From ee76506a6edfb8a7db45d3e961a567f2573a5180 Mon Sep 17 00:00:00 2001
From: Wing Lian <wing.lian@gmail.com>
Date: Fri, 8 Mar 2024 11:59:19 -0500
Subject: [PATCH] add example yml

---
 examples/llama-2/qlora-fsdp.yml | 70 +++++++++++++++++++++++++++++++++
 1 file changed, 70 insertions(+)
 create mode 100644 examples/llama-2/qlora-fsdp.yml

diff --git a/examples/llama-2/qlora-fsdp.yml b/examples/llama-2/qlora-fsdp.yml
new file mode 100644
index 0000000000..da6c06020f
--- /dev/null
+++ b/examples/llama-2/qlora-fsdp.yml
@@ -0,0 +1,70 @@
+base_model: NousResearch/Llama-2-7b-hf
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: yahma/alpaca-cleaned
+    type: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.05
+output_dir: ./qlora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 512
+sample_packing: false
+pad_to_sequence_len: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 4
+num_epochs: 4
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.00001
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 4
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+  - full_shard
+fsdp_config:
+  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
+special_tokens: