Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
yalhessi commited on
Commit
72a7437
·
verified ·
1 Parent(s): 16f5bf9

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 +2 -2
  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: 0.1979
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
- | 0.516 | 0.2002 | 721 | 0.3475 |
56
- | 0.3492 | 0.4003 | 1442 | 0.3040 |
57
- | 0.3089 | 0.6005 | 2163 | 0.3088 |
58
- | 0.3013 | 0.8007 | 2884 | 0.2717 |
59
- | 0.2873 | 1.0008 | 3605 | 0.2692 |
60
- | 0.2711 | 1.2010 | 4326 | 0.2625 |
61
- | 0.2674 | 1.4012 | 5047 | 0.2643 |
62
- | 0.2618 | 1.6013 | 5768 | 0.2565 |
63
- | 0.2631 | 1.8015 | 6489 | 0.2522 |
64
- | 0.2567 | 2.0017 | 7210 | 0.2511 |
65
- | 0.2488 | 2.2018 | 7931 | 0.2474 |
66
- | 0.2434 | 2.4020 | 8652 | 0.2439 |
67
- | 0.2416 | 2.6022 | 9373 | 0.2454 |
68
- | 0.2402 | 2.8023 | 10094 | 0.2400 |
69
- | 0.2393 | 3.0025 | 10815 | 0.2395 |
70
- | 0.225 | 3.2027 | 11536 | 0.2360 |
71
- | 0.2279 | 3.4028 | 12257 | 0.2329 |
72
- | 0.223 | 3.6030 | 12978 | 0.2299 |
73
- | 0.2222 | 3.8032 | 13699 | 0.2305 |
74
- | 0.2219 | 4.0033 | 14420 | 0.2261 |
75
- | 0.2088 | 4.2035 | 15141 | 0.2215 |
76
- | 0.2085 | 4.4037 | 15862 | 0.2218 |
77
- | 0.2096 | 4.6038 | 16583 | 0.2180 |
78
- | 0.2072 | 4.8040 | 17304 | 0.2144 |
79
- | 0.2047 | 5.0042 | 18025 | 0.2154 |
80
- | 0.1923 | 5.2043 | 18746 | 0.2197 |
81
- | 0.1947 | 5.4045 | 19467 | 0.2124 |
82
- | 0.193 | 5.6047 | 20188 | 0.2095 |
83
- | 0.1935 | 5.8048 | 20909 | 0.2118 |
84
- | 0.1924 | 6.0050 | 21630 | 0.2062 |
85
- | 0.1834 | 6.2052 | 22351 | 0.2031 |
86
- | 0.1811 | 6.4053 | 23072 | 0.2063 |
87
- | 0.179 | 6.6055 | 23793 | 0.2031 |
88
- | 0.18 | 6.8057 | 24514 | 0.2017 |
89
- | 0.1768 | 7.0058 | 25235 | 0.2045 |
90
- | 0.1682 | 7.2060 | 25956 | 0.1976 |
91
- | 0.1673 | 7.4062 | 26677 | 0.1954 |
92
- | 0.166 | 7.6063 | 27398 | 0.1953 |
93
- | 0.1637 | 7.8065 | 28119 | 0.1954 |
94
- | 0.1637 | 8.0067 | 28840 | 0.1896 |
95
- | 0.1489 | 8.2068 | 29561 | 0.1918 |
96
- | 0.1511 | 8.4070 | 30282 | 0.1894 |
97
- | 0.1513 | 8.6072 | 31003 | 0.1877 |
98
- | 0.1495 | 8.8073 | 31724 | 0.1924 |
99
- | 0.1486 | 9.0075 | 32445 | 0.1935 |
100
- | 0.1352 | 9.2077 | 33166 | 0.1928 |
101
- | 0.1356 | 9.4078 | 33887 | 0.1896 |
102
- | 0.1347 | 9.6080 | 34608 | 0.1865 |
103
- | 0.1356 | 9.8082 | 35329 | 0.1867 |
104
- | 0.1346 | 10.0083 | 36050 | 0.1889 |
105
- | 0.119 | 10.2085 | 36771 | 0.1927 |
106
- | 0.1184 | 10.4087 | 37492 | 0.1933 |
107
- | 0.1203 | 10.6088 | 38213 | 0.1937 |
108
- | 0.1211 | 10.8090 | 38934 | 0.1895 |
109
- | 0.1198 | 11.0092 | 39655 | 0.1937 |
110
- | 0.1102 | 11.2093 | 40376 | 0.1975 |
111
- | 0.1086 | 11.4095 | 41097 | 0.2016 |
112
- | 0.1086 | 11.6097 | 41818 | 0.1994 |
113
- | 0.108 | 11.8098 | 42539 | 0.1979 |
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: 0.1520
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.428 | 0.2002 | 721 | 0.3134 |
56
+ | 0.308 | 0.4003 | 1442 | 0.2745 |
57
+ | 0.2674 | 0.6005 | 2163 | 0.2665 |
58
+ | 0.2618 | 0.8007 | 2884 | 0.2526 |
59
+ | 0.2488 | 1.0008 | 3605 | 0.2386 |
60
+ | 0.2333 | 1.2010 | 4326 | 0.2362 |
61
+ | 0.2308 | 1.4012 | 5047 | 0.2231 |
62
+ | 0.2254 | 1.6013 | 5768 | 0.2292 |
63
+ | 0.2238 | 1.8015 | 6489 | 0.2197 |
64
+ | 0.219 | 2.0017 | 7210 | 0.2146 |
65
+ | 0.2096 | 2.2018 | 7931 | 0.2149 |
66
+ | 0.2078 | 2.4020 | 8652 | 0.2135 |
67
+ | 0.2047 | 2.6022 | 9373 | 0.2064 |
68
+ | 0.2033 | 2.8023 | 10094 | 0.2077 |
69
+ | 0.2016 | 3.0025 | 10815 | 0.1990 |
70
+ | 0.1912 | 3.2027 | 11536 | 0.2029 |
71
+ | 0.1889 | 3.4028 | 12257 | 0.1974 |
72
+ | 0.187 | 3.6030 | 12978 | 0.1986 |
73
+ | 0.1861 | 3.8032 | 13699 | 0.1946 |
74
+ | 0.1854 | 4.0033 | 14420 | 0.1931 |
75
+ | 0.1754 | 4.2035 | 15141 | 0.1851 |
76
+ | 0.1752 | 4.4037 | 15862 | 0.1863 |
77
+ | 0.1731 | 4.6038 | 16583 | 0.1875 |
78
+ | 0.1747 | 4.8040 | 17304 | 0.1848 |
79
+ | 0.1725 | 5.0042 | 18025 | 0.1823 |
80
+ | 0.1606 | 5.2043 | 18746 | 0.1818 |
81
+ | 0.1606 | 5.4045 | 19467 | 0.1817 |
82
+ | 0.1599 | 5.6047 | 20188 | 0.1791 |
83
+ | 0.1609 | 5.8048 | 20909 | 0.1759 |
84
+ | 0.1583 | 6.0050 | 21630 | 0.1764 |
85
+ | 0.1507 | 6.2052 | 22351 | 0.1741 |
86
+ | 0.1489 | 6.4053 | 23072 | 0.1730 |
87
+ | 0.1479 | 6.6055 | 23793 | 0.1693 |
88
+ | 0.148 | 6.8057 | 24514 | 0.1691 |
89
+ | 0.1472 | 7.0058 | 25235 | 0.1664 |
90
+ | 0.139 | 7.2060 | 25956 | 0.1653 |
91
+ | 0.1376 | 7.4062 | 26677 | 0.1633 |
92
+ | 0.1358 | 7.6063 | 27398 | 0.1627 |
93
+ | 0.134 | 7.8065 | 28119 | 0.1625 |
94
+ | 0.1341 | 8.0067 | 28840 | 0.1630 |
95
+ | 0.1212 | 8.2068 | 29561 | 0.1612 |
96
+ | 0.1235 | 8.4070 | 30282 | 0.1598 |
97
+ | 0.1227 | 8.6072 | 31003 | 0.1568 |
98
+ | 0.1224 | 8.8073 | 31724 | 0.1543 |
99
+ | 0.122 | 9.0075 | 32445 | 0.1548 |
100
+ | 0.1094 | 9.2077 | 33166 | 0.1557 |
101
+ | 0.1087 | 9.4078 | 33887 | 0.1512 |
102
+ | 0.1095 | 9.6080 | 34608 | 0.1530 |
103
+ | 0.1088 | 9.8082 | 35329 | 0.1516 |
104
+ | 0.1103 | 10.0083 | 36050 | 0.1523 |
105
+ | 0.0967 | 10.2085 | 36771 | 0.1581 |
106
+ | 0.0958 | 10.4087 | 37492 | 0.1528 |
107
+ | 0.0969 | 10.6088 | 38213 | 0.1526 |
108
+ | 0.0964 | 10.8090 | 38934 | 0.1526 |
109
+ | 0.0953 | 11.0092 | 39655 | 0.1528 |
110
+ | 0.088 | 11.2093 | 40376 | 0.1560 |
111
+ | 0.0857 | 11.4095 | 41097 | 0.1546 |
112
+ | 0.0862 | 11.6097 | 41818 | 0.1547 |
113
+ | 0.0864 | 11.8098 | 42539 | 0.1520 |
114
 
115
 
116
  ### Framework versions
adapter_config.json CHANGED
@@ -23,8 +23,8 @@
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,
 
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,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3814a678e5cbed915bca029edb3b18564a68b340707b3e579d1df0014861feb1
3
- size 268661312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b868037fd4d5dc2953954fa4cf77099051daabef4e324ba980797ea53c9cc8a
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:b5d7753fa4e712fc4eacfab01afe4c73230b4b8a7c095438906ef8312956f9e6
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc294184d1bae8414f2ffe8737b9e35b4f59b5f51c0896059b0f14c5b55f3fe5
3
  size 5496