Hugging Face's logo

Zacktree
/
code-bench-Mistral-7B-text-to-sql-v1

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Zacktree commited on
Commit
60e6951
·
verified ·
1 Parent(s): 6f36d62

Model save

Browse files
Files changed (2) hide show
  1. README.md +113 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: mistralai/Mistral-7B-v0.1
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ datasets:
10
+ - generator
11
+ model-index:
12
+ - name: code-bench-Mistral-7B-text-to-sql-v1
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # code-bench-Mistral-7B-text-to-sql-v1
20
+
21
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.4298
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.0002
43
+ - train_batch_size: 1
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 8
47
+ - total_train_batch_size: 8
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.03
51
+ - num_epochs: 3
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:----:|:---------------:|
57
+ | 0.8246 | 0.0619 | 10 | 0.7742 |
58
+ | 0.6351 | 0.1238 | 20 | 0.7373 |
59
+ | 0.573 | 0.1858 | 30 | 0.5941 |
60
+ | 0.5628 | 0.2477 | 40 | 0.5330 |
61
+ | 0.5169 | 0.3096 | 50 | 0.5149 |
62
+ | 0.5002 | 0.3715 | 60 | 0.4909 |
63
+ | 0.4825 | 0.4334 | 70 | 0.4721 |
64
+ | 0.466 | 0.4954 | 80 | 0.4628 |
65
+ | 0.4523 | 0.5573 | 90 | 0.4580 |
66
+ | 0.4536 | 0.6192 | 100 | 0.4474 |
67
+ | 0.4435 | 0.6811 | 110 | 0.4356 |
68
+ | 0.4399 | 0.7430 | 120 | 0.4318 |
69
+ | 0.4073 | 0.8050 | 130 | 0.4261 |
70
+ | 0.4372 | 0.8669 | 140 | 0.4198 |
71
+ | 0.4046 | 0.9288 | 150 | 0.4135 |
72
+ | 0.3836 | 0.9907 | 160 | 0.4131 |
73
+ | 0.2902 | 1.0526 | 170 | 0.4158 |
74
+ | 0.3228 | 1.1146 | 180 | 0.4141 |
75
+ | 0.3094 | 1.1765 | 190 | 0.4167 |
76
+ | 0.294 | 1.2384 | 200 | 0.4127 |
77
+ | 0.3081 | 1.3003 | 210 | 0.4047 |
78
+ | 0.285 | 1.3622 | 220 | 0.4034 |
79
+ | 0.2814 | 1.4241 | 230 | 0.4065 |
80
+ | 0.2649 | 1.4861 | 240 | 0.4016 |
81
+ | 0.2715 | 1.5480 | 250 | 0.3956 |
82
+ | 0.2715 | 1.6099 | 260 | 0.3967 |
83
+ | 0.2768 | 1.6718 | 270 | 0.3914 |
84
+ | 0.2618 | 1.7337 | 280 | 0.3905 |
85
+ | 0.2663 | 1.7957 | 290 | 0.3887 |
86
+ | 0.2639 | 1.8576 | 300 | 0.3844 |
87
+ | 0.2601 | 1.9195 | 310 | 0.3831 |
88
+ | 0.2625 | 1.9814 | 320 | 0.3808 |
89
+ | 0.1607 | 2.0433 | 330 | 0.4298 |
90
+ | 0.1505 | 2.1053 | 340 | 0.4149 |
91
+ | 0.1483 | 2.1672 | 350 | 0.4370 |
92
+ | 0.1597 | 2.2291 | 360 | 0.4287 |
93
+ | 0.1456 | 2.2910 | 370 | 0.4301 |
94
+ | 0.1567 | 2.3529 | 380 | 0.4304 |
95
+ | 0.1469 | 2.4149 | 390 | 0.4247 |
96
+ | 0.1539 | 2.4768 | 400 | 0.4291 |
97
+ | 0.1546 | 2.5387 | 410 | 0.4330 |
98
+ | 0.1434 | 2.6006 | 420 | 0.4297 |
99
+ | 0.1387 | 2.6625 | 430 | 0.4301 |
100
+ | 0.1491 | 2.7245 | 440 | 0.4302 |
101
+ | 0.1538 | 2.7864 | 450 | 0.4298 |
102
+ | 0.1445 | 2.8483 | 460 | 0.4299 |
103
+ | 0.1405 | 2.9102 | 470 | 0.4299 |
104
+ | 0.1392 | 2.9721 | 480 | 0.4298 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - PEFT 0.12.0
110
+ - Transformers 4.44.2
111
+ - Pytorch 2.5.1+cu121
112
+ - Datasets 2.21.0
113
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69e886dc2e72c077a484671dba346e50f6c5e4f3f8cacc94bcc2d89e0acb5c0a
3
  size 3208737208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2878061c882c63dc8d9a29608afbff8362cd17229b2d0c511be9c8788ea9b14
3
  size 3208737208