Update README.md

README.md

@@ -112,4 +112,40 @@ for s in generation_output.sequences:
 
 ```
 
-# Training:
+# Training:
+
+## Dataset:
+
+- Jumtra/oasst1_ja
+
+- Jumtra/jglue_jsquads_with_input
+
+- Jumtra/dolly_oast_jglue_ja
+
+- Aruno/guanaco_jp
+
+- yahma/alpaca-cleaned
+
+- databricks/databricks-dolly-15k
+
+with about 750k entries, 2k entries used for evaluate process
+
+## Training setup
+
+I trained this model on an instance from **vast.ai**
+
+- 1 NVIDIA RTX 4090
+
+- 90 GB Storage
+
+- Time spend about 3 and a half days
+
+- use ```python export.py``` to merge weight
+
+- Training loss
+
+![training loss chart](image/W&B Chart 7_28_2023, 1_18_59 PM.png)
+
+- Eval loss chart
+
+![eval loss chart](image/W&B Chart 7_28_2023, 1_19_47 PM.png)