diff --git a/examples/roberta/README.finetune_custom_classification.md b/examples/roberta/README.finetune_custom_classification.md
new file mode 100644
index 0000000000..de3a4cc37a
--- /dev/null
+++ b/examples/roberta/README.finetune_custom_classification.md
@@ -0,0 +1,120 @@
+# RoBERTa fine-tuning on custom classification task (example IMDB)
+
+## 1) Get the data
+```
+wget http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz
+tar zxvf aclImdb_v1.tar.gz
+```
+
+## 2) Format data
+`IMDB` data has one data-sample in each file, below python code-snippet converts it one file for train and valid each for ease of processing.  
+```
+import argparse
+import os
+import random
+from glob import glob
+
+random.seed(0)
+
+def main(args):
+    for split in ['train', 'test']:
+        samples = []
+        for class_label in ['pos', 'neg']:
+            fnames = glob(os.path.join(args.datadir, split, class_label) + '/*.txt')
+            for fname in fnames:
+                with open(fname) as fin:
+                    line = fin.readline()
+                    samples.append((line, 1 if class_label == 'pos' else 0))
+        random.shuffle(samples)
+        out_fname = 'train' if split == 'train' else 'dev'
+        f1 = open(os.path.join(args.datadir, out_fname + '.input0'), 'w')
+        f2 = open(os.path.join(args.datadir, out_fname + '.label'), 'w')
+        for sample in samples:
+            f1.write(sample[0] + '\n')
+            f2.write(str(sample[1]) + '\n')
+        f1.close()
+        f2.close()
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--datadir', default='aclImdb')
+    args = parser.parse_args()
+    main(args)
+```
+
+## 3) BPE Encode
+Run `multiprocessing_bpe_encoder`, you can also do this in previous step for each sample but that might be slower.
+```
+# Download encoder.json and vocab.bpe
+wget -N 'https://dl.fbaipublicfiles.com/fairseq/gpt2_bpe/encoder.json'
+wget -N 'https://dl.fbaipublicfiles.com/fairseq/gpt2_bpe/vocab.bpe'
+
+for SPLIT in train dev;
+do
+  python -m examples.roberta.multiprocessing_bpe_encoder \
+  --encoder-json encoder.json \
+  --vocab-bpe vocab.bpe \
+  --inputs "aclImdb/$SPLIT.input0" \
+  --outputs "aclImdb/$SPLIT.input0.bpe" \
+  --workers 60 \
+  --keep-empty;
+done
+```
+
+
+## 4) Preprocess data
+
+```
+# Download fairseq dictionary.
+wget -N 'https://dl.fbaipublicfiles.com/fairseq/gpt2_bpe/dict.txt'  
+
+fairseq-preprocess \
+  --only-source \
+  --trainpref "aclImdb/train.input0.bpe" \
+  --validpref "aclImdb/dev.input0.bpe" \
+  --destdir "IMDB-bin/input0" \
+  --workers 60 \
+  --srcdict dict.txt;
+
+fairseq-preprocess \
+  --only-source \
+  --trainpref "aclImdb/train.label" \
+  --validpref "aclImdb/dev.label" \
+  --destdir "IMDB-bin/label" \
+  --workers 60;
+
+```
+
+## 5) Run Training
+
+```
+TOTAL_NUM_UPDATES=7812  # 10 epochs through IMDB for bsz 32
+WARMUP_UPDATES=469      # 6 percent of the number of updates
+LR=1e-05                # Peak LR for polynomial LR scheduler.
+NUM_CLASSES=2
+MAX_SENTENCES=8        # Batch size.
+
+CUDA_VISIBLE_DEVICES=0 python train.py IMDB-bin/ \
+--restore-file <roberta_large_absolute_path> \
+--max-positions 512 \
+--max-sentences $MAX_SENTENCES \
+--max-tokens 4400 \
+--task sentence_prediction \
+--reset-optimizer --reset-dataloader --reset-meters \
+--required-batch-size-multiple 1 \
+--init-token 0 --separator-token 2 \
+--arch roberta_large \
+--criterion sentence_prediction \
+--num-classes $NUM_CLASSES \
+--dropout 0.1 --attention-dropout 0.1 \
+--weight-decay 0.1 --optimizer adam --adam-betas "(0.9, 0.98)" --adam-eps 1e-06 \
+--clip-norm 0.0 \
+--lr-scheduler polynomial_decay --lr $LR --total-num-update $TOTAL_NUM_UPDATES --warmup-updates $WARMUP_UPDATES \
+--fp16 --fp16-init-scale 4 --threshold-loss-scale 1 --fp16-scale-window 128 \
+--max-epoch 10 \
+--best-checkpoint-metric accuracy --maximize-best-checkpoint-metric \
+--truncate-sequence \
+--update-freq 4;
+```
+Above will train with effective batch-size of `32`, tested on one `Nvidia V100 32gb`.
+Expected `best-validation-accuracy` after `10` epochs is `~96.5%`.
diff --git a/examples/roberta/README.md b/examples/roberta/README.md
index f8c3974bd5..989c9d750e 100644
--- a/examples/roberta/README.md
+++ b/examples/roberta/README.md
@@ -208,6 +208,9 @@ b) Above cmd-args and hyperparams are tested on one Nvidia `V100` GPU with `32gb
 
 c) All the settings in above table are suggested settings based on our hyperparam search within a fixed search space (for careful comparison across models). You might be able to find better metrics with wider hyperparam search.  
 
+## Fine-tuning on custom classification tasks
+[Example of fine-tuning Roberta on simple custom classification task](README.finetune_custom_classification.md)
+
 ## Pretraining using your own data
 
 You can use the [`masked_lm` task](/fairseq/tasks/masked_lm.py) to pretrain RoBERTa from scratch, or to continue pretraining RoBERTa starting from one of the released checkpoints.