|
--- |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: TheBloke/Llama-2-7B-fp16 |
|
model-index: |
|
- name: Saiga_timelist_task30steps |
|
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_timelist_task30steps |
|
|
|
This model is a fine-tuned version of [TheBloke/Llama-2-7B-fp16](https://huggingface.co/TheBloke/Llama-2-7B-fp16) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7980 |
|
|
|
## 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: 5e-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: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.5376 | 0.05 | 2 | 1.7979 | |
|
| 1.6041 | 0.1 | 4 | 1.7978 | |
|
| 1.6858 | 0.15 | 6 | 1.7979 | |
|
| 1.7722 | 0.21 | 8 | 1.7979 | |
|
| 1.6524 | 0.26 | 10 | 1.7979 | |
|
| 1.6374 | 0.31 | 12 | 1.7979 | |
|
| 1.7269 | 0.36 | 14 | 1.7979 | |
|
| 1.7028 | 0.41 | 16 | 1.7978 | |
|
| 1.6422 | 0.46 | 18 | 1.7980 | |
|
| 1.666 | 0.52 | 20 | 1.7979 | |
|
| 1.5679 | 0.57 | 22 | 1.7977 | |
|
| 1.7614 | 0.62 | 24 | 1.7978 | |
|
| 1.7053 | 0.67 | 26 | 1.7978 | |
|
| 1.7438 | 0.72 | 28 | 1.7981 | |
|
| 1.8348 | 0.77 | 30 | 1.7980 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.2+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
