Hugging Face's logo

imdatta0
/
mistral_7b_v_Magiccoder_evol_10k_ortho

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
bd78638
·
verified ·
1 Parent(s): 29a64af

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: 1.1371
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
- | 1.1548 | 0.0262 | 4 | 1.1975 |
55
- | 1.1117 | 0.0523 | 8 | 1.1750 |
56
- | 1.1638 | 0.0785 | 12 | 1.1670 |
57
- | 1.0902 | 0.1047 | 16 | 1.1675 |
58
- | 1.1292 | 0.1308 | 20 | 1.1671 |
59
- | 1.0469 | 0.1570 | 24 | 1.1621 |
60
- | 1.2005 | 0.1832 | 28 | 1.1638 |
61
- | 1.1491 | 0.2093 | 32 | 1.1638 |
62
- | 1.0749 | 0.2355 | 36 | 1.1475 |
63
- | 1.1758 | 0.2617 | 40 | 1.1525 |
64
- | 1.1511 | 0.2878 | 44 | 1.1410 |
65
- | 1.1229 | 0.3140 | 48 | 1.1532 |
66
- | 1.1349 | 0.3401 | 52 | 1.1592 |
67
- | 1.1116 | 0.3663 | 56 | 1.1465 |
68
- | 1.1127 | 0.3925 | 60 | 1.1517 |
69
- | 1.1709 | 0.4186 | 64 | 1.1460 |
70
- | 1.0574 | 0.4448 | 68 | 1.1504 |
71
- | 1.0794 | 0.4710 | 72 | 1.1414 |
72
- | 1.0711 | 0.4971 | 76 | 1.1485 |
73
- | 1.1984 | 0.5233 | 80 | 1.1544 |
74
- | 1.0625 | 0.5495 | 84 | 1.1346 |
75
- | 1.151 | 0.5756 | 88 | 1.1728 |
76
- | 1.1977 | 0.6018 | 92 | 1.1364 |
77
- | 1.1757 | 0.6280 | 96 | 1.1418 |
78
- | 1.1191 | 0.6541 | 100 | 1.1487 |
79
- | 1.1415 | 0.6803 | 104 | 1.1431 |
80
- | 1.1272 | 0.7065 | 108 | 1.1399 |
81
- | 1.0134 | 0.7326 | 112 | 1.1431 |
82
- | 1.09 | 0.7588 | 116 | 1.1261 |
83
- | 1.0848 | 0.7850 | 120 | 1.1346 |
84
- | 1.1346 | 0.8111 | 124 | 1.1401 |
85
- | 1.1336 | 0.8373 | 128 | 1.1371 |
86
- | 1.1458 | 0.8635 | 132 | 1.1338 |
87
- | 1.0835 | 0.8896 | 136 | 1.1334 |
88
- | 1.1795 | 0.9158 | 140 | 1.1345 |
89
- | 1.0422 | 0.9419 | 144 | 1.1359 |
90
- | 1.0608 | 0.9681 | 148 | 1.1367 |
91
- | 1.2045 | 0.9943 | 152 | 1.1371 |
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: 1.1790
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
+ | 1.173 | 0.0261 | 4 | 1.2153 |
55
+ | 1.1501 | 0.0523 | 8 | 1.1905 |
56
+ | 1.19 | 0.0784 | 12 | 1.1831 |
57
+ | 1.0875 | 0.1046 | 16 | 1.1805 |
58
+ | 1.1648 | 0.1307 | 20 | 1.1844 |
59
+ | 1.077 | 0.1569 | 24 | 1.1861 |
60
+ | 1.2251 | 0.1830 | 28 | 1.1925 |
61
+ | 1.1615 | 0.2092 | 32 | 1.1922 |
62
+ | 1.1153 | 0.2353 | 36 | 1.1763 |
63
+ | 1.2024 | 0.2614 | 40 | 1.1803 |
64
+ | 1.2181 | 0.2876 | 44 | 1.1724 |
65
+ | 1.1503 | 0.3137 | 48 | 1.2055 |
66
+ | 1.1639 | 0.3399 | 52 | 1.1896 |
67
+ | 1.1405 | 0.3660 | 56 | 1.1827 |
68
+ | 1.177 | 0.3922 | 60 | 1.2037 |
69
+ | 1.1958 | 0.4183 | 64 | 1.1796 |
70
+ | 1.1044 | 0.4444 | 68 | 1.1970 |
71
+ | 1.1115 | 0.4706 | 72 | 1.1735 |
72
+ | 1.1152 | 0.4967 | 76 | 1.2061 |
73
+ | 1.2009 | 0.5229 | 80 | 1.1671 |
74
+ | 1.1154 | 0.5490 | 84 | 1.1960 |
75
+ | 1.1739 | 0.5752 | 88 | 1.1892 |
76
+ | 1.2224 | 0.6013 | 92 | 1.1764 |
77
+ | 1.2229 | 0.6275 | 96 | 1.1926 |
78
+ | 1.1573 | 0.6536 | 100 | 1.1849 |
79
+ | 1.1629 | 0.6797 | 104 | 1.1787 |
80
+ | 1.1855 | 0.7059 | 108 | 1.1955 |
81
+ | 1.0586 | 0.7320 | 112 | 1.1814 |
82
+ | 1.1258 | 0.7582 | 116 | 1.1631 |
83
+ | 1.1273 | 0.7843 | 120 | 1.1787 |
84
+ | 1.1869 | 0.8105 | 124 | 1.1873 |
85
+ | 1.1765 | 0.8366 | 128 | 1.1852 |
86
+ | 1.1954 | 0.8627 | 132 | 1.1809 |
87
+ | 1.1277 | 0.8889 | 136 | 1.1763 |
88
+ | 1.2109 | 0.9150 | 140 | 1.1747 |
89
+ | 1.0842 | 0.9412 | 144 | 1.1771 |
90
+ | 1.0941 | 0.9673 | 148 | 1.1787 |
91
+ | 1.2413 | 0.9935 | 152 | 1.1790 |
92
 
93
 
94
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71b8b0ba59dcf7954390413dcbce5964f55d09f218066d5d10675038a6b8f591
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d11e3979ea3e9742edd87d4c3cee2708dde3abb9b4a497bc8410e3594406537
3
  size 83945296