metadata

license: mit
base_model: MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: mDeBERTa-v3-base-xnli-multilingual-nli-2mil7-energy
    results: []

mDeBERTa-v3-base-xnli-multilingual-nli-2mil7-energy

This model is a fine-tuned version of MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2328
Accuracy: 0.9637
Precision: 0.9637
Recall: 0.9636
F1: 0.9637
Ratio: 0.4847

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: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.06
lr_scheduler_warmup_steps: 3
num_epochs: 5
label_smoothing_factor: 0.01

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Ratio
0.5212	0.43	400	0.3449	0.8948	0.8964	0.8940	0.8945	0.4596
0.4083	0.86	800	0.3203	0.9224	0.9232	0.9218	0.9222	0.4684
0.2384	1.29	1200	0.3149	0.9361	0.9365	0.9358	0.9360	0.4759
0.213	1.72	1600	0.3024	0.9443	0.9442	0.9442	0.9442	0.4865
0.1686	2.15	2000	0.2742	0.9493	0.6332	0.6329	0.6330	0.4934
0.105	2.58	2400	0.2641	0.9518	0.9519	0.9522	0.9518	0.5041
0.116	3.01	2800	0.2515	0.9555	0.6374	0.6372	0.6372	0.4997
0.077	3.44	3200	0.2511	0.9580	0.9580	0.9583	0.9580	0.4966
0.0622	3.86	3600	0.2355	0.9643	0.9644	0.9642	0.9643	0.4828
0.0524	4.29	4000	0.2289	0.9637	0.9636	0.9637	0.9637	0.4884
0.0498	4.72	4400	0.2336	0.9643	0.9644	0.9642	0.9643	0.4840

Framework versions

Transformers 4.31.0
Pytorch 2.1.0+cu121
Datasets 2.14.7
Tokenizers 0.13.3