metadata
base_model: ylacombe/w2v-bert-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_16_0
model-index:
- name: w2v-bert-2.0-japanese-colab-CV16.0
results: []
w2v-bert-2.0-japanese-colab-CV16.0
This model is a fine-tuned version of ylacombe/w2v-bert-2.0 on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:
- Loss: inf
- Cer: 0.3171
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: 8
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 4.2694 | 0.96 | 300 | inf | 0.6823 |
| 2.0595 | 1.93 | 600 | inf | 0.4528 |
| 1.3044 | 2.89 | 900 | inf | 0.3920 |
| 1.0889 | 3.85 | 1200 | inf | 0.3579 |
| 0.7867 | 4.82 | 1500 | inf | 0.3518 |
| 0.4371 | 5.78 | 1800 | inf | 0.3371 |
| 0.3414 | 6.74 | 2100 | inf | 0.3246 |
| 0.2373 | 7.7 | 2400 | inf | 0.3253 |
| 0.1171 | 8.67 | 2700 | inf | 0.3183 |
| 0.0524 | 9.63 | 3000 | inf | 0.3171 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1