Update README.md

README.md

@@ -47,50 +47,54 @@ pipe(text.split())
 ## Training
 The `mini-bart-g2p` model was trained on a combination of both the [Librispeech Alignments dataset](https://zenodo.org/records/2619474#.YuCdaC8r1ZF) and the [CMUDict dataset](https://github.com/cmusphinx/cmudict).
 The model was trained using the [translation training script](https://github.com/huggingface/transformers/blob/main/examples/pytorch/translation/run_translation.py) provided by HuggingFace Transformers repo. 
-The following parametrs were specified in the training script to produce the model.
-```
-python run_translation.py \
---model_name_or_path <MODEL DIR> \
---source_lang wrd \
---target_lang phon \
---num_train_epochs 500 \
---train_file <TRAIN SPLIT> \
---validation_file <VAL SPLIT> \
---test_file <TEST SPLIT> \
---num_beams 5 \
---generation_num_beams 5 \
---max_source_length 128 \
---max_target_length 128 \
---overwrite_cache \
---overwrite_output_dir \
---do_train \
---do_eval \
---do_predict \
---evaluation_strategy epoch \
---eval_delay 3 \
---save_strategy epoch \
---per_device_train_batch_size 16 \
---per_device_eval_batch_size 16 \
---learning_rate 5e-4 \
---label_smoothing_factor 0.1 \
---weight_decay 0.00001 \
---adam_beta1 0.9 \
---adam_beta2 0.98 \
---load_best_model_at_end True \
---predict_with_generate True \
---generation_max_length 20 \
---output_dir <OUTPUT DIR> \
---seed 4664427 \
---lr_scheduler_type cosine_with_restarts \
---warmup_steps 120000 \
---optim adafactor \
---group_by_length \
---metric_for_best_model bleu \
---greater_is_better True \
---save_total_limit 10 \
---log_level info \
---logging_steps 500
-```
+The following parameters were specified in the training script to produce the model.
+<details>
+<summary>Training script parameters</summary>
+
+  ```bash
+  python run_translation.py \
+  --model_name_or_path <MODEL DIR> \
+  --source_lang wrd \
+  --target_lang phon \
+  --num_train_epochs 500 \
+  --train_file <TRAIN SPLIT> \
+  --validation_file <VAL SPLIT> \
+  --test_file <TEST SPLIT> \
+  --num_beams 5 \
+  --generation_num_beams 5 \
+  --max_source_length 128 \
+  --max_target_length 128 \
+  --overwrite_cache \
+  --overwrite_output_dir \
+  --do_train \
+  --do_eval \
+  --do_predict \
+  --evaluation_strategy epoch \
+  --eval_delay 3 \
+  --save_strategy epoch \
+  --per_device_train_batch_size 16 \
+  --per_device_eval_batch_size 16 \
+  --learning_rate 5e-4 \
+  --label_smoothing_factor 0.1 \
+  --weight_decay 0.00001 \
+  --adam_beta1 0.9 \
+  --adam_beta2 0.98 \
+  --load_best_model_at_end True \
+  --predict_with_generate True \
+  --generation_max_length 20 \
+  --output_dir <OUTPUT DIR> \
+  --seed 4664427 \
+  --lr_scheduler_type cosine_with_restarts \
+  --warmup_steps 120000 \
+  --optim adafactor \
+  --group_by_length \
+  --metric_for_best_model bleu \
+  --greater_is_better True \
+  --save_total_limit 10 \
+  --log_level info \
+  --logging_steps 500
+  ```
+</details>
 
 
 ## Limitations