teacher_laroseda

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

  • Loss: 0.1746
  • F1: 0.9510
  • Roc Auc: 0.9510
  • Accuracy: 0.951
  • Precision: 0.9510
  • Recall: 0.951

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: 1.7e-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
0.2117 1.0 688 0.1362 0.9450 0.9450 0.945 0.9450 0.945
0.1154 2.0 1376 0.1746 0.9510 0.9510 0.951 0.9510 0.951

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.4.0
  • Datasets 3.0.1
  • Tokenizers 0.20.0
Downloads last month
111
Safetensors
Model size
124M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for mateiaassAI/teacher_laroseda

Finetuned
(8)
this model

Dataset used to train mateiaassAI/teacher_laroseda

Evaluation results