metadata
library_name: peft
base_model: lcw99/zephykor-ko-7b-chang
tags:
- axolotl
- generated_from_trainer
model-index:
- name: dd45babb-0c73-48fc-8094-eebfde4df372
results: []
dd45babb-0c73-48fc-8094-eebfde4df372
This model is a fine-tuned version of lcw99/zephykor-ko-7b-chang on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4921
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: 0.000202
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 50
- training_steps: 400
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0001 | 1 | 4.4533 |
| 10.7481 | 0.0056 | 50 | 2.5631 |
| 9.4069 | 0.0113 | 100 | 2.4389 |
| 9.64 | 0.0169 | 150 | 2.3673 |
| 9.6174 | 0.0226 | 200 | 2.3359 |
| 9.1584 | 0.0282 | 250 | 2.3844 |
| 9.1216 | 0.0339 | 300 | 2.3883 |
| 8.7793 | 0.0395 | 350 | 2.4921 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1