Hugging Face's logo

imdatta0
/
Qwen2-7B_metamath_default

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
a5a55f1
•
1 Parent(s): ba59103

End of training

Browse files
Files changed (2) hide show
  1. README.md +50 -50
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: unsloth/qwen2-7b-bnb-4bit
3
  library_name: peft
4
  license: apache-2.0
5
  tags:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # Qwen2-7B_metamath_default
17
 
18
- This model is a fine-tuned version of [unsloth/qwen2-7b-bnb-4bit](https://huggingface.co/unsloth/qwen2-7b-bnb-4bit) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1552
21
 
22
  ## Model description
23
 
@@ -51,53 +51,53 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 0.2406 | 0.0211 | 13 | 0.1655 |
55
- | 0.1558 | 0.0421 | 26 | 0.1578 |
56
- | 0.1536 | 0.0632 | 39 | 0.1560 |
57
- | 0.1467 | 0.0842 | 52 | 0.1547 |
58
- | 0.1457 | 0.1053 | 65 | 0.1551 |
59
- | 0.15 | 0.1264 | 78 | 0.1552 |
60
- | 0.1547 | 0.1474 | 91 | 0.1548 |
61
- | 0.1494 | 0.1685 | 104 | 0.1559 |
62
- | 0.1543 | 0.1896 | 117 | 0.1563 |
63
- | 0.1511 | 0.2106 | 130 | 0.1563 |
64
- | 0.1545 | 0.2317 | 143 | 0.1567 |
65
- | 0.148 | 0.2527 | 156 | 0.1576 |
66
- | 0.1559 | 0.2738 | 169 | 0.1584 |
67
- | 0.1497 | 0.2949 | 182 | 0.1579 |
68
- | 0.1577 | 0.3159 | 195 | 0.1582 |
69
- | 0.1505 | 0.3370 | 208 | 0.1585 |
70
- | 0.152 | 0.3580 | 221 | 0.1583 |
71
- | 0.1498 | 0.3791 | 234 | 0.1586 |
72
- | 0.1522 | 0.4002 | 247 | 0.1581 |
73
- | 0.1536 | 0.4212 | 260 | 0.1574 |
74
- | 0.1614 | 0.4423 | 273 | 0.1583 |
75
- | 0.1555 | 0.4633 | 286 | 0.1580 |
76
- | 0.1605 | 0.4844 | 299 | 0.1573 |
77
- | 0.1497 | 0.5055 | 312 | 0.1580 |
78
- | 0.1477 | 0.5265 | 325 | 0.1579 |
79
- | 0.1497 | 0.5476 | 338 | 0.1570 |
80
- | 0.1539 | 0.5687 | 351 | 0.1573 |
81
- | 0.1573 | 0.5897 | 364 | 0.1576 |
82
- | 0.1535 | 0.6108 | 377 | 0.1570 |
83
- | 0.146 | 0.6318 | 390 | 0.1562 |
84
- | 0.1546 | 0.6529 | 403 | 0.1564 |
85
- | 0.1554 | 0.6740 | 416 | 0.1564 |
86
- | 0.1521 | 0.6950 | 429 | 0.1565 |
87
- | 0.1557 | 0.7161 | 442 | 0.1557 |
88
- | 0.1469 | 0.7371 | 455 | 0.1554 |
89
- | 0.1513 | 0.7582 | 468 | 0.1558 |
90
- | 0.153 | 0.7793 | 481 | 0.1557 |
91
- | 0.1518 | 0.8003 | 494 | 0.1555 |
92
- | 0.1482 | 0.8214 | 507 | 0.1554 |
93
- | 0.1514 | 0.8424 | 520 | 0.1554 |
94
- | 0.1533 | 0.8635 | 533 | 0.1553 |
95
- | 0.1521 | 0.8846 | 546 | 0.1554 |
96
- | 0.148 | 0.9056 | 559 | 0.1553 |
97
- | 0.1473 | 0.9267 | 572 | 0.1553 |
98
- | 0.1482 | 0.9478 | 585 | 0.1552 |
99
- | 0.1498 | 0.9688 | 598 | 0.1553 |
100
- | 0.155 | 0.9899 | 611 | 0.1552 |
101
 
102
 
103
  ### Framework versions
 
1
  ---
2
+ base_model: unsloth/Qwen2-7B
3
  library_name: peft
4
  license: apache-2.0
5
  tags:
 
15
 
16
  # Qwen2-7B_metamath_default
17
 
18
+ This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2149
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.1753 | 0.0211 | 13 | 0.1875 |
55
+ | 0.2034 | 0.0421 | 26 | 0.2488 |
56
+ | 0.2604 | 0.0632 | 39 | 0.2850 |
57
+ | 0.2823 | 0.0842 | 52 | 0.3067 |
58
+ | 0.2953 | 0.1053 | 65 | 0.3213 |
59
+ | 0.3151 | 0.1264 | 78 | 0.3321 |
60
+ | 0.3224 | 0.1474 | 91 | 0.3354 |
61
+ | 0.3144 | 0.1685 | 104 | 0.3366 |
62
+ | 0.3291 | 0.1896 | 117 | 0.3428 |
63
+ | 0.3233 | 0.2106 | 130 | 0.3447 |
64
+ | 0.3342 | 0.2317 | 143 | 0.3455 |
65
+ | 0.3292 | 0.2527 | 156 | 0.3393 |
66
+ | 0.3322 | 0.2738 | 169 | 0.3418 |
67
+ | 0.3225 | 0.2949 | 182 | 0.3334 |
68
+ | 0.3306 | 0.3159 | 195 | 0.3326 |
69
+ | 0.315 | 0.3370 | 208 | 0.3303 |
70
+ | 0.3135 | 0.3580 | 221 | 0.3307 |
71
+ | 0.3131 | 0.3791 | 234 | 0.3264 |
72
+ | 0.3114 | 0.4002 | 247 | 0.3211 |
73
+ | 0.3065 | 0.4212 | 260 | 0.3160 |
74
+ | 0.315 | 0.4423 | 273 | 0.3122 |
75
+ | 0.296 | 0.4633 | 286 | 0.3074 |
76
+ | 0.306 | 0.4844 | 299 | 0.2980 |
77
+ | 0.2821 | 0.5055 | 312 | 0.2968 |
78
+ | 0.2861 | 0.5265 | 325 | 0.2924 |
79
+ | 0.2717 | 0.5476 | 338 | 0.2850 |
80
+ | 0.2704 | 0.5687 | 351 | 0.2784 |
81
+ | 0.2693 | 0.5897 | 364 | 0.2716 |
82
+ | 0.2612 | 0.6108 | 377 | 0.2652 |
83
+ | 0.2512 | 0.6318 | 390 | 0.2601 |
84
+ | 0.2537 | 0.6529 | 403 | 0.2543 |
85
+ | 0.2543 | 0.6740 | 416 | 0.2498 |
86
+ | 0.2443 | 0.6950 | 429 | 0.2463 |
87
+ | 0.2441 | 0.7161 | 442 | 0.2407 |
88
+ | 0.2286 | 0.7371 | 455 | 0.2362 |
89
+ | 0.2298 | 0.7582 | 468 | 0.2327 |
90
+ | 0.2304 | 0.7793 | 481 | 0.2300 |
91
+ | 0.2266 | 0.8003 | 494 | 0.2270 |
92
+ | 0.2127 | 0.8214 | 507 | 0.2231 |
93
+ | 0.2193 | 0.8424 | 520 | 0.2205 |
94
+ | 0.2136 | 0.8635 | 533 | 0.2190 |
95
+ | 0.2099 | 0.8846 | 546 | 0.2176 |
96
+ | 0.2042 | 0.9056 | 559 | 0.2165 |
97
+ | 0.2077 | 0.9267 | 572 | 0.2158 |
98
+ | 0.2136 | 0.9478 | 585 | 0.2152 |
99
+ | 0.2131 | 0.9688 | 598 | 0.2150 |
100
+ | 0.2124 | 0.9899 | 611 | 0.2149 |
101
 
102
 
103
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1feb5fee24cbee2758ed49099b1b0df7df9d6994c57f1e8f592dc9091d642020
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c731889ad69f835f99aa6a71813f9b627b8f562c6ccc732ed30474ccbba839a
3
  size 80792096