matthewleechen/capital_saving_stated_aim_classifier

xlm-roberta-large

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3291
• Accuracy: 0.8895
• Precision: 0.8845
• Recall: 0.8895
• F1: 0.8864

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: 2e-05
• train_batch_size: 44
• eval_batch_size: 44
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	137	0.2702	0.901	0.8970	0.901	0.8985
No log	2.0	274	0.2688	0.9035	0.8985	0.9035	0.9000
No log	3.0	411	0.2695	0.909	0.9053	0.909	0.9066
0.2887	4.0	548	0.3043	0.9125	0.9086	0.9125	0.9043
0.2887	5.0	685	0.3059	0.9075	0.9016	0.9075	0.9016

Framework versions

• Transformers 4.48.2
• Pytorch 2.0.1+cu117
• Datasets 3.0.1
• Tokenizers 0.21.0