5616	4
0.6681	0.5446	5
0.6848	0.5260	6
0.7026	0.5247	7

Framework versions

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