|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
base_model: Qwen/Qwen2-7B |
|
model-index: |
|
- name: qwen2_Magiccoder_evol_10k_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_Magiccoder_evol_10k_reverse |
|
|
|
This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8272 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 32 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 0.02 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.8303 | 0.0261 | 4 | 0.8571 | |
|
| 0.8267 | 0.0522 | 8 | 0.8449 | |
|
| 0.8201 | 0.0784 | 12 | 0.8389 | |
|
| 0.8002 | 0.1045 | 16 | 0.8436 | |
|
| 0.8491 | 0.1306 | 20 | 0.8414 | |
|
| 0.7448 | 0.1567 | 24 | 0.8434 | |
|
| 0.7606 | 0.1828 | 28 | 0.8459 | |
|
| 0.9214 | 0.2089 | 32 | 0.8474 | |
|
| 0.8071 | 0.2351 | 36 | 0.8466 | |
|
| 0.8353 | 0.2612 | 40 | 0.8479 | |
|
| 0.8762 | 0.2873 | 44 | 0.8473 | |
|
| 0.8544 | 0.3134 | 48 | 0.8475 | |
|
| 0.7855 | 0.3395 | 52 | 0.8482 | |
|
| 0.7725 | 0.3656 | 56 | 0.8467 | |
|
| 0.8044 | 0.3918 | 60 | 0.8470 | |
|
| 0.8282 | 0.4179 | 64 | 0.8446 | |
|
| 0.853 | 0.4440 | 68 | 0.8449 | |
|
| 0.8047 | 0.4701 | 72 | 0.8439 | |
|
| 0.8145 | 0.4962 | 76 | 0.8431 | |
|
| 0.8063 | 0.5223 | 80 | 0.8411 | |
|
| 0.8782 | 0.5485 | 84 | 0.8395 | |
|
| 0.7944 | 0.5746 | 88 | 0.8395 | |
|
| 0.8728 | 0.6007 | 92 | 0.8370 | |
|
| 0.7882 | 0.6268 | 96 | 0.8363 | |
|
| 0.8999 | 0.6529 | 100 | 0.8354 | |
|
| 0.7857 | 0.6790 | 104 | 0.8341 | |
|
| 0.8258 | 0.7052 | 108 | 0.8331 | |
|
| 0.7877 | 0.7313 | 112 | 0.8317 | |
|
| 0.7686 | 0.7574 | 116 | 0.8305 | |
|
| 0.7422 | 0.7835 | 120 | 0.8299 | |
|
| 0.8229 | 0.8096 | 124 | 0.8292 | |
|
| 0.7577 | 0.8357 | 128 | 0.8285 | |
|
| 0.8811 | 0.8619 | 132 | 0.8278 | |
|
| 0.8243 | 0.8880 | 136 | 0.8277 | |
|
| 0.8243 | 0.9141 | 140 | 0.8275 | |
|
| 0.8096 | 0.9402 | 144 | 0.8275 | |
|
| 0.8476 | 0.9663 | 148 | 0.8274 | |
|
| 0.8154 | 0.9925 | 152 | 0.8272 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |