metadata
license: cc-by-nc-nd-4.0
library_name: peft
tags:
- generated_from_trainer
base_model: kakaobrain/kogpt
model-index:
- name: pretrained-asd_wo-cot_w-asd_gpt
results: []
pretrained-asd_wo-cot_w-asd_gpt
This model is a fine-tuned version of kakaobrain/kogpt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.5349
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: 3e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 10.3358 | 0.1290 | 1 | 10.3445 |
| 9.6433 | 0.2581 | 2 | 9.6464 |
| 8.9317 | 0.3871 | 3 | 8.9778 |
| 8.4529 | 0.5161 | 4 | 8.3759 |
| 7.8797 | 0.6452 | 5 | 8.3759 |
| 7.9183 | 0.7742 | 6 | 7.7919 |
| 7.3288 | 0.9032 | 7 | 7.2000 |
| 6.8404 | 1.0323 | 8 | 6.6658 |
| 6.1929 | 1.1613 | 9 | 6.1626 |
| 5.7018 | 1.2903 | 10 | 5.6848 |
| 5.3948 | 1.4194 | 11 | 5.2752 |
| 4.9769 | 1.5484 | 12 | 4.9355 |
| 4.7513 | 1.6774 | 13 | 4.6277 |
| 4.5139 | 1.8065 | 14 | 4.3709 |
| 4.1545 | 1.9355 | 15 | 4.1658 |
| 3.895 | 2.0645 | 16 | 3.9919 |
| 3.6844 | 2.1935 | 17 | 3.8500 |
| 3.6875 | 2.3226 | 18 | 3.7336 |
| 3.6514 | 2.4516 | 19 | 3.6427 |
| 3.4645 | 2.5806 | 20 | 3.5779 |
| 3.3493 | 2.7097 | 21 | 3.5349 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1