Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ja
|
| 4 |
+
base_model:
|
| 5 |
+
- microsoft/Phi-3.5-mini-instruct
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
## Base Model
|
| 9 |
+
- [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)
|
| 10 |
+
|
| 11 |
+
## Dataset
|
| 12 |
+
- [amazon-science/esci-data](https://github.com/amazon-science/esci-data)
|
| 13 |
+
- shopping_qeries_dataset_products.parquetの日本語データを使用（339,059件）
|
| 14 |
+
|
| 15 |
+
## Parameter
|
| 16 |
+
- learning_rate: 1e-6
|
| 17 |
+
- num_train_epochs: 10
|
| 18 |
+
- per_device_train_batch_size: 64
|
| 19 |
+
- per_device_eval_batch_size: 64
|
| 20 |
+
- gradient_accumulation_steps: 1
|