Hugging Face's logo

PopularPenguin
/
sparql-qwen

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
PopularPenguin commited on
Commit
0b94368
·
verified ·
1 Parent(s): c77c98b

End of training

Browse files
Files changed (4) hide show
  1. README.md +47 -44
  2. adapter_config.json +1 -1
  3. runs/Dec17_06-37-25_fdd2bd660959/events.out.tfevents.1734417458.fdd2bd660959.23.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,9 +1,11 @@
1
  ---
2
  library_name: peft
3
  license: apache-2.0
4
- base_model: Qwen/Qwen2.5-Coder-0.5B
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: sparql-qwen
9
  results: []
@@ -14,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # sparql-qwen
16
 
17
- This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-0.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.6232
20
 
21
  ## Model description
22
 
@@ -49,47 +51,48 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:------:|:-----:|:---------------:|
52
- | 0.7485 | 0.1048 | 500 | 0.8336 |
53
- | 0.7336 | 0.2096 | 1000 | 0.7696 |
54
- | 0.6787 | 0.3143 | 1500 | 0.7376 |
55
- | 0.6756 | 0.4191 | 2000 | 0.7190 |
56
- | 0.6651 | 0.5239 | 2500 | 0.7038 |
57
- | 0.6835 | 0.6287 | 3000 | 0.6932 |
58
- | 0.6572 | 0.7334 | 3500 | 0.6810 |
59
- | 0.6664 | 0.8382 | 4000 | 0.6773 |
60
- | 0.6304 | 0.9430 | 4500 | 0.6675 |
61
- | 0.7408 | 1.0478 | 5000 | 0.6648 |
62
- | 0.7004 | 1.1526 | 5500 | 0.6616 |
63
- | 0.6466 | 1.2573 | 6000 | 0.6579 |
64
- | 0.6914 | 1.3621 | 6500 | 0.6543 |
65
- | 0.6885 | 1.4669 | 7000 | 0.6507 |
66
- | 0.6508 | 1.5717 | 7500 | 0.6478 |
67
- | 0.7039 | 1.6764 | 8000 | 0.6442 |
68
- | 0.665 | 1.7812 | 8500 | 0.6436 |
69
- | 0.6483 | 1.8860 | 9000 | 0.6405 |
70
- | 0.699 | 1.9908 | 9500 | 0.6373 |
71
- | 0.4961 | 2.0956 | 10000 | 0.6380 |
72
- | 0.5103 | 2.2003 | 10500 | 0.6367 |
73
- | 0.5443 | 2.3051 | 11000 | 0.6349 |
74
- | 0.4813 | 2.4099 | 11500 | 0.6340 |
75
- | 0.5555 | 2.5147 | 12000 | 0.6324 |
76
- | 0.5711 | 2.6194 | 12500 | 0.6313 |
77
- | 0.5088 | 2.7242 | 13000 | 0.6309 |
78
- | 0.492 | 2.8290 | 13500 | 0.6297 |
79
- | 0.4936 | 2.9338 | 14000 | 0.6267 |
80
- | 0.6411 | 3.0386 | 14500 | 0.6271 |
81
- | 0.6618 | 3.1433 | 15000 | 0.6267 |
82
- | 0.6212 | 3.2481 | 15500 | 0.6260 |
83
- | 0.6337 | 3.3529 | 16000 | 0.6253 |
84
- | 0.6412 | 3.4577 | 16500 | 0.6234 |
85
- | 0.6208 | 3.5624 | 17000 | 0.6232 |
86
- | 0.676 | 3.6672 | 17500 | 0.6226 |
87
- | 0.6465 | 3.7720 | 18000 | 0.6217 |
88
- | 0.6157 | 3.8768 | 18500 | 0.6210 |
89
- | 0.6622 | 3.9816 | 19000 | 0.6200 |
90
- | 0.4811 | 4.0863 | 19500 | 0.6219 |
91
- | 0.5264 | 4.1911 | 20000 | 0.6213 |
92
- | 0.4738 | 4.2959 | 20500 | 0.6232 |
 
93
 
94
 
95
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
  license: apache-2.0
4
+ base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
5
  tags:
6
  - generated_from_trainer
7
+ datasets:
8
+ - arrow
9
  model-index:
10
  - name: sparql-qwen
11
  results: []
 
16
 
17
  # sparql-qwen
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct) on the arrow dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5436
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:-----:|:---------------:|
54
+ | 0.7618 | 0.1048 | 500 | 0.7231 |
55
+ | 0.7397 | 0.2096 | 1000 | 0.6676 |
56
+ | 0.7213 | 0.3143 | 1500 | 0.6440 |
57
+ | 0.7047 | 0.4191 | 2000 | 0.6283 |
58
+ | 0.6905 | 0.5239 | 2500 | 0.6181 |
59
+ | 0.6822 | 0.6287 | 3000 | 0.6081 |
60
+ | 0.6651 | 0.7334 | 3500 | 0.6007 |
61
+ | 0.662 | 0.8382 | 4000 | 0.5938 |
62
+ | 0.6535 | 0.9430 | 4500 | 0.5889 |
63
+ | 0.562 | 1.0478 | 5000 | 0.5846 |
64
+ | 0.4974 | 1.1526 | 5500 | 0.5820 |
65
+ | 0.5317 | 1.2573 | 6000 | 0.5778 |
66
+ | 0.572 | 1.3621 | 6500 | 0.5743 |
67
+ | 0.5167 | 1.4669 | 7000 | 0.5718 |
68
+ | 0.5479 | 1.5717 | 7500 | 0.5692 |
69
+ | 0.5368 | 1.6764 | 8000 | 0.5659 |
70
+ | 0.5622 | 1.7812 | 8500 | 0.5643 |
71
+ | 0.5146 | 1.8860 | 9000 | 0.5621 |
72
+ | 0.509 | 1.9908 | 9500 | 0.5602 |
73
+ | 0.5536 | 2.0956 | 10000 | 0.5589 |
74
+ | 0.5035 | 2.2003 | 10500 | 0.5592 |
75
+ | 0.5399 | 2.3051 | 11000 | 0.5567 |
76
+ | 0.5247 | 2.4099 | 11500 | 0.5553 |
77
+ | 0.5365 | 2.5147 | 12000 | 0.5549 |
78
+ | 0.4425 | 2.6194 | 12500 | 0.5545 |
79
+ | 0.4761 | 2.7242 | 13000 | 0.5524 |
80
+ | 0.5368 | 2.8290 | 13500 | 0.5509 |
81
+ | 0.5214 | 2.9338 | 14000 | 0.5494 |
82
+ | 0.519 | 3.0386 | 14500 | 0.5496 |
83
+ | 0.5606 | 3.1433 | 15000 | 0.5492 |
84
+ | 0.5362 | 3.2481 | 15500 | 0.5476 |
85
+ | 0.5275 | 3.3529 | 16000 | 0.5476 |
86
+ | 0.5159 | 3.4577 | 16500 | 0.5464 |
87
+ | 0.5171 | 3.5624 | 17000 | 0.5461 |
88
+ | 0.5242 | 3.6672 | 17500 | 0.5454 |
89
+ | 0.5053 | 3.7720 | 18000 | 0.5445 |
90
+ | 0.512 | 3.8768 | 18500 | 0.5441 |
91
+ | 0.5259 | 3.9816 | 19000 | 0.5428 |
92
+ | 0.4363 | 4.0863 | 19500 | 0.5437 |
93
+ | 0.4784 | 4.1911 | 20000 | 0.5440 |
94
+ | 0.4703 | 4.2959 | 20500 | 0.5448 |
95
+ | 0.4467 | 4.4007 | 21000 | 0.5436 |
96
 
97
 
98
  ### Framework versions
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "Qwen/Qwen2.5-Coder-0.5B",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
runs/Dec17_06-37-25_fdd2bd660959/events.out.tfevents.1734417458.fdd2bd660959.23.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b51906d0da70ffc4b96f2986abbf09745bd197ac2c95860278f28323f025ba
3
+ size 462297
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a37a5128de6898677143bf9e10edaa1a8bbe7dc250bf5520cc96066c9b533acf
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9a0b99a1f43e05c0500e845cd2edbedfdff8bb05f738e94e6ff8156d9807e1
3
  size 5240