|
--- |
|
base_model: unsloth/qwen2-7b-bnb-4bit |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Qwen2-7B_magiccoder_default |
|
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. --> |
|
|
|
# Qwen2-7B_magiccoder_default |
|
|
|
This model is a fine-tuned version of [unsloth/qwen2-7b-bnb-4bit](https://huggingface.co./unsloth/qwen2-7b-bnb-4bit) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8796 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.02 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.9592 | 0.0261 | 4 | 1.0014 | |
|
| 0.9246 | 0.0522 | 8 | 0.9342 | |
|
| 0.9101 | 0.0783 | 12 | 0.9148 | |
|
| 0.8605 | 0.1044 | 16 | 0.9008 | |
|
| 0.9093 | 0.1305 | 20 | 0.8958 | |
|
| 0.7967 | 0.1566 | 24 | 0.8949 | |
|
| 0.8075 | 0.1827 | 28 | 0.8941 | |
|
| 0.9522 | 0.2088 | 32 | 0.8917 | |
|
| 0.8503 | 0.2349 | 36 | 0.8890 | |
|
| 0.8704 | 0.2610 | 40 | 0.8864 | |
|
| 0.9286 | 0.2871 | 44 | 0.8852 | |
|
| 0.894 | 0.3132 | 48 | 0.8839 | |
|
| 0.8171 | 0.3393 | 52 | 0.8835 | |
|
| 0.8224 | 0.3654 | 56 | 0.8828 | |
|
| 0.8392 | 0.3915 | 60 | 0.8822 | |
|
| 0.897 | 0.4176 | 64 | 0.8817 | |
|
| 0.8942 | 0.4437 | 68 | 0.8813 | |
|
| 0.8501 | 0.4698 | 72 | 0.8809 | |
|
| 0.8768 | 0.4959 | 76 | 0.8807 | |
|
| 0.8337 | 0.5220 | 80 | 0.8806 | |
|
| 0.9285 | 0.5481 | 84 | 0.8801 | |
|
| 0.8301 | 0.5742 | 88 | 0.8803 | |
|
| 0.9212 | 0.6003 | 92 | 0.8805 | |
|
| 0.8485 | 0.6264 | 96 | 0.8804 | |
|
| 0.9419 | 0.6525 | 100 | 0.8801 | |
|
| 0.8191 | 0.6786 | 104 | 0.8799 | |
|
| 0.8668 | 0.7047 | 108 | 0.8799 | |
|
| 0.8335 | 0.7308 | 112 | 0.8798 | |
|
| 0.8003 | 0.7569 | 116 | 0.8797 | |
|
| 0.794 | 0.7830 | 120 | 0.8796 | |
|
| 0.863 | 0.8091 | 124 | 0.8797 | |
|
| 0.8262 | 0.8352 | 128 | 0.8795 | |
|
| 0.9269 | 0.8613 | 132 | 0.8796 | |
|
| 0.876 | 0.8874 | 136 | 0.8795 | |
|
| 0.8955 | 0.9135 | 140 | 0.8794 | |
|
| 0.8481 | 0.9396 | 144 | 0.8796 | |
|
| 0.9111 | 0.9657 | 148 | 0.8795 | |
|
| 0.8653 | 0.9918 | 152 | 0.8796 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
