Commit
•
69691cd
1
Parent(s):
c80e7cb
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-base
|
| 7 |
+
model-index:
|
| 8 |
+
- name: peft-deepseek-code-lora-7b
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# peft-deepseek-code-lora-7b
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.7491
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0005
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
+
- lr_scheduler_warmup_steps: 45
|
| 45 |
+
- training_steps: 4000
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 0.801 | 0.025 | 100 | 0.7577 |
|
| 52 |
+
| 0.7385 | 0.05 | 200 | 0.7172 |
|
| 53 |
+
| 0.7535 | 0.075 | 300 | 0.6915 |
|
| 54 |
+
| 0.6987 | 0.1 | 400 | 0.6718 |
|
| 55 |
+
| 0.6345 | 0.125 | 500 | 0.6596 |
|
| 56 |
+
| 0.623 | 0.15 | 600 | 0.6515 |
|
| 57 |
+
| 0.6228 | 0.175 | 700 | 0.6413 |
|
| 58 |
+
| 0.5966 | 0.2 | 800 | 0.6362 |
|
| 59 |
+
| 0.5503 | 0.225 | 900 | 0.6403 |
|
| 60 |
+
| 0.504 | 0.25 | 1000 | 0.6274 |
|
| 61 |
+
| 0.4782 | 0.275 | 1100 | 0.6270 |
|
| 62 |
+
| 0.5021 | 0.3 | 1200 | 0.6272 |
|
| 63 |
+
| 0.4737 | 0.325 | 1300 | 0.6190 |
|
| 64 |
+
| 0.4343 | 0.35 | 1400 | 0.6233 |
|
| 65 |
+
| 0.458 | 0.375 | 1500 | 0.6247 |
|
| 66 |
+
| 0.4316 | 0.4 | 1600 | 0.6302 |
|
| 67 |
+
| 0.4161 | 0.425 | 1700 | 0.6337 |
|
| 68 |
+
| 0.3798 | 0.45 | 1800 | 0.6307 |
|
| 69 |
+
| 0.3731 | 0.475 | 1900 | 0.6382 |
|
| 70 |
+
| 0.3339 | 0.5 | 2000 | 0.6468 |
|
| 71 |
+
| 0.3279 | 0.525 | 2100 | 0.6529 |
|
| 72 |
+
| 0.3042 | 0.55 | 2200 | 0.6484 |
|
| 73 |
+
| 0.2738 | 0.575 | 2300 | 0.6612 |
|
| 74 |
+
| 0.3121 | 0.6 | 2400 | 0.6684 |
|
| 75 |
+
| 0.2735 | 0.625 | 2500 | 0.6795 |
|
| 76 |
+
| 0.2595 | 0.65 | 2600 | 0.6802 |
|
| 77 |
+
| 0.2291 | 0.675 | 2700 | 0.6856 |
|
| 78 |
+
| 0.2239 | 0.7 | 2800 | 0.6964 |
|
| 79 |
+
| 0.2242 | 0.725 | 2900 | 0.7081 |
|
| 80 |
+
| 0.2357 | 0.75 | 3000 | 0.7200 |
|
| 81 |
+
| 0.2058 | 0.775 | 3100 | 0.7166 |
|
| 82 |
+
| 0.1881 | 0.8 | 3200 | 0.7303 |
|
| 83 |
+
| 0.1859 | 0.825 | 3300 | 0.7299 |
|
| 84 |
+
| 0.193 | 0.85 | 3400 | 0.7375 |
|
| 85 |
+
| 0.2061 | 0.875 | 3500 | 0.7392 |
|
| 86 |
+
| 0.1719 | 0.9 | 3600 | 0.7461 |
|
| 87 |
+
| 0.1908 | 0.925 | 3700 | 0.7464 |
|
| 88 |
+
| 0.1756 | 0.95 | 3800 | 0.7480 |
|
| 89 |
+
| 0.1863 | 0.975 | 3900 | 0.7489 |
|
| 90 |
+
| 0.1619 | 1.0 | 4000 | 0.7491 |
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
### Framework versions
|
| 94 |
+
|
| 95 |
+
- PEFT 0.11.1
|
| 96 |
+
- Transformers 4.41.2
|
| 97 |
+
- Pytorch 2.3.0+cu121
|
| 98 |
+
- Datasets 2.14.6
|
| 99 |
+
- Tokenizers 0.19.1
|