Hugging Face's logo

Spaces:
homeway
/
PromptCARE
Sleeping

App Files Community
PromptCARE
File size: 7,040 Bytes 
7713b1f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
# 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
"""

from transformers import Trainer, is_torch_tpu_available
from transformers.trainer_utils import PredictionOutput
from training.trainer_exp import ExponentialTrainer, logger
from typing import Dict, OrderedDict

if is_torch_tpu_available():
    import torch_xla.core.xla_model as xm
    import torch_xla.debug.metrics as met


class QuestionAnsweringTrainer(ExponentialTrainer):
    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
        self.best_metrics = OrderedDict({
            "best_epoch": 0,
            "best_eval_f1": 0,
            "best_eval_exact_match": 0,
        })

    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
        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,
            )
        finally:
            self.compute_metrics = compute_metrics

        if self.post_process_function is not None and self.compute_metrics is not None:
            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)

            self.log(metrics)
        else:
            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
        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,
            )
        finally:
            self.compute_metrics = compute_metrics

        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)

        return PredictionOutput(predictions=predictions.predictions, label_ids=predictions.label_ids, metrics=metrics)

    def _maybe_log_save_evaluate(self, tr_loss, model, trial, epoch, ignore_keys_for_eval):
        if self.control.should_log:
            logs: Dict[str, float] = {}


            tr_loss_scalar = self._nested_gather(tr_loss).mean().item()

            # reset tr_loss to zero
            tr_loss -= tr_loss

            logs["loss"] = round(tr_loss_scalar / (self.state.global_step - self._globalstep_last_logged), 4)
            logs["learning_rate"] = self._get_learning_rate()

            self._total_loss_scalar += tr_loss_scalar
            self._globalstep_last_logged = self.state.global_step
            self.store_flos()

            self.log(logs)

        eval_metrics = None
        if self.control.should_evaluate:
            eval_metrics = self.evaluate(ignore_keys=ignore_keys_for_eval)
            self._report_to_hp_search(trial, epoch, eval_metrics)

            if eval_metrics["eval_f1"] > self.best_metrics["best_eval_f1"]:
                self.best_metrics["best_epoch"] = epoch
                self.best_metrics["best_eval_f1"] = eval_metrics["eval_f1"]
                if "eval_exact_match" in eval_metrics:
                    self.best_metrics["best_eval_exact_match"] = eval_metrics["eval_exact_match"]
                if "eval_exact" in eval_metrics:
                    self.best_metrics["best_eval_exact_match"] = eval_metrics["eval_exact"]
            
              
            logger.info(f"\n***** Epoch {epoch}: Best results *****")
            for key, value in self.best_metrics.items():
                logger.info(f"{key} = {value}")
            self.log(self.best_metrics)

        if self.control.should_save:
            self._save_checkpoint(model, trial, metrics=eval_metrics)
            self.control = self.callback_handler.on_save(self.args, self.state, self.control)

    def log_best_metrics(self):
        best_metrics = OrderedDict()
        for key, value in self.best_metrics.items():
            best_metrics[f"best_{key}"] = value
        self.log_metrics("best", best_metrics)