---
library_name: transformers
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
model-index:
- name: w2v-bert-2.0_somali_alpha
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# w2v-bert-2.0_somali_alpha

This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
It achieves the following results on the evaluation set:
- eval_loss: inf
- eval_cer: 0.1080
- eval_wer: 0.3958
- eval_runtime: 39.932
- eval_samples_per_second: 10.192
- eval_steps_per_second: 1.277
- epoch: 10.3448
- step: 600

## 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: 1e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 800
- num_epochs: 16
- mixed_precision_training: Native AMP

### Framework versions

- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2