metadata
library_name: transformers
base_model: digit82/kobart-summarization
tags:
- generated_from_trainer
model-index:
- name: ASR_KoBART_PostProcess
results: []
ASR_KoBART_PostProcess
This model is a fine-tuned version of digit82/kobart-summarization on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5180
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: 16
- eval_batch_size: 16
- seed: 42
- 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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 14 | 4.4617 |
| 5.3245 | 2.0 | 28 | 3.9843 |
| 4.0978 | 3.0 | 42 | 3.6403 |
| 4.0978 | 4.0 | 56 | 3.3431 |
| 3.5966 | 5.0 | 70 | 3.0924 |
| 3.2521 | 6.0 | 84 | 2.8834 |
| 3.2521 | 7.0 | 98 | 2.7240 |
| 2.944 | 8.0 | 112 | 2.6109 |
| 2.767 | 9.0 | 126 | 2.5419 |
| 2.6582 | 10.0 | 140 | 2.5180 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1