marcelcastrobr_sagemaker-distilbert-emotion-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of marcelcastrobr/sagemaker-distilbert-emotion on the tweet_eval dataset. It achieves the following results on the evaluation set:

• accuracy: 0.6555

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
0.4450	None	0
0.5791	0.7029	0
0.6094	0.6496	1
0.6398	0.6141	2
0.6461	0.5801	3
0.6492	0.5610	4
0.6262	0.5536	5
0.6534	0.5240	6
0.6555	0.5214	7

Framework versions

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