How to use the t5.evaluation.eval_utils.Metric function in t5

To help you get started, we’ve selected a few t5 examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

google-research / text-to-text-transfer-transformer / t5 / evaluation / eval_utils.py View on Github

class Metric(object):

  def __init__(self, name, group=None):
    self.name = name
    self.group = group or name

# This OrderedDict maps TensorBoard tags to nice-looking metric names.
# The order of the keys in the dict determine the order they get logged.
METRIC_NAMES = collections.OrderedDict([
    ("glue_average", Metric("Average GLUE Score")),
    ("glue_cola_v002/matthews_corrcoef", Metric("CoLA")),
    ("glue_sst2_v002/accuracy", Metric("SST-2")),
    ("glue_mrpc_v002/f1", Metric("MRPC (F1)", "MRPC")),
    ("glue_mrpc_v002/accuracy", Metric("MRPC (accuracy)", "MRPC")),
    ("glue_stsb_v002/pearson_corrcoef", Metric("STSB (Pearson)", "STSB")),
    ("glue_stsb_v002/spearman_corrcoef", Metric("STSB (Spearman)", "STSB")),
    ("glue_qqp_v002/f1", Metric("QQP (F1)", "QQP")),
    ("glue_qqp_v002/accuracy", Metric("QQP (accuracy)", "QQP")),
    ("glue_mnli_matched_v002/accuracy", Metric("MNLIm", "MNLI")),
    ("glue_mnli_mismatched_v002/accuracy", Metric("MNLImm", "MNLI")),
    ("glue_qnli_v002/accuracy", Metric("QNLI")),
    ("glue_rte_v002/accuracy", Metric("GLUE RTE")),
    ("cnn_dailymail_v002/rouge1", Metric("CNN/DM (ROUGE-1)", "CNN/DM")),
    ("cnn_dailymail_v002/rouge2", Metric("CNN/DM (ROUGE-2)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeL", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeLsum", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("squad_v010_allanswers/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010_allanswers_span/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers_span/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010/f1", Metric("SQuAD (F1)", "SQuAD")),

google-research / text-to-text-transfer-transformer / t5 / evaluation / eval_utils.py View on Github

METRIC_NAMES = collections.OrderedDict([
    ("glue_average", Metric("Average GLUE Score")),
    ("glue_cola_v002/matthews_corrcoef", Metric("CoLA")),
    ("glue_sst2_v002/accuracy", Metric("SST-2")),
    ("glue_mrpc_v002/f1", Metric("MRPC (F1)", "MRPC")),
    ("glue_mrpc_v002/accuracy", Metric("MRPC (accuracy)", "MRPC")),
    ("glue_stsb_v002/pearson_corrcoef", Metric("STSB (Pearson)", "STSB")),
    ("glue_stsb_v002/spearman_corrcoef", Metric("STSB (Spearman)", "STSB")),
    ("glue_qqp_v002/f1", Metric("QQP (F1)", "QQP")),
    ("glue_qqp_v002/accuracy", Metric("QQP (accuracy)", "QQP")),
    ("glue_mnli_matched_v002/accuracy", Metric("MNLIm", "MNLI")),
    ("glue_mnli_mismatched_v002/accuracy", Metric("MNLImm", "MNLI")),
    ("glue_qnli_v002/accuracy", Metric("QNLI")),
    ("glue_rte_v002/accuracy", Metric("GLUE RTE")),
    ("cnn_dailymail_v002/rouge1", Metric("CNN/DM (ROUGE-1)", "CNN/DM")),
    ("cnn_dailymail_v002/rouge2", Metric("CNN/DM (ROUGE-2)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeL", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeLsum", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("squad_v010_allanswers/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010_allanswers_span/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers_span/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("super_glue_average", Metric("Average SuperGLUE Score")),
    ("super_glue_boolq_v102/accuracy", Metric("BoolQ (accuracy)")),
    ("super_glue_cb_v102/mean_3class_f1", Metric("CB (F1)", "CB")),
    ("super_glue_cb_v102/accuracy", Metric("CB (accuracy)", "CB")),
    ("super_glue_copa_v102/accuracy", Metric("CoPA")),
    ("super_glue_multirc_v102/f1", Metric("MultiRC (F1)", "MultiRC")),
    ("super_glue_multirc_v102/exact_match", Metric("MultiRC (EM)", "MultiRC")),
    ("super_glue_record_v102/f1", Metric("ReCoRD (F1)", "ReCoRD")),

google-research / text-to-text-transfer-transformer / t5 / evaluation / eval_utils.py View on Github

import tensorflow.compat.v1 as tf


class Metric(object):

  def __init__(self, name, group=None):
    self.name = name
    self.group = group or name

# This OrderedDict maps TensorBoard tags to nice-looking metric names.
# The order of the keys in the dict determine the order they get logged.
METRIC_NAMES = collections.OrderedDict([
    ("glue_average", Metric("Average GLUE Score")),
    ("glue_cola_v002/matthews_corrcoef", Metric("CoLA")),
    ("glue_sst2_v002/accuracy", Metric("SST-2")),
    ("glue_mrpc_v002/f1", Metric("MRPC (F1)", "MRPC")),
    ("glue_mrpc_v002/accuracy", Metric("MRPC (accuracy)", "MRPC")),
    ("glue_stsb_v002/pearson_corrcoef", Metric("STSB (Pearson)", "STSB")),
    ("glue_stsb_v002/spearman_corrcoef", Metric("STSB (Spearman)", "STSB")),
    ("glue_qqp_v002/f1", Metric("QQP (F1)", "QQP")),
    ("glue_qqp_v002/accuracy", Metric("QQP (accuracy)", "QQP")),
    ("glue_mnli_matched_v002/accuracy", Metric("MNLIm", "MNLI")),
    ("glue_mnli_mismatched_v002/accuracy", Metric("MNLImm", "MNLI")),
    ("glue_qnli_v002/accuracy", Metric("QNLI")),
    ("glue_rte_v002/accuracy", Metric("GLUE RTE")),
    ("cnn_dailymail_v002/rouge1", Metric("CNN/DM (ROUGE-1)", "CNN/DM")),
    ("cnn_dailymail_v002/rouge2", Metric("CNN/DM (ROUGE-2)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeL", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeLsum", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("squad_v010_allanswers/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010_allanswers_span/em", Metric("SQuAD (EM)", "SQuAD")),

google-research / text-to-text-transfer-transformer / t5 / evaluation / eval_utils.py View on Github

("squad_v010_allanswers/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010_allanswers_span/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers_span/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("super_glue_average", Metric("Average SuperGLUE Score")),
    ("super_glue_boolq_v102/accuracy", Metric("BoolQ (accuracy)")),
    ("super_glue_cb_v102/mean_3class_f1", Metric("CB (F1)", "CB")),
    ("super_glue_cb_v102/accuracy", Metric("CB (accuracy)", "CB")),
    ("super_glue_copa_v102/accuracy", Metric("CoPA")),
    ("super_glue_multirc_v102/f1", Metric("MultiRC (F1)", "MultiRC")),
    ("super_glue_multirc_v102/exact_match", Metric("MultiRC (EM)", "MultiRC")),
    ("super_glue_record_v102/f1", Metric("ReCoRD (F1)", "ReCoRD")),
    ("super_glue_record_v102/em", Metric("ReCoRD (EM)", "ReCoRD")),
    ("super_glue_rte_v102/accuracy", Metric("SuperGLUE RTE")),
    ("super_glue_wic_v102/accuracy", Metric("WiC")),
    ("super_glue_wsc_v102_simple_eval/accuracy", Metric("WSC")),
    ("dpr_v001_simple/accuracy", Metric("DPR")),
    ("wmt_t2t_ende_v003/bleu", Metric("WMT T2T En-De")),
    ("wmt14_ende_v003/bleu", Metric("WMT14 En-De")),
    ("wmt15_enfr_v003/bleu", Metric("WMT15 En-Fr")),
    ("wmt16_enro_v003/bleu", Metric("WMT16 En-Ro")),
])

Event = collections.namedtuple("event", ["step", "value"])


def parse_events_files(tb_summary_dir):
  """Parse all TensorBoard events files in tb_summary_dir.

  Args:
    tb_summary_dir: str, path to look for events files in.

google-research / text-to-text-transfer-transformer / t5 / evaluation / eval_utils.py View on Github

def __init__(self, name, group=None):
    self.name = name
    self.group = group or name

# This OrderedDict maps TensorBoard tags to nice-looking metric names.
# The order of the keys in the dict determine the order they get logged.
METRIC_NAMES = collections.OrderedDict([
    ("glue_average", Metric("Average GLUE Score")),
    ("glue_cola_v002/matthews_corrcoef", Metric("CoLA")),
    ("glue_sst2_v002/accuracy", Metric("SST-2")),
    ("glue_mrpc_v002/f1", Metric("MRPC (F1)", "MRPC")),
    ("glue_mrpc_v002/accuracy", Metric("MRPC (accuracy)", "MRPC")),
    ("glue_stsb_v002/pearson_corrcoef", Metric("STSB (Pearson)", "STSB")),
    ("glue_stsb_v002/spearman_corrcoef", Metric("STSB (Spearman)", "STSB")),
    ("glue_qqp_v002/f1", Metric("QQP (F1)", "QQP")),
    ("glue_qqp_v002/accuracy", Metric("QQP (accuracy)", "QQP")),
    ("glue_mnli_matched_v002/accuracy", Metric("MNLIm", "MNLI")),
    ("glue_mnli_mismatched_v002/accuracy", Metric("MNLImm", "MNLI")),
    ("glue_qnli_v002/accuracy", Metric("QNLI")),
    ("glue_rte_v002/accuracy", Metric("GLUE RTE")),
    ("cnn_dailymail_v002/rouge1", Metric("CNN/DM (ROUGE-1)", "CNN/DM")),
    ("cnn_dailymail_v002/rouge2", Metric("CNN/DM (ROUGE-2)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeL", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeLsum", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("squad_v010_allanswers/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010_allanswers_span/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers_span/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("super_glue_average", Metric("Average SuperGLUE Score")),

google-research / text-to-text-transfer-transformer / t5 / evaluation / eval_utils.py View on Github

("glue_rte_v002/accuracy", Metric("GLUE RTE")),
    ("cnn_dailymail_v002/rouge1", Metric("CNN/DM (ROUGE-1)", "CNN/DM")),
    ("cnn_dailymail_v002/rouge2", Metric("CNN/DM (ROUGE-2)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeL", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeLsum", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("squad_v010_allanswers/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010_allanswers_span/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers_span/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("super_glue_average", Metric("Average SuperGLUE Score")),
    ("super_glue_boolq_v102/accuracy", Metric("BoolQ (accuracy)")),
    ("super_glue_cb_v102/mean_3class_f1", Metric("CB (F1)", "CB")),
    ("super_glue_cb_v102/accuracy", Metric("CB (accuracy)", "CB")),
    ("super_glue_copa_v102/accuracy", Metric("CoPA")),
    ("super_glue_multirc_v102/f1", Metric("MultiRC (F1)", "MultiRC")),
    ("super_glue_multirc_v102/exact_match", Metric("MultiRC (EM)", "MultiRC")),
    ("super_glue_record_v102/f1", Metric("ReCoRD (F1)", "ReCoRD")),
    ("super_glue_record_v102/em", Metric("ReCoRD (EM)", "ReCoRD")),
    ("super_glue_rte_v102/accuracy", Metric("SuperGLUE RTE")),
    ("super_glue_wic_v102/accuracy", Metric("WiC")),
    ("super_glue_wsc_v102_simple_eval/accuracy", Metric("WSC")),
    ("dpr_v001_simple/accuracy", Metric("DPR")),
    ("wmt_t2t_ende_v003/bleu", Metric("WMT T2T En-De")),
    ("wmt14_ende_v003/bleu", Metric("WMT14 En-De")),
    ("wmt15_enfr_v003/bleu", Metric("WMT15 En-Fr")),
    ("wmt16_enro_v003/bleu", Metric("WMT16 En-Ro")),
])

Event = collections.namedtuple("event", ["step", "value"])

google-research / text-to-text-transfer-transformer / t5 / evaluation / eval_utils.py View on Github

import numpy as np
import pandas as pd
import tensorflow.compat.v1 as tf


class Metric(object):

  def __init__(self, name, group=None):
    self.name = name
    self.group = group or name

# This OrderedDict maps TensorBoard tags to nice-looking metric names.
# The order of the keys in the dict determine the order they get logged.
METRIC_NAMES = collections.OrderedDict([
    ("glue_average", Metric("Average GLUE Score")),
    ("glue_cola_v002/matthews_corrcoef", Metric("CoLA")),
    ("glue_sst2_v002/accuracy", Metric("SST-2")),
    ("glue_mrpc_v002/f1", Metric("MRPC (F1)", "MRPC")),
    ("glue_mrpc_v002/accuracy", Metric("MRPC (accuracy)", "MRPC")),
    ("glue_stsb_v002/pearson_corrcoef", Metric("STSB (Pearson)", "STSB")),
    ("glue_stsb_v002/spearman_corrcoef", Metric("STSB (Spearman)", "STSB")),
    ("glue_qqp_v002/f1", Metric("QQP (F1)", "QQP")),
    ("glue_qqp_v002/accuracy", Metric("QQP (accuracy)", "QQP")),
    ("glue_mnli_matched_v002/accuracy", Metric("MNLIm", "MNLI")),
    ("glue_mnli_mismatched_v002/accuracy", Metric("MNLImm", "MNLI")),
    ("glue_qnli_v002/accuracy", Metric("QNLI")),
    ("glue_rte_v002/accuracy", Metric("GLUE RTE")),
    ("cnn_dailymail_v002/rouge1", Metric("CNN/DM (ROUGE-1)", "CNN/DM")),
    ("cnn_dailymail_v002/rouge2", Metric("CNN/DM (ROUGE-2)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeL", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeLsum", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("squad_v010_allanswers/em", Metric("SQuAD (EM)", "SQuAD")),

google-research / text-to-text-transfer-transformer / t5 / evaluation / eval_utils.py View on Github

self.name = name
    self.group = group or name

# This OrderedDict maps TensorBoard tags to nice-looking metric names.
# The order of the keys in the dict determine the order they get logged.
METRIC_NAMES = collections.OrderedDict([
    ("glue_average", Metric("Average GLUE Score")),
    ("glue_cola_v002/matthews_corrcoef", Metric("CoLA")),
    ("glue_sst2_v002/accuracy", Metric("SST-2")),
    ("glue_mrpc_v002/f1", Metric("MRPC (F1)", "MRPC")),
    ("glue_mrpc_v002/accuracy", Metric("MRPC (accuracy)", "MRPC")),
    ("glue_stsb_v002/pearson_corrcoef", Metric("STSB (Pearson)", "STSB")),
    ("glue_stsb_v002/spearman_corrcoef", Metric("STSB (Spearman)", "STSB")),
    ("glue_qqp_v002/f1", Metric("QQP (F1)", "QQP")),
    ("glue_qqp_v002/accuracy", Metric("QQP (accuracy)", "QQP")),
    ("glue_mnli_matched_v002/accuracy", Metric("MNLIm", "MNLI")),
    ("glue_mnli_mismatched_v002/accuracy", Metric("MNLImm", "MNLI")),
    ("glue_qnli_v002/accuracy", Metric("QNLI")),
    ("glue_rte_v002/accuracy", Metric("GLUE RTE")),
    ("cnn_dailymail_v002/rouge1", Metric("CNN/DM (ROUGE-1)", "CNN/DM")),
    ("cnn_dailymail_v002/rouge2", Metric("CNN/DM (ROUGE-2)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeL", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeLsum", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("squad_v010_allanswers/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010_allanswers_span/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers_span/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("super_glue_average", Metric("Average SuperGLUE Score")),
    ("super_glue_boolq_v102/accuracy", Metric("BoolQ (accuracy)")),
    ("super_glue_cb_v102/mean_3class_f1", Metric("CB (F1)", "CB")),

google-research / text-to-text-transfer-transformer / t5 / evaluation / eval_utils.py View on Github

class Metric(object):

  def __init__(self, name, group=None):
    self.name = name
    self.group = group or name

# This OrderedDict maps TensorBoard tags to nice-looking metric names.
# The order of the keys in the dict determine the order they get logged.
METRIC_NAMES = collections.OrderedDict([
    ("glue_average", Metric("Average GLUE Score")),
    ("glue_cola_v002/matthews_corrcoef", Metric("CoLA")),
    ("glue_sst2_v002/accuracy", Metric("SST-2")),
    ("glue_mrpc_v002/f1", Metric("MRPC (F1)", "MRPC")),
    ("glue_mrpc_v002/accuracy", Metric("MRPC (accuracy)", "MRPC")),
    ("glue_stsb_v002/pearson_corrcoef", Metric("STSB (Pearson)", "STSB")),
    ("glue_stsb_v002/spearman_corrcoef", Metric("STSB (Spearman)", "STSB")),
    ("glue_qqp_v002/f1", Metric("QQP (F1)", "QQP")),
    ("glue_qqp_v002/accuracy", Metric("QQP (accuracy)", "QQP")),
    ("glue_mnli_matched_v002/accuracy", Metric("MNLIm", "MNLI")),
    ("glue_mnli_mismatched_v002/accuracy", Metric("MNLImm", "MNLI")),
    ("glue_qnli_v002/accuracy", Metric("QNLI")),
    ("glue_rte_v002/accuracy", Metric("GLUE RTE")),
    ("cnn_dailymail_v002/rouge1", Metric("CNN/DM (ROUGE-1)", "CNN/DM")),
    ("cnn_dailymail_v002/rouge2", Metric("CNN/DM (ROUGE-2)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeL", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeLsum", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("squad_v010_allanswers/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010_allanswers_span/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers_span/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010/em", Metric("SQuAD (EM)", "SQuAD")),

google-research / text-to-text-transfer-transformer / t5 / evaluation / eval_utils.py View on Github

("cnn_dailymail_v002/rouge2", Metric("CNN/DM (ROUGE-2)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeL", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("cnn_dailymail_v002/rougeLsum", Metric("CNN/DM (ROUGE-L)", "CNN/DM")),
    ("squad_v010_allanswers/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010_allanswers_span/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010_allanswers_span/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("squad_v010/em", Metric("SQuAD (EM)", "SQuAD")),
    ("squad_v010/f1", Metric("SQuAD (F1)", "SQuAD")),
    ("super_glue_average", Metric("Average SuperGLUE Score")),
    ("super_glue_boolq_v102/accuracy", Metric("BoolQ (accuracy)")),
    ("super_glue_cb_v102/mean_3class_f1", Metric("CB (F1)", "CB")),
    ("super_glue_cb_v102/accuracy", Metric("CB (accuracy)", "CB")),
    ("super_glue_copa_v102/accuracy", Metric("CoPA")),
    ("super_glue_multirc_v102/f1", Metric("MultiRC (F1)", "MultiRC")),
    ("super_glue_multirc_v102/exact_match", Metric("MultiRC (EM)", "MultiRC")),
    ("super_glue_record_v102/f1", Metric("ReCoRD (F1)", "ReCoRD")),
    ("super_glue_record_v102/em", Metric("ReCoRD (EM)", "ReCoRD")),
    ("super_glue_rte_v102/accuracy", Metric("SuperGLUE RTE")),
    ("super_glue_wic_v102/accuracy", Metric("WiC")),
    ("super_glue_wsc_v102_simple_eval/accuracy", Metric("WSC")),
    ("dpr_v001_simple/accuracy", Metric("DPR")),
    ("wmt_t2t_ende_v003/bleu", Metric("WMT T2T En-De")),
    ("wmt14_ende_v003/bleu", Metric("WMT14 En-De")),
    ("wmt15_enfr_v003/bleu", Metric("WMT15 En-Fr")),
    ("wmt16_enro_v003/bleu", Metric("WMT16 En-Ro")),
])

Event = collections.namedtuple("event", ["step", "value"])


def parse_events_files(tb_summary_dir):

How to use the t5.evaluation.eval_utils.Metric function in t5

To help you get started, we’ve selected a few t5 examples, based on popular ways it is used in public projects.

t5

Package Health Score

Popular t5 functions

Similar packages