Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,84 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: peft
|
| 3 |
-
license: apache-2.0
|
| 4 |
-
base_model: Qwen/Qwen3.6-27B
|
| 5 |
-
tags:
|
| 6 |
-
- base_model:adapter:Qwen/Qwen3.6-27B
|
| 7 |
-
- lora
|
| 8 |
-
- transformers
|
| 9 |
-
pipeline_tag: text-generation
|
| 10 |
-
model-index:
|
| 11 |
-
- name: qwen36-27b-cyber-v2
|
| 12 |
-
results: []
|
| 13 |
-
---
|
| 14 |
-
|
| 15 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
-
|
| 18 |
-
# qwen36-27b-cyber-v2
|
| 19 |
-
|
| 20 |
-
This model is a fine-tuned version of [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) on an unknown dataset.
|
| 21 |
-
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.6560
|
| 23 |
-
|
| 24 |
-
## Model description
|
| 25 |
-
|
| 26 |
-
More information needed
|
| 27 |
-
|
| 28 |
-
## Intended uses & limitations
|
| 29 |
-
|
| 30 |
-
More information needed
|
| 31 |
-
|
| 32 |
-
## Training and evaluation data
|
| 33 |
-
|
| 34 |
-
More information needed
|
| 35 |
-
|
| 36 |
-
## Training procedure
|
| 37 |
-
|
| 38 |
-
### Training hyperparameters
|
| 39 |
-
|
| 40 |
-
The following hyperparameters were used during training:
|
| 41 |
-
- learning_rate: 5e-05
|
| 42 |
-
- train_batch_size: 1
|
| 43 |
-
- eval_batch_size: 1
|
| 44 |
-
- seed: 42
|
| 45 |
-
- gradient_accumulation_steps: 16
|
| 46 |
-
- total_train_batch_size: 16
|
| 47 |
-
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
-
- lr_scheduler_type: cosine
|
| 49 |
-
- lr_scheduler_warmup_steps: 57
|
| 50 |
-
- num_epochs: 2.0
|
| 51 |
-
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
-
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
-
| 1.0844 | 0.1040 | 100 | 1.0904 |
|
| 57 |
-
| 1.0237 | 0.2080 | 200 | 1.0211 |
|
| 58 |
-
| 0.9783 | 0.3121 | 300 | 1.0151 |
|
| 59 |
-
| 0.9684 | 0.4161 | 400 | 0.9857 |
|
| 60 |
-
| 0.9207 | 0.5201 | 500 | 0.9551 |
|
| 61 |
-
| 0.9207 | 0.6241 | 600 | 0.9301 |
|
| 62 |
-
| 1.0160 | 0.7281 | 700 | 1.0173 |
|
| 63 |
-
| 0.9393 | 0.8321 | 800 | 0.9664 |
|
| 64 |
-
| 0.9089 | 0.9362 | 900 | 0.9006 |
|
| 65 |
-
| 0.6763 | 1.0395 | 1000 | 0.8659 |
|
| 66 |
-
| 0.6022 | 1.1435 | 1100 | 0.8314 |
|
| 67 |
-
| 0.5831 | 1.2476 | 1200 | 0.7889 |
|
| 68 |
-
| 0.5711 | 1.3516 | 1300 | 0.7517 |
|
| 69 |
-
| 0.5579 | 1.4556 | 1400 | 0.7210 |
|
| 70 |
-
| 0.5409 | 1.5596 | 1500 | 0.6939 |
|
| 71 |
-
| 0.5155 | 1.6636 | 1600 | 0.6775 |
|
| 72 |
-
| 0.4945 | 1.7677 | 1700 | 0.6653 |
|
| 73 |
-
| 0.5007 | 1.8717 | 1800 | 0.6576 |
|
| 74 |
-
| 0.5011 | 1.9757 | 1900 | 0.6560 |
|
| 75 |
-
| 0.5017 | 2.0 | 1924 | 0.6560 |
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
### Framework versions
|
| 79 |
-
|
| 80 |
-
- PEFT 0.20.0
|
| 81 |
-
- Transformers 5.14.1
|
| 82 |
-
- Pytorch 2.11.0+cu130
|
| 83 |
-
- Datasets 5.0.1
|
| 84 |
-
- Tokenizers 0.22.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|