|
--- |
|
base_model: unsloth/Qwen2-7B |
|
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](https://huggingface.co./unsloth/Qwen2-7B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9869 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.8213 | 0.0261 | 4 | 0.9216 | |
|
| 0.9106 | 0.0522 | 8 | 0.9644 | |
|
| 0.9506 | 0.0783 | 12 | 0.9631 | |
|
| 0.9339 | 0.1044 | 16 | 0.9845 | |
|
| 1.0039 | 0.1305 | 20 | 0.9997 | |
|
| 0.9095 | 0.1566 | 24 | 1.0116 | |
|
| 0.9241 | 0.1827 | 28 | 1.0198 | |
|
| 1.0582 | 0.2088 | 32 | 1.0291 | |
|
| 0.9677 | 0.2349 | 36 | 1.0307 | |
|
| 1.0044 | 0.2610 | 40 | 1.0355 | |
|
| 1.0672 | 0.2871 | 44 | 1.0388 | |
|
| 1.0368 | 0.3132 | 48 | 1.0402 | |
|
| 0.9603 | 0.3393 | 52 | 1.0420 | |
|
| 0.9709 | 0.3654 | 56 | 1.0398 | |
|
| 1.0019 | 0.3915 | 60 | 1.0403 | |
|
| 1.0537 | 0.4176 | 64 | 1.0384 | |
|
| 1.0365 | 0.4437 | 68 | 1.0345 | |
|
| 1.0 | 0.4698 | 72 | 1.0332 | |
|
| 1.0165 | 0.4959 | 76 | 1.0306 | |
|
| 0.9778 | 0.5220 | 80 | 1.0271 | |
|
| 1.0497 | 0.5481 | 84 | 1.0229 | |
|
| 0.9652 | 0.5742 | 88 | 1.0203 | |
|
| 1.0435 | 0.6003 | 92 | 1.0185 | |
|
| 0.9769 | 0.6264 | 96 | 1.0141 | |
|
| 1.0648 | 0.6525 | 100 | 1.0104 | |
|
| 0.9463 | 0.6786 | 104 | 1.0079 | |
|
| 0.9835 | 0.7047 | 108 | 1.0049 | |
|
| 0.9584 | 0.7308 | 112 | 1.0010 | |
|
| 0.9185 | 0.7569 | 116 | 0.9973 | |
|
| 0.9021 | 0.7830 | 120 | 0.9950 | |
|
| 0.9684 | 0.8091 | 124 | 0.9930 | |
|
| 0.9461 | 0.8352 | 128 | 0.9913 | |
|
| 1.0232 | 0.8613 | 132 | 0.9895 | |
|
| 0.9646 | 0.8874 | 136 | 0.9885 | |
|
| 0.9912 | 0.9135 | 140 | 0.9874 | |
|
| 0.9464 | 0.9396 | 144 | 0.9870 | |
|
| 1.0104 | 0.9657 | 148 | 0.9868 | |
|
| 0.9624 | 0.9918 | 152 | 0.9869 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
