metadata

license: mit
base_model: MoritzLaurer/mDeBERTa-v3-base-mnli-xnli
tags:
  - generated_from_trainer
metrics:
  - f1
  - recall
  - accuracy
  - precision
model-index:
  - name: >-
      mDeBERTa-v3-base-xnli-multilingual-nli-2mil7-base-fine-tuned-text-classificarion-ds-ss
    results: []

mDeBERTa-v3-base-xnli-multilingual-nli-2mil7-base-fine-tuned-text-classificarion-ds-ss

This model is a fine-tuned version of MoritzLaurer/mDeBERTa-v3-base-mnli-xnli on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.0473
F1: 0.7427
Recall: 0.7662
Accuracy: 0.7662
Precision: 0.7444

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Recall	Accuracy	Precision
3.4822	1.0	883	2.0495	0.3963	0.4790	0.4790	0.3791
1.6347	2.0	1766	1.2672	0.6622	0.7030	0.7030	0.6535
1.0807	3.0	2649	1.0711	0.7172	0.7420	0.7420	0.7065
0.8958	4.0	3532	1.0654	0.7232	0.7489	0.7489	0.7218
0.7766	5.0	4415	1.0473	0.7427	0.7662	0.7662	0.7444

Framework versions

Transformers 4.33.1
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3