Commit
•
5106b47
1
Parent(s):
1609809
azma-deepseek-coder-1.3b-instruct-structured-output
Browse files- README.md +85 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: deepseek-ai/deepseek-coder-1.3b-instruct
|
| 9 |
+
model-index:
|
| 10 |
+
- name: results
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# results
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.1804
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2.5e-05
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 49 |
+
- lr_scheduler_warmup_steps: 50
|
| 50 |
+
- training_steps: 500
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 1.8004 | 0.01 | 25 | 1.8163 |
|
| 58 |
+
| 1.8977 | 0.01 | 50 | 1.6053 |
|
| 59 |
+
| 1.5414 | 0.02 | 75 | 1.4712 |
|
| 60 |
+
| 0.9012 | 0.02 | 100 | 1.3793 |
|
| 61 |
+
| 1.2741 | 0.03 | 125 | 1.3288 |
|
| 62 |
+
| 0.7702 | 0.04 | 150 | 1.2922 |
|
| 63 |
+
| 1.3633 | 0.04 | 175 | 1.2580 |
|
| 64 |
+
| 0.5385 | 0.05 | 200 | 1.2341 |
|
| 65 |
+
| 1.3172 | 0.06 | 225 | 1.2157 |
|
| 66 |
+
| 0.5901 | 0.06 | 250 | 1.2088 |
|
| 67 |
+
| 1.2612 | 0.07 | 275 | 1.1989 |
|
| 68 |
+
| 0.6468 | 0.07 | 300 | 1.1937 |
|
| 69 |
+
| 1.2991 | 0.08 | 325 | 1.1891 |
|
| 70 |
+
| 0.5557 | 0.09 | 350 | 1.1858 |
|
| 71 |
+
| 1.148 | 0.09 | 375 | 1.1838 |
|
| 72 |
+
| 0.634 | 0.1 | 400 | 1.1823 |
|
| 73 |
+
| 1.2453 | 0.1 | 425 | 1.1812 |
|
| 74 |
+
| 0.5921 | 0.11 | 450 | 1.1807 |
|
| 75 |
+
| 1.0155 | 0.12 | 475 | 1.1805 |
|
| 76 |
+
| 0.6354 | 0.12 | 500 | 1.1804 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- PEFT 0.7.2.dev0
|
| 82 |
+
- Transformers 4.37.0.dev0
|
| 83 |
+
- Pytorch 2.1.0+cu121
|
| 84 |
+
- Datasets 2.16.1
|
| 85 |
+
- Tokenizers 0.15.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 429430864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88e5764d90e20618299f452cc6f2d610a6c51bbdc9d945069f99861ad76e7433
|
| 3 |
size 429430864
|