metadata
license: mit
base_model: gogamza/kobart-base-v2
tags:
- generated_from_trainer
model-index:
- name: modelling
results: []
modelling
This model is a fine-tuned version of gogamza/kobart-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6042
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: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.164 | 1.41 | 500 | 0.6552 |
| 0.4948 | 2.82 | 1000 | 0.6042 |
| 0.2967 | 4.24 | 1500 | 0.7162 |
| 0.1858 | 5.65 | 2000 | 0.7271 |
| 0.1245 | 7.06 | 2500 | 0.7639 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0