|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- llama-factory |
|
- lora |
|
- generated_from_trainer |
|
base_model: /data1/model/llama2/meta-llama/Llama2-13b |
|
model-index: |
|
- name: fuze_28_balance_no_sys |
|
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. --> |
|
|
|
# fuze_28_balance_no_sys |
|
|
|
This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the fuze_28_balance_no_sys dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6174 |
|
|
|
## 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-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 20 |
|
- num_epochs: 2.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 0.9806 | 0.4355 | 3000 | 0.6490 | |
|
| 0.753 | 0.8711 | 6000 | 0.6240 | |
|
| 0.5062 | 1.3066 | 9000 | 0.6196 | |
|
| 0.7913 | 1.7422 | 12000 | 0.6174 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.0 |
|
- Pytorch 2.2.1 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.19.1 |
