README.md

metadata

license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: Full-2epoch-BERT-base-multilingual-finetuned-CEFR_ner-60000news
    results: []

Full-2epoch-BERT-base-multilingual-finetuned-CEFR_ner-60000news

This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1113
• Accuracy: 0.3015
• Precision: 0.5856
• Recall: 0.8155
• F1: 0.5650

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.1704	1.0	1563	0.1348	0.2991	0.5538	0.7961	0.5345
0.1196	2.0	3126	0.1113	0.3015	0.5856	0.8155	0.5650

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.1
• Datasets 2.19.2
• Tokenizers 0.19.1