Hugging Face's logo

imdatta0
/
Mistral-7B-v0.3_magiccoder_ortho

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
ec18602
•
1 Parent(s): 65b1705

End of training

Browse files
Files changed (2) hide show
  1. README.md +40 -40
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 7.8283
21
 
22
  ## Model description
23
 
@@ -36,7 +36,7 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 0.0001
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
@@ -51,44 +51,44 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 4.9343 | 0.0262 | 4 | 4.5673 |
55
- | 9.0563 | 0.0523 | 8 | 8.5844 |
56
- | 8.1428 | 0.0785 | 12 | 10.0610 |
57
- | 8.7401 | 0.1047 | 16 | 9.0322 |
58
- | 8.5719 | 0.1308 | 20 | 8.2514 |
59
- | 8.0244 | 0.1570 | 24 | 7.8997 |
60
- | 7.9039 | 0.1832 | 28 | 7.9731 |
61
- | 7.9369 | 0.2093 | 32 | 7.9012 |
62
- | 7.8205 | 0.2355 | 36 | 7.8752 |
63
- | 7.9507 | 0.2617 | 40 | 7.9134 |
64
- | 7.915 | 0.2878 | 44 | 7.8308 |
65
- | 7.831 | 0.3140 | 48 | 7.8336 |
66
- | 7.8959 | 0.3401 | 52 | 7.9525 |
67
- | 7.7961 | 0.3663 | 56 | 7.8919 |
68
- | 7.8427 | 0.3925 | 60 | 7.8129 |
69
- | 7.8487 | 0.4186 | 64 | 7.8477 |
70
- | 7.8967 | 0.4448 | 68 | 7.9020 |
71
- | 7.8156 | 0.4710 | 72 | 7.8256 |
72
- | 7.846 | 0.4971 | 76 | 7.8840 |
73
- | 7.9218 | 0.5233 | 80 | 7.8602 |
74
- | 7.8865 | 0.5495 | 84 | 7.9132 |
75
- | 7.822 | 0.5756 | 88 | 7.8519 |
76
- | 7.9065 | 0.6018 | 92 | 7.8543 |
77
- | 7.8396 | 0.6280 | 96 | 7.8155 |
78
- | 7.8712 | 0.6541 | 100 | 7.8228 |
79
- | 7.8596 | 0.6803 | 104 | 7.8771 |
80
- | 7.9394 | 0.7065 | 108 | 7.9084 |
81
- | 7.8879 | 0.7326 | 112 | 7.9153 |
82
- | 7.8493 | 0.7588 | 116 | 7.8012 |
83
- | 7.8292 | 0.7850 | 120 | 7.8120 |
84
- | 7.9685 | 0.8111 | 124 | 7.8322 |
85
- | 7.8764 | 0.8373 | 128 | 7.8079 |
86
- | 7.8677 | 0.8635 | 132 | 7.8023 |
87
- | 7.8468 | 0.8896 | 136 | 7.8377 |
88
- | 7.752 | 0.9158 | 140 | 7.8209 |
89
- | 7.8344 | 0.9419 | 144 | 7.8189 |
90
- | 7.7879 | 0.9681 | 148 | 7.8257 |
91
- | 7.8357 | 0.9943 | 152 | 7.8283 |
92
 
93
 
94
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 7.8291
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.0003
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.2179 | 0.0262 | 4 | 1.6151 |
55
+ | 4.1153 | 0.0523 | 8 | 11.4846 |
56
+ | 9.4045 | 0.0785 | 12 | 10.9796 |
57
+ | 8.1663 | 0.1047 | 16 | 8.2167 |
58
+ | 9.0474 | 0.1308 | 20 | 10.0032 |
59
+ | 8.4796 | 0.1570 | 24 | 8.3873 |
60
+ | 7.9286 | 0.1832 | 28 | 8.0296 |
61
+ | 7.8704 | 0.2093 | 32 | 7.9253 |
62
+ | 7.7139 | 0.2355 | 36 | 7.8579 |
63
+ | 7.9416 | 0.2617 | 40 | 7.7372 |
64
+ | 7.9342 | 0.2878 | 44 | 7.8272 |
65
+ | 7.7907 | 0.3140 | 48 | 7.8569 |
66
+ | 7.9106 | 0.3401 | 52 | 7.8776 |
67
+ | 7.8242 | 0.3663 | 56 | 7.8943 |
68
+ | 7.8321 | 0.3925 | 60 | 7.8261 |
69
+ | 7.861 | 0.4186 | 64 | 7.8201 |
70
+ | 7.9374 | 0.4448 | 68 | 7.8658 |
71
+ | 7.8396 | 0.4710 | 72 | 7.8735 |
72
+ | 7.8607 | 0.4971 | 76 | 7.8436 |
73
+ | 7.9294 | 0.5233 | 80 | 7.8951 |
74
+ | 7.9017 | 0.5495 | 84 | 7.8877 |
75
+ | 7.8512 | 0.5756 | 88 | 7.8694 |
76
+ | 7.9036 | 0.6018 | 92 | 7.8331 |
77
+ | 7.8496 | 0.6280 | 96 | 7.8269 |
78
+ | 7.8837 | 0.6541 | 100 | 7.8142 |
79
+ | 7.8718 | 0.6803 | 104 | 7.9025 |
80
+ | 7.934 | 0.7065 | 108 | 7.8767 |
81
+ | 7.8706 | 0.7326 | 112 | 7.8579 |
82
+ | 7.8889 | 0.7588 | 116 | 7.8467 |
83
+ | 7.8279 | 0.7850 | 120 | 7.7952 |
84
+ | 7.9176 | 0.8111 | 124 | 7.8180 |
85
+ | 7.8894 | 0.8373 | 128 | 7.8068 |
86
+ | 7.8625 | 0.8635 | 132 | 7.8081 |
87
+ | 7.8447 | 0.8896 | 136 | 7.8196 |
88
+ | 7.7559 | 0.9158 | 140 | 7.8307 |
89
+ | 7.8508 | 0.9419 | 144 | 7.8304 |
90
+ | 7.8058 | 0.9681 | 148 | 7.8295 |
91
+ | 7.8377 | 0.9943 | 152 | 7.8291 |
92
 
93
 
94
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2c4dbd04a2cbe44f9b72c2aca2f4d3b0adec4608546c6a7ca57732568a39be6
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6627fb53dbb9447c401c24d1df8671fae57a4e1467747b8f23b83288b70663
3
  size 83945296