albert_emotion

This model is a fine-tuned version of lilyray/albert_emotion on the emotion dataset. It achieves the following results on the evaluation set:

• Loss: 0.2391
• Accuracy: 0.9295

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: 9.363600088100325e-06
• train_batch_size: 4
• eval_batch_size: 8
• seed: 19
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1744	1.0	4000	0.2001	0.938

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2