Hugging Face's logo

Litzy619
/
Phi0503HMA2

Safetensors
Generated from Trainer
Model card Files Community
Litzy619 commited on
Commit
e8c12c8
•
1 Parent(s): 59ab096

End of training

Browse files
Files changed (4) hide show
  1. README.md +34 -34
  2. adapter_model.bin +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0593
19
 
20
  ## Model description
21
 
@@ -50,39 +50,39 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 4.4065 | 0.09 | 10 | 0.9610 |
54
- | 0.4208 | 0.18 | 20 | 0.2489 |
55
- | 0.2546 | 0.27 | 30 | 0.2302 |
56
- | 0.2272 | 0.36 | 40 | 0.2254 |
57
- | 0.2494 | 0.45 | 50 | 0.2282 |
58
- | 0.2419 | 0.54 | 60 | 1.1856 |
59
- | 2.4107 | 0.63 | 70 | 0.1741 |
60
- | 0.1609 | 0.73 | 80 | 0.1520 |
61
- | 0.1255 | 0.82 | 90 | 0.1318 |
62
- | 0.1273 | 0.91 | 100 | 0.1066 |
63
- | 0.0938 | 1.0 | 110 | 0.0854 |
64
- | 0.0658 | 1.09 | 120 | 0.0693 |
65
- | 0.0603 | 1.18 | 130 | 0.0809 |
66
- | 0.086 | 1.27 | 140 | 0.0880 |
67
- | 0.0658 | 1.36 | 150 | 0.0709 |
68
- | 0.0716 | 1.45 | 160 | 0.0690 |
69
- | 0.0634 | 1.54 | 170 | 0.0688 |
70
- | 0.0634 | 1.63 | 180 | 0.0661 |
71
- | 0.0576 | 1.72 | 190 | 0.0665 |
72
- | 0.06 | 1.81 | 200 | 0.0640 |
73
- | 0.0546 | 1.9 | 210 | 0.0639 |
74
- | 0.0488 | 1.99 | 220 | 0.0622 |
75
- | 0.0171 | 2.08 | 230 | 0.0611 |
76
- | 0.0111 | 2.18 | 240 | 0.0784 |
77
- | 0.0109 | 2.27 | 250 | 0.0724 |
78
- | 0.0128 | 2.36 | 260 | 0.0589 |
79
- | 0.012 | 2.45 | 270 | 0.0595 |
80
- | 0.0105 | 2.54 | 280 | 0.0629 |
81
- | 0.0111 | 2.63 | 290 | 0.0641 |
82
- | 0.0122 | 2.72 | 300 | 0.0620 |
83
- | 0.0155 | 2.81 | 310 | 0.0604 |
84
- | 0.0148 | 2.9 | 320 | 0.0593 |
85
- | 0.0085 | 2.99 | 330 | 0.0593 |
86
 
87
 
88
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1630
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 4.4067 | 0.09 | 10 | 0.9597 |
54
+ | 0.5121 | 0.18 | 20 | 0.4807 |
55
+ | 0.3541 | 0.27 | 30 | 0.2436 |
56
+ | 0.2345 | 0.36 | 40 | 0.2271 |
57
+ | 0.2398 | 0.45 | 50 | 0.2915 |
58
+ | 0.2538 | 0.54 | 60 | 0.2847 |
59
+ | 0.216 | 0.63 | 70 | 0.2622 |
60
+ | 0.247 | 0.73 | 80 | 0.2132 |
61
+ | 0.2135 | 0.82 | 90 | 0.2269 |
62
+ | 0.2383 | 0.91 | 100 | 0.2018 |
63
+ | 0.1876 | 1.0 | 110 | 0.1702 |
64
+ | 0.1708 | 1.09 | 120 | 0.1679 |
65
+ | 0.1662 | 1.18 | 130 | 0.1660 |
66
+ | 0.1802 | 1.27 | 140 | 0.1703 |
67
+ | 0.1759 | 1.36 | 150 | 0.1664 |
68
+ | 0.1622 | 1.45 | 160 | 0.1666 |
69
+ | 0.1654 | 1.54 | 170 | 0.1636 |
70
+ | 0.1648 | 1.63 | 180 | 0.1627 |
71
+ | 0.1656 | 1.72 | 190 | 0.1691 |
72
+ | 0.1667 | 1.81 | 200 | 0.1640 |
73
+ | 0.166 | 1.9 | 210 | 0.1633 |
74
+ | 0.1628 | 1.99 | 220 | 0.1643 |
75
+ | 0.1638 | 2.08 | 230 | 0.1628 |
76
+ | 0.1604 | 2.18 | 240 | 0.1625 |
77
+ | 0.1599 | 2.27 | 250 | 0.1631 |
78
+ | 0.163 | 2.36 | 260 | 0.1638 |
79
+ | 0.1611 | 2.45 | 270 | 0.1634 |
80
+ | 0.1615 | 2.54 | 280 | 0.1635 |
81
+ | 0.1616 | 2.63 | 290 | 0.1637 |
82
+ | 0.1625 | 2.72 | 300 | 0.1633 |
83
+ | 0.1626 | 2.81 | 310 | 0.1631 |
84
+ | 0.1619 | 2.9 | 320 | 0.1630 |
85
+ | 0.1659 | 2.99 | 330 | 0.1630 |
86
 
87
 
88
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cae50e8089805d41acd61353fd5a338ec0b51bf9fa094ce84d4b808c46bb053
3
  size 430750193
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0225da4bd1d9c6cb2b406c899fe1a4bb54aa84df61465173403366af515a5f
3
  size 430750193
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8d418539b44219b45518ba1f7fbad00432ac2e581bd87ff678cc6d28d6f1c73
3
  size 7921324520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2fdd1b06e7f6d3493189b26733d088dd99591287bab4c2fcfff76565242cf12
3
  size 7921324520
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:468082f8b8867f7f6f58e138a1e9c973564f41d601f0b6fb643754d0ea3a448a
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18d4830543b416f5bba4dca6a47dcef1846017e81fa7535b0a309460d9110c3d
3
  size 5176