Hugging Face's logo

jlpan
/
starcoder-finetuned-test_newProgram

Generated from Trainer
Model card Files Community
jlpan commited on
Commit
f9833ec
·
1 Parent(s): 8774e42

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -25
README.md CHANGED
@@ -6,7 +6,6 @@ tags:
6
  model-index:
7
  - name: starcoder-finetuned-test_newProgram
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: 0.1046
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: 8e-06
39
  - train_batch_size: 4
40
  - eval_batch_size: 4
41
  - seed: 42
@@ -43,37 +42,23 @@ The following hyperparameters were used during training:
43
  - total_train_batch_size: 32
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
- - lr_scheduler_warmup_steps: 80
47
- - training_steps: 800
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.1341 | 0.06 | 50 | 0.1215 |
54
- | 0.1238 | 0.12 | 100 | 0.1098 |
55
- | 0.1157 | 1.01 | 150 | 0.1077 |
56
- | 0.1147 | 1.07 | 200 | 0.1068 |
57
- | 0.1147 | 1.13 | 250 | 0.1062 |
58
- | 0.1123 | 2.01 | 300 | 0.1059 |
59
- | 0.1121 | 2.07 | 350 | 0.1055 |
60
- | 0.1126 | 2.14 | 400 | 0.1052 |
61
- | 0.1106 | 3.02 | 450 | 0.1051 |
62
- | 0.1109 | 3.08 | 500 | 0.1049 |
63
- | 0.1125 | 3.14 | 550 | 0.1048 |
64
- | 0.1103 | 4.02 | 600 | 0.1047 |
65
- | 0.1104 | 4.08 | 650 | 0.1047 |
66
- | 0.1118 | 4.15 | 700 | 0.1047 |
67
- | 0.1095 | 5.03 | 750 | 0.1047 |
68
- | 0.1107 | 5.09 | 800 | 0.1046 |
69
 
70
 
71
  ### Framework versions
72
 
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-finetuned-test_newProgram
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: 0.1121
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 3e-05
38
  - train_batch_size: 4
39
  - eval_batch_size: 4
40
  - seed: 42
 
42
  - total_train_batch_size: 32
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_steps: 15
46
+ - training_steps: 150
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 0.1365 | 0.17 | 25 | 0.1203 |
53
+ | 0.1261 | 0.33 | 50 | 0.1160 |
54
+ | 0.1215 | 0.5 | 75 | 0.1138 |
55
+ | 0.1215 | 0.67 | 100 | 0.1126 |
56
+ | 0.1194 | 0.83 | 125 | 0.1121 |
57
+ | 0.1167 | 1.03 | 150 | 0.1121 |
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
61
 
 
 
 
 
62
  - Transformers 4.32.0.dev0
63
  - Pytorch 2.0.1+cu117
64
  - Datasets 2.12.0