|
--- |
|
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_reverse |
|
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_reverse |
|
|
|
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: 1.0421 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.9108 | 0.0261 | 4 | 0.9707 | |
|
| 0.9882 | 0.0522 | 8 | 1.0348 | |
|
| 1.0325 | 0.0783 | 12 | 1.0383 | |
|
| 1.0044 | 0.1044 | 16 | 1.0488 | |
|
| 1.0614 | 0.1305 | 20 | 1.0597 | |
|
| 0.9711 | 0.1566 | 24 | 1.0676 | |
|
| 0.979 | 0.1827 | 28 | 1.0751 | |
|
| 1.1009 | 0.2088 | 32 | 1.0812 | |
|
| 1.014 | 0.2349 | 36 | 1.0818 | |
|
| 1.057 | 0.2610 | 40 | 1.0841 | |
|
| 1.1137 | 0.2871 | 44 | 1.0848 | |
|
| 1.0856 | 0.3132 | 48 | 1.0879 | |
|
| 1.0044 | 0.3393 | 52 | 1.0875 | |
|
| 1.0199 | 0.3654 | 56 | 1.0862 | |
|
| 1.0503 | 0.3915 | 60 | 1.0861 | |
|
| 1.0973 | 0.4176 | 64 | 1.0831 | |
|
| 1.0846 | 0.4437 | 68 | 1.0824 | |
|
| 1.051 | 0.4698 | 72 | 1.0805 | |
|
| 1.0629 | 0.4959 | 76 | 1.0797 | |
|
| 1.0294 | 0.5220 | 80 | 1.0759 | |
|
| 1.0989 | 0.5481 | 84 | 1.0724 | |
|
| 1.0112 | 0.5742 | 88 | 1.0708 | |
|
| 1.0885 | 0.6003 | 92 | 1.0696 | |
|
| 1.0212 | 0.6264 | 96 | 1.0651 | |
|
| 1.1114 | 0.6525 | 100 | 1.0617 | |
|
| 0.994 | 0.6786 | 104 | 1.0602 | |
|
| 1.0346 | 0.7047 | 108 | 1.0566 | |
|
| 1.0053 | 0.7308 | 112 | 1.0539 | |
|
| 0.9673 | 0.7569 | 116 | 1.0506 | |
|
| 0.9526 | 0.7830 | 120 | 1.0489 | |
|
| 1.0196 | 0.8091 | 124 | 1.0475 | |
|
| 1.0054 | 0.8352 | 128 | 1.0456 | |
|
| 1.0743 | 0.8613 | 132 | 1.0439 | |
|
| 1.011 | 0.8874 | 136 | 1.0430 | |
|
| 1.0417 | 0.9135 | 140 | 1.0426 | |
|
| 0.9953 | 0.9396 | 144 | 1.0422 | |
|
| 1.0592 | 0.9657 | 148 | 1.0420 | |
|
| 1.019 | 0.9918 | 152 | 1.0421 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
