smohammadi commited on
Commit
e9e88bb
·
verified ·
1 Parent(s): abc6e1b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -24,7 +24,8 @@ More information needed
24
  This model was trained using the [torchtune](https://github.com/pytorch/torchtune) library using the following command:
25
 
26
  ```bash
27
- ppo_full_finetune_single_device.py --config ./target/7B_full_ppo_low_memory_single_device.yaml device=cuda metric_logger._component_=torchtune.utils.metric_logging.WandBLogger metric_logger.project=torchtune_ppo forward_batch_size=2 batch_size=64 ppo_batch_size=32 gradient_accumulation_steps=16 compile=True optimizer._component_=bitsandbytes.optim.PagedAdamW optimizer.lr=3e-4
 
28
  ```
29
 
30
 
 
24
  This model was trained using the [torchtune](https://github.com/pytorch/torchtune) library using the following command:
25
 
26
  ```bash
27
+ ppo_full_finetune_single_device.py --config \
28
+ ./target/7B_full_ppo_low_memory_single_device.yaml device=cuda metric_logger._component_=torchtune.utils.metric_logging.WandBLogger metric_logger.project=torchtune_ppo forward_batch_size=2 batch_size=64 ppo_batch_size=32 gradient_accumulation_steps=16 compile=True optimizer._component_=bitsandbytes.optim.PagedAdamW optimizer.lr=3e-4
29
  ```
30
 
31