Hugging Face's logo

imdatta0
/
mistral_7b_v_Magiccoder_evol_10k_reverse

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
cf56834
•
1 Parent(s): e5f22e3

End of training

Browse files
Files changed (2) hide show
  1. README.md +42 -42
  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 [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.1146
21
 
22
  ## Model description
23
 
@@ -37,10 +37,10 @@ More information needed
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
43
- - gradient_accumulation_steps: 8
44
  - total_train_batch_size: 64
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
@@ -51,44 +51,44 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 1.1799 | 0.0262 | 4 | 1.1888 |
55
- | 1.1193 | 0.0523 | 8 | 1.1757 |
56
- | 1.1603 | 0.0785 | 12 | 1.1751 |
57
- | 1.0847 | 0.1047 | 16 | 1.1702 |
58
- | 1.1304 | 0.1308 | 20 | 1.1674 |
59
- | 1.042 | 0.1570 | 24 | 1.1582 |
60
- | 1.1863 | 0.1832 | 28 | 1.1633 |
61
- | 1.14 | 0.2093 | 32 | 1.1597 |
62
- | 1.0763 | 0.2355 | 36 | 1.1503 |
63
- | 1.135 | 0.2617 | 40 | 1.1458 |
64
- | 1.1623 | 0.2878 | 44 | 1.1393 |
65
- | 1.1173 | 0.3140 | 48 | 1.1423 |
66
- | 1.1283 | 0.3401 | 52 | 1.1482 |
67
- | 1.0967 | 0.3663 | 56 | 1.1356 |
68
- | 1.1131 | 0.3925 | 60 | 1.1338 |
69
- | 1.1613 | 0.4186 | 64 | 1.1419 |
70
- | 1.0548 | 0.4448 | 68 | 1.1454 |
71
- | 1.0629 | 0.4710 | 72 | 1.1320 |
72
- | 1.0679 | 0.4971 | 76 | 1.1355 |
73
- | 1.16 | 0.5233 | 80 | 1.1287 |
74
- | 1.0579 | 0.5495 | 84 | 1.1295 |
75
- | 1.1214 | 0.5756 | 88 | 1.1392 |
76
- | 1.1681 | 0.6018 | 92 | 1.1242 |
77
- | 1.1667 | 0.6280 | 96 | 1.1223 |
78
- | 1.0871 | 0.6541 | 100 | 1.1221 |
79
- | 1.1147 | 0.6803 | 104 | 1.1243 |
80
- | 1.1075 | 0.7065 | 108 | 1.1254 |
81
- | 0.9958 | 0.7326 | 112 | 1.1186 |
82
- | 1.0718 | 0.7588 | 116 | 1.1085 |
83
- | 1.0748 | 0.7850 | 120 | 1.1193 |
84
- | 1.1082 | 0.8111 | 124 | 1.1138 |
85
- | 1.0981 | 0.8373 | 128 | 1.1102 |
86
- | 1.1231 | 0.8635 | 132 | 1.1133 |
87
- | 1.0687 | 0.8896 | 136 | 1.1143 |
88
- | 1.1568 | 0.9158 | 140 | 1.1139 |
89
- | 1.0177 | 0.9419 | 144 | 1.1140 |
90
- | 1.0401 | 0.9681 | 148 | 1.1145 |
91
- | 1.1827 | 0.9943 | 152 | 1.1146 |
92
 
93
 
94
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.1558
21
 
22
  ## Model description
23
 
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 0.0001
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 16
42
  - seed: 42
43
+ - gradient_accumulation_steps: 4
44
  - total_train_batch_size: 64
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.3236 | 0.0261 | 4 | 1.3076 |
55
+ | 1.2244 | 0.0523 | 8 | 1.2947 |
56
+ | 1.5369 | 0.0784 | 12 | 1.4240 |
57
+ | 5.2765 | 0.1046 | 16 | 3.1163 |
58
+ | 3.5831 | 0.1307 | 20 | 1.7562 |
59
+ | 1.7895 | 0.1569 | 24 | 1.7124 |
60
+ | 1.914 | 0.1830 | 28 | 1.7797 |
61
+ | 2.9106 | 0.2092 | 32 | 2.3285 |
62
+ | 1.5011 | 0.2353 | 36 | 1.4598 |
63
+ | 1.4755 | 0.2614 | 40 | 1.4380 |
64
+ | 1.4568 | 0.2876 | 44 | 1.3801 |
65
+ | 1.2952 | 0.3137 | 48 | 1.3155 |
66
+ | 1.3008 | 0.3399 | 52 | 1.2782 |
67
+ | 1.2098 | 0.3660 | 56 | 1.2382 |
68
+ | 1.2073 | 0.3922 | 60 | 1.2299 |
69
+ | 1.2424 | 0.4183 | 64 | 1.2237 |
70
+ | 1.1401 | 0.4444 | 68 | 1.2220 |
71
+ | 1.1368 | 0.4706 | 72 | 1.2071 |
72
+ | 1.1203 | 0.4967 | 76 | 1.2119 |
73
+ | 1.21 | 0.5229 | 80 | 1.2026 |
74
+ | 1.12 | 0.5490 | 84 | 1.1905 |
75
+ | 1.199 | 0.5752 | 88 | 1.1893 |
76
+ | 1.2302 | 0.6013 | 92 | 1.1889 |
77
+ | 1.2382 | 0.6275 | 96 | 1.1797 |
78
+ | 1.1521 | 0.6536 | 100 | 1.1765 |
79
+ | 1.1563 | 0.6797 | 104 | 1.1728 |
80
+ | 1.1676 | 0.7059 | 108 | 1.1718 |
81
+ | 1.0429 | 0.7320 | 112 | 1.1642 |
82
+ | 1.1303 | 0.7582 | 116 | 1.1660 |
83
+ | 1.126 | 0.7843 | 120 | 1.1641 |
84
+ | 1.1603 | 0.8105 | 124 | 1.1598 |
85
+ | 1.146 | 0.8366 | 128 | 1.1587 |
86
+ | 1.1689 | 0.8627 | 132 | 1.1547 |
87
+ | 1.1046 | 0.8889 | 136 | 1.1533 |
88
+ | 1.201 | 0.9150 | 140 | 1.1565 |
89
+ | 1.0665 | 0.9412 | 144 | 1.1566 |
90
+ | 1.0795 | 0.9673 | 148 | 1.1561 |
91
+ | 1.2229 | 0.9935 | 152 | 1.1558 |
92
 
93
 
94
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b321b4d43638fea63f5586d8c5fb4dc44644eaa1ab8085543abe605a1e36ec2
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551f15c5cbbc2c089df52733014336d1952b1bd2e19c97841bde2a2775dd4f62
3
  size 83945296