rreit commited on
Commit
d568a3a
·
verified ·
1 Parent(s): b631ad4

Model save

Browse files
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama2
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: codellama/CodeLlama-13b-hf
7
+ model-index:
8
+ - name: codeLlama13B-StaproCoder
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
+ # codeLlama13B-StaproCoder
16
+
17
+ This model is a fine-tuned version of [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1794
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: 0.0005
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - training_steps: 2000
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 0.2404 | 0.05 | 100 | 0.2456 |
54
+ | 0.289 | 0.1 | 200 | 0.2349 |
55
+ | 0.236 | 0.15 | 300 | 0.2281 |
56
+ | 0.1928 | 0.2 | 400 | 0.2200 |
57
+ | 0.1999 | 0.25 | 500 | 0.2217 |
58
+ | 0.1697 | 0.3 | 600 | 0.2134 |
59
+ | 0.1825 | 0.35 | 700 | 0.2129 |
60
+ | 0.1904 | 0.4 | 800 | 0.2093 |
61
+ | 0.159 | 0.45 | 900 | 0.2054 |
62
+ | 0.1448 | 0.5 | 1000 | 0.1994 |
63
+ | 0.1993 | 0.55 | 1100 | 0.1954 |
64
+ | 0.2424 | 0.6 | 1200 | 0.1896 |
65
+ | 0.1385 | 0.65 | 1300 | 0.1891 |
66
+ | 0.1427 | 0.7 | 1400 | 0.1860 |
67
+ | 0.2021 | 0.75 | 1500 | 0.1836 |
68
+ | 0.1884 | 0.8 | 1600 | 0.1824 |
69
+ | 0.26 | 0.85 | 1700 | 0.1809 |
70
+ | 0.1641 | 0.9 | 1800 | 0.1799 |
71
+ | 0.1503 | 0.95 | 1900 | 0.1794 |
72
+ | 0.1613 | 1.0 | 2000 | 0.1794 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - PEFT 0.9.0
78
+ - Transformers 4.39.0.dev0
79
+ - Pytorch 2.2.1+cu121
80
+ - Datasets 2.17.1
81
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dc037700863aeae07b7259ecf51c571550730585f79bc1fc6e7f90026b7f802
3
  size 500770656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e9db7f958e1bc2ce744b3030197194db17eeb36c4075aadd66c8d0697ab9de3
3
  size 500770656
runs/Mar03_12-06-53_grace1/events.out.tfevents.1709464284.grace1.498559.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01863300d8254357c562ec195127c2a710de5faf5d76ed2ec87f01987a66a9c8
3
- size 90330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00dae5267cf96f47535b5b69a27875c157a4f6b96036d88962b0ee8ca5e6cb79
3
+ size 95175