End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: deepseek-ai/deepseek-coder-1.3b-base
|
| 7 |
+
model-index:
|
| 8 |
+
- name: peft-deepseek-code-lora
|
| 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
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.7771
|
| 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: 12
|
| 40 |
+
- eval_batch_size: 12
|
| 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: 3000
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 51 |
+
| 0.869 | 0.0333 | 100 | 0.8371 |
|
| 52 |
+
| 0.8608 | 0.0667 | 200 | 0.7918 |
|
| 53 |
+
| 0.7746 | 0.1 | 300 | 0.7638 |
|
| 54 |
+
| 0.7381 | 0.1333 | 400 | 0.7487 |
|
| 55 |
+
| 0.7078 | 0.1667 | 500 | 0.7371 |
|
| 56 |
+
| 0.7066 | 0.2 | 600 | 0.7261 |
|
| 57 |
+
| 0.6709 | 0.2333 | 700 | 0.7235 |
|
| 58 |
+
| 0.6487 | 0.2667 | 800 | 0.7191 |
|
| 59 |
+
| 0.6103 | 0.3 | 900 | 0.7196 |
|
| 60 |
+
| 0.6109 | 0.3333 | 1000 | 0.7197 |
|
| 61 |
+
| 0.5804 | 0.3667 | 1100 | 0.7112 |
|
| 62 |
+
| 0.563 | 0.4 | 1200 | 0.7162 |
|
| 63 |
+
| 0.5406 | 0.4333 | 1300 | 0.7157 |
|
| 64 |
+
| 0.5286 | 0.4667 | 1400 | 0.7256 |
|
| 65 |
+
| 0.4839 | 0.5 | 1500 | 0.7208 |
|
| 66 |
+
| 0.5268 | 0.5333 | 1600 | 0.7258 |
|
| 67 |
+
| 0.4565 | 0.5667 | 1700 | 0.7280 |
|
| 68 |
+
| 0.4366 | 0.6 | 1800 | 0.7298 |
|
| 69 |
+
| 0.4729 | 0.6333 | 1900 | 0.7393 |
|
| 70 |
+
| 0.4451 | 0.6667 | 2000 | 0.7463 |
|
| 71 |
+
| 0.4008 | 0.7 | 2100 | 0.7533 |
|
| 72 |
+
| 0.3915 | 0.7333 | 2200 | 0.7609 |
|
| 73 |
+
| 0.3769 | 0.7667 | 2300 | 0.7601 |
|
| 74 |
+
| 0.3776 | 0.8 | 2400 | 0.7671 |
|
| 75 |
+
| 0.3896 | 0.8333 | 2500 | 0.7694 |
|
| 76 |
+
| 0.3798 | 0.8667 | 2600 | 0.7727 |
|
| 77 |
+
| 0.3683 | 0.9 | 2700 | 0.7756 |
|
| 78 |
+
| 0.36 | 0.9333 | 2800 | 0.7774 |
|
| 79 |
+
| 0.3713 | 0.9667 | 2900 | 0.7769 |
|
| 80 |
+
| 0.352 | 1.0 | 3000 | 0.7771 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- PEFT 0.11.1
|
| 86 |
+
- Transformers 4.41.2
|
| 87 |
+
- Pytorch 2.3.0+cu121
|
| 88 |
+
- Datasets 2.14.6
|
| 89 |
+
- Tokenizers 0.19.1
|