Hugging Face's logo

imdatta0
/
Qwen2-7B_magiccoder_reverse

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
7e31b7b
•
1 Parent(s): 2eac108

End of training

Browse files
Files changed (2) hide show
  1. README.md +41 -41
  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_magiccoder_reverse
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: 1.0421
21
 
22
  ## Model description
23
 
@@ -51,44 +51,44 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 0.9108 | 0.0261 | 4 | 0.9707 |
55
- | 0.9882 | 0.0522 | 8 | 1.0348 |
56
- | 1.0325 | 0.0783 | 12 | 1.0383 |
57
- | 1.0044 | 0.1044 | 16 | 1.0488 |
58
- | 1.0614 | 0.1305 | 20 | 1.0597 |
59
- | 0.9711 | 0.1566 | 24 | 1.0676 |
60
- | 0.979 | 0.1827 | 28 | 1.0751 |
61
- | 1.1009 | 0.2088 | 32 | 1.0812 |
62
- | 1.014 | 0.2349 | 36 | 1.0818 |
63
- | 1.057 | 0.2610 | 40 | 1.0841 |
64
- | 1.1137 | 0.2871 | 44 | 1.0848 |
65
- | 1.0856 | 0.3132 | 48 | 1.0879 |
66
- | 1.0044 | 0.3393 | 52 | 1.0875 |
67
- | 1.0199 | 0.3654 | 56 | 1.0862 |
68
- | 1.0503 | 0.3915 | 60 | 1.0861 |
69
- | 1.0973 | 0.4176 | 64 | 1.0831 |
70
- | 1.0846 | 0.4437 | 68 | 1.0824 |
71
- | 1.051 | 0.4698 | 72 | 1.0805 |
72
- | 1.0629 | 0.4959 | 76 | 1.0797 |
73
- | 1.0294 | 0.5220 | 80 | 1.0759 |
74
- | 1.0989 | 0.5481 | 84 | 1.0724 |
75
- | 1.0112 | 0.5742 | 88 | 1.0708 |
76
- | 1.0885 | 0.6003 | 92 | 1.0696 |
77
- | 1.0212 | 0.6264 | 96 | 1.0651 |
78
- | 1.1114 | 0.6525 | 100 | 1.0617 |
79
- | 0.994 | 0.6786 | 104 | 1.0602 |
80
- | 1.0346 | 0.7047 | 108 | 1.0566 |
81
- | 1.0053 | 0.7308 | 112 | 1.0539 |
82
- | 0.9673 | 0.7569 | 116 | 1.0506 |
83
- | 0.9526 | 0.7830 | 120 | 1.0489 |
84
- | 1.0196 | 0.8091 | 124 | 1.0475 |
85
- | 1.0054 | 0.8352 | 128 | 1.0456 |
86
- | 1.0743 | 0.8613 | 132 | 1.0439 |
87
- | 1.011 | 0.8874 | 136 | 1.0430 |
88
- | 1.0417 | 0.9135 | 140 | 1.0426 |
89
- | 0.9953 | 0.9396 | 144 | 1.0422 |
90
- | 1.0592 | 0.9657 | 148 | 1.0420 |
91
- | 1.019 | 0.9918 | 152 | 1.0421 |
92
 
93
 
94
  ### Framework versions
 
1
  ---
2
+ base_model: unsloth/Qwen2-7B
3
  library_name: peft
4
  license: apache-2.0
5
  tags:
 
15
 
16
  # Qwen2-7B_magiccoder_reverse
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: 0.9869
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.8213 | 0.0261 | 4 | 0.9216 |
55
+ | 0.9106 | 0.0522 | 8 | 0.9644 |
56
+ | 0.9506 | 0.0783 | 12 | 0.9631 |
57
+ | 0.9339 | 0.1044 | 16 | 0.9845 |
58
+ | 1.0039 | 0.1305 | 20 | 0.9997 |
59
+ | 0.9095 | 0.1566 | 24 | 1.0116 |
60
+ | 0.9241 | 0.1827 | 28 | 1.0198 |
61
+ | 1.0582 | 0.2088 | 32 | 1.0291 |
62
+ | 0.9677 | 0.2349 | 36 | 1.0307 |
63
+ | 1.0044 | 0.2610 | 40 | 1.0355 |
64
+ | 1.0672 | 0.2871 | 44 | 1.0388 |
65
+ | 1.0368 | 0.3132 | 48 | 1.0402 |
66
+ | 0.9603 | 0.3393 | 52 | 1.0420 |
67
+ | 0.9709 | 0.3654 | 56 | 1.0398 |
68
+ | 1.0019 | 0.3915 | 60 | 1.0403 |
69
+ | 1.0537 | 0.4176 | 64 | 1.0384 |
70
+ | 1.0365 | 0.4437 | 68 | 1.0345 |
71
+ | 1.0 | 0.4698 | 72 | 1.0332 |
72
+ | 1.0165 | 0.4959 | 76 | 1.0306 |
73
+ | 0.9778 | 0.5220 | 80 | 1.0271 |
74
+ | 1.0497 | 0.5481 | 84 | 1.0229 |
75
+ | 0.9652 | 0.5742 | 88 | 1.0203 |
76
+ | 1.0435 | 0.6003 | 92 | 1.0185 |
77
+ | 0.9769 | 0.6264 | 96 | 1.0141 |
78
+ | 1.0648 | 0.6525 | 100 | 1.0104 |
79
+ | 0.9463 | 0.6786 | 104 | 1.0079 |
80
+ | 0.9835 | 0.7047 | 108 | 1.0049 |
81
+ | 0.9584 | 0.7308 | 112 | 1.0010 |
82
+ | 0.9185 | 0.7569 | 116 | 0.9973 |
83
+ | 0.9021 | 0.7830 | 120 | 0.9950 |
84
+ | 0.9684 | 0.8091 | 124 | 0.9930 |
85
+ | 0.9461 | 0.8352 | 128 | 0.9913 |
86
+ | 1.0232 | 0.8613 | 132 | 0.9895 |
87
+ | 0.9646 | 0.8874 | 136 | 0.9885 |
88
+ | 0.9912 | 0.9135 | 140 | 0.9874 |
89
+ | 0.9464 | 0.9396 | 144 | 0.9870 |
90
+ | 1.0104 | 0.9657 | 148 | 0.9868 |
91
+ | 0.9624 | 0.9918 | 152 | 0.9869 |
92
 
93
 
94
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e583d9b1b24ed95df9c82042afda814842d4ee4947c6255f16b46784f48c6381
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca037a404242449496aa3c232e4e86d60295b50ec72851d439ef22363073678
3
  size 80792096