-
Notifications
You must be signed in to change notification settings - Fork 1
/
sut_loss.py
executable file
·174 lines (153 loc) · 6.3 KB
/
sut_loss.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
import math
from dataclasses import dataclass, field
import torch
from fairseq import metrics, utils
from fairseq.criterions import FairseqCriterion, register_criterion
from fairseq.dataclass import FairseqDataclass
from omegaconf import II
@dataclass
class LabelSmoothedCrossEntropyCriterionConfig(FairseqDataclass):
label_smoothing: float = field(
default=0.0,
metadata={"help": "epsilon for label smoothing, 0 means no label smoothing"},
)
report_accuracy: bool = field(
default=False,
metadata={"help": "report accuracy metric"},
)
ignore_prefix_size: int = field(
default=0,
metadata={"help": "Ignore first N tokens"},
)
sentence_avg: bool = II("optimization.sentence_avg")
def label_smoothed_nll_loss(lprobs, target, epsilon, ignore_index=None, reduce=True):
if target.dim() == lprobs.dim() - 1:
target = target.unsqueeze(-1)
nll_loss = -lprobs.gather(dim=-1, index=target)
smooth_loss = -lprobs.sum(dim=-1, keepdim=True)
if ignore_index is not None:
pad_mask = target.eq(ignore_index)
nll_loss.masked_fill_(pad_mask, 0.0)
smooth_loss.masked_fill_(pad_mask, 0.0)
else:
nll_loss = nll_loss.squeeze(-1)
smooth_loss = smooth_loss.squeeze(-1)
if reduce:
nll_loss = nll_loss.sum()
smooth_loss = smooth_loss.sum()
eps_i = epsilon / (lprobs.size(-1) - 1)
loss = (1.0 - epsilon - eps_i) * nll_loss + eps_i * smooth_loss
return loss, nll_loss
@register_criterion(
"sut_ce_loss", dataclass=LabelSmoothedCrossEntropyCriterionConfig
)
class SUTLabelSmoothedCrossEntropyCriterion(FairseqCriterion):
def __init__(
self,
task,
sentence_avg,
label_smoothing,
ignore_prefix_size=0,
report_accuracy=False,
):
super().__init__(task)
self.sentence_avg = sentence_avg
self.eps = label_smoothing
self.ignore_prefix_size = ignore_prefix_size
self.report_accuracy = report_accuracy
def forward(self, model, sample, reduce=True):
"""Compute the loss for the given sample.
Returns a tuple with three elements:
1) the loss
2) the sample size, which is used as the denominator for the gradient
3) logging outputs to display while training
"""
net_output = model(**sample["net_input"])
loss, nll_loss = self.compute_loss(model, net_output, sample, reduce=reduce)
if self.training:
loss = loss + net_output[1]["total_aux_loss"]
for n in model.moe_modules:
m = model.moe_modules[n]
mod_loss = m.get_aux_loss_and_clear()
loss = loss + mod_loss
sample_size = (
sample["target"].size(0) if self.sentence_avg else sample["ntokens"]
)
logging_output = {
"loss": loss.data,
"nll_loss": nll_loss.data,
"ntokens": sample["ntokens"],
"nsentences": sample["target"].size(0),
"sample_size": sample_size,
"encoder.expected_halt": net_output[1]["encoder_expected_halt"] * sample_size,
"decoder.expected_halt": net_output[1]["decoder_expected_halt"] * sample_size
}
if self.report_accuracy:
n_correct, total = self.compute_accuracy(model, net_output, sample)
logging_output["n_correct"] = utils.item(n_correct.data)
logging_output["total"] = utils.item(total.data)
return loss, sample_size, logging_output
def get_lprobs_and_target(self, model, net_output, sample):
lprobs = model.get_normalized_probs(net_output, log_probs=True)
target = model.get_targets(sample, net_output)
if self.ignore_prefix_size > 0:
# lprobs: B x T x C
lprobs = lprobs[:, self.ignore_prefix_size :, :].contiguous()
target = target[:, self.ignore_prefix_size :].contiguous()
return lprobs.view(-1, lprobs.size(-1)), target.view(-1)
def compute_loss(self, model, net_output, sample, reduce=True):
lprobs, target = self.get_lprobs_and_target(model, net_output, sample)
loss, nll_loss = label_smoothed_nll_loss(
lprobs,
target,
self.eps,
ignore_index=self.padding_idx,
reduce=reduce,
)
return loss, nll_loss
def compute_accuracy(self, model, net_output, sample):
lprobs, target = self.get_lprobs_and_target(model, net_output, sample)
mask = target.ne(self.padding_idx)
n_correct = torch.sum(
lprobs.argmax(1).masked_select(mask).eq(target.masked_select(mask))
)
total = torch.sum(mask)
return n_correct, total
@classmethod
def reduce_metrics(cls, logging_outputs) -> None:
"""Aggregate logging outputs from data parallel training."""
loss_sum = sum(log.get("loss", 0) for log in logging_outputs)
nll_loss_sum = sum(log.get("nll_loss", 0) for log in logging_outputs)
ntokens = sum(log.get("ntokens", 0) for log in logging_outputs)
sample_size = sum(log.get("sample_size", 0) for log in logging_outputs)
metrics.log_scalar(
"loss", loss_sum / sample_size / math.log(2), sample_size, round=3
)
metrics.log_scalar(
"nll_loss", nll_loss_sum / ntokens / math.log(2), ntokens, round=3
)
metrics.log_derived(
"ppl", lambda meters: utils.get_perplexity(meters["nll_loss"].avg)
)
metrics.log_scalar(
"encoder.expected_halt",
sum(log.get("encoder.expected_halt", 0)
for log in logging_outputs) / sample_size
)
metrics.log_scalar(
"decoder.expected_halt",
sum(log.get("decoder.expected_halt", 0)
for log in logging_outputs) / sample_size
)
@staticmethod
def logging_outputs_can_be_summed() -> bool:
"""
Whether the logging outputs returned by `forward` can be summed
across workers prior to calling `reduce_metrics`. Setting this
to True will improves distributed training speed.
"""
return True