metadata

license: mit
base_model: igorsterner/german-english-code-switching-bert
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: tsBERT_sa_cv_11_full_training
    results: []

tsBERT_sa_cv_11_full_training

This model is a fine-tuned version of igorsterner/german-english-code-switching-bert on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4383
F1: 0.6883

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: 4.47e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	251	0.4106	0.5435
0.3693	2.0	502	0.4038	0.6419
0.3693	3.0	753	0.4383	0.6883

Framework versions

Transformers 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1