Hugging Face's logo

jlpan
/
starcoder-tune-cpp2py-snippet1

Generated from Trainer
Model card Files Community
jlpan commited on
Commit
ba9a718
•
1 Parent(s): ad6fd4f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -23
README.md CHANGED
@@ -6,7 +6,6 @@ tags:
6
  model-index:
7
  - name: starcoder-tune-cpp2py-snippet1
8
  results: []
9
- library_name: peft
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3914
20
 
21
  ## Model description
22
 
@@ -35,7 +34,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0003
39
  - train_batch_size: 1
40
  - eval_batch_size: 1
41
  - seed: 42
@@ -50,30 +49,20 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.7375 | 0.1 | 50 | 0.3869 |
54
- | 0.4809 | 0.2 | 100 | 0.3847 |
55
- | 0.4753 | 0.3 | 150 | 0.3898 |
56
- | 0.4472 | 0.4 | 200 | 0.3882 |
57
- | 0.4509 | 0.5 | 250 | 0.3938 |
58
- | 0.4369 | 0.6 | 300 | 0.3897 |
59
- | 0.432 | 0.7 | 350 | 0.3968 |
60
- | 0.4324 | 0.8 | 400 | 0.3917 |
61
- | 0.4219 | 0.9 | 450 | 0.3920 |
62
- | 0.4314 | 1.0 | 500 | 0.3914 |
63
 
64
 
65
  ### Framework versions
66
 
67
- - PEFT 0.5.0.dev0
68
- - PEFT 0.5.0.dev0
69
- - PEFT 0.5.0.dev0
70
- - PEFT 0.5.0.dev0
71
- - PEFT 0.5.0.dev0
72
- - PEFT 0.5.0.dev0
73
- - PEFT 0.5.0.dev0
74
- - PEFT 0.5.0.dev0
75
- - PEFT 0.5.0.dev0
76
- - PEFT 0.5.0.dev0
77
  - Transformers 4.32.0.dev0
78
  - Pytorch 2.0.1+cu117
79
  - Datasets 2.12.0
 
6
  model-index:
7
  - name: starcoder-tune-cpp2py-snippet1
8
  results: []
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
15
 
16
  This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.3488
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 8e-05
38
  - train_batch_size: 1
39
  - eval_batch_size: 1
40
  - seed: 42
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 0.8208 | 0.1 | 50 | 0.3781 |
53
+ | 0.4662 | 0.2 | 100 | 0.3514 |
54
+ | 0.4402 | 0.3 | 150 | 0.3529 |
55
+ | 0.4406 | 0.4 | 200 | 0.3492 |
56
+ | 0.432 | 0.5 | 250 | 0.3505 |
57
+ | 0.4205 | 0.6 | 300 | 0.3539 |
58
+ | 0.42 | 0.7 | 350 | 0.3504 |
59
+ | 0.4277 | 0.8 | 400 | 0.3480 |
60
+ | 0.4238 | 0.9 | 450 | 0.3491 |
61
+ | 0.4143 | 1.0 | 500 | 0.3488 |
62
 
63
 
64
  ### Framework versions
65
 
 
 
 
 
 
 
 
 
 
 
66
  - Transformers 4.32.0.dev0
67
  - Pytorch 2.0.1+cu117
68
  - Datasets 2.12.0