|
--- |
|
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: 1.0907 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.9111 | 0.0261 | 4 | 0.9716 | |
|
| 1.0695 | 0.0522 | 8 | 1.1827 | |
|
| 1.1409 | 0.0783 | 12 | 1.1378 | |
|
| 1.1017 | 0.1044 | 16 | 1.1270 | |
|
| 1.1579 | 0.1305 | 20 | 1.1441 | |
|
| 1.0234 | 0.1566 | 24 | 1.1212 | |
|
| 1.0225 | 0.1827 | 28 | 1.1567 | |
|
| 1.1587 | 0.2088 | 32 | 1.1425 | |
|
| 1.0519 | 0.2349 | 36 | 1.1214 | |
|
| 1.1006 | 0.2610 | 40 | 1.1195 | |
|
| 1.1443 | 0.2871 | 44 | 1.1159 | |
|
| 1.1088 | 0.3132 | 48 | 1.1123 | |
|
| 1.0303 | 0.3393 | 52 | 1.1125 | |
|
| 1.0499 | 0.3654 | 56 | 1.1232 | |
|
| 1.082 | 0.3915 | 60 | 1.1239 | |
|
| 1.1319 | 0.4176 | 64 | 1.1299 | |
|
| 1.1228 | 0.4437 | 68 | 1.1170 | |
|
| 1.0796 | 0.4698 | 72 | 1.1129 | |
|
| 1.0974 | 0.4959 | 76 | 1.1162 | |
|
| 1.0566 | 0.5220 | 80 | 1.1066 | |
|
| 1.1243 | 0.5481 | 84 | 1.1036 | |
|
| 1.0449 | 0.5742 | 88 | 1.1075 | |
|
| 1.1215 | 0.6003 | 92 | 1.1022 | |
|
| 1.0506 | 0.6264 | 96 | 1.0941 | |
|
| 1.1367 | 0.6525 | 100 | 1.0924 | |
|
| 1.03 | 0.6786 | 104 | 1.1014 | |
|
| 1.0844 | 0.7047 | 108 | 1.1160 | |
|
| 1.0575 | 0.7308 | 112 | 1.1058 | |
|
| 1.0169 | 0.7569 | 116 | 1.1061 | |
|
| 1.002 | 0.7830 | 120 | 1.1091 | |
|
| 1.0741 | 0.8091 | 124 | 1.1094 | |
|
| 1.0651 | 0.8352 | 128 | 1.1032 | |
|
| 1.1222 | 0.8613 | 132 | 1.0976 | |
|
| 1.0595 | 0.8874 | 136 | 1.0952 | |
|
| 1.0879 | 0.9135 | 140 | 1.0931 | |
|
| 1.0433 | 0.9396 | 144 | 1.0917 | |
|
| 1.1012 | 0.9657 | 148 | 1.0908 | |
|
| 1.0587 | 0.9918 | 152 | 1.0907 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
