metadata
library_name: peft
license: llama3
base_model: Eurdem/Defne_llama3_2x8B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: c9503349-1e52-4cf6-9d18-e19e2b1ba638
results: []
c9503349-1e52-4cf6-9d18-e19e2b1ba638
This model is a fine-tuned version of Eurdem/Defne_llama3_2x8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1945
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: 0.000206
- 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 | 0.0002 | 1 | 1.4330 |
| 1.2281 | 0.0085 | 50 | 1.2456 |
| 1.3016 | 0.0170 | 100 | 1.3395 |
| 1.1985 | 0.0255 | 150 | 1.2455 |
| 1.2808 | 0.0340 | 200 | 1.3786 |
| 1.2372 | 0.0424 | 250 | 1.2279 |
| 1.285 | 0.0509 | 300 | 1.2770 |
| 1.1768 | 0.0594 | 350 | 1.2068 |
| 1.2147 | 0.0679 | 400 | 1.2110 |
| 1.2383 | 0.0764 | 450 | 1.1963 |
| 1.2776 | 0.0849 | 500 | 1.1945 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1