BERTweet

This model is a fine-tuned version of vinai/bertweet-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3206
• Accuracy: 0.8898

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6119	0.0994	47	0.5232	0.7661
0.4769	0.1987	94	0.5216	0.7661
0.4077	0.2981	141	0.4198	0.8433
0.401	0.3975	188	0.3780	0.8718
0.3604	0.4968	235	0.3832	0.8628
0.317	0.5962	282	0.3229	0.8913
0.3708	0.6956	329	0.3560	0.8831
0.3589	0.7949	376	0.3496	0.8913
0.3847	0.8943	423	0.4977	0.8411
0.3504	0.9937	470	0.3206	0.8898

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1