Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
saiga_double_lora
This model is a fine-tuned version of TheBloke/Llama-2-7B-fp16 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0512
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: 2e-06
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1113 | 1.43 | 10 | 2.0512 |
| 2.1068 | 2.86 | 20 | 2.0512 |
Framework versions
- PEFT 0.10.0
- Transformers 4.36.2
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for marcus2000/saiga_double_lora
Base model
TheBloke/Llama-2-7B-fp16
Adapter
this model