update example docs

Former-commit-id: 102cd42768d9eb2cf1219309a25b41e26149067e

examples/qlora_single_gpu/llama3_lora_sft_aqlm.yaml

@@ -1,27 +1,38 @@
+# model
+model_name_or_path: ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16
+
+# method
 stage: sft
 do_train: true
-model_name_or_path: BlackSamorez/Llama-2-7b-AQLM-2Bit-1x16-hf
-dataset: alpaca_gpt4_en,glaive_toolcall
-dataset_dir: data
-template: default
 finetuning_type: lora
 lora_target: q_proj,v_proj
-output_dir: ../../saves/LLaMA2-7B/lora/sft
-overwrite_cache: true
-overwrite_output_dir: true
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+template: llama3
 cutoff_len: 1024
-per_device_train_batch_size: 1
-per_device_eval_batch_size: 1
-gradient_accumulation_steps: 8
-lr_scheduler_type: cosine
-logging_steps: 10
-save_steps: 100
-eval_steps: 100
-evaluation_strategy: steps
-load_best_model_at_end: true
-learning_rate: 5e-5
-num_train_epochs: 3.0
-max_samples: 3000
+max_samples: 1000
 val_size: 0.1
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+# output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
 plot_loss: true
+overwrite_output_dir: true
+
+# train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
 fp16: true
+
+# eval
+per_device_eval_batch_size: 1
+evaluation_strategy: steps
+eval_steps: 500

examples/qlora_single_gpu/llama3_lora_sft_awq.yaml

@@ -0,0 +1,38 @@
+# model
+model_name_or_path: TechxGenus/Meta-Llama-3-8B-Instruct-AWQ
+
+# method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: q_proj,v_proj
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+val_size: 0.1
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+# output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+# train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+per_device_eval_batch_size: 1
+evaluation_strategy: steps
+eval_steps: 500

examples/qlora_single_gpu/llama3_lora_sft_bitsandbytes.yaml

@@ -0,0 +1,42 @@
+# model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+quantization_bit: 4
+
+# method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: q_proj,v_proj
+
+# ddp
+ddp_timeout: 180000000
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+val_size: 0.1
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+# output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+# train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+per_device_eval_batch_size: 1
+evaluation_strategy: steps
+eval_steps: 500

examples/qlora_single_gpu/llama3_lora_sft_gptq.yaml

@@ -0,0 +1,38 @@
+# model
+model_name_or_path: TechxGenus/Meta-Llama-3-8B-Instruct-GPTQ
+
+# method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: q_proj,v_proj
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+val_size: 0.1
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+# output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+# train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+per_device_eval_batch_size: 1
+evaluation_strategy: steps
+eval_steps: 500