|
--- |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: TheBloke/Llama-2-7B-fp16 |
|
model-index: |
|
- name: saiga_task_double_lora350 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# saiga_task_double_lora350 |
|
|
|
This model is a fine-tuned version of [TheBloke/Llama-2-7B-fp16](https://huggingface.co/TheBloke/Llama-2-7B-fp16) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.6634 |
|
|
|
## 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: 0.0003 |
|
- 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: 350 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.5302 | 9.26 | 50 | 2.1777 | |
|
| 1.0061 | 18.52 | 100 | 2.4897 | |
|
| 0.5505 | 27.78 | 150 | 2.8614 | |
|
| 0.2832 | 37.04 | 200 | 3.2451 | |
|
| 0.1525 | 46.3 | 250 | 3.5339 | |
|
| 0.1026 | 55.56 | 300 | 3.6407 | |
|
| 0.0902 | 64.81 | 350 | 3.6634 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.2.2+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.15.2 |