SOMD-xlm-stage2-pre-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: 0.0149

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	202	0.8929
No log	1.99	404	0.5770
0.9912	2.99	606	0.3821
0.9912	3.98	808	0.2613
0.377	4.98	1010	0.1956
0.377	5.97	1212	0.1237
0.377	6.97	1414	0.1022
0.1873	7.96	1616	0.0802
0.1873	8.96	1818	0.0625
0.1002	9.95	2020	0.0627
0.1002	10.95	2222	0.0325
0.1002	11.94	2424	0.0302
0.0608	12.94	2626	0.0392
0.0608	13.93	2828	0.0244
0.0385	14.93	3030	0.0237
0.0385	15.92	3232	0.0204
0.0385	16.92	3434	0.0179
0.0279	17.91	3636	0.0154
0.0279	18.91	3838	0.0165
0.0232	19.9	4040	0.0149

Framework versions

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