|
--- |
|
license: mit |
|
datasets: |
|
- radce/datasetGPT4o-mini |
|
- radce/YandexGPT |
|
- radce/ru_instruct_gpt4 |
|
- radce/communication_dataset |
|
- radce/shorts_dataset |
|
- radce/istruction_dataset |
|
language: |
|
- ru |
|
base_model: |
|
- radce/llama3.2-1B-Instruct-ru |
|
library_name: transformers |
|
--- |
|
Дообучались слои 14, 15, 16. |
|
|
|
Датасет состоял из 13 862 816 токенов. |
|
|
|
Видеокарта для дообучения: Tesla A100. |
|
|
|
Обучение |
|
``` |
|
{'loss': 0.8521, 'grad_norm': 0.5644629001617432, 'learning_rate': 2.9148375768217733e-05, 'epoch': 1.29} |
|
{'loss': 0.6742, 'grad_norm': 0.5370610952377319, 'learning_rate': 7.199297629499562e-06, 'epoch': 2.58} |
|
{'train_runtime': 5708.2175, 'train_samples_per_second': 22.869, 'train_steps_per_second': 0.204, 'train_loss': 0.7442483934749853, 'epoch': 3.0} |
|
``` |