mindspore-Ecosystem
/
mindspore
21
0
Fork 27
Code Issues Pull Requests 6 Projects Releases Wiki Activity

fix bug and update readme

This commit is contained in:
w00517672 2021-02-02 19:09:26 +08:00
parent ae39553df1
commit 0b4b7dfab0
6 changed files with 58 additions and 93 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

70
model_zoo/research/nlp/ternarybert/README.md
View File

@ -80,7 +80,7 @@ Before running the shell script, please set the `task_name`, `model_dir` and `da
```text
.
└─bert
└─ternarybert
├─README.md
├─scripts
├─run_train.sh # shell script for training phase
@ -106,26 +106,12 @@ Before running the shell script, please set the `task_name`, `model_dir` and `da
```text
usage: train.py [--h]
[--device_target {GPU,Ascend}]
[--do_eval {true,false}]
[--epoch_size EPOCH_SIZE]
[--device_id DEVICE_ID]
[--do_shuffle {true,false}]
[--enable_data_sink {true,false}]
[--save_ckpt_step SAVE_CKPT_STEP]
[--eval_ckpt_step EVAL_CKPT_STEP]
[--max_ckpt_num MAX_CKPT_NUM]
[--data_sink_steps DATA_SINK_STEPS]
[--teacher_model_dir TEACHER_MODEL_DIR]
[--student_model_dir STUDENT_MODEL_DIR]
[--data_dir DATA_DIR]
[--output_dir OUTPUT_DIR]
[--task_name {sts-b,qnli,mnli}]
[--dataset_type DATASET_TYPE]
[--seed SEED]
[--train_batch_size TRAIN_BATCH_SIZE]
[--eval_batch_size EVAL_BATCH_SIZE]
usage: train.py [--h] [--device_target {GPU,Ascend}] [--do_eval {true,false}] [--epoch_size EPOCH_SIZE]
[--device_id DEVICE_ID] [--do_shuffle {true,false}] [--enable_data_sink {true,false}] [--save_ckpt_step SAVE_CKPT_STEP]
[--eval_ckpt_step EVAL_CKPT_STEP] [--max_ckpt_num MAX_CKPT_NUM] [--data_sink_steps DATA_SINK_STEPS]
[--teacher_model_dir TEACHER_MODEL_DIR] [--student_model_dir STUDENT_MODEL_DIR] [--data_dir DATA_DIR]
[--output_dir OUTPUT_DIR] [--task_name {sts-b,qnli,mnli}] [--dataset_type DATASET_TYPE] [--seed SEED]
[--train_batch_size TRAIN_BATCH_SIZE] [--eval_batch_size EVAL_BATCH_SIZE]
options:
--device_target Device where the code will be implemented: "GPU" | "Ascend", default is "GPU"
@ -154,14 +140,8 @@ options:
```text
usage: eval.py [--h]
[--device_target {GPU,Ascend}]
[--device_id DEVICE_ID]
[--model_dir MODEL_DIR]
[--data_dir DATA_DIR]
[--task_name {sts-b,qnli,mnli}]
[--dataset_type DATASET_TYPE]
[--batch_size BATCH_SIZE]
usage: eval.py [--h] [--device_target {GPU,Ascend}] [--device_id DEVICE_ID] [--model_dir MODEL_DIR] [--data_dir DATA_DIR]
[--task_name {sts-b,qnli,mnli}] [--dataset_type DATASET_TYPE] [--batch_size BATCH_SIZE]
options:
--device_target Device where the code will be implemented: "GPU" | "Ascend", default is "GPU"
@ -205,7 +185,7 @@ Parameters for eval:
Parameters for teacher bert network:
seq_length length of input sequence: N, default is 128
vocab_size size of each embedding vector: N, must be consistant with the dataset you use. Default is 30522
vocab_size size of each embedding vector: N, must be consistent with the dataset you use. Default is 30522
hidden_size size of bert encoder layers: N
num_hidden_layers number of hidden layers: N
num_attention_heads number of attention heads: N, default is 12
@ -224,7 +204,7 @@ Parameters for teacher bert network:
Parameters for student bert network:
seq_length length of input sequence: N, default is 128
vocab_size size of each embedding vector: N, must be consistant with the dataset you use. Default is 30522
vocab_size size of each embedding vector: N, must be consistent with the dataset you use. Default is 30522
hidden_size size of bert encoder layers: N
num_hidden_layers number of hidden layers: N
num_attention_heads number of attention heads: N, default is 12
@ -348,7 +328,7 @@ eval step: 0, Accuracy: 90.625
eval step: 1, Accuracy: 81.25
eval step: 2, Accuracy: 79.16666666666666
...
The best Accuracy: 83.70860927152319
The best Accuracy: 83.58388835685436
```
@ -362,27 +342,13 @@ The best Accuracy: 83.70860927152319
| ----------------- | :---------------------------------------------------- |
| Model Version | TernaryBERT |
| Resource | NV SMX2 V100-32G |
| uploaded Date | 08/20/2020 |
| uploaded Date | 02/01/2020 |
| MindSpore Version | 1.1.0 |
| Dataset | STS-B, QNLI, MNLI |
| batch_size | 16, 16, 16 |
| Metric value | 87.58388835685437, 90.426505583013, 83.70860927152319 |
| Speed | |
| Total time | |
### Inference Performance
| Parameters | GPU |
| ----------------- | :---------------------------------------------------- |
| Model Version | TernaryBERT |
| Resource | NV SMX2 V100-32G |
| uploaded Date | 08/20/2020 |
| MindSpore Version | 1.1.0 |
| Dataset | STS-B, QNLI, MNLI |
| batch_size | 32, 32, 32 |
| Accuracy | 87.58388835685437, 90.426505583013, 83.70860927152319 |
| Speed | |
| Total time | |
| Dataset | STS-B |
| batch_size | 16 |
| Metric value | 87.5839 |
| Speed | 0.19s/step |
| Total time | 6.7min(3epoch, 1p) |
# [Description of Random Situation](#contents)

4
model_zoo/research/nlp/ternarybert/eval.py
View File

@ -20,7 +20,7 @@ import re
import argparse
from mindspore import context
from mindspore.train.serialization import load_checkpoint, load_param_into_net
from src.dataset import create_tinybert_dataset
from src.dataset import create_dataset
from src.config import eval_cfg, student_net_cfg, task_cfg
from src.tinybert_model import BertModelCLS
@ -66,7 +66,7 @@ def do_eval_standalone(args_opt):
context.set_context(mode=context.GRAPH_MODE, device_target=args_opt.device_target, device_id=args.device_id)
eval_dataset = create_tinybert_dataset(batch_size=eval_cfg.batch_size,
eval_dataset = create_dataset(batch_size=eval_cfg.batch_size,
device_num=1,
rank=0,
do_shuffle='false',

12
model_zoo/research/nlp/ternarybert/src/cell_wrapper.py
View File

@ -313,7 +313,7 @@ class BertNetworkWithLoss(nn.Cell):
class BertTrainWithLossScaleCell(nn.Cell):
"""
Especifically defined for finetuning where only four inputs tensor are needed.
Specifically defined for finetuning where only four inputs tensor are needed.
"""
def __init__(self, network, optimizer, scale_update_cell=None):
super(BertTrainWithLossScaleCell, self).__init__(auto_prefix=False)
@ -333,6 +333,8 @@ class BertTrainWithLossScaleCell(nn.Cell):
if self.reducer_flag:
self.degree = get_group_size()
self.grad_reducer = DistributedGradReducer(optimizer.parameters, False, self.degree)
self.clip_type = gradient_cfg.clip_type
self.clip_value = gradient_cfg.clip_value
self.is_distributed = (self.parallel_mode != ParallelMode.STAND_ALONE)
self.cast = P.Cast()
self.alloc_status = P.NPUAllocFloatStatus()
@ -410,7 +412,7 @@ class BertTrainWithLossScaleCell(nn.Cell):
# apply grad reducer on grads
grads = self.grad_reducer(grads)
grads = self.hyper_map(F.partial(grad_scale, scaling_sens * self.degree), grads)
grads = self.hyper_map(F.partial(clip_grad, gradient_cfg.clip_type, gradient_cfg.clip_value), grads)
grads = self.hyper_map(F.partial(clip_grad, self.clip_type, self.clip_value), grads)
restore = ()
for i in range(self.length):
restore = restore + (F.assign(weights[i], self.saved_params[i]),)
@ -437,7 +439,7 @@ class BertTrainWithLossScaleCell(nn.Cell):
class BertTrainCell(nn.Cell):
"""
Especifically defined for finetuning where only four inputs tensor are needed.
Specifically defined for finetuning where only four inputs tensor are needed.
"""
def __init__(self, network, optimizer, sens=1.0):
super(BertTrainCell, self).__init__(auto_prefix=False)
@ -448,6 +450,8 @@ class BertTrainCell(nn.Cell):
self.sens = sens
self.grad = C.GradOperation(get_by_list=True,
sens_param=True)
self.clip_type = gradient_cfg.clip_type
self.clip_value = gradient_cfg.clip_value
self.reducer_flag = False
self.parallel_mode = context.get_auto_parallel_context("parallel_mode")
if self.parallel_mode in [ParallelMode.DATA_PARALLEL, ParallelMode.HYBRID_PARALLEL]:
@ -514,7 +518,7 @@ class BertTrainCell(nn.Cell):
F.control_depend(input_ids, grads)
# apply grad reducer on grads
grads = self.grad_reducer(grads)
grads = self.hyper_map(F.partial(clip_grad, gradient_cfg.clip_type, gradient_cfg.clip_value), grads)
grads = self.hyper_map(F.partial(clip_grad, self.clip_type, self.clip_value), grads)
restore = ()
for i in range(self.length):
restore = restore + (F.assign(weights[i], self.saved_params[i]),)

2
model_zoo/research/nlp/ternarybert/src/dataset.py
View File

@ -27,7 +27,7 @@ class DataType(Enum):
MINDRECORD = 2
def create_tinybert_dataset(batch_size=32, device_num=1, rank=0, do_shuffle="true", data_dir=None,
def create_dataset(batch_size=32, device_num=1, rank=0, do_shuffle="true", data_dir=None,
data_type='tfrecord', seq_length=128, task_type=mstype.int32, drop_remainder=True):
"""create tinybert dataset"""
if isinstance(data_dir, list):

7
model_zoo/research/nlp/ternarybert/src/utils.py
View File

@ -89,12 +89,7 @@ class LossCallBack(Callback):
class StepCallBack(Callback):
"""
Monitor the loss in training.
If the loss in NAN or INF terminating training.
Note:
if per_print_times is 0 do not print loss.
Args:
per_print_times (int): Print loss every times. Default: 1.
Monitor the time in training.
"""
def __init__(self):
super(StepCallBack, self).__init__()

6
model_zoo/research/nlp/ternarybert/train.py
View File

@ -21,7 +21,7 @@ from mindspore import context
from mindspore.train.model import Model
from mindspore.nn.optim import AdamWeightDecay
from mindspore import set_seed
from src.dataset import create_tinybert_dataset
from src.dataset import create_dataset
from src.utils import StepCallBack, ModelSaveCkpt, EvalCallBack, BertLearningRate
from src.config import train_cfg, eval_cfg, teacher_net_cfg, student_net_cfg, task_cfg
from src.cell_wrapper import BertNetworkWithLoss, BertTrainCell
@ -86,7 +86,7 @@ def run_task_distill(args_opt):
rank = 0
device_num = 1
train_dataset = create_tinybert_dataset(batch_size=train_cfg.batch_size,
train_dataset = create_dataset(batch_size=train_cfg.batch_size,
device_num=device_num,
rank=rank,
do_shuffle=args_opt.do_shuffle,
@ -97,7 +97,7 @@ def run_task_distill(args_opt):
drop_remainder=True)
dataset_size = train_dataset.get_dataset_size()
print('train dataset size:', dataset_size)
eval_dataset = create_tinybert_dataset(batch_size=eval_cfg.batch_size,
eval_dataset = create_dataset(batch_size=eval_cfg.batch_size,
device_num=device_num,
rank=rank,
do_shuffle=args_opt.do_shuffle,