Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
yalhessi commited on
Commit
34bf20c
·
verified ·
1 Parent(s): 5f0cbba

End of training

Browse files
Files changed (5) hide show
  1. README.md +64 -34
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. loss_plot.png +0 -0
  5. training_args.bin +2 -2
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: 0.1511
20
 
21
  ## Model description
22
 
@@ -45,43 +45,73 @@ The following hyperparameters were used during training:
45
  - total_eval_batch_size: 16
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
- - num_epochs: 6
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss |
54
- |:-------------:|:-----:|:-----:|:---------------:|
55
- | 0.2738 | 0.2 | 3094 | 0.2743 |
56
- | 0.2543 | 0.4 | 6188 | 0.2529 |
57
- | 0.2473 | 0.6 | 9282 | 0.2452 |
58
- | 0.2395 | 0.8 | 12376 | 0.2414 |
59
- | 0.236 | 1.0 | 15470 | 0.2337 |
60
- | 0.227 | 1.2 | 18564 | 0.2317 |
61
- | 0.2256 | 1.4 | 21658 | 0.2184 |
62
- | 0.2178 | 1.6 | 24752 | 0.2154 |
63
- | 0.2172 | 1.8 | 27846 | 0.2153 |
64
- | 0.2107 | 2.0 | 30940 | 0.2135 |
65
- | 0.2048 | 2.2 | 34034 | 0.2110 |
66
- | 0.2022 | 2.4 | 37128 | 0.2038 |
67
- | 0.1967 | 2.6 | 40222 | 0.1990 |
68
- | 0.1947 | 2.8 | 43316 | 0.1957 |
69
- | 0.1923 | 3.0 | 46410 | 0.1944 |
70
- | 0.1841 | 3.2 | 49504 | 0.1878 |
71
- | 0.1831 | 3.4 | 52598 | 0.1876 |
72
- | 0.179 | 3.6 | 55692 | 0.1844 |
73
- | 0.1766 | 3.8 | 58786 | 0.1808 |
74
- | 0.1753 | 4.0 | 61880 | 0.1750 |
75
- | 0.1652 | 4.2 | 64974 | 0.1735 |
76
- | 0.1631 | 4.4 | 68068 | 0.1686 |
77
- | 0.1584 | 4.6 | 71162 | 0.1662 |
78
- | 0.1534 | 4.8 | 74256 | 0.1632 |
79
- | 0.1523 | 5.0 | 77350 | 0.1608 |
80
- | 0.1445 | 5.2 | 80444 | 0.1576 |
81
- | 0.1429 | 5.4 | 83538 | 0.1574 |
82
- | 0.1408 | 5.6 | 86632 | 0.1549 |
83
- | 0.1383 | 5.8 | 89726 | 0.1527 |
84
- | 0.1361 | 6.0 | 92820 | 0.1511 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
 
86
 
87
  ### 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: 0.1453
20
 
21
  ## Model description
22
 
 
45
  - total_eval_batch_size: 16
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 12
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:------:|:---------------:|
55
+ | 0.2767 | 0.2 | 3094 | 0.2776 |
56
+ | 0.2557 | 0.4 | 6188 | 0.2610 |
57
+ | 0.2507 | 0.6 | 9282 | 0.2532 |
58
+ | 0.2434 | 0.8 | 12376 | 0.2445 |
59
+ | 0.2395 | 1.0 | 15470 | 0.2353 |
60
+ | 0.2339 | 1.2 | 18564 | 0.2381 |
61
+ | 0.2332 | 1.4 | 21658 | 0.2260 |
62
+ | 0.2275 | 1.6 | 24752 | 0.2299 |
63
+ | 0.2298 | 1.8 | 27846 | 0.2205 |
64
+ | 0.2233 | 2.0 | 30940 | 0.2328 |
65
+ | 0.221 | 2.2 | 34034 | 0.2231 |
66
+ | 0.2201 | 2.4 | 37128 | 0.2136 |
67
+ | 0.2154 | 2.6 | 40222 | 0.2186 |
68
+ | 0.2152 | 2.8 | 43316 | 0.2148 |
69
+ | 0.2153 | 3.0 | 46410 | 0.2166 |
70
+ | 0.21 | 3.2 | 49504 | 0.2103 |
71
+ | 0.2094 | 3.4 | 52598 | 0.2103 |
72
+ | 0.2054 | 3.6 | 55692 | 0.2095 |
73
+ | 0.2046 | 3.8 | 58786 | 0.2053 |
74
+ | 0.2056 | 4.0 | 61880 | 0.2002 |
75
+ | 0.1989 | 4.2 | 64974 | 0.2069 |
76
+ | 0.1968 | 4.4 | 68068 | 0.1943 |
77
+ | 0.1948 | 4.6 | 71162 | 0.2035 |
78
+ | 0.1905 | 4.8 | 74256 | 0.1966 |
79
+ | 0.1909 | 5.0 | 77350 | 0.1933 |
80
+ | 0.1879 | 5.2 | 80444 | 0.1892 |
81
+ | 0.1877 | 5.4 | 83538 | 0.1933 |
82
+ | 0.186 | 5.6 | 86632 | 0.1895 |
83
+ | 0.1844 | 5.8 | 89726 | 0.1868 |
84
+ | 0.1815 | 6.0 | 92820 | 0.1869 |
85
+ | 0.1764 | 6.2 | 95914 | 0.1845 |
86
+ | 0.1764 | 6.4 | 99008 | 0.1874 |
87
+ | 0.1754 | 6.6 | 102102 | 0.1894 |
88
+ | 0.176 | 6.8 | 105196 | 0.1816 |
89
+ | 0.1724 | 7.0 | 108290 | 0.1799 |
90
+ | 0.1656 | 7.2 | 111384 | 0.1761 |
91
+ | 0.1637 | 7.4 | 114478 | 0.1751 |
92
+ | 0.1672 | 7.6 | 117572 | 0.1767 |
93
+ | 0.164 | 7.8 | 120666 | 0.1714 |
94
+ | 0.1637 | 8.0 | 123760 | 0.1714 |
95
+ | 0.1553 | 8.2 | 126854 | 0.1694 |
96
+ | 0.1538 | 8.4 | 129948 | 0.1700 |
97
+ | 0.1533 | 8.6 | 133042 | 0.1686 |
98
+ | 0.1561 | 8.8 | 136136 | 0.1641 |
99
+ | 0.1544 | 9.0 | 139230 | 0.1627 |
100
+ | 0.1457 | 9.2 | 142324 | 0.1582 |
101
+ | 0.1458 | 9.4 | 145418 | 0.1593 |
102
+ | 0.1447 | 9.6 | 148512 | 0.1590 |
103
+ | 0.1446 | 9.8 | 151606 | 0.1565 |
104
+ | 0.1405 | 10.0 | 154700 | 0.1557 |
105
+ | 0.1357 | 10.2 | 157794 | 0.1539 |
106
+ | 0.1338 | 10.4 | 160888 | 0.1528 |
107
+ | 0.1333 | 10.6 | 163982 | 0.1518 |
108
+ | 0.1319 | 10.8 | 167076 | 0.1509 |
109
+ | 0.1324 | 11.0 | 170170 | 0.1479 |
110
+ | 0.1264 | 11.2 | 173264 | 0.1487 |
111
+ | 0.1227 | 11.4 | 176358 | 0.1483 |
112
+ | 0.1234 | 11.6 | 179452 | 0.1458 |
113
+ | 0.1223 | 11.8 | 182546 | 0.1461 |
114
+ | 0.1226 | 12.0 | 185640 | 0.1453 |
115
 
116
 
117
  ### 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 sha256:55ed00ae722b9b8d87dedad60834b14e0735e50254f98e9349553453882d4074
3
  size 268636736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcefa9a05595c1552d61360f26bfd2ac55da7d452cfe6d1d3eaedccf59d3792d
3
  size 268636736
loss_plot.png CHANGED
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a3c5a4303b651a77e4529d53946154de2124ed20038489bebe7a7094e2d3e4a
3
- size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80ee36ab86eebcc1b99ff36929f1bb60e80bbda3f41a2652be0b3ed0cb48187
3
+ size 5496