Upload README.md with huggingface_hub

README.md

@@ -1,10 +1,10 @@
 ---
-language:
-- fi
-license: apache-2.0
 base_model: TurkuNLP/gpt3-finnish-xl
+license: apache-2.0
 datasets:
 - TurkuNLP/squad_v2_fi
+language:
+- fi
 pipeline_tag: text-generation
 ---
 
@@ -76,7 +76,7 @@ Use pipeline with task text-generation and the recommended format.
 
 ### Training Data
 
-Trained with 10000 random samples from test data in: [TurkuNLP/squad_v2_fi](https://huggingface.co/datasets/TurkuNLP/squad_v2_fi).
+Trained with 40000 random samples from test data in: [TurkuNLP/squad_v2_fi](https://huggingface.co/datasets/TurkuNLP/squad_v2_fi).
 
 ### Training Procedure
 
@@ -84,7 +84,7 @@ Training was done for 4-bit base model with supervised fine-tuning and Lora.
 
 #### Training Hyperparameters
 
-- **Training regime:** 4-bit, batch size 4, max steps 1000, data collator for completion only
+- **Training regime:** 4-bit, batch size 4, max steps 20000, data collator for completion only
 
 ## Evaluation
 
@@ -94,7 +94,7 @@ Evaluation has not been done properly yet.
 
 #### Testing Data
 
-Evaluated with 500 random samples from test data in: [TurkuNLP/squad_v2_fi](https://huggingface.co/datasets/TurkuNLP/squad_v2_fi).
+Evaluated with 1000 random samples from test data in: [TurkuNLP/squad_v2_fi](https://huggingface.co/datasets/TurkuNLP/squad_v2_fi).
 
 #### Factors