metadata

base_model: microsoft/mdeberta-v3-base
datasets:
  - eriktks/conll2003
language:
  - en
library_name: transformers
license: mit
metrics:
  - precision
  - recall
  - f1
  - accuracy
pipeline_tag: token-classification
tags:
  - generated_from_trainer
model-index:
  - name: mdeberta
    results:
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: eriktks/conll2003
          type: eriktks/conll2003
          config: conll2003
          split: validation
          args: conll2003
        metrics:
          - type: precision
            value: 0.9566232899566233
            name: Precision
          - type: recall
            value: 0.9649949511948839
            name: Recall
          - type: f1
            value: 0.9607908847184986
            name: F1
          - type: accuracy
            value: 0.9929130485572991
            name: Accuracy

mdeberta-v3-base-conll2003-en

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the eriktks/conll2003 dataset (English split of the CONLL 2003). It achieves the following results on the evaluation set:

Loss: 0.0342
Precision: 0.9566
Recall: 0.9650
F1: 0.9608
Accuracy: 0.9929

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
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
num_epochs: 5.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	439	0.0509	0.9303	0.9456	0.9379	0.9890
0.1482	2.0	878	0.0359	0.9501	0.9583	0.9542	0.9918
0.0335	3.0	1317	0.0338	0.9530	0.9615	0.9572	0.9924
0.0191	4.0	1756	0.0346	0.9538	0.9635	0.9586	0.9926
0.0137	5.0	2195	0.0342	0.9566	0.9650	0.9608	0.9929

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1