metadata

library_name: transformers
license: mit
base_model: dumitrescustefan/bert-base-romanian-cased-v1
tags:
  - generated_from_trainer
datasets:
  - moroco
metrics:
  - f1
  - accuracy
  - precision
  - recall
model-index:
  - name: teacher_moroco
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: moroco
          type: moroco
          config: moroco
          split: validation
          args: moroco
        metrics:
          - name: F1
            type: f1
            value: 0.8683940771433114
          - name: Accuracy
            type: accuracy
            value: 0.8485053200472893
          - name: Precision
            type: precision
            value: 0.8698117604818486
          - name: Recall
            type: recall
            value: 0.8672521533524743

teacher_moroco

This model is a fine-tuned version of dumitrescustefan/bert-base-romanian-cased-v1 on the moroco dataset. It achieves the following results on the evaluation set:

Loss: 0.1075
F1: 0.8684
Roc Auc: 0.9149
Accuracy: 0.8485
Precision: 0.8698
Recall: 0.8673

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: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy	Precision	Recall
0.1332	1.0	1358	0.1120	0.8630	0.9075	0.8428	0.8822	0.8456
0.0935	2.0	2716	0.1075	0.8684	0.9149	0.8485	0.8698	0.8673

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0