Update README.md

README.md

@@ -33,6 +33,11 @@ The following hyperparameters were used during training:
 - num_epochs: 1.0
 - mixed_precision_training: Native AMP
 
+### Training script
+
+CUDA_VISIBLE_DEVICES=0 python src/train_bash.py --stage sft --do_train True --model_name_or_path upstage/SOLAR-10.7B-v1.0 --template solar --finetuning_type lora --quantization_bit 4 --flash_attn True --dataset_dir data --dataset oncc_medqa_instruct --cutoff_len 1024 --learning_rate 0.0005 --num_train_epochs 1.0 --max_samples 5000 --per_device_train_batch_size 4 --gradient_accumulation_steps 4 --lr_scheduler_type cosine --max_grad_norm 1.0 --logging_steps 10 --save_steps 100 --warmup_steps 10 --neftune_noise_alpha 0.5 --lora_rank 8 --lora_dropout 0.2 --lora_target wqkv --output_dir /workspace/solar-10b-ocn-v1 --fp16 True --plot_loss True
+
+
 ### Framework versions
 
 - PEFT 0.8.2
@@ -54,3 +59,4 @@ hf (pretrained=upstage/SOLAR-10.7B-v1.0,peft=chenhugging/solar-10b-ocn-v1,trust_
 |ocn                  |Yaml   |none  |     0|acc     | 0.83|±  |0.0378|
 |aocnp                |Yaml   |none  |     0|acc     | 0.72|±  |0.0451|
 
+