ukr-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: 0.0619
• F1-micro: 0.4793
• F1-macro: 0.3770

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: 49
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	F1-micro	F1-macro
0.081	1.0	124	0.0794	0.2544	0.0940
0.0788	2.0	248	0.0785	0.2621	0.0950
0.0731	3.0	372	0.0646	0.4561	0.3056
0.0601	4.0	496	0.0619	0.4793	0.3770

Framework versions

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