rus-xlm-asym-lr-3e-5

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0530
• F1-micro: 0.7641
• F1-macro: 0.7552

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 8
• 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
• lr_scheduler_warmup_steps: 53
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	F1-micro	F1-macro
0.1101	1.0	134	0.0800	0.6399	0.6431
0.0714	2.0	268	0.0596	0.7241	0.7232
0.0512	3.0	402	0.0552	0.7465	0.7427
0.0396	4.0	536	0.0530	0.7641	0.7552

Framework versions

• Transformers 4.48.1
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0