Hugging Face's logo

Litzy619
/
Phi0503HMA19

Safetensors
Generated from Trainer
Model card Files
xet
 Community
Litzy619 commited on
Commit
8b4ef11
·
verified ·
1 Parent(s): 3ffcb14

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: 0.0782
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
- | 3.8941 | 0.09 | 10 | 0.5252 |
54
- | 0.304 | 0.18 | 20 | 0.2303 |
55
- | 0.286 | 0.27 | 30 | 0.2215 |
56
- | 0.2077 | 0.36 | 40 | 0.1718 |
57
- | 0.153 | 0.45 | 50 | 0.1491 |
58
- | 0.1408 | 0.54 | 60 | 0.1229 |
59
- | 0.1063 | 0.63 | 70 | 0.1014 |
60
- | 0.1079 | 0.73 | 80 | 0.0884 |
61
- | 0.0837 | 0.82 | 90 | 0.0777 |
62
- | 0.081 | 0.91 | 100 | 0.0710 |
63
- | 0.0749 | 1.0 | 110 | 0.0747 |
64
- | 0.0557 | 1.09 | 120 | 0.0717 |
65
- | 0.0566 | 1.18 | 130 | 0.0735 |
66
- | 0.0588 | 1.27 | 140 | 0.0713 |
67
- | 0.0535 | 1.36 | 150 | 0.0778 |
68
- | 0.0672 | 1.45 | 160 | 0.0677 |
69
- | 0.0548 | 1.54 | 170 | 0.0702 |
70
- | 0.0536 | 1.63 | 180 | 0.0633 |
71
- | 0.0474 | 1.72 | 190 | 0.0653 |
72
- | 0.0537 | 1.81 | 200 | 0.0633 |
73
- | 0.0438 | 1.9 | 210 | 0.0669 |
74
- | 0.0483 | 1.99 | 220 | 0.0669 |
75
- | 0.0233 | 2.08 | 230 | 0.0749 |
76
- | 0.0245 | 2.18 | 240 | 0.0840 |
77
- | 0.017 | 2.27 | 250 | 0.0868 |
78
- | 0.0166 | 2.36 | 260 | 0.0866 |
79
- | 0.0258 | 2.45 | 270 | 0.0823 |
80
- | 0.015 | 2.54 | 280 | 0.0805 |
81
- | 0.018 | 2.63 | 290 | 0.0811 |
82
- | 0.0227 | 2.72 | 300 | 0.0795 |
83
- | 0.0217 | 2.81 | 310 | 0.0788 |
84
- | 0.0196 | 2.9 | 320 | 0.0784 |
85
- | 0.0198 | 2.99 | 330 | 0.0782 |
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: 0.0771
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 4.0653 | 0.09 | 10 | 0.4649 |
54
+ | 0.2835 | 0.18 | 20 | 0.2213 |
55
+ | 0.2868 | 0.27 | 30 | 0.2329 |
56
+ | 0.2284 | 0.36 | 40 | 0.2334 |
57
+ | 0.2317 | 0.45 | 50 | 0.2268 |
58
+ | 0.219 | 0.54 | 60 | 0.2073 |
59
+ | 0.211 | 0.63 | 70 | 0.1848 |
60
+ | 0.1692 | 0.73 | 80 | 0.1167 |
61
+ | 0.1311 | 0.82 | 90 | 0.1255 |
62
+ | 0.1138 | 0.91 | 100 | 0.0954 |
63
+ | 0.0918 | 1.0 | 110 | 0.0852 |
64
+ | 0.0756 | 1.09 | 120 | 0.1067 |
65
+ | 0.0746 | 1.18 | 130 | 0.0875 |
66
+ | 0.0826 | 1.27 | 140 | 0.0751 |
67
+ | 0.0723 | 1.36 | 150 | 0.0737 |
68
+ | 0.0739 | 1.45 | 160 | 0.0685 |
69
+ | 0.0674 | 1.54 | 170 | 0.0687 |
70
+ | 0.0667 | 1.63 | 180 | 0.0673 |
71
+ | 0.0599 | 1.72 | 190 | 0.0692 |
72
+ | 0.0675 | 1.81 | 200 | 0.0677 |
73
+ | 0.0565 | 1.9 | 210 | 0.0731 |
74
+ | 0.0551 | 1.99 | 220 | 0.0714 |
75
+ | 0.0316 | 2.08 | 230 | 0.0762 |
76
+ | 0.0331 | 2.18 | 240 | 0.0865 |
77
+ | 0.0233 | 2.27 | 250 | 0.0880 |
78
+ | 0.0205 | 2.36 | 260 | 0.0863 |
79
+ | 0.0316 | 2.45 | 270 | 0.0802 |
80
+ | 0.0201 | 2.54 | 280 | 0.0790 |
81
+ | 0.0221 | 2.63 | 290 | 0.0803 |
82
+ | 0.0303 | 2.72 | 300 | 0.0800 |
83
+ | 0.0302 | 2.81 | 310 | 0.0781 |
84
+ | 0.027 | 2.9 | 320 | 0.0772 |
85
+ | 0.0268 | 2.99 | 330 | 0.0771 |
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:e88f93fb0c59645b9a00533277541668a1c4289052011aa73664e7a50a027cad
3
- size 431155958
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f2071e803885d35b72f605d46fe40c34fd3eacbef905c2542cb324f8a01c21
3
+ size 430750193
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcedff0ce95b454a5b844927ecad58d54f80716cec39f9be6d9b2df58c5b5618
3
- size 7921726216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce7a769653476c98e072fca20dcffcb654c4d95ddc052c5ac001902b792cfaea
3
+ size 7921324520
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b909c63d8c491b4ce79d251fb97e112e33d7269e97d461365ed514b4b0b8ce8
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21827319a0e0c123cb673bf41f635c36c7887f1c75370eb95edc59f0bd884d24
3
  size 5176