Hugging Face's logo

yalhessi
/
lemexp-task1-v2-template_small_nodefs_old_defs-deepseek-coder-1.3b-base-ddp-8lr-v2

PEFT
Safetensors
Generated from Trainer
Model card Files Community
yalhessi commited on
Commit
da73627
·
verified ·
1 Parent(s): 2ecddd6

End of training

Browse files
Files changed (5) hide show
  1. README.md +60 -60
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. loss_plot.png +0 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.1541
20
 
21
  ## Model description
22
 
@@ -52,65 +52,65 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
- | 0.4239 | 0.2002 | 721 | 0.3024 |
56
- | 0.3036 | 0.4003 | 1442 | 0.2672 |
57
- | 0.263 | 0.6005 | 2163 | 0.2597 |
58
- | 0.2607 | 0.8007 | 2884 | 0.2491 |
59
- | 0.2473 | 1.0008 | 3605 | 0.2362 |
60
- | 0.2333 | 1.2010 | 4326 | 0.2299 |
61
- | 0.2281 | 1.4012 | 5047 | 0.2272 |
62
- | 0.2235 | 1.6013 | 5768 | 0.2181 |
63
- | 0.2225 | 1.8015 | 6489 | 0.2186 |
64
- | 0.217 | 2.0017 | 7210 | 0.2166 |
65
- | 0.2092 | 2.2018 | 7931 | 0.2102 |
66
- | 0.2066 | 2.4020 | 8652 | 0.2109 |
67
- | 0.2045 | 2.6022 | 9373 | 0.2045 |
68
- | 0.202 | 2.8023 | 10094 | 0.2027 |
69
- | 0.2 | 3.0025 | 10815 | 0.2075 |
70
- | 0.1908 | 3.2027 | 11536 | 0.1984 |
71
- | 0.1896 | 3.4028 | 12257 | 0.1921 |
72
- | 0.1864 | 3.6030 | 12978 | 0.1908 |
73
- | 0.1852 | 3.8032 | 13699 | 0.1907 |
74
- | 0.1853 | 4.0033 | 14420 | 0.1882 |
75
- | 0.1735 | 4.2035 | 15141 | 0.1908 |
76
- | 0.1741 | 4.4037 | 15862 | 0.1886 |
77
- | 0.1729 | 4.6038 | 16583 | 0.1859 |
78
- | 0.1737 | 4.8040 | 17304 | 0.1786 |
79
- | 0.1716 | 5.0042 | 18025 | 0.1800 |
80
- | 0.1599 | 5.2043 | 18746 | 0.1772 |
81
- | 0.1606 | 5.4045 | 19467 | 0.1760 |
82
- | 0.1595 | 5.6047 | 20188 | 0.1782 |
83
- | 0.1596 | 5.8048 | 20909 | 0.1727 |
84
- | 0.1587 | 6.0050 | 21630 | 0.1730 |
85
- | 0.1492 | 6.2052 | 22351 | 0.1717 |
86
- | 0.1488 | 6.4053 | 23072 | 0.1712 |
87
- | 0.1478 | 6.6055 | 23793 | 0.1689 |
88
- | 0.1483 | 6.8057 | 24514 | 0.1669 |
89
- | 0.1468 | 7.0058 | 25235 | 0.1655 |
90
- | 0.138 | 7.2060 | 25956 | 0.1630 |
91
- | 0.137 | 7.4062 | 26677 | 0.1632 |
92
- | 0.1359 | 7.6063 | 27398 | 0.1621 |
93
- | 0.1342 | 7.8065 | 28119 | 0.1631 |
94
- | 0.134 | 8.0067 | 28840 | 0.1608 |
95
- | 0.1213 | 8.2068 | 29561 | 0.1596 |
96
- | 0.1236 | 8.4070 | 30282 | 0.1596 |
97
- | 0.1228 | 8.6072 | 31003 | 0.1553 |
98
- | 0.1237 | 8.8073 | 31724 | 0.1558 |
99
- | 0.122 | 9.0075 | 32445 | 0.1559 |
100
- | 0.1095 | 9.2077 | 33166 | 0.1544 |
101
- | 0.1093 | 9.4078 | 33887 | 0.1539 |
102
- | 0.1098 | 9.6080 | 34608 | 0.1508 |
103
- | 0.1091 | 9.8082 | 35329 | 0.1513 |
104
- | 0.1096 | 10.0083 | 36050 | 0.1517 |
105
- | 0.0976 | 10.2085 | 36771 | 0.1566 |
106
- | 0.0964 | 10.4087 | 37492 | 0.1523 |
107
- | 0.0971 | 10.6088 | 38213 | 0.1520 |
108
- | 0.097 | 10.8090 | 38934 | 0.1527 |
109
- | 0.0957 | 11.0092 | 39655 | 0.1525 |
110
- | 0.0886 | 11.2093 | 40376 | 0.1555 |
111
- | 0.0861 | 11.4095 | 41097 | 0.1545 |
112
- | 0.0872 | 11.6097 | 41818 | 0.1554 |
113
- | 0.0868 | 11.8098 | 42539 | 0.1541 |
114
 
115
 
116
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.1551
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.438 | 0.2002 | 721 | 0.3096 |
56
+ | 0.3098 | 0.4003 | 1442 | 0.2840 |
57
+ | 0.2714 | 0.6005 | 2163 | 0.2634 |
58
+ | 0.2619 | 0.8007 | 2884 | 0.2561 |
59
+ | 0.2529 | 1.0008 | 3605 | 0.2385 |
60
+ | 0.2363 | 1.2010 | 4326 | 0.2378 |
61
+ | 0.2334 | 1.4012 | 5047 | 0.2336 |
62
+ | 0.2275 | 1.6013 | 5768 | 0.2318 |
63
+ | 0.2263 | 1.8015 | 6489 | 0.2268 |
64
+ | 0.223 | 2.0017 | 7210 | 0.2194 |
65
+ | 0.2133 | 2.2018 | 7931 | 0.2129 |
66
+ | 0.2104 | 2.4020 | 8652 | 0.2150 |
67
+ | 0.2073 | 2.6022 | 9373 | 0.2089 |
68
+ | 0.206 | 2.8023 | 10094 | 0.2061 |
69
+ | 0.2045 | 3.0025 | 10815 | 0.2018 |
70
+ | 0.1949 | 3.2027 | 11536 | 0.1990 |
71
+ | 0.1919 | 3.4028 | 12257 | 0.2000 |
72
+ | 0.1917 | 3.6030 | 12978 | 0.1974 |
73
+ | 0.1893 | 3.8032 | 13699 | 0.1960 |
74
+ | 0.189 | 4.0033 | 14420 | 0.1947 |
75
+ | 0.1783 | 4.2035 | 15141 | 0.1881 |
76
+ | 0.1759 | 4.4037 | 15862 | 0.1905 |
77
+ | 0.1767 | 4.6038 | 16583 | 0.1871 |
78
+ | 0.1761 | 4.8040 | 17304 | 0.1867 |
79
+ | 0.1757 | 5.0042 | 18025 | 0.1866 |
80
+ | 0.1631 | 5.2043 | 18746 | 0.1840 |
81
+ | 0.1642 | 5.4045 | 19467 | 0.1840 |
82
+ | 0.1629 | 5.6047 | 20188 | 0.1791 |
83
+ | 0.1626 | 5.8048 | 20909 | 0.1781 |
84
+ | 0.1621 | 6.0050 | 21630 | 0.1761 |
85
+ | 0.1535 | 6.2052 | 22351 | 0.1774 |
86
+ | 0.1506 | 6.4053 | 23072 | 0.1769 |
87
+ | 0.1507 | 6.6055 | 23793 | 0.1700 |
88
+ | 0.1507 | 6.8057 | 24514 | 0.1722 |
89
+ | 0.1494 | 7.0058 | 25235 | 0.1688 |
90
+ | 0.141 | 7.2060 | 25956 | 0.1671 |
91
+ | 0.1404 | 7.4062 | 26677 | 0.1681 |
92
+ | 0.1388 | 7.6063 | 27398 | 0.1657 |
93
+ | 0.1368 | 7.8065 | 28119 | 0.1629 |
94
+ | 0.1365 | 8.0067 | 28840 | 0.1610 |
95
+ | 0.1238 | 8.2068 | 29561 | 0.1599 |
96
+ | 0.1253 | 8.4070 | 30282 | 0.1577 |
97
+ | 0.1253 | 8.6072 | 31003 | 0.1566 |
98
+ | 0.127 | 8.8073 | 31724 | 0.1567 |
99
+ | 0.124 | 9.0075 | 32445 | 0.1571 |
100
+ | 0.1119 | 9.2077 | 33166 | 0.1584 |
101
+ | 0.1113 | 9.4078 | 33887 | 0.1570 |
102
+ | 0.1125 | 9.6080 | 34608 | 0.1525 |
103
+ | 0.1121 | 9.8082 | 35329 | 0.1563 |
104
+ | 0.1121 | 10.0083 | 36050 | 0.1559 |
105
+ | 0.099 | 10.2085 | 36771 | 0.1581 |
106
+ | 0.0986 | 10.4087 | 37492 | 0.1541 |
107
+ | 0.0998 | 10.6088 | 38213 | 0.1531 |
108
+ | 0.0992 | 10.8090 | 38934 | 0.1530 |
109
+ | 0.0981 | 11.0092 | 39655 | 0.1546 |
110
+ | 0.0909 | 11.2093 | 40376 | 0.1566 |
111
+ | 0.0887 | 11.4095 | 41097 | 0.1568 |
112
+ | 0.0895 | 11.6097 | 41818 | 0.1546 |
113
+ | 0.0887 | 11.8098 | 42539 | 0.1551 |
114
 
115
 
116
  ### Framework versions
adapter_config.json CHANGED
@@ -23,8 +23,8 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "v_proj",
27
- "q_proj"
28
  ],
29
  "task_type": "CAUSAL_LM",
30
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "q_proj",
27
+ "v_proj"
28
  ],
29
  "task_type": "CAUSAL_LM",
30
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:220e8c00c48b4cb59c7d349ad11b5c557f50dd1e2d6bc49d7df4e877453ef585
3
  size 268677696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13f369622a592ae500dbcf03b53ffefd9c3c7d941367d2daf974b58fad4f52b
3
  size 268677696
loss_plot.png CHANGED
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:658e9bde5914223dc483e71520857b03713af3f7cb744fc63b91ccb9aa581280
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd1025e2e306f83be3e4a51e7de7823e85805b08b0ad0b293c890e47ed182c6
3
  size 5496