Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,17 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
# Model Card for GPT_2_CODE
|
5 |
-Goal is to create a small GPT2 python coder
|
@@ -71,17 +83,17 @@ Train/Val/Scheduler
|
|
71 |
More information needed
|
72 |
### Speeds, Sizes, Times
|
73 |
Epochs 3
|
74 |
-
flytech/python-codes-25k
|
75 |
Training Loss: 0.4007
|
76 |
Validation Loss: 0.5526
|
77 |
Epochs 3
|
78 |
|
79 |
# "espejelomar/code_search_net_python_10000_examples"
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
|
86 |
# Evaluation
|
87 |
Manual comparison with base model
|
@@ -117,4 +129,4 @@ CodeMonkeyXL
|
|
117 |
# Model Card Contact
|
118 |
K00B404 huggingface
|
119 |
# How to Get Started with the Model
|
120 |
-
Use the code below to get started with the model.
|
|
|
1 |
---
|
2 |
+
license: wtfpl
|
3 |
+
datasets:
|
4 |
+
- flytech/python-codes-25k
|
5 |
+
- espejelomar/code_search_net_python_10000_examples
|
6 |
+
language:
|
7 |
+
- en
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
library_name: transformers
|
11 |
+
pipeline_tag: text-generation
|
12 |
+
tags:
|
13 |
+
- code
|
14 |
+
- text-generation-inference
|
15 |
---
|
16 |
# Model Card for GPT_2_CODE
|
17 |
-Goal is to create a small GPT2 python coder
|
|
|
83 |
More information needed
|
84 |
### Speeds, Sizes, Times
|
85 |
Epochs 3
|
86 |
+
# "flytech/python-codes-25k"
|
87 |
Training Loss: 0.4007
|
88 |
Validation Loss: 0.5526
|
89 |
Epochs 3
|
90 |
|
91 |
# "espejelomar/code_search_net_python_10000_examples"
|
92 |
+
--Starting Loss: 2.0862
|
93 |
+
-Epoch 1/4 | Training Loss: 1.5355 | Validation Loss: 1.1723
|
94 |
+
-Epoch 2/4 | Training Loss: 1.0501 | Validation Loss: 1.0702
|
95 |
+
-Epoch 3/4 | Training Loss: 0.9804 | Validation Loss: 1.0798
|
96 |
+
-Epoch 4/4 | Training Loss: 0.9073 | Validation Loss: 1.0772
|
97 |
|
98 |
# Evaluation
|
99 |
Manual comparison with base model
|
|
|
129 |
# Model Card Contact
|
130 |
K00B404 huggingface
|
131 |
# How to Get Started with the Model
|
132 |
+
Use the code below to get started with the model.
|