Update README.md
Browse files
README.md
CHANGED
@@ -69,11 +69,11 @@ The model was trained on one A100 GPU with the following hyperparameters:
|
|
69 |
| `total_batch_size` | 256 (~130K tokens per step) |
|
70 |
| `num_epochs` | 4 |
|
71 |
|
72 |
-
More details about fine-tuning can be found in the technical report.
|
73 |
|
74 |
# Fine-tuning data
|
75 |
|
76 |
-
For tuning this model, we used 15K exmaples from the synthetically generated [Kotlin Exercices
|
77 |
|
78 |
# Evaluation
|
79 |
|
|
|
69 |
| `total_batch_size` | 256 (~130K tokens per step) |
|
70 |
| `num_epochs` | 4 |
|
71 |
|
72 |
+
More details about fine-tuning can be found in the technical report (coming soon).
|
73 |
|
74 |
# Fine-tuning data
|
75 |
|
76 |
+
For tuning this model, we used 15K exmaples from the synthetically generated [Kotlin Exercices](https://huggingface.co/datasets/JetBrains/KExercises) dataset. Every example follows the HumanEval format. In total, the dataset contains about 3.5M tokens.
|
77 |
|
78 |
# Evaluation
|
79 |
|