metadata
library_name: peft
base_model: oopsung/llama2-7b-koNqa-test-v1
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 3a140fda-d4eb-40c1-9fc3-75c917099143
results: []
3a140fda-d4eb-40c1-9fc3-75c917099143
This model is a fine-tuned version of oopsung/llama2-7b-koNqa-test-v1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1435
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: 0.000201
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0009 | 1 | 2.8770 |
| 0.4097 | 0.0443 | 50 | 0.5165 |
| 0.2715 | 0.0887 | 100 | 0.3821 |
| 0.2237 | 0.1330 | 150 | 0.3168 |
| 0.1994 | 0.1774 | 200 | 0.3108 |
| 0.1585 | 0.2217 | 250 | 0.2560 |
| 0.1516 | 0.2661 | 300 | 0.2386 |
| 0.1805 | 0.3104 | 350 | 0.1783 |
| 0.1338 | 0.3548 | 400 | 0.1555 |
| 0.1133 | 0.3991 | 450 | 0.1427 |
| 0.104 | 0.4435 | 500 | 0.1435 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1