Hi all,
I am having an issue when running Peft LoRA with DeepSpeed Zero3.
Error:
ValueError: fp16 is enabled but the following parameters have dtype that is not fp16: base_model.model.gpt_neox.layers.0.attention.query_key_value.lora_A.weight,
base_model.model.gpt_neox.layers.0.attention.query_key_value.lora_B.weight, base_model.model.gpt_neox.layers.1.attention.query_key_value.lora_A.weight,
base_model.model.gpt_neox.layers.1.attention.query_key_value.lora_B.weight, base_model.model.gpt_neox.layers.2.attention.query_key_value.lora_A.weight,
base_model.model.gpt_neox.layers.2.attention.query_key_value.lora_B.weight, base_model.model.gpt_neox.layers.3.attention.query_key_value.lora_A.weight,
How to reproduce:
CLI:
deepspeed finetune_pythia.py --per_device_train_batch_size 1 --output_dir /home/training_scripts/pythia-1.4b --fp16 --deepspeed configs/ds_z3_config.json
Code:
from transformers import AutoTokenizer, GPTNeoXForCausalLM
from peft import get_peft_model, LoraConfig, TaskType
peft_config = LoraConfig(
task_type=TaskType.CAUSAL_LM,
inference_mode=False,
r=16,
lora_alpha=32,
lora_dropout=0.1,
)
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pythia-1.4b")
model = GPTNeoXForCausalLM.from_pretrained("EleutherAI/pythia-1.4b")
model = get_peft_model(model, peft_config)
model.print_trainable_parameters()
DeepSpeed Zero 3 config:
{
"fp16": {
"enabled": "auto",
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"optimizer": {
"type": "AdamW",
"params": {
"lr": "auto",
"betas": "auto",
"eps": "auto",
"weight_decay": "auto"
}
},
"scheduler": {
"type": "WarmupLR",
"params": {
"warmup_min_lr": "auto",
"warmup_max_lr": "auto",
"warmup_num_steps": "auto"
}
},
"zero_optimization": {
"stage": 3,
"offload_optimizer": {
"device": "cpu",
"pin_memory": true
},
"offload_param": {
"device": "cpu",
"pin_memory": true
},
"overlap_comm": true,
"contiguous_gradients": true,
"sub_group_size": 1e9,
"reduce_bucket_size": "auto",
"stage3_prefetch_bucket_size": "auto",
"stage3_param_persistence_threshold": "auto",
"stage3_max_live_parameters": 1e9,
"stage3_max_reuse_distance": 1e9,
"stage3_gather_16bit_weights_on_model_save": true
},
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"steps_per_print": 2000,
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"wall_clock_breakdown": false
}
Any help would be greatly appreciated.
Thank you,
Enrico