xlm-roberta-base-cefr-all-classifier

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: 0.1171
• F1: 0.9529

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: 3.6e-05
• train_batch_size: 2
• eval_batch_size: 3
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.1481	1.0	13623	0.1473	0.9416
0.1133	2.0	27246	0.1190	0.9486
0.0852	2.9998	40866	0.1171	0.9529

Framework versions

• Transformers 4.51.0
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.21.0