keyword / README.md
BINFOOL's picture
End of training
67a19d7 verified
|
Raw History Blame Contribute Delete
2.06 kB
---
library_name: transformers
base_model: Kkonjeong/wav2vec2-base-korean
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: keyword
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. -->
# keyword
This model is a fine-tuned version of [Kkonjeong/wav2vec2-base-korean](https://huggingface.co/Kkonjeong/wav2vec2-base-korean) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6729
- Accuracy: 1.0
## 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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 6 | 1.9897 | 0.2105 |
| No log | 2.0 | 12 | 1.8225 | 0.2105 |
| No log | 3.0 | 18 | 1.7221 | 0.4737 |
| No log | 4.0 | 24 | 1.4401 | 0.7895 |
| No log | 5.0 | 30 | 1.2758 | 0.8947 |
| No log | 6.0 | 36 | 1.0380 | 1.0 |
| No log | 7.0 | 42 | 0.8992 | 1.0 |
| No log | 8.0 | 48 | 0.7875 | 1.0 |
| No log | 9.0 | 54 | 0.6988 | 1.0 |
| No log | 10.0 | 60 | 0.6729 | 1.0 |
### Framework versions
- Transformers 5.18.0
- Pytorch 2.11.0+cu130
- Datasets 4.8.5
- Tokenizers 0.23.2