financial-twhin-bert-large-7labels

This model is a fine-tuned version of Twitter/twhin-bert-large on financial tweets. It achieves the following results on the evaluation set:

• Loss: 0.2960
• Accuracy: 0.9023
• F1: 0.9014

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: 2.1732582582331977e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 1203
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.0082	0.3272	1500	0.4766	0.8302	0.8179
0.4354	0.9817	4500	0.3823	0.8616	0.8532
0.3136	1.6361	7500	0.3266	0.8872	0.8902
0.246	2.2906	10500	0.3183	0.8976	0.8923
0.2173	2.9450	13500	0.2960	0.9023	0.9014

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1