metadata
license: apache-2.0
base_model: studio-ousia/mluke-base
tags:
- generated_from_trainer
model-index:
- name: exp_boss_mongkol
results: []
exp_boss_mongkol
This model is a fine-tuned version of studio-ousia/mluke-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3283
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: 2e-05
- train_batch_size: 16
- 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: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6493 | 1.0 | 306 | 0.6468 |
| 0.5945 | 2.0 | 612 | 0.6391 |
| 0.5368 | 3.0 | 918 | 0.5322 |
| 0.3295 | 4.0 | 1224 | 0.4335 |
| 0.3575 | 5.0 | 1530 | 0.4009 |
| 0.2772 | 6.0 | 1836 | 0.3509 |
| 0.3161 | 7.0 | 2142 | 0.3285 |
| 0.3384 | 8.0 | 2448 | 0.3348 |
| 0.3611 | 9.0 | 2754 | 0.3301 |
| 0.2944 | 10.0 | 3060 | 0.3283 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1