mDeBERTa-v3-base-xnli-multilingual-zeroshot-v1.3

This model is a fine-tuned version of asadfgglie/mDeBERTa-v3-base-xnli-multilingual-zeroshot-v1.0 on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.4780
• eval_f1_macro: 0.8407
• eval_f1_micro: 0.8429
• eval_accuracy_balanced: 0.8388
• eval_accuracy: 0.8429
• eval_precision_macro: 0.8473
• eval_recall_macro: 0.8388
• eval_precision_micro: 0.8429
• eval_recall_micro: 0.8429
• eval_runtime: 59.812
• eval_samples_per_second: 126.346
• eval_steps_per_second: 1.003
• epoch: 0.0
• step: 4

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: 128
• seed: 40
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.06
• num_epochs: 3

Framework versions

• Transformers 4.33.3
• Pytorch 2.5.1+cu121
• Datasets 2.14.7
• Tokenizers 0.13.3