sft
This model is a fine-tuned version of IlyaGusev/saiga_mistral_7b_merged on the gazeta dataset.
Model description
This model was trained on IlyaGusev/gazeta dataset for summarization on Russian language. Context window size is 2048.
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2.0
- mixed_precision_training: Native AMP
Training results
Framework versions
- PEFT 0.10.0
- Transformers 4.39.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 12
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The HF Inference API does not support text2text-generation models for peft library.
Model tree for SouthMemphis/Saiga-lora-2048-2epochs
Base model
IlyaGusev/saiga_mistral_7b_merged