diff --git a/configs/cls/cls_mv3.yml b/configs/cls/cls_mv3.yml
index 5e643dc3839b2e2edf3c811db813dd6a90797366..2d8b52a44e9cf9a24b32b8258d59aed259ac17d2 100644
--- a/configs/cls/cls_mv3.yml
+++ b/configs/cls/cls_mv3.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/cls/mv3/
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 1000 iterations after the 0th iteration
   eval_batch_step: [0, 1000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml b/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml
index 0f08909add17d8c73ad6e1b00e17d4c351def7e5..a7221d7c4c39f6f37328e290b80577af407b6949 100644
--- a/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml
+++ b/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 2
   save_model_dir: ./output/ch_db_mv3/
   save_epoch_step: 1200
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 3000th iteration
   eval_batch_step: [3000, 2000]
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/ch_PP-OCRv2_det_distill_train/best_accuracy
diff --git a/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_distill.yml b/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_distill.yml
index 1159d71bf94c330e26c3009b38c5c2b4a9c96f52..9566a3f7b2dbda633d7333dc890565006d2c570c 100644
--- a/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_distill.yml
+++ b/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_distill.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 2
   save_model_dir: ./output/ch_db_mv3/
   save_epoch_step: 1200
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 3000th iteration
   eval_batch_step: [3000, 2000]
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
diff --git a/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_dml.yml b/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_dml.yml
index 7fe2d2e1a065b54d0e2479475f5f67ac5e38a166..3a6f181104ea21df99d6896f7b620dd28a2ceb9d 100644
--- a/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_dml.yml
+++ b/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_dml.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 2
   save_model_dir: ./output/ch_db_mv3/
   save_epoch_step: 1200
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 3000th iteration
   eval_batch_step: [3000, 2000]
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
diff --git a/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_student.yml b/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_student.yml
index cca2a596ce73d7f66a14e5967e5926c5ee36295c..f07f38168cd2ba3234f6adc3764c055667882590 100644
--- a/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_student.yml
+++ b/configs/det/ch_PP-OCRv2/ch_PP-OCR_det_student.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/ch_db_mv3/
   save_epoch_step: 1200
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 400 iterations after the 0th iteration
   eval_batch_step: [0, 400]
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/student.pdparams
diff --git a/configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml b/configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml
index 87718cad68743880dbfcd6b4c574bb09b9f53204..5951ff65b53621a133483c33d269b1ca3916f9e7 100644
--- a/configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml
+++ b/configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 2
   save_model_dir: ./output/ch_db_mv3/
   save_epoch_step: 1200
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 3000th iteration
   eval_batch_step: [3000, 2000]
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
diff --git a/configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml b/configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml
index 7b07ef99648956a70b5a71f1e61f09b592226f90..f819a0c24744dabd820027b2175658ee85a07020 100644
--- a/configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml
+++ b/configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 2
   save_model_dir: ./output/ch_db_res18/
   save_epoch_step: 1200
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 3000th iteration
   eval_batch_step: [3000, 2000]
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/ResNet18_vd_pretrained
diff --git a/configs/det/det_mv3_db.yml b/configs/det/det_mv3_db.yml
index b69ed58cd6f64b82b419d46f4f91458d7d167d84..addbf9f56fac64f9dcedda3962a5827d075f7041 100644
--- a/configs/det/det_mv3_db.yml
+++ b/configs/det/det_mv3_db.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/db_mv3/
   save_epoch_step: 1200
-  # evaluation is run every 2000 iterations
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
diff --git a/configs/det/det_r50_vd_db.yml b/configs/det/det_r50_vd_db.yml
index 42b3898ef463b8dba6338f37824ade0c93794212..3104aec0acce11dc3a14c0395399c8839fcdd6b4 100644
--- a/configs/det/det_r50_vd_db.yml
+++ b/configs/det/det_r50_vd_db.yml
@@ -5,8 +5,8 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/det_r50_vd/
   save_epoch_step: 1200
-  # evaluation is run every 2000 iterations
-  eval_batch_step: [0,2000]
+  # evaluation is run every 2000 iterations after the 0th iteration
+  eval_batch_step: [0, 2000]
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
   checkpoints:
diff --git a/configs/e2e/e2e_r50_vd_pg.yml b/configs/e2e/e2e_r50_vd_pg.yml
index 4a6e19f4461c7236f3a9a5253437eff97fa72f67..d17a32cbdf9e8944c18defeeead584849aec85a5 100644
--- a/configs/e2e/e2e_r50_vd_pg.yml
+++ b/configs/e2e/e2e_r50_vd_pg.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/pgnet_r50_vd_totaltext/
   save_epoch_step: 10
-  # evaluation is run every 0 iterationss after the 1000th iteration
+  # evaluation is run every 1000 iterationss after the 0th iteration
   eval_batch_step: [ 0, 1000 ]
   cal_metric_during_train: False
   pretrained_model:
diff --git a/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml b/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml
index 38f77f7372c4e422b5601deb5119c24fd1e3f787..21e55b03b8a21c1e7d571220ca0bea7745e36b4d 100644
--- a/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml
+++ b/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml
@@ -6,6 +6,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_mobile_pp-OCRv2
   save_epoch_step: 3
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: true
   pretrained_model:
diff --git a/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml b/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml
index d2308fd5747f3fadf3bb1c98c5602c67d5e63eca..852502987b04359f51e64053f4d20672a92c63bd 100644
--- a/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml
+++ b/configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml
@@ -6,6 +6,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_pp-OCRv2_distillation
   save_epoch_step: 3
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: true
   pretrained_model:
diff --git a/configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml b/configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml
index 717c16814bac2f6fca78aa63566df12bd8cbf67b..3f3cd4b325f52de88a70200974904adf600af2f1 100644
--- a/configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml
+++ b/configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_chinese_common_v2.0
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml b/configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml
index 660465f301047110db7001db7a32e687f2917b61..94d19e8af86445139c446f923b896e06addb9b47 100644
--- a/configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml
+++ b/configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_chinese_lite_v2.0
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/multi_language/rec_arabic_lite_train.yml b/configs/rec/multi_language/rec_arabic_lite_train.yml
index 6dcfd1b69988b09c7dfc05cdbacce9756ea1f7cb..22487d1b43c7ce45ba0f1b550bd48560cd8a66ec 100644
--- a/configs/rec/multi_language/rec_arabic_lite_train.yml
+++ b/configs/rec/multi_language/rec_arabic_lite_train.yml
@@ -5,9 +5,8 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_arabic_lite
   save_epoch_step: 3
-  eval_batch_step:
-  - 0
-  - 2000
+  # evaluation is run every 2000 iterations after the 0th iteration
+  eval_batch_step: [0, 2000]
   cal_metric_during_train: true
   pretrained_model: null
   checkpoints: null
diff --git a/configs/rec/multi_language/rec_cyrillic_lite_train.yml b/configs/rec/multi_language/rec_cyrillic_lite_train.yml
index 52527c1dfb9a306429bbab9241c623581d546e45..3fe189531edacc7e9645ca17f8cabe7e0c9cd89d 100644
--- a/configs/rec/multi_language/rec_cyrillic_lite_train.yml
+++ b/configs/rec/multi_language/rec_cyrillic_lite_train.yml
@@ -5,9 +5,8 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_cyrillic_lite
   save_epoch_step: 3
-  eval_batch_step:
-  - 0
-  - 2000
+  # evaluation is run every 2000 iterations after the 0th iteration
+  eval_batch_step: [0, 2000]
   cal_metric_during_train: true
   pretrained_model: null
   checkpoints: null
diff --git a/configs/rec/multi_language/rec_devanagari_lite_train.yml b/configs/rec/multi_language/rec_devanagari_lite_train.yml
index e1a7c829c3e6d3c3a57f1d501cdd80a560703ec7..aab87bbcfa3b8db5dc572661a2931f3270f26681 100644
--- a/configs/rec/multi_language/rec_devanagari_lite_train.yml
+++ b/configs/rec/multi_language/rec_devanagari_lite_train.yml
@@ -5,9 +5,8 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_devanagari_lite
   save_epoch_step: 3
-  eval_batch_step:
-  - 0
-  - 2000
+  # evaluation is run every 2000 iterations after the 0th iteration
+  eval_batch_step: [0, 2000]
   cal_metric_during_train: true
   pretrained_model: null
   checkpoints: null
diff --git a/configs/rec/multi_language/rec_en_number_lite_train.yml b/configs/rec/multi_language/rec_en_number_lite_train.yml
index fff4dfcd905b406964bb07cf14017af22f40e91e..b413d89843544b620e300169febc89fdd10f7933 100644
--- a/configs/rec/multi_language/rec_en_number_lite_train.yml
+++ b/configs/rec/multi_language/rec_en_number_lite_train.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_en_number_lite
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   # if pretrained_model is saved in static mode, load_static_weights must set to True
   cal_metric_during_train: True
diff --git a/configs/rec/multi_language/rec_french_lite_train.yml b/configs/rec/multi_language/rec_french_lite_train.yml
index 63378d38a0d31fc77c33173e0ed864f28c5c3a8b..ebd3fab910f4193c2ebcea57da1300967a15d134 100644
--- a/configs/rec/multi_language/rec_french_lite_train.yml
+++ b/configs/rec/multi_language/rec_french_lite_train.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_french_lite
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   # if pretrained_model is saved in static mode, load_static_weights must set to True
   cal_metric_during_train: True
diff --git a/configs/rec/multi_language/rec_german_lite_train.yml b/configs/rec/multi_language/rec_german_lite_train.yml
index 1651510c5e4597e82298135d2f6c64aa747cf961..b02cd640cf9ee5d3b6e8574c3e15ceea58dc7574 100644
--- a/configs/rec/multi_language/rec_german_lite_train.yml
+++ b/configs/rec/multi_language/rec_german_lite_train.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_german_lite
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   # if pretrained_model is saved in static mode, load_static_weights must set to True
   cal_metric_during_train: True
diff --git a/configs/rec/multi_language/rec_japan_lite_train.yml b/configs/rec/multi_language/rec_japan_lite_train.yml
index bb47584edbc70f68d8d2d89dced3ec9b12f0e1cb..c1414f462716044ebcb1256ea0c8f99343896002 100644
--- a/configs/rec/multi_language/rec_japan_lite_train.yml
+++ b/configs/rec/multi_language/rec_japan_lite_train.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_japan_lite
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   # if pretrained_model is saved in static mode, load_static_weights must set to True
   cal_metric_during_train: True
diff --git a/configs/rec/multi_language/rec_korean_lite_train.yml b/configs/rec/multi_language/rec_korean_lite_train.yml
index 77f15524f78cd7f1c3dcf4988960e718422f5d89..1ca0d6457050fab1b2d97ca23bb24379af6c5169 100644
--- a/configs/rec/multi_language/rec_korean_lite_train.yml
+++ b/configs/rec/multi_language/rec_korean_lite_train.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_korean_lite
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   # if pretrained_model is saved in static mode, load_static_weights must set to True
   cal_metric_during_train: True
diff --git a/configs/rec/multi_language/rec_latin_lite_train.yml b/configs/rec/multi_language/rec_latin_lite_train.yml
index e71112b4b4f0afd3ceab9f10078bc5d518ee9e59..2aee8861f53f2e1e5b33e33e7ba8e4a58ed572ae 100644
--- a/configs/rec/multi_language/rec_latin_lite_train.yml
+++ b/configs/rec/multi_language/rec_latin_lite_train.yml
@@ -5,9 +5,8 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_latin_lite
   save_epoch_step: 3
-  eval_batch_step:
-  - 0
-  - 2000
+  # evaluation is run every 2000 iterations after the 0th iteration
+  eval_batch_step: [0, 2000]
   cal_metric_during_train: true
   pretrained_model: null
   checkpoints: null
diff --git a/configs/rec/multi_language/rec_multi_language_lite_train.yml b/configs/rec/multi_language/rec_multi_language_lite_train.yml
index c42a3d1a3a5971365967effd4fdb2cc43725ef75..67eaeea34cc2de31c6e254afee3ed4f5bb90105c 100644
--- a/configs/rec/multi_language/rec_multi_language_lite_train.yml
+++ b/configs/rec/multi_language/rec_multi_language_lite_train.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec_multi_language_lite
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   # if pretrained_model is saved in static mode, load_static_weights must set to True
   cal_metric_during_train: True
diff --git a/configs/rec/rec_icdar15_train.yml b/configs/rec/rec_icdar15_train.yml
index 17a4d76483635d648ebb8cb897f621a186dcd516..ac58262d3b5143ca2aea12bf4fe2e6d7d6795b2d 100644
--- a/configs/rec/rec_icdar15_train.yml
+++ b/configs/rec/rec_icdar15_train.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec/ic15/
   save_epoch_step: 3
-  # evaluation is run every 2000 iterations
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/rec_mtb_nrtr.yml b/configs/rec/rec_mtb_nrtr.yml
index 635c392d705acd1fcfbf9f744a8d7167c448d74c..65c584488883e6936a8c5c010fade153be7c88b1 100644
--- a/configs/rec/rec_mtb_nrtr.yml
+++ b/configs/rec/rec_mtb_nrtr.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec/nrtr/
   save_epoch_step: 1
-  # evaluation is run every 2000 iterations
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/rec_mv3_none_bilstm_ctc.yml b/configs/rec/rec_mv3_none_bilstm_ctc.yml
index 9e0bd23edba053b44fc7241c0a587ced5cd1ac76..2d6abc668af3236ebb42b8ecd5f7d895da02ef89 100644
--- a/configs/rec/rec_mv3_none_bilstm_ctc.yml
+++ b/configs/rec/rec_mv3_none_bilstm_ctc.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec/mv3_none_bilstm_ctc/
   save_epoch_step: 3
-  # evaluation is run every 2000 iterations
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/rec_mv3_none_none_ctc.yml b/configs/rec/rec_mv3_none_none_ctc.yml
index 904afe1134b565d6459cdcda4cbfa43ae4925b92..8557e9ca94739a1bf5b783310bb346477f2729b6 100644
--- a/configs/rec/rec_mv3_none_none_ctc.yml
+++ b/configs/rec/rec_mv3_none_none_ctc.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec/mv3_none_none_ctc/
   save_epoch_step: 3
-  # evaluation is run every 2000 iterations
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/rec_mv3_tps_bilstm_att.yml b/configs/rec/rec_mv3_tps_bilstm_att.yml
index feaeb0545c687774938521e4c45c026207172f11..759bcc0699d419b116f963502bc4b34ed6878b4c 100644
--- a/configs/rec/rec_mv3_tps_bilstm_att.yml
+++ b/configs/rec/rec_mv3_tps_bilstm_att.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec/rec_mv3_tps_bilstm_att/
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/rec_mv3_tps_bilstm_ctc.yml b/configs/rec/rec_mv3_tps_bilstm_ctc.yml
index 65ab23c42aff54ee548867e3482d7400603551ad..7b886fcd2ae56af0483a1511d1b787823d958fc4 100644
--- a/configs/rec/rec_mv3_tps_bilstm_ctc.yml
+++ b/configs/rec/rec_mv3_tps_bilstm_ctc.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec/mv3_tps_bilstm_ctc/
   save_epoch_step: 3
-  # evaluation is run every 2000 iterations
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/rec_r34_vd_none_bilstm_ctc.yml b/configs/rec/rec_r34_vd_none_bilstm_ctc.yml
index 331bb36ed84b83dc62a0f9b15524457238dedc13..8c91af49687bdbffb6c01c152d53d13930cf5888 100644
--- a/configs/rec/rec_r34_vd_none_bilstm_ctc.yml
+++ b/configs/rec/rec_r34_vd_none_bilstm_ctc.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec/r34_vd_none_bilstm_ctc/
   save_epoch_step: 3
-  # evaluation is run every 2000 iterations
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/rec_r34_vd_none_none_ctc.yml b/configs/rec/rec_r34_vd_none_none_ctc.yml
index 695a46958f669e4cb9508646080b45ac0767b8c9..47be09de66a536bb902f604e765f0e5425a83027 100644
--- a/configs/rec/rec_r34_vd_none_none_ctc.yml
+++ b/configs/rec/rec_r34_vd_none_none_ctc.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec/r34_vd_none_none_ctc/
   save_epoch_step: 3
-  # evaluation is run every 2000 iterations
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/rec_r34_vd_tps_bilstm_att.yml b/configs/rec/rec_r34_vd_tps_bilstm_att.yml
index fdd3588c844ffd7ed61de73077ae2994f0ad498d..6d7e5ef64d50fdd6bb5a0130ca5ef30391064480 100644
--- a/configs/rec/rec_r34_vd_tps_bilstm_att.yml
+++ b/configs/rec/rec_r34_vd_tps_bilstm_att.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec/b3_rare_r34_none_gru/
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/rec_r34_vd_tps_bilstm_ctc.yml b/configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
index 67108a6eaca2dd6f239261f5184341e5ade00dc0..4f14cc37f1565c1d4e758e3c8cb17516edaab0b5 100644
--- a/configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
+++ b/configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 10
   save_model_dir: ./output/rec/r34_vd_tps_bilstm_ctc/
   save_epoch_step: 3
-  # evaluation is run every 2000 iterations
+  # evaluation is run every 2000 iterations after the 0th iteration
   eval_batch_step: [0, 2000]
   cal_metric_during_train: True
   pretrained_model:
diff --git a/configs/rec/rec_r50_fpn_srn.yml b/configs/rec/rec_r50_fpn_srn.yml
index fa7b1ae4e5fed41d3aa3670d6672cca01b63c359..8ad4e7074c9dfcf9215b1918624b44183f9d3903 100644
--- a/configs/rec/rec_r50_fpn_srn.yml
+++ b/configs/rec/rec_r50_fpn_srn.yml
@@ -5,7 +5,7 @@ Global:
   print_batch_step: 5
   save_model_dir: ./output/rec/srn_new
   save_epoch_step: 3
-  # evaluation is run every 5000 iterations after the 4000th iteration
+  # evaluation is run every 5000 iterations after the 0th iteration
   eval_batch_step: [0, 5000]
   cal_metric_during_train: True
   pretrained_model: 
diff --git a/doc/doc_ch/detection.md b/doc/doc_ch/detection.md
index 59bf6384f6c4fef4aba04064dbba09d14273b755..5ec880b7996015d4baad4e50442ac67f1d260f69 100644
--- a/doc/doc_ch/detection.md
+++ b/doc/doc_ch/detection.md
@@ -230,6 +230,7 @@ python3 tools/infer/predict_det.py --det_algorithm="EAST" --det_model_dir="./out
 # 5. FAQ
 
 Q1: 训练模型转inference 模型之后预测效果不一致？
+
 **A**：此类问题出现较多，问题多是trained model预测时候的预处理、后处理参数和inference model预测的时候的预处理、后处理参数不一致导致的。以det_mv3_db.yml配置文件训练的模型为例，训练模型、inference模型预测结果不一致问题解决方式如下：
 - 检查[trained model预处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L116)，和[inference model的预测预处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/predict_det.py#L42)函数是否一致。算法在评估的时候，输入图像大小会影响精度，为了和论文保持一致，训练icdar15配置文件中将图像resize到[736, 1280]，但是在inference model预测的时候只有一套默认参数，会考虑到预测速度问题，默认限制图像最长边为960做resize的。训练模型预处理和inference模型的预处理函数位于[ppocr/data/imaug/operators.py](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/ppocr/data/imaug/operators.py#L147)
 - 检查[trained model后处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L51)，和[inference 后处理参数](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/utility.py#L50)是否一致。
diff --git a/doc/doc_ch/pgnet.md b/doc/doc_ch/pgnet.md
index 357d222d2160002436e9e757c50de179bb55f932..264d5a1170ce7ee3c38feb1a85a0e324e4228d4f 100644
--- a/doc/doc_ch/pgnet.md
+++ b/doc/doc_ch/pgnet.md
@@ -28,9 +28,9 @@ PGNet算法细节详见[论文](https://www.aaai.org/AAAI21Papers/AAAI-2885.Wang
 
 ### 性能指标
 
-测试集: Total Text
+#### 测试集: Total Text
 
-测试环境: NVIDIA Tesla V100-SXM2-16GB
+#### 测试环境: NVIDIA Tesla V100-SXM2-16GB
 
 |PGNetA|det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS|下载|
 | --- | --- | --- | --- | --- | --- | --- | --- | --- |
diff --git a/doc/doc_en/detection_en.md b/doc/doc_en/detection_en.md
index df96fd5336cd64049e8f5d9b898f60c55b82b7b4..4f8143d03f09a83d51bdbe3a9674bbfe4e3181ef 100644
--- a/doc/doc_en/detection_en.md
+++ b/doc/doc_en/detection_en.md
@@ -223,6 +223,7 @@ python3 tools/infer/predict_det.py --det_algorithm="EAST" --det_model_dir="./out
 ## 5. FAQ
 
 Q1: The prediction results of trained model and inference model are inconsistent?
+
 **A**: Most of the problems are caused by the inconsistency of the pre-processing and post-processing parameters during the prediction of the trained model and the pre-processing and post-processing parameters during the prediction of the inference model. Taking the model trained by the det_mv3_db.yml configuration file as an example, the solution to the problem of inconsistent prediction results between the training model and the inference model is as follows:
 - Check whether the [trained model preprocessing](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L116) is consistent with the prediction [preprocessing function of the inference model](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/predict_det.py#L42). When the algorithm is evaluated, the input image size will affect the accuracy. In order to be consistent with the paper, the image is resized to [736, 1280] in the training icdar15 configuration file, but there is only a set of default parameters when the inference model predicts, which will be considered To predict the speed problem, the longest side of the image is limited to 960 for resize by default. The preprocessing function of the training model preprocessing and the inference model is located in [ppocr/data/imaug/operators.py](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/ppocr/data/imaug/operators.py#L147)
 - Check whether the [post-processing of the trained model](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L51) is consistent with the [post-processing parameters of the inference](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/utility.py#L50).
diff --git a/doc/doc_en/pgnet_en.md b/doc/doc_en/pgnet_en.md
index df5610e59f80bbc390c43b15ce1e0dee81ae8689..d2c6b30248ebad920c41ca53ee38cce828dddb8c 100644
--- a/doc/doc_en/pgnet_en.md
+++ b/doc/doc_en/pgnet_en.md
@@ -24,9 +24,9 @@ The results of detection and recognition are as follows:
 ![](../imgs_results/e2e_res_img293_pgnet.png)
 ![](../imgs_results/e2e_res_img295_pgnet.png)
 ### Performance
-####Test set: Total Text
+#### Test set: Total Text
 
-####Test environment: NVIDIA Tesla V100-SXM2-16GB
+#### Test environment: NVIDIA Tesla V100-SXM2-16GB
 |PGNetA|det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS|download|
 | --- | --- | --- | --- | --- | --- | --- | --- | --- |
 |Paper|85.30|86.80|86.1|-|-|61.7|38.20 (size=640)|-|