AI4PD
/

ZymCTRL

@@ -348,11 +348,11 @@ The command below shows an example at an specific learning rate,
 but you could try with other hyperparameters to obtain the best training and evaluation losses.
 ```
-python 5.run_clm-post.py --tokenizer_name /path/to/ZymCTRL
  --do_train --do_eval --output_dir output --evaluation_strategy steps --eval_steps 10
  --logging_steps 5 --save_steps 500 --num_train_epochs 28 --per_device_train_batch_size 1
  --per_device_eval_batch_size 4 --cache_dir '.' --save_total_limit 2 --learning_rate  0.8e-04
- --dataloader_drop_last True --model_name_or_path /path/to/ZymCTRL
 ```
 In any case, the original HuggingFace script run_clm.py can be found here:
 https://github.com/huggingface/transformers/blob/master/examples/pytorch/language-modeling/run_clm.py

 but you could try with other hyperparameters to obtain the best training and evaluation losses.
 ```
+python 5.run_clm-post.py --tokenizer_name AI4PD/ZymCTRL
  --do_train --do_eval --output_dir output --evaluation_strategy steps --eval_steps 10
  --logging_steps 5 --save_steps 500 --num_train_epochs 28 --per_device_train_batch_size 1
  --per_device_eval_batch_size 4 --cache_dir '.' --save_total_limit 2 --learning_rate  0.8e-04
+ --dataloader_drop_last True --model_name_or_path AI4PD/ZymCTRL
 ```
 In any case, the original HuggingFace script run_clm.py can be found here:
 https://github.com/huggingface/transformers/blob/master/examples/pytorch/language-modeling/run_clm.py