From 228420972ee0d0ab82e1221eb9bc5bf13afd5693 Mon Sep 17 00:00:00 2001
From: Wing Lian <wing.lian@gmail.com>
Date: Thu, 14 Sep 2023 11:17:47 -0400
Subject: [PATCH] Phi examples (#569)

* add phi full ft example

* Add readme to point out that deepspeed should be used

* zero1 is better than zero2 for phi
---
 examples/phi/README.md  |  7 ++++
 examples/phi/phi-ft.yml | 75 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+)
 create mode 100644 examples/phi/README.md
 create mode 100644 examples/phi/phi-ft.yml

diff --git a/examples/phi/README.md b/examples/phi/README.md
new file mode 100644
index 0000000000..6e12eec184
--- /dev/null
+++ b/examples/phi/README.md
@@ -0,0 +1,7 @@
+# Phi
+
+Due to some nuances with the phi code, please use deepspeed when training phi.
+
+```shell
+accelerate launch scripts/finetune.py examples/phi/phi-ft.yml --deepspeed deepspeed/zero1.json
+```
diff --git a/examples/phi/phi-ft.yml b/examples/phi/phi-ft.yml
new file mode 100644
index 0000000000..b5cde8139c
--- /dev/null
+++ b/examples/phi/phi-ft.yml
@@ -0,0 +1,75 @@
+base_model: microsoft/phi-1_5
+base_model_config: microsoft/phi-1_5
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+is_llama_derived_model: false
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: garage-bAInd/Open-Platypus
+    type: alpaca
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.05
+output_dir: ./phi-sft-out
+
+sequence_len: 2048
+sample_packing: false  # does not work with phi
+pad_to_sequence_len:
+
+adapter:
+lora_model_dir:
+lora_r:
+lora_alpha:
+lora_dropout:
+lora_target_linear:
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+adam_beta2: 0.95
+adam_epsilon: 0.00001
+max_grad_norm: 1.0
+lr_scheduler: cosine
+learning_rate: 0.000003
+
+train_on_inputs: false
+group_by_length: true
+bf16: true
+fp16: false
+tf32: true
+
+gradient_checkpointing:
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention:
+
+warmup_steps: 100
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+resize_token_embeddings_to_32x: true
+special_tokens:
+  bos_token: "<|endoftext|>"
+  eos_token: "<|endoftext|>"
+  unk_token: "<|endoftext|>"
+  pad_token: "<|endoftext|>"