SOMD-train-xlm-v1

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

• Loss: 0.0001
• F1: 0.9963

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	1243	0.0069	0.6471
No log	2.0	2486	0.0147	0.4535
No log	3.0	3729	0.0030	0.8179
No log	4.0	4972	0.0014	0.9087
No log	5.0	6215	0.0007	0.9353
No log	6.0	7458	0.0004	0.9664
No log	7.0	8701	0.0002	0.9867
No log	8.0	9944	0.0001	0.9918
No log	9.0	11187	0.0001	0.9954
No log	10.0	12430	0.0001	0.9963

Framework versions

• Transformers 4.37.0
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.1