make phi training work with Loras (#588)

* valdiation for phi loras

* fix model config class check

* update readme for phi traiing

examples/phi/README.md

@@ -1,7 +1,11 @@
 # Phi
 
-Due to some nuances with the phi code, please use deepspeed when training phi.
+Due to some nuances with the phi code, please use deepspeed when training phi for full finetune.
 
 ```shell
-accelerate launch scripts/finetune.py examples/phi/phi-ft.yml --deepspeed deepspeed/zero1.json
+accelerate launch -m axolotl.cli.train examples/phi/phi-ft.yml --deepspeed deepspeed/zero1.json
+
+# OR
+
+python -m axolotl.cli.train examples/phi/phi-qlora.yml
 ```

examples/phi/phi-qlora.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: true
+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: 1024
+sample_packing: false  # not CURRENTLY compatible with LoRAs
+pad_to_sequence_len:
+
+adapter: qlora
+lora_model_dir:
+lora_r: 64
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_torch
+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|>"