Hugging Face's logo

Litzy619
/
Phi0503HMA18OLD

Safetensors
Generated from Trainer
Model card Files Community
Litzy619 commited on
Commit
5d10862
•
1 Parent(s): bca69fb

End of training

Browse files
Files changed (5) hide show
  1. README.md +34 -34
  2. adapter_config.json +1 -1
  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: 0.0856
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
- | 3.766 | 0.09 | 10 | 0.4613 |
54
- | 0.3024 | 0.18 | 20 | 0.2538 |
55
- | 0.2469 | 0.27 | 30 | 0.2178 |
56
- | 0.261 | 0.36 | 40 | 0.2338 |
57
- | 0.482 | 0.45 | 50 | 0.2783 |
58
- | 0.2062 | 0.54 | 60 | 0.1451 |
59
- | 0.1438 | 0.63 | 70 | 0.1608 |
60
- | 0.1457 | 0.73 | 80 | 0.1216 |
61
- | 0.103 | 0.82 | 90 | 0.1031 |
62
- | 0.1028 | 0.91 | 100 | 0.0730 |
63
- | 0.0779 | 1.0 | 110 | 0.0722 |
64
- | 0.0572 | 1.09 | 120 | 0.0660 |
65
- | 0.0543 | 1.18 | 130 | 0.0833 |
66
- | 0.0669 | 1.27 | 140 | 0.0697 |
67
- | 0.0573 | 1.36 | 150 | 0.0711 |
68
- | 0.0636 | 1.45 | 160 | 0.0659 |
69
- | 0.0579 | 1.54 | 170 | 0.0680 |
70
- | 0.0595 | 1.63 | 180 | 0.0651 |
71
- | 0.0541 | 1.72 | 190 | 0.0692 |
72
- | 0.0579 | 1.81 | 200 | 0.0626 |
73
- | 0.0487 | 1.9 | 210 | 0.0663 |
74
- | 0.0501 | 1.99 | 220 | 0.0655 |
75
- | 0.0269 | 2.08 | 230 | 0.0733 |
76
- | 0.0241 | 2.18 | 240 | 0.0912 |
77
- | 0.0172 | 2.27 | 250 | 0.1040 |
78
- | 0.0171 | 2.36 | 260 | 0.0972 |
79
- | 0.0242 | 2.45 | 270 | 0.0892 |
80
- | 0.0153 | 2.54 | 280 | 0.0907 |
81
- | 0.0193 | 2.63 | 290 | 0.0904 |
82
- | 0.0252 | 2.72 | 300 | 0.0876 |
83
- | 0.0245 | 2.81 | 310 | 0.0862 |
84
- | 0.0202 | 2.9 | 320 | 0.0857 |
85
- | 0.0207 | 2.99 | 330 | 0.0856 |
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: 0.0803
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 3.9264 | 0.09 | 10 | 0.4060 |
54
+ | 0.5196 | 0.18 | 20 | 2.6047 |
55
+ | 0.5297 | 0.27 | 30 | 0.2263 |
56
+ | 0.2143 | 0.36 | 40 | 0.1990 |
57
+ | 0.2823 | 0.45 | 50 | 0.2488 |
58
+ | 0.2513 | 0.54 | 60 | 0.1911 |
59
+ | 0.1606 | 0.63 | 70 | 0.1463 |
60
+ | 0.1446 | 0.73 | 80 | 0.1406 |
61
+ | 0.1202 | 0.82 | 90 | 0.1288 |
62
+ | 0.1229 | 0.91 | 100 | 0.1081 |
63
+ | 0.1123 | 1.0 | 110 | 0.1439 |
64
+ | 0.123 | 1.09 | 120 | 0.1062 |
65
+ | 0.0765 | 1.18 | 130 | 0.0812 |
66
+ | 0.0736 | 1.27 | 140 | 0.0723 |
67
+ | 0.0629 | 1.36 | 150 | 0.0730 |
68
+ | 0.0554 | 1.45 | 160 | 0.0738 |
69
+ | 0.0532 | 1.54 | 170 | 0.0671 |
70
+ | 0.0595 | 1.63 | 180 | 0.0657 |
71
+ | 0.0594 | 1.72 | 190 | 0.0681 |
72
+ | 0.0613 | 1.81 | 200 | 0.0624 |
73
+ | 0.0488 | 1.9 | 210 | 0.0623 |
74
+ | 0.0576 | 1.99 | 220 | 0.0607 |
75
+ | 0.0284 | 2.08 | 230 | 0.0712 |
76
+ | 0.0171 | 2.18 | 240 | 0.1021 |
77
+ | 0.0287 | 2.27 | 250 | 0.0831 |
78
+ | 0.0209 | 2.36 | 260 | 0.0753 |
79
+ | 0.0229 | 2.45 | 270 | 0.0752 |
80
+ | 0.0209 | 2.54 | 280 | 0.0759 |
81
+ | 0.0206 | 2.63 | 290 | 0.0773 |
82
+ | 0.0199 | 2.72 | 300 | 0.0788 |
83
+ | 0.0162 | 2.81 | 310 | 0.0796 |
84
+ | 0.0181 | 2.9 | 320 | 0.0802 |
85
+ | 0.0213 | 2.99 | 330 | 0.0803 |
86
 
87
 
88
  ### Framework versions
adapter_config.json CHANGED
@@ -2,7 +2,7 @@
2
  "adaptive_ratio": 0.01,
3
  "adaptive_ratio_decay": 1.0,
4
  "additive_modeling": false,
5
- "allow_empty_lora": true,
6
  "auto_mapping": null,
7
  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
8
  "bias": "none",
 
2
  "adaptive_ratio": 0.01,
3
  "adaptive_ratio_decay": 1.0,
4
  "additive_modeling": false,
5
+ "allow_empty_lora": false,
6
  "auto_mapping": null,
7
  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
8
  "bias": "none",
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e892ec140136e3a12b6bf26026ecff3be71ba9e5096788c1b8f9d2db4fdb49be
3
- size 431155958
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f6a4610b5a028ff2cfae5abaae4fc097d311e30dd493daf1c49d9891038189
3
+ size 430750193
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f09142b8d998137b8cfd69edd34d37ae1da6c20a900c302cc8d23a0ddffdc53
3
- size 7921726216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89305dac159408b747ab5327111ed2c1a22eb279198fc59330108bb157dcfb70
3
+ size 7921324520
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1d4d0fbbd7b90aa8d90deb273884f196cc13ef3f26c3799da308e6cf9acf1c2
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd1749e59c1e7250499bb4843cbdc6a89b6ce9679ba6d846786bb8e19c0f7d6b
3
  size 5176