Hugging Face's logo

Litzy619
/
Phi0503HMA4

Safetensors
Generated from Trainer
Model card Files Community
Litzy619 commited on
Commit
bff0904
•
1 Parent(s): 81af1d2

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: 0.0958
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
- | 4.3203 | 0.09 | 10 | 0.8287 |
54
- | 0.439 | 0.18 | 20 | 0.2584 |
55
- | 0.2853 | 0.27 | 30 | 0.2324 |
56
- | 0.3519 | 0.36 | 40 | 0.2819 |
57
- | 0.2642 | 0.45 | 50 | 1.2134 |
58
- | 3.7539 | 0.54 | 60 | 4.0368 |
59
- | 2.718 | 0.63 | 70 | 1.9987 |
60
- | 1.3059 | 0.73 | 80 | 0.5453 |
61
- | 0.534 | 0.82 | 90 | 0.4644 |
62
- | 0.3535 | 0.91 | 100 | 0.2428 |
63
- | 0.2618 | 1.0 | 110 | 0.2259 |
64
- | 0.2222 | 1.09 | 120 | 0.2072 |
65
- | 0.1939 | 1.18 | 130 | 0.1850 |
66
- | 0.2268 | 1.27 | 140 | 0.1876 |
67
- | 0.1966 | 1.36 | 150 | 0.1927 |
68
- | 0.1942 | 1.45 | 160 | 0.1838 |
69
- | 0.1937 | 1.54 | 170 | 0.1900 |
70
- | 0.1808 | 1.63 | 180 | 0.1781 |
71
- | 0.1785 | 1.72 | 190 | 0.1795 |
72
- | 0.1737 | 1.81 | 200 | 0.1694 |
73
- | 0.176 | 1.9 | 210 | 0.1708 |
74
- | 0.1648 | 1.99 | 220 | 0.1751 |
75
- | 0.1702 | 2.08 | 230 | 0.1576 |
76
- | 0.1576 | 2.18 | 240 | 0.1524 |
77
- | 0.1477 | 2.27 | 250 | 0.1389 |
78
- | 0.1333 | 2.36 | 260 | 0.1172 |
79
- | 0.1267 | 2.45 | 270 | 0.1126 |
80
- | 0.1128 | 2.54 | 280 | 0.1016 |
81
- | 0.1112 | 2.63 | 290 | 0.0995 |
82
- | 0.1032 | 2.72 | 300 | 0.0976 |
83
- | 0.1001 | 2.81 | 310 | 0.0971 |
84
- | 0.0996 | 2.9 | 320 | 0.0957 |
85
- | 0.0968 | 2.99 | 330 | 0.0958 |
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: 0.0153
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 4.327 | 0.09 | 10 | 0.8261 |
54
+ | 0.4359 | 0.18 | 20 | 0.2664 |
55
+ | 0.2914 | 0.27 | 30 | 0.2506 |
56
+ | 0.2542 | 0.36 | 40 | 0.2504 |
57
+ | 0.2976 | 0.45 | 50 | 0.3288 |
58
+ | 0.3986 | 0.54 | 60 | 0.2542 |
59
+ | 2.3932 | 0.63 | 70 | 0.2711 |
60
+ | 1.9638 | 0.73 | 80 | 4.8527 |
61
+ | 3.6131 | 0.82 | 90 | 1.5739 |
62
+ | 1.1269 | 0.91 | 100 | 0.7721 |
63
+ | 0.4633 | 1.0 | 110 | 0.3521 |
64
+ | 0.2947 | 1.09 | 120 | 0.2266 |
65
+ | 0.2156 | 1.18 | 130 | 0.1790 |
66
+ | 0.2026 | 1.27 | 140 | 0.1381 |
67
+ | 0.1618 | 1.36 | 150 | 0.2401 |
68
+ | 0.1723 | 1.45 | 160 | 0.1317 |
69
+ | 0.1256 | 1.54 | 170 | 0.0996 |
70
+ | 0.1171 | 1.63 | 180 | 0.0833 |
71
+ | 0.0767 | 1.72 | 190 | 0.0579 |
72
+ | 0.0578 | 1.81 | 200 | 0.0514 |
73
+ | 0.0497 | 1.9 | 210 | 0.0414 |
74
+ | 0.0456 | 1.99 | 220 | 0.0376 |
75
+ | 0.042 | 2.08 | 230 | 0.0374 |
76
+ | 0.0435 | 2.18 | 240 | 0.0295 |
77
+ | 0.0429 | 2.27 | 250 | 0.0304 |
78
+ | 0.0396 | 2.36 | 260 | 0.0243 |
79
+ | 0.0305 | 2.45 | 270 | 0.0214 |
80
+ | 0.0277 | 2.54 | 280 | 0.0191 |
81
+ | 0.0205 | 2.63 | 290 | 0.0186 |
82
+ | 0.0228 | 2.72 | 300 | 0.0165 |
83
+ | 0.0202 | 2.81 | 310 | 0.0157 |
84
+ | 0.0236 | 2.9 | 320 | 0.0155 |
85
+ | 0.0196 | 2.99 | 330 | 0.0153 |
86
 
87
 
88
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:921090f33e20804f3c5716be76194ff3c44db2195152549f53ce1620504f588d
3
  size 430750193
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e531379ebd76489d03be053401fe42a766315ceba5095b40b875bd1eb0aab724
3
  size 430750193
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db294a443db39692c1000c6714d546b297a45545036f5d16f1ec441610ab78e3
3
  size 7921324520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5a457b326f18d42d87c054ebdde8a782d83865fdb1c1f5ce2e8993bd5e3f6c
3
  size 7921324520
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c4f9831b3dfe394c191d6772e9c9b2ed3b939f93de14d03cb0c8d2514e8af9f
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0f3576efb1b0b5e723eb67f2f4d413e1246a521e302c2abf6a1192d109793b
3
  size 5176