From 5cd79f9cc957cf5648c6acd3e5d2b9bcd54fa0ae Mon Sep 17 00:00:00 2001
From: loubnabnl <loubnabenallal1999@gmail.com>
Date: Sat, 25 Mar 2023 02:12:45 +0000
Subject: [PATCH] add readme

---
 pii/ner/README.md | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
 create mode 100644 pii/ner/README.md

diff --git a/pii/ner/README.md b/pii/ner/README.md
new file mode 100644
index 0000000..c0c8685
--- /dev/null
+++ b/pii/ner/README.md
@@ -0,0 +1,14 @@
+# Fine-tuning Bigcode-Encoder on an NER task  for PII detection
+
+To run the training on all the dataset `bigcode/pii-full-ds`, use the following command: 
+```bash
+python -m torch.distributed.launch \
+        --nproc_per_node number_of_gpus train.py \
+        --dataset_name bigcode/pii-full-ds \
+        --debug \
+        --learning_rate 2e-5 \
+        --train_batch_size 8 \
+        --bf16 \
+        --add_not_curated
+```
+Note that we use a global batch size of 64 (8*8 GPUs). To use only curated dataset remove the flag `--add_not_curated`.
\ No newline at end of file