Update README.md

README.md

@@ -10,7 +10,37 @@ GPT-CC-125M-Code-Search is a [GPT-Neo-125M model](https://huggingface.co/Eleuthe
 
 ## Training procedure
 
-The training script used to train this model can be found [here](https://github.com/ncoop57/gpt-code-clippy/blob/camera-ready/training/run_clm_apps.py).
+The training script used to train this model can be found [here](https://github.com/ncoop57/gpt-code-clippy/blob/camera-ready/training/run_clm_flax.py).
+
+```bash
+./run_clm_flax.py \
+    --output_dir $HOME/gpt-neo-125M-code-search-py \
+    --model_name_or_path="EleutherAI/gpt-neo-125M" \
+    --dataset_name code_search_net \
+    --dataset_config_name="python" \
+    --do_train --do_eval \
+    --block_size="512" \
+    --per_device_train_batch_size="32" \
+    --per_device_eval_batch_size="64" \
+    --preprocessing_num_workers="8" \
+    --learning_rate="1.2e-4" \
+    --num_train_epochs 20 \
+    --warmup_steps 3000 \
+    --adam_beta1="0.9" \
+    --adam_beta2="0.95" \
+    --weight_decay="0.1" \
+    --overwrite_output_dir \
+    --logging_steps="25" \
+    --eval_steps="500" \
+    --push_to_hub="False" \
+    --report_to="all" \
+    --dtype="bfloat16" \
+    --skip_memory_metrics="True" \
+    --save_steps="500" \
+    --save_total_limit 10 \
+    --report_to="wandb" \
+    --run_name="gpt-neo-125M-code-search-py"
+```
 
 ## Intended Use and Limitations