SOMD-train-xlm-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: 0.0000
• F1: 1.0

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	1243	0.0067	0.6281
No log	2.0	2486	0.0034	0.7847
No log	3.0	3729	0.0031	0.7984
No log	4.0	4972	0.0015	0.8925
No log	5.0	6215	0.0010	0.9170
No log	6.0	7458	0.0009	0.9312
No log	7.0	8701	0.0006	0.9476
No log	8.0	9944	0.0008	0.9508
No log	9.0	11187	0.0004	0.9829
No log	10.0	12430	0.0001	0.9915
No log	11.0	13673	0.0002	0.9894
No log	12.0	14916	0.0001	0.9940
No log	13.0	16159	0.0000	0.9978
No log	14.0	17402	0.0000	0.9978
No log	15.0	18645	0.0000	0.9991
No log	16.0	19888	0.0000	0.9974
No log	17.0	21131	0.0000	0.9995
No log	18.0	22374	0.0000	0.9997
No log	19.0	23617	0.0000	1.0
No log	20.0	24860	0.0000	1.0

Framework versions

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