环境
- MS:mindspore2.2.13
- CANN:7.0
- mindformers:
- version:1.0
- branch: 1.0
- tag:ac544ba7b4346700142c0cf4d0d73391d8548504
- npu: Ascend910A * 8
- config:
seed: 0
output_dir: './output' # path to save checkpoint/strategy
load_checkpoint: '/mnt/dataset/mindformers/research/pretrain/ckpt'
src_strategy_path_or_dir: ''
auto_trans_ckpt: True # If true, auto transform load_checkpoint to load in distributed model
only_save_strategy: False
resume_training: False
use_parallel: True
run_mode: 'finetune'
# trainer config
trainer:
type: CausalLanguageModelingTrainer
model_name: 'qwen2_7b'
# dataset
train_dataset: &train_dataset
data_loader:
type: MindDataset
dataset_dir: "/mnt/dataset/alpaca_ds/mindrecord/alpaca-messages.mindrecord"
shuffle: True
input_columns: ["input_ids", "target_ids", "attention_mask"]
num_parallel_workers: 8
python_multiprocessing: False
drop_remainder: True
batch_size: 2
repeat: 1
numa_enable: False
prefetch_size: 1
train_dataset_task:
type: CausalLanguageModelDataset
dataset_config: *train_dataset
# runner config
runner_config:
epochs: 5
batch_size: 2
sink_mode: True
sink_size: 2
runner_wrapper:
type: MFTrainOneStepCell
scale_sense:
type: DynamicLossScaleUpdateCell
loss_scale_value: 65536
scale_factor: 2
scale_window: 1000
use_clip_grad: True
# optimizer
optimizer:
type: FP32StateAdamWeightDecay
beta1: 0.9
beta2: 0.95
eps: 1.e-6
weight_decay: 0.1
# lr sechdule
lr_schedule:
type: CosineWithWarmUpLR
learning_rate: 8.e-4
lr_end: 3.e-5
warmup_ratio: 0.01
total_steps: -1 # -1 means it will load the total steps of the dataset
# callbacks
callbacks:
- type: MFLossMonitor
- type: CheckpointMointor
prefix: "qwen2"
save_checkpoint_steps: 10000
keep_checkpoint_max: 3
integrated_save: False
async_save: False
- type: ObsMonitor
# default parallel of device num = 8 for Atlas 800T A2
parallel_config:
data_parallel: 2
model_parallel: 4
pipeline_stage: 1
micro_batch_num: 4
vocab_emb_dp: True
gradient_aggregation_group: 4
# when model parallel is greater than 1, we can set micro_batch_interleave_num=2, that may accelerate the train process.
micro_batch_interleave_num: 1
# recompute config
recompute_config:
recompute: False
select_recompute: False
parallel_optimizer_comm_recompute: False
mp_comm_recompute: False
recompute_slice_activation: False
model:
model_config:
type: LlamaConfig
batch_size: 1
seq_length: 2048
hidden_size: 4096
num_layers: 32
num_heads: 32
vocab_size: 151936
intermediate_size: 11008
qkv_has_bias: True
rms_norm_eps: 1.0e-6
theta: 1000000.0
emb_dropout_prob: 0.0
eos_token_id: 151643
pad_token_id: 151643
bos_token_id: 151643
compute_dtype: "float16"
layernorm_compute_type: "float16"
softmax_compute_type: "float16"
rotary_dtype: "float16"
param_init_type: "float16"
use_past: True
use_flash_attention: False
use_paged_attention: False
# block_size: 16
# num_blocks: 512
use_past_shard: False
offset: 0
checkpoint_name_or_path: ""
repetition_penalty: 1
max_decode_length: 512
top_k: 0
top_p: 0.8
do_sample: False
pet_config:
pet_type: lora
# configuration of lora
lora_rank: 64
lora_alpha: 16
lora_dropout: 0.05
target_modules: '.*wq|.*wk|.*wv|.*wo|.*w1|.*w2|.*w3'
freeze_exclude: ["*wte*", "*lm_head*"]
# configuration items copied from Qwen
rotary_pct: 1.0
rotary_emb_base: 10000
kv_channels: 128
arch:
type: LlamaForCausalLM
processor:
return_tensors: ms
tokenizer:
model_max_length: 32768
vocab_file: "/mnt/dataset/mindformers/research/pretrain/vocab.json"
merges_file: "/mnt/dataset/mindformers/research/pretrain/merges.txt"
unk_token: "<|endoftext|>"
eos_token: "<|endoftext|>"
pad_token: "<|endoftext|>"
type: Qwen2Tokenizer
type: Qwen2Processor
# mindspore context init config
context:
mode: 0 #0--Graph Mode; 1--Pynative Mode
device_target: "Ascend"
enable_graph_kernel: False
graph_kernel_flags: "--disable_expand_ops=Softmax,Dropout --enable_parallel_fusion=true --reduce_fuse_depth=8 --enable_auto_tensor_inplace=true"
ascend_config:
precision_mode: "must_keep_origin_dtype"
max_call_depth: 10000
max_device_memory: "31GB"
save_graphs: False
save_graphs_path: "./graph"
device_id: 0
# parallel context config
parallel:
parallel_mode: 1 # 0-data parallel, 1-semi-auto parallel, 2-auto parallel, 3-hybrid parallel
gradients_mean: False
enable_alltoall: False
full_batch: True
search_mode: "sharding_propagation"
enable_parallel_optimizer: True
strategy_ckpt_config:
save_file: "./ckpt_strategy.ckpt"
only_trainable_params: False
parallel_optimizer_config:
gradient_accumulation_shard: False
parallel_optimizer_threshold: 64
、
问题描述
910A使用MindFormers1.0 跑qwen1_5 7b的lora微调报错,Cast failed, original value: 0.0883883, type: FP32Imm,如下:
File "/home/ma-user/anaconda3/envs/MindSpore/lib/python3.9/site-packages/mindspore/common/api.py", line 1547, in compile
result = self._graph_executor.compile(obj, args, kwargs, phase, self._use_vm_mode())
RuntimeError: Cast failed, original value: 0.0883883, type: FP32Imm
----------------------------------------------------
- Framework Unexpected Exception Raised:
----------------------------------------------------
This exception is caused by framework's unexpected error. Please create an issue at https://gitee.com/mindspore/mindspore/issues to get help.
----------------------------------------------------
- C++ Call Stack: (For framework developers)
----------------------------------------------------
mindspore/core/ir/anf.h:910 GetValue
[WARNING] MD(67780,ffffb77d0010,python):2024-05-11-03:04:21.629.364 [mindspore/ccsrc/minddata/dataset/engine/datasetops/data_queue_op.cc:163] ~DataQueueOp]
preprocess_batch: 100;
batch_queue: 1, 1, 1, 1, 1, 1, 1, 1, 1, 1;
解决办法
如下,配置文件修改项:
use_flash_attention: False
use_paged_attention: False