|
--- |
|
base_model: unsloth/Qwen2-7B |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Qwen2-7B_magiccoder_ortho |
|
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_ortho |
|
|
|
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: 0.9916 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.8262 | 0.0261 | 4 | 1.0884 | |
|
| 0.9776 | 0.0522 | 8 | 0.9663 | |
|
| 0.9345 | 0.0783 | 12 | 0.9389 | |
|
| 0.9026 | 0.1044 | 16 | 0.9482 | |
|
| 0.9618 | 0.1305 | 20 | 0.9571 | |
|
| 0.8685 | 0.1566 | 24 | 0.9719 | |
|
| 0.8834 | 0.1827 | 28 | 0.9752 | |
|
| 1.0185 | 0.2088 | 32 | 0.9876 | |
|
| 0.9354 | 0.2349 | 36 | 0.9923 | |
|
| 0.9734 | 0.2610 | 40 | 0.9982 | |
|
| 1.034 | 0.2871 | 44 | 1.0035 | |
|
| 1.0067 | 0.3132 | 48 | 1.0048 | |
|
| 0.932 | 0.3393 | 52 | 1.0081 | |
|
| 0.9407 | 0.3654 | 56 | 1.0061 | |
|
| 0.9682 | 0.3915 | 60 | 1.0054 | |
|
| 1.0224 | 0.4176 | 64 | 1.0093 | |
|
| 1.0145 | 0.4437 | 68 | 1.0094 | |
|
| 0.9756 | 0.4698 | 72 | 1.0101 | |
|
| 0.9968 | 0.4959 | 76 | 1.0087 | |
|
| 0.9566 | 0.5220 | 80 | 1.0094 | |
|
| 1.0394 | 0.5481 | 84 | 1.0087 | |
|
| 0.9546 | 0.5742 | 88 | 1.0074 | |
|
| 1.0347 | 0.6003 | 92 | 1.0086 | |
|
| 0.9639 | 0.6264 | 96 | 1.0042 | |
|
| 1.0543 | 0.6525 | 100 | 1.0027 | |
|
| 0.9346 | 0.6786 | 104 | 1.0030 | |
|
| 0.9744 | 0.7047 | 108 | 1.0019 | |
|
| 0.9546 | 0.7308 | 112 | 0.9985 | |
|
| 0.9138 | 0.7569 | 116 | 0.9969 | |
|
| 0.9026 | 0.7830 | 120 | 0.9961 | |
|
| 0.9746 | 0.8091 | 124 | 0.9953 | |
|
| 0.9453 | 0.8352 | 128 | 0.9950 | |
|
| 1.0311 | 0.8613 | 132 | 0.9934 | |
|
| 0.971 | 0.8874 | 136 | 0.9927 | |
|
| 0.9957 | 0.9135 | 140 | 0.9919 | |
|
| 0.9502 | 0.9396 | 144 | 0.9917 | |
|
| 1.0133 | 0.9657 | 148 | 0.9915 | |
|
| 0.9684 | 0.9918 | 152 | 0.9916 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
