Spaces:
Paused
Paused
File size: 6,253 Bytes
ee6e328 |
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 |
# coding=utf-8
# Copyright 2020 The HuggingFace Team All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
A subclass of `Trainer` specific to Question-Answering tasks
"""
import math
import time
from transformers import Trainer, is_torch_tpu_available
from transformers.trainer_utils import PredictionOutput, speed_metrics
if is_torch_tpu_available(check_device=False):
import torch_xla.core.xla_model as xm
import torch_xla.debug.metrics as met
class QuestionAnsweringTrainer(Trainer):
def __init__(self, *args, eval_examples=None, post_process_function=None, **kwargs):
super().__init__(*args, **kwargs)
self.eval_examples = eval_examples
self.post_process_function = post_process_function
def evaluate(self, eval_dataset=None, eval_examples=None, ignore_keys=None, metric_key_prefix: str = "eval"):
eval_dataset = self.eval_dataset if eval_dataset is None else eval_dataset
eval_dataloader = self.get_eval_dataloader(eval_dataset)
eval_examples = self.eval_examples if eval_examples is None else eval_examples
# Temporarily disable metric computation, we will do it in the loop here.
compute_metrics = self.compute_metrics
self.compute_metrics = None
eval_loop = self.prediction_loop if self.args.use_legacy_prediction_loop else self.evaluation_loop
start_time = time.time()
try:
output = eval_loop(
eval_dataloader,
description="Evaluation",
# No point gathering the predictions if there are no metrics, otherwise we defer to
# self.args.prediction_loss_only
prediction_loss_only=True if compute_metrics is None else None,
ignore_keys=ignore_keys,
metric_key_prefix=metric_key_prefix,
)
finally:
self.compute_metrics = compute_metrics
total_batch_size = self.args.eval_batch_size * self.args.world_size
if f"{metric_key_prefix}_jit_compilation_time" in output.metrics:
start_time += output.metrics[f"{metric_key_prefix}_jit_compilation_time"]
output.metrics.update(
speed_metrics(
metric_key_prefix,
start_time,
num_samples=output.num_samples,
num_steps=math.ceil(output.num_samples / total_batch_size),
)
)
if self.post_process_function is not None and self.compute_metrics is not None and self.args.should_save:
# Only the main node write the results by default
eval_preds = self.post_process_function(eval_examples, eval_dataset, output.predictions)
metrics = self.compute_metrics(eval_preds)
# Prefix all keys with metric_key_prefix + '_'
for key in list(metrics.keys()):
if not key.startswith(f"{metric_key_prefix}_"):
metrics[f"{metric_key_prefix}_{key}"] = metrics.pop(key)
metrics.update(output.metrics)
else:
metrics = output.metrics
if self.args.should_log:
# Only the main node log the results by default
self.log(metrics)
if self.args.tpu_metrics_debug or self.args.debug:
# tpu-comment: Logging debug metrics for PyTorch/XLA (compile, execute times, ops, etc.)
xm.master_print(met.metrics_report())
self.control = self.callback_handler.on_evaluate(self.args, self.state, self.control, metrics)
return metrics
def predict(self, predict_dataset, predict_examples, ignore_keys=None, metric_key_prefix: str = "test"):
predict_dataloader = self.get_test_dataloader(predict_dataset)
# Temporarily disable metric computation, we will do it in the loop here.
compute_metrics = self.compute_metrics
self.compute_metrics = None
eval_loop = self.prediction_loop if self.args.use_legacy_prediction_loop else self.evaluation_loop
start_time = time.time()
try:
output = eval_loop(
predict_dataloader,
description="Prediction",
# No point gathering the predictions if there are no metrics, otherwise we defer to
# self.args.prediction_loss_only
prediction_loss_only=True if compute_metrics is None else None,
ignore_keys=ignore_keys,
metric_key_prefix=metric_key_prefix,
)
finally:
self.compute_metrics = compute_metrics
total_batch_size = self.args.eval_batch_size * self.args.world_size
if f"{metric_key_prefix}_jit_compilation_time" in output.metrics:
start_time += output.metrics[f"{metric_key_prefix}_jit_compilation_time"]
output.metrics.update(
speed_metrics(
metric_key_prefix,
start_time,
num_samples=output.num_samples,
num_steps=math.ceil(output.num_samples / total_batch_size),
)
)
if self.post_process_function is None or self.compute_metrics is None:
return output
predictions = self.post_process_function(predict_examples, predict_dataset, output.predictions, "predict")
metrics = self.compute_metrics(predictions)
# Prefix all keys with metric_key_prefix + '_'
for key in list(metrics.keys()):
if not key.startswith(f"{metric_key_prefix}_"):
metrics[f"{metric_key_prefix}_{key}"] = metrics.pop(key)
metrics.update(output.metrics)
return PredictionOutput(predictions=predictions.predictions, label_ids=predictions.label_ids, metrics=metrics)
|