metadata

base_model: ylacombe/w2v-bert-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: w2v-bert-2.0-dutch-colab-CV16.0
    results: []

w2v-bert-2.0-dutch-colab-CV16.0

This model is a fine-tuned version of ylacombe/w2v-bert-2.0 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0920
Wer: 0.0573

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: 5e-05
train_batch_size: 64
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.3106	1.0	358	0.1833	0.1350
0.0924	2.0	716	0.1365	0.0932
0.0521	3.0	1074	0.1121	0.0732
0.033	3.99	1432	0.0957	0.0619
0.0221	4.99	1790	0.0920	0.0573

Framework versions

Transformers 4.37.0.dev0
Pytorch 1.12.1+cu116
Datasets 2.4.0
Tokenizers 0.15.2