SOMD-xlm-stage2-v2

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: 0.0189

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	202	0.7700
No log	1.99	404	0.4359
0.9071	2.99	606	0.2860
0.9071	3.98	808	0.2105
0.3139	4.98	1010	0.1515
0.3139	5.97	1212	0.1064
0.3139	6.97	1414	0.0768
0.1382	7.96	1616	0.0572
0.1382	8.96	1818	0.0412
0.0715	9.95	2020	0.0357
0.0715	10.95	2222	0.0316
0.0715	11.94	2424	0.0267
0.0424	12.94	2626	0.0215
0.0424	13.93	2828	0.0194
0.0292	14.93	3030	0.0189

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2