yalhessi commited on
Commit
e6dfd35
·
verified ·
1 Parent(s): 59869d0

End of training

Browse files
Files changed (1) hide show
  1. README.md +123 -0
README.md ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: deepseek-ai/deepseek-coder-6.7b-base
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: lemexp-task1-v3-template_full-deepseek-coder-6.7b-base
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # lemexp-task1-v3-template_full-deepseek-coder-6.7b-base
16
+
17
+ This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0906
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0004
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 16
46
+ - total_eval_batch_size: 8
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 12
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:-------:|:------:|:---------------:|
56
+ | 0.3446 | 0.2000 | 3114 | 0.1641 |
57
+ | 0.305 | 0.4000 | 6228 | 0.1487 |
58
+ | 0.2848 | 0.6000 | 9342 | 0.1397 |
59
+ | 0.2755 | 0.8001 | 12456 | 0.1333 |
60
+ | 0.2646 | 1.0001 | 15570 | 0.1328 |
61
+ | 0.2486 | 1.2001 | 18684 | 0.1218 |
62
+ | 0.2438 | 1.4001 | 21798 | 0.1231 |
63
+ | 0.2413 | 1.6001 | 24912 | 0.1177 |
64
+ | 0.2375 | 1.8001 | 28026 | 0.1173 |
65
+ | 0.2326 | 2.0001 | 31140 | 0.1166 |
66
+ | 0.2178 | 2.2001 | 34254 | 0.1147 |
67
+ | 0.2187 | 2.4002 | 37368 | 0.1126 |
68
+ | 0.2196 | 2.6002 | 40482 | 0.1110 |
69
+ | 0.2163 | 2.8002 | 43596 | 0.1093 |
70
+ | 0.2101 | 3.0002 | 46710 | 0.1079 |
71
+ | 0.199 | 3.2002 | 49824 | 0.1073 |
72
+ | 0.2002 | 3.4002 | 52938 | 0.1073 |
73
+ | 0.1985 | 3.6002 | 56052 | 0.1070 |
74
+ | 0.1966 | 3.8002 | 59166 | 0.1017 |
75
+ | 0.197 | 4.0003 | 62280 | 0.1033 |
76
+ | 0.1819 | 4.2003 | 65394 | 0.1020 |
77
+ | 0.1835 | 4.4003 | 68508 | 0.1000 |
78
+ | 0.181 | 4.6003 | 71622 | 0.1032 |
79
+ | 0.1808 | 4.8003 | 74736 | 0.0971 |
80
+ | 0.1802 | 5.0003 | 77850 | 0.0960 |
81
+ | 0.1663 | 5.2003 | 80964 | 0.0967 |
82
+ | 0.1687 | 5.4003 | 84078 | 0.0966 |
83
+ | 0.1694 | 5.6004 | 87192 | 0.0958 |
84
+ | 0.1654 | 5.8004 | 90306 | 0.0933 |
85
+ | 0.167 | 6.0004 | 93420 | 0.0910 |
86
+ | 0.1528 | 6.2004 | 96534 | 0.0927 |
87
+ | 0.1534 | 6.4004 | 99648 | 0.0934 |
88
+ | 0.1542 | 6.6004 | 102762 | 0.0925 |
89
+ | 0.1519 | 6.8004 | 105876 | 0.0921 |
90
+ | 0.1546 | 7.0004 | 108990 | 0.0888 |
91
+ | 0.139 | 7.2005 | 112104 | 0.0926 |
92
+ | 0.1365 | 7.4005 | 115218 | 0.0882 |
93
+ | 0.1387 | 7.6005 | 118332 | 0.0874 |
94
+ | 0.1366 | 7.8005 | 121446 | 0.0848 |
95
+ | 0.1361 | 8.0005 | 124560 | 0.0867 |
96
+ | 0.1225 | 8.2005 | 127674 | 0.0887 |
97
+ | 0.123 | 8.4005 | 130788 | 0.0867 |
98
+ | 0.1254 | 8.6006 | 133902 | 0.0871 |
99
+ | 0.1259 | 8.8006 | 137016 | 0.0865 |
100
+ | 0.1205 | 9.0006 | 140130 | 0.0842 |
101
+ | 0.1064 | 9.2006 | 143244 | 0.0890 |
102
+ | 0.1071 | 9.4006 | 146358 | 0.0865 |
103
+ | 0.109 | 9.6006 | 149472 | 0.0853 |
104
+ | 0.1087 | 9.8006 | 152586 | 0.0844 |
105
+ | 0.1066 | 10.0006 | 155700 | 0.0846 |
106
+ | 0.0938 | 10.2007 | 158814 | 0.0877 |
107
+ | 0.0936 | 10.4007 | 161928 | 0.0892 |
108
+ | 0.0961 | 10.6007 | 165042 | 0.0880 |
109
+ | 0.0923 | 10.8007 | 168156 | 0.0882 |
110
+ | 0.0924 | 11.0007 | 171270 | 0.0863 |
111
+ | 0.082 | 11.2007 | 174384 | 0.0897 |
112
+ | 0.0828 | 11.4007 | 177498 | 0.0928 |
113
+ | 0.0799 | 11.6007 | 180612 | 0.0909 |
114
+ | 0.0823 | 11.8008 | 183726 | 0.0906 |
115
+
116
+
117
+ ### Framework versions
118
+
119
+ - PEFT 0.14.0
120
+ - Transformers 4.47.0
121
+ - Pytorch 2.5.1+cu124
122
+ - Datasets 3.2.0
123
+ - Tokenizers 0.21.1