Hugging Face's logo

Litzy619
/
Phi0503HMA26

Safetensors
Generated from Trainer
Model card Files
xet
Community
Litzy619 commited on
Commit
7abf5aa
·
verified ·
1 Parent(s): 19a8267

End of training

Browse files
Files changed (5) hide show
  1. README.md +34 -34
  2. adapter_config.json +1 -2
  3. adapter_model.bin +2 -2
  4. model.safetensors +2 -2
  5. 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: 0.0793
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
- | 4.0777 | 0.09 | 10 | 0.4600 |
54
- | 0.2898 | 0.18 | 20 | 0.2397 |
55
- | 0.2373 | 0.27 | 30 | 0.2282 |
56
- | 0.2193 | 0.36 | 40 | 0.2107 |
57
- | 0.2103 | 0.45 | 50 | 0.2865 |
58
- | 0.1796 | 0.54 | 60 | 0.1327 |
59
- | 1.8078 | 0.63 | 70 | 1.0824 |
60
- | 0.2232 | 0.73 | 80 | 0.0985 |
61
- | 0.1319 | 0.82 | 90 | 0.1969 |
62
- | 0.1317 | 0.91 | 100 | 0.1082 |
63
- | 0.0954 | 1.0 | 110 | 0.1045 |
64
- | 0.0735 | 1.09 | 120 | 0.0701 |
65
- | 0.07 | 1.18 | 130 | 0.0840 |
66
- | 0.0742 | 1.27 | 140 | 0.0764 |
67
- | 0.0699 | 1.36 | 150 | 0.0727 |
68
- | 0.0727 | 1.45 | 160 | 0.0744 |
69
- | 0.0642 | 1.54 | 170 | 0.0733 |
70
- | 0.0702 | 1.63 | 180 | 0.0726 |
71
- | 0.0657 | 1.72 | 190 | 0.0670 |
72
- | 0.0605 | 1.81 | 200 | 0.0661 |
73
- | 0.0625 | 1.9 | 210 | 0.0747 |
74
- | 0.0603 | 1.99 | 220 | 0.0679 |
75
- | 0.0318 | 2.08 | 230 | 0.0775 |
76
- | 0.0275 | 2.18 | 240 | 0.0901 |
77
- | 0.026 | 2.27 | 250 | 0.0907 |
78
- | 0.023 | 2.36 | 260 | 0.0831 |
79
- | 0.0281 | 2.45 | 270 | 0.0792 |
80
- | 0.0197 | 2.54 | 280 | 0.0813 |
81
- | 0.0203 | 2.63 | 290 | 0.0850 |
82
- | 0.0281 | 2.72 | 300 | 0.0830 |
83
- | 0.0277 | 2.81 | 310 | 0.0809 |
84
- | 0.0248 | 2.9 | 320 | 0.0798 |
85
- | 0.0257 | 2.99 | 330 | 0.0793 |
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: 0.0635
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 4.4865 | 0.09 | 10 | 0.8844 |
54
+ | 0.3885 | 0.18 | 20 | 0.2386 |
55
+ | 0.2667 | 0.27 | 30 | 0.2422 |
56
+ | 0.2338 | 0.36 | 40 | 0.2291 |
57
+ | 0.2321 | 0.45 | 50 | 0.2215 |
58
+ | 0.226 | 0.54 | 60 | 0.2156 |
59
+ | 0.2283 | 0.63 | 70 | 0.2006 |
60
+ | 0.2115 | 0.73 | 80 | 0.2034 |
61
+ | 0.1803 | 0.82 | 90 | 0.1707 |
62
+ | 0.1687 | 0.91 | 100 | 0.2004 |
63
+ | 0.1851 | 1.0 | 110 | 0.1699 |
64
+ | 0.1641 | 1.09 | 120 | 0.1648 |
65
+ | 0.1642 | 1.18 | 130 | 0.1666 |
66
+ | 0.1748 | 1.27 | 140 | 0.1629 |
67
+ | 0.1665 | 1.36 | 150 | 0.1627 |
68
+ | 0.134 | 1.45 | 160 | 0.1023 |
69
+ | 0.1085 | 1.54 | 170 | 0.0887 |
70
+ | 0.0876 | 1.63 | 180 | 0.0784 |
71
+ | 0.0749 | 1.72 | 190 | 0.0729 |
72
+ | 0.0673 | 1.81 | 200 | 0.0721 |
73
+ | 0.0687 | 1.9 | 210 | 0.0764 |
74
+ | 0.0648 | 1.99 | 220 | 0.0698 |
75
+ | 0.0477 | 2.08 | 230 | 0.0734 |
76
+ | 0.0522 | 2.18 | 240 | 0.0681 |
77
+ | 0.0437 | 2.27 | 250 | 0.0679 |
78
+ | 0.0437 | 2.36 | 260 | 0.0661 |
79
+ | 0.0497 | 2.45 | 270 | 0.0651 |
80
+ | 0.0437 | 2.54 | 280 | 0.0651 |
81
+ | 0.0433 | 2.63 | 290 | 0.0651 |
82
+ | 0.0464 | 2.72 | 300 | 0.0649 |
83
+ | 0.0558 | 2.81 | 310 | 0.0640 |
84
+ | 0.0455 | 2.9 | 320 | 0.0635 |
85
+ | 0.0469 | 2.99 | 330 | 0.0635 |
86
 
87
 
88
  ### Framework versions
adapter_config.json CHANGED
@@ -41,8 +41,7 @@
41
  "simple_hidden_matching": false,
42
  "simple_instance_matching": true,
43
  "target_modules": [
44
- "qkv_proj",
45
- "o_proj"
46
  ],
47
  "task_type": "CAUSAL_LM",
48
  "token_dim": 3072
 
41
  "simple_hidden_matching": false,
42
  "simple_instance_matching": true,
43
  "target_modules": [
44
+ "qkv_proj"
 
45
  ],
46
  "task_type": "CAUSAL_LM",
47
  "token_dim": 3072
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f68193b835a1d5b176c3956ad28fbc4d6e51dceca4366310266bb79369392a6
3
- size 430750193
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3181e3dc62e83e655d1bf550e1aed15fb425eb74fbda084d595f81c533750c21
3
+ size 326557137
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7d14620493647deec0828464d681f2998a90c48007d220f9351a5c81a2bd0c4
3
- size 7921324520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8c97b1070649166c0547cade33800fdd2572cf65871424ea30fd4942e647d94
3
+ size 7867763280
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6619c2b6033f4d4af46ad40b9303ab2bce7e6049dcea2a5e3d401732a24db1b
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df9ed098d2194169ec196f89c95288beae3d5dfe9868d67bc0caaefb114c25d
3
  size 5176