ali2066_finetuned_sentence_itr1_2e-05_all_26_02_2022-04_03_26-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of ali2066/finetuned_sentence_itr1_2e-05_all_26_02_2022-04_03_26 on the tweet_eval dataset. It achieves the following results on the evaluation set:

• accuracy: 0.6450

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
0.5267	None	0
0.6021	0.6826	0
0.6073	0.6339	1
0.6262	0.5942	2
0.6440	0.5648	3
0.6492	0.5346	4
0.6251	0.5172	5
0.6450	0.5033	6
0.6450	0.4850	7

Framework versions

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