Link the dataset mparts/CODer-aigcodeset
Browse files
README.md
CHANGED
|
@@ -4,6 +4,7 @@ base_model: microsoft/unixcoder-base
|
|
| 4 |
library_name: transformers
|
| 5 |
pipeline_tag: text-classification
|
| 6 |
datasets:
|
|
|
|
| 7 |
- basakdemirok/AIGCodeSet
|
| 8 |
tags:
|
| 9 |
- code
|
|
@@ -42,7 +43,7 @@ The models were trained on whitespace-normalised code (line endings unified, tab
|
|
| 42 |
|
| 43 |
## Training
|
| 44 |
|
| 45 |
-
Fine-tuned on the train split of the repository's problem-grouped split of AIGCodeSet, in which no programming problem is shared between train, dev and test: 4 epochs, learning rate 2e-5, batch size 16, max length 256, weight decay 0.01, warmup ratio 0.1. The saved weights are from the epoch with the best dev macro-F1.
|
| 46 |
|
| 47 |
## Limitations
|
| 48 |
|
|
|
|
| 4 |
library_name: transformers
|
| 5 |
pipeline_tag: text-classification
|
| 6 |
datasets:
|
| 7 |
+
- mparts/CODer-aigcodeset
|
| 8 |
- basakdemirok/AIGCodeSet
|
| 9 |
tags:
|
| 10 |
- code
|
|
|
|
| 43 |
|
| 44 |
## Training
|
| 45 |
|
| 46 |
+
Fine-tuned on the train split of [mparts/CODer-aigcodeset](https://huggingface.co/datasets/mparts/CODer-aigcodeset), the repository's problem-grouped split of AIGCodeSet, in which no programming problem is shared between train, dev and test (rows flagged `conflict` dropped): 4 epochs, learning rate 2e-5, batch size 16, max length 256, weight decay 0.01, warmup ratio 0.1. The saved weights are from the epoch with the best dev macro-F1.
|
| 47 |
|
| 48 |
## Limitations
|
| 49 |
|