Hugging Face's logo

sharoz
/
codeparrot-small-custom-functions-dataset-python

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files Community
2
sharoz commited on
Commit
f1b51fe
·
1 Parent(s): ae353a5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +95 -0
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: codeparrot-small-custom-functions-dataset-python
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # codeparrot-small-custom-functions-dataset-python
14
+
15
+ This model is a fine-tuned version of [codeparrot/codeparrot-small](https://huggingface.co/codeparrot/codeparrot-small) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.4934
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 5
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 1.2357 | 0.12 | 1 | 0.9450 |
49
+ | 1.0585 | 0.25 | 2 | 0.8835 |
50
+ | 0.9853 | 0.38 | 3 | 0.8324 |
51
+ | 0.9877 | 0.5 | 4 | 0.7932 |
52
+ | 1.0075 | 0.62 | 5 | 0.7623 |
53
+ | 0.8744 | 0.75 | 6 | 0.7335 |
54
+ | 0.8627 | 0.88 | 7 | 0.7091 |
55
+ | 0.8615 | 1.0 | 8 | 0.6893 |
56
+ | 0.8016 | 1.12 | 9 | 0.6706 |
57
+ | 0.7458 | 1.25 | 10 | 0.6540 |
58
+ | 0.7335 | 1.38 | 11 | 0.6378 |
59
+ | 0.7754 | 1.5 | 12 | 0.6243 |
60
+ | 0.7684 | 1.62 | 13 | 0.6107 |
61
+ | 0.7335 | 1.75 | 14 | 0.5985 |
62
+ | 0.7418 | 1.88 | 15 | 0.5878 |
63
+ | 0.5644 | 2.0 | 16 | 0.5792 |
64
+ | 0.6464 | 2.12 | 17 | 0.5711 |
65
+ | 0.7304 | 2.25 | 18 | 0.5622 |
66
+ | 0.6848 | 2.38 | 19 | 0.5545 |
67
+ | 0.7221 | 2.5 | 20 | 0.5480 |
68
+ | 0.6053 | 2.62 | 21 | 0.5420 |
69
+ | 0.6168 | 2.75 | 22 | 0.5370 |
70
+ | 0.5823 | 2.88 | 23 | 0.5323 |
71
+ | 0.7512 | 3.0 | 24 | 0.5279 |
72
+ | 0.5745 | 3.12 | 25 | 0.5241 |
73
+ | 0.674 | 3.25 | 26 | 0.5202 |
74
+ | 0.5441 | 3.38 | 27 | 0.5167 |
75
+ | 0.6236 | 3.5 | 28 | 0.5134 |
76
+ | 0.6006 | 3.62 | 29 | 0.5102 |
77
+ | 0.6279 | 3.75 | 30 | 0.5072 |
78
+ | 0.6257 | 3.88 | 31 | 0.5046 |
79
+ | 0.5408 | 4.0 | 32 | 0.5025 |
80
+ | 0.5855 | 4.12 | 33 | 0.5004 |
81
+ | 0.594 | 4.25 | 34 | 0.4984 |
82
+ | 0.5985 | 4.38 | 35 | 0.4970 |
83
+ | 0.6279 | 4.5 | 36 | 0.4958 |
84
+ | 0.6151 | 4.62 | 37 | 0.4949 |
85
+ | 0.5629 | 4.75 | 38 | 0.4942 |
86
+ | 0.5148 | 4.88 | 39 | 0.4937 |
87
+ | 0.4823 | 5.0 | 40 | 0.4934 |
88
+
89
+
90
+ ### Framework versions
91
+
92
+ - Transformers 4.28.1
93
+ - Pytorch 2.0.0+cu118
94
+ - Datasets 2.12.0
95
+ - Tokenizers 0.13.3