apwic commited on
Commit
5f96fb5
1 Parent(s): 0aba29c

End of training

Browse files
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  license: mit
3
  base_model: indolem/indobert-base-uncased
4
  tags:
 
1
  ---
2
+ language:
3
+ - id
4
  license: mit
5
  base_model: indolem/indobert-base-uncased
6
  tags:
all_results.json CHANGED
@@ -17,10 +17,10 @@
17
  "eval_overall_f1": 0.9368029739776952,
18
  "eval_overall_precision": 0.9310344827586207,
19
  "eval_overall_recall": 0.942643391521197,
20
- "eval_runtime": 0.3222,
21
  "eval_samples": 170,
22
- "eval_samples_per_second": 527.605,
23
- "eval_steps_per_second": 9.311,
24
  "predict_LOCATION_f1": 0.9878048780487805,
25
  "predict_LOCATION_number": 245,
26
  "predict_LOCATION_precision": 0.9838056680161943,
@@ -38,12 +38,12 @@
38
  "predict_overall_f1": 0.9913793103448276,
39
  "predict_overall_precision": 0.9894837476099426,
40
  "predict_overall_recall": 0.9932821497120922,
41
- "predict_runtime": 0.7654,
42
- "predict_samples_per_second": 555.28,
43
- "predict_steps_per_second": 9.146,
44
  "train_loss": 0.03755435147012273,
45
- "train_runtime": 554.4341,
46
  "train_samples": 1531,
47
- "train_samples_per_second": 276.137,
48
- "train_steps_per_second": 17.315
49
  }
 
17
  "eval_overall_f1": 0.9368029739776952,
18
  "eval_overall_precision": 0.9310344827586207,
19
  "eval_overall_recall": 0.942643391521197,
20
+ "eval_runtime": 0.3027,
21
  "eval_samples": 170,
22
+ "eval_samples_per_second": 561.548,
23
+ "eval_steps_per_second": 9.91,
24
  "predict_LOCATION_f1": 0.9878048780487805,
25
  "predict_LOCATION_number": 245,
26
  "predict_LOCATION_precision": 0.9838056680161943,
 
38
  "predict_overall_f1": 0.9913793103448276,
39
  "predict_overall_precision": 0.9894837476099426,
40
  "predict_overall_recall": 0.9932821497120922,
41
+ "predict_runtime": 0.7486,
42
+ "predict_samples_per_second": 567.724,
43
+ "predict_steps_per_second": 9.351,
44
  "train_loss": 0.03755435147012273,
45
+ "train_runtime": 532.4294,
46
  "train_samples": 1531,
47
+ "train_samples_per_second": 287.55,
48
+ "train_steps_per_second": 18.031
49
  }
eval_results.json CHANGED
@@ -17,8 +17,8 @@
17
  "eval_overall_f1": 0.9368029739776952,
18
  "eval_overall_precision": 0.9310344827586207,
19
  "eval_overall_recall": 0.942643391521197,
20
- "eval_runtime": 0.3222,
21
  "eval_samples": 170,
22
- "eval_samples_per_second": 527.605,
23
- "eval_steps_per_second": 9.311
24
  }
 
17
  "eval_overall_f1": 0.9368029739776952,
18
  "eval_overall_precision": 0.9310344827586207,
19
  "eval_overall_recall": 0.942643391521197,
20
+ "eval_runtime": 0.3027,
21
  "eval_samples": 170,
22
+ "eval_samples_per_second": 561.548,
23
+ "eval_steps_per_second": 9.91
24
  }
predict_results.json CHANGED
@@ -16,7 +16,7 @@
16
  "predict_overall_f1": 0.9913793103448276,
17
  "predict_overall_precision": 0.9894837476099426,
18
  "predict_overall_recall": 0.9932821497120922,
19
- "predict_runtime": 0.7654,
20
- "predict_samples_per_second": 555.28,
21
- "predict_steps_per_second": 9.146
22
  }
 
16
  "predict_overall_f1": 0.9913793103448276,
17
  "predict_overall_precision": 0.9894837476099426,
18
  "predict_overall_recall": 0.9932821497120922,
19
+ "predict_runtime": 0.7486,
20
+ "predict_samples_per_second": 567.724,
21
+ "predict_steps_per_second": 9.351
22
  }
runs/Jun04_10-22-35_a358b85c7679/events.out.tfevents.1717497101.a358b85c7679.622750.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73eee2401e963ddfb59382937db66c63dbc94103df75ae8591587736722a5d0
3
+ size 1305
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 100.0,
3
  "train_loss": 0.03755435147012273,
4
- "train_runtime": 554.4341,
5
  "train_samples": 1531,
6
- "train_samples_per_second": 276.137,
7
- "train_steps_per_second": 17.315
8
  }
 
1
  {
2
  "epoch": 100.0,
3
  "train_loss": 0.03755435147012273,
4
+ "train_runtime": 532.4294,
5
  "train_samples": 1531,
6
+ "train_samples_per_second": 287.55,
7
+ "train_steps_per_second": 18.031
8
  }
trainer_state.json CHANGED
@@ -35,7 +35,7 @@
35
  "eval_overall_precision": 0.24620060790273557,
36
  "eval_overall_recall": 0.20199501246882792,
37
  "eval_runtime": 0.2929,
38
- "eval_samples_per_second": 580.415,
39
  "eval_steps_per_second": 10.243,
40
  "step": 96
41
  },
@@ -65,9 +65,9 @@
65
  "eval_overall_f1": 0.5772266065388952,
66
  "eval_overall_precision": 0.5267489711934157,
67
  "eval_overall_recall": 0.6384039900249376,
68
- "eval_runtime": 0.2904,
69
- "eval_samples_per_second": 585.432,
70
- "eval_steps_per_second": 10.331,
71
  "step": 192
72
  },
73
  {
@@ -96,9 +96,9 @@
96
  "eval_overall_f1": 0.826923076923077,
97
  "eval_overall_precision": 0.7981438515081206,
98
  "eval_overall_recall": 0.85785536159601,
99
- "eval_runtime": 0.2959,
100
- "eval_samples_per_second": 574.554,
101
- "eval_steps_per_second": 10.139,
102
  "step": 288
103
  },
104
  {
@@ -127,9 +127,9 @@
127
  "eval_overall_f1": 0.8501170960187353,
128
  "eval_overall_precision": 0.8013245033112583,
129
  "eval_overall_recall": 0.9052369077306733,
130
- "eval_runtime": 0.2924,
131
- "eval_samples_per_second": 581.361,
132
- "eval_steps_per_second": 10.259,
133
  "step": 384
134
  },
135
  {
@@ -158,9 +158,9 @@
158
  "eval_overall_f1": 0.8985148514851485,
159
  "eval_overall_precision": 0.8918918918918919,
160
  "eval_overall_recall": 0.9052369077306733,
161
- "eval_runtime": 0.2962,
162
- "eval_samples_per_second": 573.926,
163
- "eval_steps_per_second": 10.128,
164
  "step": 480
165
  },
166
  {
@@ -189,9 +189,9 @@
189
  "eval_overall_f1": 0.8913308913308914,
190
  "eval_overall_precision": 0.8732057416267942,
191
  "eval_overall_recall": 0.9102244389027432,
192
- "eval_runtime": 0.2937,
193
- "eval_samples_per_second": 578.83,
194
- "eval_steps_per_second": 10.215,
195
  "step": 576
196
  },
197
  {
@@ -220,9 +220,9 @@
220
  "eval_overall_f1": 0.9106280193236714,
221
  "eval_overall_precision": 0.882903981264637,
222
  "eval_overall_recall": 0.940149625935162,
223
- "eval_runtime": 0.2926,
224
- "eval_samples_per_second": 581.049,
225
- "eval_steps_per_second": 10.254,
226
  "step": 672
227
  },
228
  {
@@ -251,9 +251,9 @@
251
  "eval_overall_f1": 0.9245742092457422,
252
  "eval_overall_precision": 0.9026128266033254,
253
  "eval_overall_recall": 0.9476309226932669,
254
- "eval_runtime": 0.2917,
255
- "eval_samples_per_second": 582.8,
256
- "eval_steps_per_second": 10.285,
257
  "step": 768
258
  },
259
  {
@@ -282,9 +282,9 @@
282
  "eval_overall_f1": 0.9185185185185184,
283
  "eval_overall_precision": 0.9095354523227384,
284
  "eval_overall_recall": 0.9276807980049875,
285
- "eval_runtime": 0.2908,
286
- "eval_samples_per_second": 584.625,
287
- "eval_steps_per_second": 10.317,
288
  "step": 864
289
  },
290
  {
@@ -313,9 +313,9 @@
313
  "eval_overall_f1": 0.9392812887236679,
314
  "eval_overall_precision": 0.9334975369458128,
315
  "eval_overall_recall": 0.9451371571072319,
316
- "eval_runtime": 0.2893,
317
- "eval_samples_per_second": 587.659,
318
- "eval_steps_per_second": 10.37,
319
  "step": 960
320
  },
321
  {
@@ -344,9 +344,9 @@
344
  "eval_overall_f1": 0.9353233830845771,
345
  "eval_overall_precision": 0.9330024813895782,
346
  "eval_overall_recall": 0.9376558603491272,
347
- "eval_runtime": 0.2913,
348
- "eval_samples_per_second": 583.542,
349
- "eval_steps_per_second": 10.298,
350
  "step": 1056
351
  },
352
  {
@@ -375,9 +375,9 @@
375
  "eval_overall_f1": 0.9321824907521579,
376
  "eval_overall_precision": 0.9219512195121952,
377
  "eval_overall_recall": 0.942643391521197,
378
- "eval_runtime": 0.2923,
379
- "eval_samples_per_second": 581.688,
380
- "eval_steps_per_second": 10.265,
381
  "step": 1152
382
  },
383
  {
@@ -406,9 +406,9 @@
406
  "eval_overall_f1": 0.9443757725587144,
407
  "eval_overall_precision": 0.9362745098039216,
408
  "eval_overall_recall": 0.9526184538653366,
409
- "eval_runtime": 0.2913,
410
- "eval_samples_per_second": 583.67,
411
- "eval_steps_per_second": 10.3,
412
  "step": 1248
413
  },
414
  {
@@ -437,9 +437,9 @@
437
  "eval_overall_f1": 0.9490683229813663,
438
  "eval_overall_precision": 0.9455445544554455,
439
  "eval_overall_recall": 0.9526184538653366,
440
- "eval_runtime": 0.2937,
441
- "eval_samples_per_second": 578.827,
442
- "eval_steps_per_second": 10.215,
443
  "step": 1344
444
  },
445
  {
@@ -468,9 +468,9 @@
468
  "eval_overall_f1": 0.9480198019801981,
469
  "eval_overall_precision": 0.941031941031941,
470
  "eval_overall_recall": 0.9551122194513716,
471
- "eval_runtime": 0.2936,
472
- "eval_samples_per_second": 578.975,
473
- "eval_steps_per_second": 10.217,
474
  "step": 1440
475
  },
476
  {
@@ -499,9 +499,9 @@
499
  "eval_overall_f1": 0.9287469287469288,
500
  "eval_overall_precision": 0.9152542372881356,
501
  "eval_overall_recall": 0.942643391521197,
502
- "eval_runtime": 0.2919,
503
- "eval_samples_per_second": 582.42,
504
- "eval_steps_per_second": 10.278,
505
  "step": 1536
506
  },
507
  {
@@ -530,9 +530,9 @@
530
  "eval_overall_f1": 0.9504950495049505,
531
  "eval_overall_precision": 0.9434889434889435,
532
  "eval_overall_recall": 0.9576059850374065,
533
- "eval_runtime": 0.2923,
534
- "eval_samples_per_second": 581.575,
535
- "eval_steps_per_second": 10.263,
536
  "step": 1632
537
  },
538
  {
@@ -561,9 +561,9 @@
561
  "eval_overall_f1": 0.946716232961586,
562
  "eval_overall_precision": 0.9408866995073891,
563
  "eval_overall_recall": 0.9526184538653366,
564
- "eval_runtime": 0.291,
565
- "eval_samples_per_second": 584.152,
566
- "eval_steps_per_second": 10.309,
567
  "step": 1728
568
  },
569
  {
@@ -592,9 +592,9 @@
592
  "eval_overall_f1": 0.946716232961586,
593
  "eval_overall_precision": 0.9408866995073891,
594
  "eval_overall_recall": 0.9526184538653366,
595
- "eval_runtime": 0.2903,
596
- "eval_samples_per_second": 585.592,
597
- "eval_steps_per_second": 10.334,
598
  "step": 1824
599
  },
600
  {
@@ -623,9 +623,9 @@
623
  "eval_overall_f1": 0.9458128078817734,
624
  "eval_overall_precision": 0.9343065693430657,
625
  "eval_overall_recall": 0.9576059850374065,
626
- "eval_runtime": 0.2926,
627
- "eval_samples_per_second": 581.005,
628
- "eval_steps_per_second": 10.253,
629
  "step": 1920
630
  },
631
  {
@@ -654,9 +654,9 @@
654
  "eval_overall_f1": 0.9443757725587144,
655
  "eval_overall_precision": 0.9362745098039216,
656
  "eval_overall_recall": 0.9526184538653366,
657
- "eval_runtime": 0.2909,
658
- "eval_samples_per_second": 584.394,
659
- "eval_steps_per_second": 10.313,
660
  "step": 2016
661
  },
662
  {
@@ -685,9 +685,9 @@
685
  "eval_overall_f1": 0.941031941031941,
686
  "eval_overall_precision": 0.927360774818402,
687
  "eval_overall_recall": 0.9551122194513716,
688
- "eval_runtime": 0.2951,
689
- "eval_samples_per_second": 576.049,
690
- "eval_steps_per_second": 10.166,
691
  "step": 2112
692
  },
693
  {
@@ -716,9 +716,9 @@
716
  "eval_overall_f1": 0.9381188118811881,
717
  "eval_overall_precision": 0.9312039312039312,
718
  "eval_overall_recall": 0.9451371571072319,
719
- "eval_runtime": 0.2946,
720
- "eval_samples_per_second": 577.009,
721
- "eval_steps_per_second": 10.183,
722
  "step": 2208
723
  },
724
  {
@@ -747,9 +747,9 @@
747
  "eval_overall_f1": 0.9468479604449938,
748
  "eval_overall_precision": 0.9387254901960784,
749
  "eval_overall_recall": 0.9551122194513716,
750
- "eval_runtime": 0.2916,
751
- "eval_samples_per_second": 582.943,
752
- "eval_steps_per_second": 10.287,
753
  "step": 2304
754
  },
755
  {
@@ -778,9 +778,9 @@
778
  "eval_overall_f1": 0.9318463444857497,
779
  "eval_overall_precision": 0.9261083743842364,
780
  "eval_overall_recall": 0.9376558603491272,
781
- "eval_runtime": 0.2914,
782
- "eval_samples_per_second": 583.339,
783
- "eval_steps_per_second": 10.294,
784
  "step": 2400
785
  },
786
  {
@@ -809,9 +809,9 @@
809
  "eval_overall_f1": 0.9464508094645082,
810
  "eval_overall_precision": 0.945273631840796,
811
  "eval_overall_recall": 0.9476309226932669,
812
- "eval_runtime": 0.2914,
813
- "eval_samples_per_second": 583.325,
814
- "eval_steps_per_second": 10.294,
815
  "step": 2496
816
  },
817
  {
@@ -840,9 +840,9 @@
840
  "eval_overall_f1": 0.942189421894219,
841
  "eval_overall_precision": 0.9296116504854369,
842
  "eval_overall_recall": 0.9551122194513716,
843
- "eval_runtime": 0.2945,
844
- "eval_samples_per_second": 577.282,
845
- "eval_steps_per_second": 10.187,
846
  "step": 2592
847
  },
848
  {
@@ -871,9 +871,9 @@
871
  "eval_overall_f1": 0.944649446494465,
872
  "eval_overall_precision": 0.9320388349514563,
873
  "eval_overall_recall": 0.9576059850374065,
874
- "eval_runtime": 0.2919,
875
- "eval_samples_per_second": 582.353,
876
- "eval_steps_per_second": 10.277,
877
  "step": 2688
878
  },
879
  {
@@ -902,9 +902,9 @@
902
  "eval_overall_f1": 0.9433497536945813,
903
  "eval_overall_precision": 0.9318734793187348,
904
  "eval_overall_recall": 0.9551122194513716,
905
- "eval_runtime": 0.2947,
906
- "eval_samples_per_second": 576.863,
907
- "eval_steps_per_second": 10.18,
908
  "step": 2784
909
  },
910
  {
@@ -933,9 +933,9 @@
933
  "eval_overall_f1": 0.9423312883435583,
934
  "eval_overall_precision": 0.927536231884058,
935
  "eval_overall_recall": 0.9576059850374065,
936
- "eval_runtime": 0.2921,
937
- "eval_samples_per_second": 581.974,
938
- "eval_steps_per_second": 10.27,
939
  "step": 2880
940
  },
941
  {
@@ -964,9 +964,9 @@
964
  "eval_overall_f1": 0.9371146732429101,
965
  "eval_overall_precision": 0.926829268292683,
966
  "eval_overall_recall": 0.9476309226932669,
967
- "eval_runtime": 0.2918,
968
- "eval_samples_per_second": 582.684,
969
- "eval_steps_per_second": 10.283,
970
  "step": 2976
971
  },
972
  {
@@ -995,9 +995,9 @@
995
  "eval_overall_f1": 0.9438202247191011,
996
  "eval_overall_precision": 0.945,
997
  "eval_overall_recall": 0.942643391521197,
998
- "eval_runtime": 0.2907,
999
- "eval_samples_per_second": 584.728,
1000
- "eval_steps_per_second": 10.319,
1001
  "step": 3072
1002
  },
1003
  {
@@ -1026,9 +1026,9 @@
1026
  "eval_overall_f1": 0.9443757725587144,
1027
  "eval_overall_precision": 0.9362745098039216,
1028
  "eval_overall_recall": 0.9526184538653366,
1029
- "eval_runtime": 0.2912,
1030
- "eval_samples_per_second": 583.778,
1031
- "eval_steps_per_second": 10.302,
1032
  "step": 3168
1033
  },
1034
  {
@@ -1057,9 +1057,9 @@
1057
  "eval_overall_f1": 0.9407407407407408,
1058
  "eval_overall_precision": 0.9315403422982885,
1059
  "eval_overall_recall": 0.9501246882793017,
1060
- "eval_runtime": 0.2886,
1061
- "eval_samples_per_second": 589.007,
1062
- "eval_steps_per_second": 10.394,
1063
  "step": 3264
1064
  },
1065
  {
@@ -1088,9 +1088,9 @@
1088
  "eval_overall_f1": 0.9346485819975339,
1089
  "eval_overall_precision": 0.9243902439024391,
1090
  "eval_overall_recall": 0.9451371571072319,
1091
- "eval_runtime": 0.2907,
1092
- "eval_samples_per_second": 584.806,
1093
- "eval_steps_per_second": 10.32,
1094
  "step": 3360
1095
  },
1096
  {
@@ -1119,9 +1119,9 @@
1119
  "eval_overall_f1": 0.9404466501240694,
1120
  "eval_overall_precision": 0.9358024691358025,
1121
  "eval_overall_recall": 0.9451371571072319,
1122
- "eval_runtime": 0.2901,
1123
- "eval_samples_per_second": 586.08,
1124
- "eval_steps_per_second": 10.343,
1125
  "step": 3456
1126
  },
1127
  {
@@ -1150,9 +1150,9 @@
1150
  "eval_overall_f1": 0.9404466501240694,
1151
  "eval_overall_precision": 0.9358024691358025,
1152
  "eval_overall_recall": 0.9451371571072319,
1153
- "eval_runtime": 0.2893,
1154
- "eval_samples_per_second": 587.579,
1155
- "eval_steps_per_second": 10.369,
1156
  "step": 3552
1157
  },
1158
  {
@@ -1181,9 +1181,9 @@
1181
  "eval_overall_f1": 0.9416149068322982,
1182
  "eval_overall_precision": 0.9381188118811881,
1183
  "eval_overall_recall": 0.9451371571072319,
1184
- "eval_runtime": 0.2898,
1185
- "eval_samples_per_second": 586.556,
1186
- "eval_steps_per_second": 10.351,
1187
  "step": 3648
1188
  },
1189
  {
@@ -1212,9 +1212,9 @@
1212
  "eval_overall_f1": 0.9354838709677419,
1213
  "eval_overall_precision": 0.9308641975308642,
1214
  "eval_overall_recall": 0.940149625935162,
1215
- "eval_runtime": 0.288,
1216
- "eval_samples_per_second": 590.367,
1217
- "eval_steps_per_second": 10.418,
1218
  "step": 3744
1219
  },
1220
  {
@@ -1243,9 +1243,9 @@
1243
  "eval_overall_f1": 0.9285714285714285,
1244
  "eval_overall_precision": 0.9172749391727494,
1245
  "eval_overall_recall": 0.940149625935162,
1246
- "eval_runtime": 0.2891,
1247
- "eval_samples_per_second": 588.081,
1248
- "eval_steps_per_second": 10.378,
1249
  "step": 3840
1250
  },
1251
  {
@@ -1274,9 +1274,9 @@
1274
  "eval_overall_f1": 0.9249692496924969,
1275
  "eval_overall_precision": 0.912621359223301,
1276
  "eval_overall_recall": 0.9376558603491272,
1277
- "eval_runtime": 0.2901,
1278
- "eval_samples_per_second": 586.09,
1279
- "eval_steps_per_second": 10.343,
1280
  "step": 3936
1281
  },
1282
  {
@@ -1305,9 +1305,9 @@
1305
  "eval_overall_f1": 0.9320148331273177,
1306
  "eval_overall_precision": 0.9240196078431373,
1307
  "eval_overall_recall": 0.940149625935162,
1308
- "eval_runtime": 0.2902,
1309
- "eval_samples_per_second": 585.717,
1310
- "eval_steps_per_second": 10.336,
1311
  "step": 4032
1312
  },
1313
  {
@@ -1336,9 +1336,9 @@
1336
  "eval_overall_f1": 0.9402985074626866,
1337
  "eval_overall_precision": 0.9379652605459057,
1338
  "eval_overall_recall": 0.942643391521197,
1339
- "eval_runtime": 0.2865,
1340
- "eval_samples_per_second": 593.421,
1341
- "eval_steps_per_second": 10.472,
1342
  "step": 4128
1343
  },
1344
  {
@@ -1367,9 +1367,9 @@
1367
  "eval_overall_f1": 0.9293680297397771,
1368
  "eval_overall_precision": 0.9236453201970444,
1369
  "eval_overall_recall": 0.9351620947630923,
1370
- "eval_runtime": 0.2944,
1371
- "eval_samples_per_second": 577.415,
1372
- "eval_steps_per_second": 10.19,
1373
  "step": 4224
1374
  },
1375
  {
@@ -1398,9 +1398,9 @@
1398
  "eval_overall_f1": 0.9353233830845771,
1399
  "eval_overall_precision": 0.9330024813895782,
1400
  "eval_overall_recall": 0.9376558603491272,
1401
- "eval_runtime": 0.2902,
1402
- "eval_samples_per_second": 585.832,
1403
- "eval_steps_per_second": 10.338,
1404
  "step": 4320
1405
  },
1406
  {
@@ -1429,9 +1429,9 @@
1429
  "eval_overall_f1": 0.9282178217821783,
1430
  "eval_overall_precision": 0.9213759213759214,
1431
  "eval_overall_recall": 0.9351620947630923,
1432
- "eval_runtime": 0.2867,
1433
- "eval_samples_per_second": 593.025,
1434
- "eval_steps_per_second": 10.465,
1435
  "step": 4416
1436
  },
1437
  {
@@ -1460,9 +1460,9 @@
1460
  "eval_overall_f1": 0.9432098765432098,
1461
  "eval_overall_precision": 0.9339853300733496,
1462
  "eval_overall_recall": 0.9526184538653366,
1463
- "eval_runtime": 0.288,
1464
- "eval_samples_per_second": 590.188,
1465
- "eval_steps_per_second": 10.415,
1466
  "step": 4512
1467
  },
1468
  {
@@ -1491,9 +1491,9 @@
1491
  "eval_overall_f1": 0.9392812887236679,
1492
  "eval_overall_precision": 0.9334975369458128,
1493
  "eval_overall_recall": 0.9451371571072319,
1494
- "eval_runtime": 0.2902,
1495
- "eval_samples_per_second": 585.775,
1496
- "eval_steps_per_second": 10.337,
1497
  "step": 4608
1498
  },
1499
  {
@@ -1522,9 +1522,9 @@
1522
  "eval_overall_f1": 0.9478908188585606,
1523
  "eval_overall_precision": 0.9432098765432099,
1524
  "eval_overall_recall": 0.9526184538653366,
1525
- "eval_runtime": 0.2898,
1526
- "eval_samples_per_second": 586.57,
1527
- "eval_steps_per_second": 10.351,
1528
  "step": 4704
1529
  },
1530
  {
@@ -1553,9 +1553,9 @@
1553
  "eval_overall_f1": 0.9346485819975339,
1554
  "eval_overall_precision": 0.9243902439024391,
1555
  "eval_overall_recall": 0.9451371571072319,
1556
- "eval_runtime": 0.2884,
1557
- "eval_samples_per_second": 589.476,
1558
- "eval_steps_per_second": 10.403,
1559
  "step": 4800
1560
  },
1561
  {
@@ -1584,9 +1584,9 @@
1584
  "eval_overall_f1": 0.9344870210135972,
1585
  "eval_overall_precision": 0.9264705882352942,
1586
  "eval_overall_recall": 0.942643391521197,
1587
- "eval_runtime": 0.2909,
1588
- "eval_samples_per_second": 584.325,
1589
- "eval_steps_per_second": 10.312,
1590
  "step": 4896
1591
  },
1592
  {
@@ -1615,9 +1615,9 @@
1615
  "eval_overall_f1": 0.9297163995067818,
1616
  "eval_overall_precision": 0.9195121951219513,
1617
  "eval_overall_recall": 0.940149625935162,
1618
- "eval_runtime": 0.2901,
1619
- "eval_samples_per_second": 585.943,
1620
- "eval_steps_per_second": 10.34,
1621
  "step": 4992
1622
  },
1623
  {
@@ -1646,9 +1646,9 @@
1646
  "eval_overall_f1": 0.9356435643564357,
1647
  "eval_overall_precision": 0.9287469287469288,
1648
  "eval_overall_recall": 0.942643391521197,
1649
- "eval_runtime": 0.2903,
1650
- "eval_samples_per_second": 585.535,
1651
- "eval_steps_per_second": 10.333,
1652
  "step": 5088
1653
  },
1654
  {
@@ -1677,9 +1677,9 @@
1677
  "eval_overall_f1": 0.9326805385556914,
1678
  "eval_overall_precision": 0.9158653846153846,
1679
  "eval_overall_recall": 0.9501246882793017,
1680
- "eval_runtime": 0.2903,
1681
- "eval_samples_per_second": 585.543,
1682
- "eval_steps_per_second": 10.333,
1683
  "step": 5184
1684
  },
1685
  {
@@ -1708,9 +1708,9 @@
1708
  "eval_overall_f1": 0.9378109452736318,
1709
  "eval_overall_precision": 0.9354838709677419,
1710
  "eval_overall_recall": 0.940149625935162,
1711
- "eval_runtime": 0.2896,
1712
- "eval_samples_per_second": 587.102,
1713
- "eval_steps_per_second": 10.361,
1714
  "step": 5280
1715
  },
1716
  {
@@ -1739,9 +1739,9 @@
1739
  "eval_overall_f1": 0.9379652605459058,
1740
  "eval_overall_precision": 0.9333333333333333,
1741
  "eval_overall_recall": 0.942643391521197,
1742
- "eval_runtime": 0.2893,
1743
- "eval_samples_per_second": 587.723,
1744
- "eval_steps_per_second": 10.372,
1745
  "step": 5376
1746
  },
1747
  {
@@ -1770,9 +1770,9 @@
1770
  "eval_overall_f1": 0.9392812887236679,
1771
  "eval_overall_precision": 0.9334975369458128,
1772
  "eval_overall_recall": 0.9451371571072319,
1773
- "eval_runtime": 0.2876,
1774
- "eval_samples_per_second": 591.033,
1775
- "eval_steps_per_second": 10.43,
1776
  "step": 5472
1777
  },
1778
  {
@@ -1801,9 +1801,9 @@
1801
  "eval_overall_f1": 0.9429280397022332,
1802
  "eval_overall_precision": 0.9382716049382716,
1803
  "eval_overall_recall": 0.9476309226932669,
1804
- "eval_runtime": 0.2942,
1805
- "eval_samples_per_second": 577.895,
1806
- "eval_steps_per_second": 10.198,
1807
  "step": 5568
1808
  },
1809
  {
@@ -1832,9 +1832,9 @@
1832
  "eval_overall_f1": 0.9375,
1833
  "eval_overall_precision": 0.9398496240601504,
1834
  "eval_overall_recall": 0.9351620947630923,
1835
- "eval_runtime": 0.2885,
1836
- "eval_samples_per_second": 589.346,
1837
- "eval_steps_per_second": 10.4,
1838
  "step": 5664
1839
  },
1840
  {
@@ -1863,9 +1863,9 @@
1863
  "eval_overall_f1": 0.9330024813895781,
1864
  "eval_overall_precision": 0.928395061728395,
1865
  "eval_overall_recall": 0.9376558603491272,
1866
- "eval_runtime": 0.2915,
1867
- "eval_samples_per_second": 583.278,
1868
- "eval_steps_per_second": 10.293,
1869
  "step": 5760
1870
  },
1871
  {
@@ -1894,9 +1894,9 @@
1894
  "eval_overall_f1": 0.935,
1895
  "eval_overall_precision": 0.9373433583959899,
1896
  "eval_overall_recall": 0.9326683291770573,
1897
- "eval_runtime": 0.2896,
1898
- "eval_samples_per_second": 587.057,
1899
- "eval_steps_per_second": 10.36,
1900
  "step": 5856
1901
  },
1902
  {
@@ -1925,9 +1925,9 @@
1925
  "eval_overall_f1": 0.9369592088998765,
1926
  "eval_overall_precision": 0.928921568627451,
1927
  "eval_overall_recall": 0.9451371571072319,
1928
- "eval_runtime": 0.2911,
1929
- "eval_samples_per_second": 583.943,
1930
- "eval_steps_per_second": 10.305,
1931
  "step": 5952
1932
  },
1933
  {
@@ -1956,9 +1956,9 @@
1956
  "eval_overall_f1": 0.9442379182156134,
1957
  "eval_overall_precision": 0.9384236453201971,
1958
  "eval_overall_recall": 0.9501246882793017,
1959
- "eval_runtime": 0.2883,
1960
- "eval_samples_per_second": 589.687,
1961
- "eval_steps_per_second": 10.406,
1962
  "step": 6048
1963
  },
1964
  {
@@ -1987,9 +1987,9 @@
1987
  "eval_overall_f1": 0.9440993788819876,
1988
  "eval_overall_precision": 0.9405940594059405,
1989
  "eval_overall_recall": 0.9476309226932669,
1990
- "eval_runtime": 0.2886,
1991
- "eval_samples_per_second": 588.967,
1992
- "eval_steps_per_second": 10.394,
1993
  "step": 6144
1994
  },
1995
  {
@@ -2018,9 +2018,9 @@
2018
  "eval_overall_f1": 0.9356435643564357,
2019
  "eval_overall_precision": 0.9287469287469288,
2020
  "eval_overall_recall": 0.942643391521197,
2021
- "eval_runtime": 0.2889,
2022
- "eval_samples_per_second": 588.45,
2023
- "eval_steps_per_second": 10.384,
2024
  "step": 6240
2025
  },
2026
  {
@@ -2049,9 +2049,9 @@
2049
  "eval_overall_f1": 0.9315068493150686,
2050
  "eval_overall_precision": 0.9303482587064676,
2051
  "eval_overall_recall": 0.9326683291770573,
2052
- "eval_runtime": 0.2942,
2053
- "eval_samples_per_second": 577.799,
2054
- "eval_steps_per_second": 10.196,
2055
  "step": 6336
2056
  },
2057
  {
@@ -2080,9 +2080,9 @@
2080
  "eval_overall_f1": 0.9405940594059405,
2081
  "eval_overall_precision": 0.9336609336609336,
2082
  "eval_overall_recall": 0.9476309226932669,
2083
- "eval_runtime": 0.2905,
2084
- "eval_samples_per_second": 585.283,
2085
- "eval_steps_per_second": 10.329,
2086
  "step": 6432
2087
  },
2088
  {
@@ -2111,9 +2111,9 @@
2111
  "eval_overall_f1": 0.9419035846724352,
2112
  "eval_overall_precision": 0.9338235294117647,
2113
  "eval_overall_recall": 0.9501246882793017,
2114
- "eval_runtime": 0.2879,
2115
- "eval_samples_per_second": 590.566,
2116
- "eval_steps_per_second": 10.422,
2117
  "step": 6528
2118
  },
2119
  {
@@ -2142,9 +2142,9 @@
2142
  "eval_overall_f1": 0.9379652605459058,
2143
  "eval_overall_precision": 0.9333333333333333,
2144
  "eval_overall_recall": 0.942643391521197,
2145
- "eval_runtime": 0.2896,
2146
- "eval_samples_per_second": 586.973,
2147
- "eval_steps_per_second": 10.358,
2148
  "step": 6624
2149
  },
2150
  {
@@ -2173,9 +2173,9 @@
2173
  "eval_overall_f1": 0.9392812887236679,
2174
  "eval_overall_precision": 0.9334975369458128,
2175
  "eval_overall_recall": 0.9451371571072319,
2176
- "eval_runtime": 0.2897,
2177
- "eval_samples_per_second": 586.718,
2178
- "eval_steps_per_second": 10.354,
2179
  "step": 6720
2180
  },
2181
  {
@@ -2204,9 +2204,9 @@
2204
  "eval_overall_f1": 0.9344870210135972,
2205
  "eval_overall_precision": 0.9264705882352942,
2206
  "eval_overall_recall": 0.942643391521197,
2207
- "eval_runtime": 0.2903,
2208
- "eval_samples_per_second": 585.692,
2209
- "eval_steps_per_second": 10.336,
2210
  "step": 6816
2211
  },
2212
  {
@@ -2235,9 +2235,9 @@
2235
  "eval_overall_f1": 0.9416149068322982,
2236
  "eval_overall_precision": 0.9381188118811881,
2237
  "eval_overall_recall": 0.9451371571072319,
2238
- "eval_runtime": 0.2905,
2239
- "eval_samples_per_second": 585.264,
2240
- "eval_steps_per_second": 10.328,
2241
  "step": 6912
2242
  },
2243
  {
@@ -2266,9 +2266,9 @@
2266
  "eval_overall_f1": 0.9318463444857497,
2267
  "eval_overall_precision": 0.9261083743842364,
2268
  "eval_overall_recall": 0.9376558603491272,
2269
- "eval_runtime": 0.2922,
2270
- "eval_samples_per_second": 581.854,
2271
- "eval_steps_per_second": 10.268,
2272
  "step": 7008
2273
  },
2274
  {
@@ -2297,9 +2297,9 @@
2297
  "eval_overall_f1": 0.9356435643564357,
2298
  "eval_overall_precision": 0.9287469287469288,
2299
  "eval_overall_recall": 0.942643391521197,
2300
- "eval_runtime": 0.2892,
2301
- "eval_samples_per_second": 587.781,
2302
- "eval_steps_per_second": 10.373,
2303
  "step": 7104
2304
  },
2305
  {
@@ -2328,9 +2328,9 @@
2328
  "eval_overall_f1": 0.9257425742574258,
2329
  "eval_overall_precision": 0.918918918918919,
2330
  "eval_overall_recall": 0.9326683291770573,
2331
- "eval_runtime": 0.2896,
2332
- "eval_samples_per_second": 586.938,
2333
- "eval_steps_per_second": 10.358,
2334
  "step": 7200
2335
  },
2336
  {
@@ -2359,9 +2359,9 @@
2359
  "eval_overall_f1": 0.9369592088998765,
2360
  "eval_overall_precision": 0.928921568627451,
2361
  "eval_overall_recall": 0.9451371571072319,
2362
- "eval_runtime": 0.2896,
2363
- "eval_samples_per_second": 587.037,
2364
- "eval_steps_per_second": 10.359,
2365
  "step": 7296
2366
  },
2367
  {
@@ -2390,9 +2390,9 @@
2390
  "eval_overall_f1": 0.9391304347826087,
2391
  "eval_overall_precision": 0.9356435643564357,
2392
  "eval_overall_recall": 0.942643391521197,
2393
- "eval_runtime": 0.2891,
2394
- "eval_samples_per_second": 588.107,
2395
- "eval_steps_per_second": 10.378,
2396
  "step": 7392
2397
  },
2398
  {
@@ -2421,9 +2421,9 @@
2421
  "eval_overall_f1": 0.9293680297397771,
2422
  "eval_overall_precision": 0.9236453201970444,
2423
  "eval_overall_recall": 0.9351620947630923,
2424
- "eval_runtime": 0.2872,
2425
- "eval_samples_per_second": 591.943,
2426
- "eval_steps_per_second": 10.446,
2427
  "step": 7488
2428
  },
2429
  {
@@ -2452,9 +2452,9 @@
2452
  "eval_overall_f1": 0.9320148331273177,
2453
  "eval_overall_precision": 0.9240196078431373,
2454
  "eval_overall_recall": 0.940149625935162,
2455
- "eval_runtime": 0.291,
2456
- "eval_samples_per_second": 584.258,
2457
- "eval_steps_per_second": 10.31,
2458
  "step": 7584
2459
  },
2460
  {
@@ -2483,9 +2483,9 @@
2483
  "eval_overall_f1": 0.9356435643564357,
2484
  "eval_overall_precision": 0.9287469287469288,
2485
  "eval_overall_recall": 0.942643391521197,
2486
- "eval_runtime": 0.2881,
2487
- "eval_samples_per_second": 590.06,
2488
- "eval_steps_per_second": 10.413,
2489
  "step": 7680
2490
  },
2491
  {
@@ -2514,9 +2514,9 @@
2514
  "eval_overall_f1": 0.9344870210135972,
2515
  "eval_overall_precision": 0.9264705882352942,
2516
  "eval_overall_recall": 0.942643391521197,
2517
- "eval_runtime": 0.2887,
2518
- "eval_samples_per_second": 588.812,
2519
- "eval_steps_per_second": 10.391,
2520
  "step": 7776
2521
  },
2522
  {
@@ -2545,9 +2545,9 @@
2545
  "eval_overall_f1": 0.9343246592317225,
2546
  "eval_overall_precision": 0.9285714285714286,
2547
  "eval_overall_recall": 0.940149625935162,
2548
- "eval_runtime": 0.2908,
2549
- "eval_samples_per_second": 584.583,
2550
- "eval_steps_per_second": 10.316,
2551
  "step": 7872
2552
  },
2553
  {
@@ -2576,9 +2576,9 @@
2576
  "eval_overall_f1": 0.9392812887236679,
2577
  "eval_overall_precision": 0.9334975369458128,
2578
  "eval_overall_recall": 0.9451371571072319,
2579
- "eval_runtime": 0.2899,
2580
- "eval_samples_per_second": 586.334,
2581
- "eval_steps_per_second": 10.347,
2582
  "step": 7968
2583
  },
2584
  {
@@ -2607,9 +2607,9 @@
2607
  "eval_overall_f1": 0.9391304347826087,
2608
  "eval_overall_precision": 0.9356435643564357,
2609
  "eval_overall_recall": 0.942643391521197,
2610
- "eval_runtime": 0.2882,
2611
- "eval_samples_per_second": 589.934,
2612
- "eval_steps_per_second": 10.411,
2613
  "step": 8064
2614
  },
2615
  {
@@ -2638,9 +2638,9 @@
2638
  "eval_overall_f1": 0.9405940594059405,
2639
  "eval_overall_precision": 0.9336609336609336,
2640
  "eval_overall_recall": 0.9476309226932669,
2641
- "eval_runtime": 0.2876,
2642
- "eval_samples_per_second": 591.174,
2643
- "eval_steps_per_second": 10.432,
2644
  "step": 8160
2645
  },
2646
  {
@@ -2669,9 +2669,9 @@
2669
  "eval_overall_f1": 0.9343246592317225,
2670
  "eval_overall_precision": 0.9285714285714286,
2671
  "eval_overall_recall": 0.940149625935162,
2672
- "eval_runtime": 0.2903,
2673
- "eval_samples_per_second": 585.654,
2674
- "eval_steps_per_second": 10.335,
2675
  "step": 8256
2676
  },
2677
  {
@@ -2700,9 +2700,9 @@
2700
  "eval_overall_f1": 0.9429280397022332,
2701
  "eval_overall_precision": 0.9382716049382716,
2702
  "eval_overall_recall": 0.9476309226932669,
2703
- "eval_runtime": 0.2878,
2704
- "eval_samples_per_second": 590.656,
2705
- "eval_steps_per_second": 10.423,
2706
  "step": 8352
2707
  },
2708
  {
@@ -2731,9 +2731,9 @@
2731
  "eval_overall_f1": 0.9366459627329192,
2732
  "eval_overall_precision": 0.9331683168316832,
2733
  "eval_overall_recall": 0.940149625935162,
2734
- "eval_runtime": 0.2916,
2735
- "eval_samples_per_second": 582.955,
2736
- "eval_steps_per_second": 10.287,
2737
  "step": 8448
2738
  },
2739
  {
@@ -2762,9 +2762,9 @@
2762
  "eval_overall_f1": 0.9356435643564357,
2763
  "eval_overall_precision": 0.9287469287469288,
2764
  "eval_overall_recall": 0.942643391521197,
2765
- "eval_runtime": 0.2879,
2766
- "eval_samples_per_second": 590.424,
2767
- "eval_steps_per_second": 10.419,
2768
  "step": 8544
2769
  },
2770
  {
@@ -2793,9 +2793,9 @@
2793
  "eval_overall_f1": 0.9417596034696407,
2794
  "eval_overall_precision": 0.9359605911330049,
2795
  "eval_overall_recall": 0.9476309226932669,
2796
- "eval_runtime": 0.2886,
2797
- "eval_samples_per_second": 589.092,
2798
- "eval_steps_per_second": 10.396,
2799
  "step": 8640
2800
  },
2801
  {
@@ -2824,9 +2824,9 @@
2824
  "eval_overall_f1": 0.9356435643564357,
2825
  "eval_overall_precision": 0.9287469287469288,
2826
  "eval_overall_recall": 0.942643391521197,
2827
- "eval_runtime": 0.2912,
2828
- "eval_samples_per_second": 583.754,
2829
- "eval_steps_per_second": 10.302,
2830
  "step": 8736
2831
  },
2832
  {
@@ -2855,9 +2855,9 @@
2855
  "eval_overall_f1": 0.9368029739776952,
2856
  "eval_overall_precision": 0.9310344827586207,
2857
  "eval_overall_recall": 0.942643391521197,
2858
- "eval_runtime": 0.2954,
2859
- "eval_samples_per_second": 575.515,
2860
- "eval_steps_per_second": 10.156,
2861
  "step": 8832
2862
  },
2863
  {
@@ -2886,9 +2886,9 @@
2886
  "eval_overall_f1": 0.9368029739776952,
2887
  "eval_overall_precision": 0.9310344827586207,
2888
  "eval_overall_recall": 0.942643391521197,
2889
- "eval_runtime": 0.2896,
2890
- "eval_samples_per_second": 587.055,
2891
- "eval_steps_per_second": 10.36,
2892
  "step": 8928
2893
  },
2894
  {
@@ -2917,9 +2917,9 @@
2917
  "eval_overall_f1": 0.9392812887236679,
2918
  "eval_overall_precision": 0.9334975369458128,
2919
  "eval_overall_recall": 0.9451371571072319,
2920
- "eval_runtime": 0.288,
2921
- "eval_samples_per_second": 590.323,
2922
- "eval_steps_per_second": 10.417,
2923
  "step": 9024
2924
  },
2925
  {
@@ -2948,9 +2948,9 @@
2948
  "eval_overall_f1": 0.9344870210135972,
2949
  "eval_overall_precision": 0.9264705882352942,
2950
  "eval_overall_recall": 0.942643391521197,
2951
- "eval_runtime": 0.3012,
2952
- "eval_samples_per_second": 564.461,
2953
- "eval_steps_per_second": 9.961,
2954
  "step": 9120
2955
  },
2956
  {
@@ -2979,9 +2979,9 @@
2979
  "eval_overall_f1": 0.9333333333333333,
2980
  "eval_overall_precision": 0.9242053789731052,
2981
  "eval_overall_recall": 0.942643391521197,
2982
- "eval_runtime": 0.2916,
2983
- "eval_samples_per_second": 583.084,
2984
- "eval_steps_per_second": 10.29,
2985
  "step": 9216
2986
  },
2987
  {
@@ -3010,9 +3010,9 @@
3010
  "eval_overall_f1": 0.9356435643564357,
3011
  "eval_overall_precision": 0.9287469287469288,
3012
  "eval_overall_recall": 0.942643391521197,
3013
- "eval_runtime": 0.2886,
3014
- "eval_samples_per_second": 589.08,
3015
- "eval_steps_per_second": 10.396,
3016
  "step": 9312
3017
  },
3018
  {
@@ -3041,9 +3041,9 @@
3041
  "eval_overall_f1": 0.9368029739776952,
3042
  "eval_overall_precision": 0.9310344827586207,
3043
  "eval_overall_recall": 0.942643391521197,
3044
- "eval_runtime": 0.2886,
3045
- "eval_samples_per_second": 589.05,
3046
- "eval_steps_per_second": 10.395,
3047
  "step": 9408
3048
  },
3049
  {
@@ -3072,9 +3072,9 @@
3072
  "eval_overall_f1": 0.9368029739776952,
3073
  "eval_overall_precision": 0.9310344827586207,
3074
  "eval_overall_recall": 0.942643391521197,
3075
- "eval_runtime": 0.2901,
3076
- "eval_samples_per_second": 585.92,
3077
- "eval_steps_per_second": 10.34,
3078
  "step": 9504
3079
  },
3080
  {
@@ -3103,9 +3103,9 @@
3103
  "eval_overall_f1": 0.9368029739776952,
3104
  "eval_overall_precision": 0.9310344827586207,
3105
  "eval_overall_recall": 0.942643391521197,
3106
- "eval_runtime": 0.2901,
3107
- "eval_samples_per_second": 586.027,
3108
- "eval_steps_per_second": 10.342,
3109
  "step": 9600
3110
  },
3111
  {
@@ -3113,9 +3113,9 @@
3113
  "step": 9600,
3114
  "total_flos": 4208466347875278.0,
3115
  "train_loss": 0.03755435147012273,
3116
- "train_runtime": 554.4341,
3117
- "train_samples_per_second": 276.137,
3118
- "train_steps_per_second": 17.315
3119
  }
3120
  ],
3121
  "logging_steps": 500,
 
35
  "eval_overall_precision": 0.24620060790273557,
36
  "eval_overall_recall": 0.20199501246882792,
37
  "eval_runtime": 0.2929,
38
+ "eval_samples_per_second": 580.419,
39
  "eval_steps_per_second": 10.243,
40
  "step": 96
41
  },
 
65
  "eval_overall_f1": 0.5772266065388952,
66
  "eval_overall_precision": 0.5267489711934157,
67
  "eval_overall_recall": 0.6384039900249376,
68
+ "eval_runtime": 0.2929,
69
+ "eval_samples_per_second": 580.324,
70
+ "eval_steps_per_second": 10.241,
71
  "step": 192
72
  },
73
  {
 
96
  "eval_overall_f1": 0.826923076923077,
97
  "eval_overall_precision": 0.7981438515081206,
98
  "eval_overall_recall": 0.85785536159601,
99
+ "eval_runtime": 0.2911,
100
+ "eval_samples_per_second": 583.932,
101
+ "eval_steps_per_second": 10.305,
102
  "step": 288
103
  },
104
  {
 
127
  "eval_overall_f1": 0.8501170960187353,
128
  "eval_overall_precision": 0.8013245033112583,
129
  "eval_overall_recall": 0.9052369077306733,
130
+ "eval_runtime": 0.2952,
131
+ "eval_samples_per_second": 575.8,
132
+ "eval_steps_per_second": 10.161,
133
  "step": 384
134
  },
135
  {
 
158
  "eval_overall_f1": 0.8985148514851485,
159
  "eval_overall_precision": 0.8918918918918919,
160
  "eval_overall_recall": 0.9052369077306733,
161
+ "eval_runtime": 0.2894,
162
+ "eval_samples_per_second": 587.518,
163
+ "eval_steps_per_second": 10.368,
164
  "step": 480
165
  },
166
  {
 
189
  "eval_overall_f1": 0.8913308913308914,
190
  "eval_overall_precision": 0.8732057416267942,
191
  "eval_overall_recall": 0.9102244389027432,
192
+ "eval_runtime": 0.2926,
193
+ "eval_samples_per_second": 580.972,
194
+ "eval_steps_per_second": 10.252,
195
  "step": 576
196
  },
197
  {
 
220
  "eval_overall_f1": 0.9106280193236714,
221
  "eval_overall_precision": 0.882903981264637,
222
  "eval_overall_recall": 0.940149625935162,
223
+ "eval_runtime": 0.2883,
224
+ "eval_samples_per_second": 589.728,
225
+ "eval_steps_per_second": 10.407,
226
  "step": 672
227
  },
228
  {
 
251
  "eval_overall_f1": 0.9245742092457422,
252
  "eval_overall_precision": 0.9026128266033254,
253
  "eval_overall_recall": 0.9476309226932669,
254
+ "eval_runtime": 0.292,
255
+ "eval_samples_per_second": 582.272,
256
+ "eval_steps_per_second": 10.275,
257
  "step": 768
258
  },
259
  {
 
282
  "eval_overall_f1": 0.9185185185185184,
283
  "eval_overall_precision": 0.9095354523227384,
284
  "eval_overall_recall": 0.9276807980049875,
285
+ "eval_runtime": 0.2917,
286
+ "eval_samples_per_second": 582.8,
287
+ "eval_steps_per_second": 10.285,
288
  "step": 864
289
  },
290
  {
 
313
  "eval_overall_f1": 0.9392812887236679,
314
  "eval_overall_precision": 0.9334975369458128,
315
  "eval_overall_recall": 0.9451371571072319,
316
+ "eval_runtime": 0.2881,
317
+ "eval_samples_per_second": 590.045,
318
+ "eval_steps_per_second": 10.413,
319
  "step": 960
320
  },
321
  {
 
344
  "eval_overall_f1": 0.9353233830845771,
345
  "eval_overall_precision": 0.9330024813895782,
346
  "eval_overall_recall": 0.9376558603491272,
347
+ "eval_runtime": 0.2902,
348
+ "eval_samples_per_second": 585.729,
349
+ "eval_steps_per_second": 10.336,
350
  "step": 1056
351
  },
352
  {
 
375
  "eval_overall_f1": 0.9321824907521579,
376
  "eval_overall_precision": 0.9219512195121952,
377
  "eval_overall_recall": 0.942643391521197,
378
+ "eval_runtime": 0.2883,
379
+ "eval_samples_per_second": 589.693,
380
+ "eval_steps_per_second": 10.406,
381
  "step": 1152
382
  },
383
  {
 
406
  "eval_overall_f1": 0.9443757725587144,
407
  "eval_overall_precision": 0.9362745098039216,
408
  "eval_overall_recall": 0.9526184538653366,
409
+ "eval_runtime": 0.2908,
410
+ "eval_samples_per_second": 584.59,
411
+ "eval_steps_per_second": 10.316,
412
  "step": 1248
413
  },
414
  {
 
437
  "eval_overall_f1": 0.9490683229813663,
438
  "eval_overall_precision": 0.9455445544554455,
439
  "eval_overall_recall": 0.9526184538653366,
440
+ "eval_runtime": 0.2897,
441
+ "eval_samples_per_second": 586.886,
442
+ "eval_steps_per_second": 10.357,
443
  "step": 1344
444
  },
445
  {
 
468
  "eval_overall_f1": 0.9480198019801981,
469
  "eval_overall_precision": 0.941031941031941,
470
  "eval_overall_recall": 0.9551122194513716,
471
+ "eval_runtime": 0.2871,
472
+ "eval_samples_per_second": 592.23,
473
+ "eval_steps_per_second": 10.451,
474
  "step": 1440
475
  },
476
  {
 
499
  "eval_overall_f1": 0.9287469287469288,
500
  "eval_overall_precision": 0.9152542372881356,
501
  "eval_overall_recall": 0.942643391521197,
502
+ "eval_runtime": 0.286,
503
+ "eval_samples_per_second": 594.461,
504
+ "eval_steps_per_second": 10.49,
505
  "step": 1536
506
  },
507
  {
 
530
  "eval_overall_f1": 0.9504950495049505,
531
  "eval_overall_precision": 0.9434889434889435,
532
  "eval_overall_recall": 0.9576059850374065,
533
+ "eval_runtime": 0.2825,
534
+ "eval_samples_per_second": 601.765,
535
+ "eval_steps_per_second": 10.619,
536
  "step": 1632
537
  },
538
  {
 
561
  "eval_overall_f1": 0.946716232961586,
562
  "eval_overall_precision": 0.9408866995073891,
563
  "eval_overall_recall": 0.9526184538653366,
564
+ "eval_runtime": 0.2887,
565
+ "eval_samples_per_second": 588.934,
566
+ "eval_steps_per_second": 10.393,
567
  "step": 1728
568
  },
569
  {
 
592
  "eval_overall_f1": 0.946716232961586,
593
  "eval_overall_precision": 0.9408866995073891,
594
  "eval_overall_recall": 0.9526184538653366,
595
+ "eval_runtime": 0.2826,
596
+ "eval_samples_per_second": 601.556,
597
+ "eval_steps_per_second": 10.616,
598
  "step": 1824
599
  },
600
  {
 
623
  "eval_overall_f1": 0.9458128078817734,
624
  "eval_overall_precision": 0.9343065693430657,
625
  "eval_overall_recall": 0.9576059850374065,
626
+ "eval_runtime": 0.2851,
627
+ "eval_samples_per_second": 596.276,
628
+ "eval_steps_per_second": 10.523,
629
  "step": 1920
630
  },
631
  {
 
654
  "eval_overall_f1": 0.9443757725587144,
655
  "eval_overall_precision": 0.9362745098039216,
656
  "eval_overall_recall": 0.9526184538653366,
657
+ "eval_runtime": 0.2873,
658
+ "eval_samples_per_second": 591.81,
659
+ "eval_steps_per_second": 10.444,
660
  "step": 2016
661
  },
662
  {
 
685
  "eval_overall_f1": 0.941031941031941,
686
  "eval_overall_precision": 0.927360774818402,
687
  "eval_overall_recall": 0.9551122194513716,
688
+ "eval_runtime": 0.2865,
689
+ "eval_samples_per_second": 593.269,
690
+ "eval_steps_per_second": 10.469,
691
  "step": 2112
692
  },
693
  {
 
716
  "eval_overall_f1": 0.9381188118811881,
717
  "eval_overall_precision": 0.9312039312039312,
718
  "eval_overall_recall": 0.9451371571072319,
719
+ "eval_runtime": 0.2891,
720
+ "eval_samples_per_second": 588.072,
721
+ "eval_steps_per_second": 10.378,
722
  "step": 2208
723
  },
724
  {
 
747
  "eval_overall_f1": 0.9468479604449938,
748
  "eval_overall_precision": 0.9387254901960784,
749
  "eval_overall_recall": 0.9551122194513716,
750
+ "eval_runtime": 0.2895,
751
+ "eval_samples_per_second": 587.229,
752
+ "eval_steps_per_second": 10.363,
753
  "step": 2304
754
  },
755
  {
 
778
  "eval_overall_f1": 0.9318463444857497,
779
  "eval_overall_precision": 0.9261083743842364,
780
  "eval_overall_recall": 0.9376558603491272,
781
+ "eval_runtime": 0.2874,
782
+ "eval_samples_per_second": 591.541,
783
+ "eval_steps_per_second": 10.439,
784
  "step": 2400
785
  },
786
  {
 
809
  "eval_overall_f1": 0.9464508094645082,
810
  "eval_overall_precision": 0.945273631840796,
811
  "eval_overall_recall": 0.9476309226932669,
812
+ "eval_runtime": 0.2884,
813
+ "eval_samples_per_second": 589.475,
814
+ "eval_steps_per_second": 10.402,
815
  "step": 2496
816
  },
817
  {
 
840
  "eval_overall_f1": 0.942189421894219,
841
  "eval_overall_precision": 0.9296116504854369,
842
  "eval_overall_recall": 0.9551122194513716,
843
+ "eval_runtime": 0.2854,
844
+ "eval_samples_per_second": 595.68,
845
+ "eval_steps_per_second": 10.512,
846
  "step": 2592
847
  },
848
  {
 
871
  "eval_overall_f1": 0.944649446494465,
872
  "eval_overall_precision": 0.9320388349514563,
873
  "eval_overall_recall": 0.9576059850374065,
874
+ "eval_runtime": 0.2852,
875
+ "eval_samples_per_second": 596.134,
876
+ "eval_steps_per_second": 10.52,
877
  "step": 2688
878
  },
879
  {
 
902
  "eval_overall_f1": 0.9433497536945813,
903
  "eval_overall_precision": 0.9318734793187348,
904
  "eval_overall_recall": 0.9551122194513716,
905
+ "eval_runtime": 0.2873,
906
+ "eval_samples_per_second": 591.689,
907
+ "eval_steps_per_second": 10.442,
908
  "step": 2784
909
  },
910
  {
 
933
  "eval_overall_f1": 0.9423312883435583,
934
  "eval_overall_precision": 0.927536231884058,
935
  "eval_overall_recall": 0.9576059850374065,
936
+ "eval_runtime": 0.2848,
937
+ "eval_samples_per_second": 596.95,
938
+ "eval_steps_per_second": 10.534,
939
  "step": 2880
940
  },
941
  {
 
964
  "eval_overall_f1": 0.9371146732429101,
965
  "eval_overall_precision": 0.926829268292683,
966
  "eval_overall_recall": 0.9476309226932669,
967
+ "eval_runtime": 0.2868,
968
+ "eval_samples_per_second": 592.731,
969
+ "eval_steps_per_second": 10.46,
970
  "step": 2976
971
  },
972
  {
 
995
  "eval_overall_f1": 0.9438202247191011,
996
  "eval_overall_precision": 0.945,
997
  "eval_overall_recall": 0.942643391521197,
998
+ "eval_runtime": 0.2867,
999
+ "eval_samples_per_second": 593.018,
1000
+ "eval_steps_per_second": 10.465,
1001
  "step": 3072
1002
  },
1003
  {
 
1026
  "eval_overall_f1": 0.9443757725587144,
1027
  "eval_overall_precision": 0.9362745098039216,
1028
  "eval_overall_recall": 0.9526184538653366,
1029
+ "eval_runtime": 0.2855,
1030
+ "eval_samples_per_second": 595.425,
1031
+ "eval_steps_per_second": 10.508,
1032
  "step": 3168
1033
  },
1034
  {
 
1057
  "eval_overall_f1": 0.9407407407407408,
1058
  "eval_overall_precision": 0.9315403422982885,
1059
  "eval_overall_recall": 0.9501246882793017,
1060
+ "eval_runtime": 0.2863,
1061
+ "eval_samples_per_second": 593.782,
1062
+ "eval_steps_per_second": 10.479,
1063
  "step": 3264
1064
  },
1065
  {
 
1088
  "eval_overall_f1": 0.9346485819975339,
1089
  "eval_overall_precision": 0.9243902439024391,
1090
  "eval_overall_recall": 0.9451371571072319,
1091
+ "eval_runtime": 0.2845,
1092
+ "eval_samples_per_second": 597.526,
1093
+ "eval_steps_per_second": 10.545,
1094
  "step": 3360
1095
  },
1096
  {
 
1119
  "eval_overall_f1": 0.9404466501240694,
1120
  "eval_overall_precision": 0.9358024691358025,
1121
  "eval_overall_recall": 0.9451371571072319,
1122
+ "eval_runtime": 0.2884,
1123
+ "eval_samples_per_second": 589.516,
1124
+ "eval_steps_per_second": 10.403,
1125
  "step": 3456
1126
  },
1127
  {
 
1150
  "eval_overall_f1": 0.9404466501240694,
1151
  "eval_overall_precision": 0.9358024691358025,
1152
  "eval_overall_recall": 0.9451371571072319,
1153
+ "eval_runtime": 0.2874,
1154
+ "eval_samples_per_second": 591.486,
1155
+ "eval_steps_per_second": 10.438,
1156
  "step": 3552
1157
  },
1158
  {
 
1181
  "eval_overall_f1": 0.9416149068322982,
1182
  "eval_overall_precision": 0.9381188118811881,
1183
  "eval_overall_recall": 0.9451371571072319,
1184
+ "eval_runtime": 0.2858,
1185
+ "eval_samples_per_second": 594.823,
1186
+ "eval_steps_per_second": 10.497,
1187
  "step": 3648
1188
  },
1189
  {
 
1212
  "eval_overall_f1": 0.9354838709677419,
1213
  "eval_overall_precision": 0.9308641975308642,
1214
  "eval_overall_recall": 0.940149625935162,
1215
+ "eval_runtime": 0.2828,
1216
+ "eval_samples_per_second": 601.107,
1217
+ "eval_steps_per_second": 10.608,
1218
  "step": 3744
1219
  },
1220
  {
 
1243
  "eval_overall_f1": 0.9285714285714285,
1244
  "eval_overall_precision": 0.9172749391727494,
1245
  "eval_overall_recall": 0.940149625935162,
1246
+ "eval_runtime": 0.2847,
1247
+ "eval_samples_per_second": 597.038,
1248
+ "eval_steps_per_second": 10.536,
1249
  "step": 3840
1250
  },
1251
  {
 
1274
  "eval_overall_f1": 0.9249692496924969,
1275
  "eval_overall_precision": 0.912621359223301,
1276
  "eval_overall_recall": 0.9376558603491272,
1277
+ "eval_runtime": 0.2865,
1278
+ "eval_samples_per_second": 593.276,
1279
+ "eval_steps_per_second": 10.47,
1280
  "step": 3936
1281
  },
1282
  {
 
1305
  "eval_overall_f1": 0.9320148331273177,
1306
  "eval_overall_precision": 0.9240196078431373,
1307
  "eval_overall_recall": 0.940149625935162,
1308
+ "eval_runtime": 0.2898,
1309
+ "eval_samples_per_second": 586.544,
1310
+ "eval_steps_per_second": 10.351,
1311
  "step": 4032
1312
  },
1313
  {
 
1336
  "eval_overall_f1": 0.9402985074626866,
1337
  "eval_overall_precision": 0.9379652605459057,
1338
  "eval_overall_recall": 0.942643391521197,
1339
+ "eval_runtime": 0.2963,
1340
+ "eval_samples_per_second": 573.712,
1341
+ "eval_steps_per_second": 10.124,
1342
  "step": 4128
1343
  },
1344
  {
 
1367
  "eval_overall_f1": 0.9293680297397771,
1368
  "eval_overall_precision": 0.9236453201970444,
1369
  "eval_overall_recall": 0.9351620947630923,
1370
+ "eval_runtime": 0.2837,
1371
+ "eval_samples_per_second": 599.261,
1372
+ "eval_steps_per_second": 10.575,
1373
  "step": 4224
1374
  },
1375
  {
 
1398
  "eval_overall_f1": 0.9353233830845771,
1399
  "eval_overall_precision": 0.9330024813895782,
1400
  "eval_overall_recall": 0.9376558603491272,
1401
+ "eval_runtime": 0.2857,
1402
+ "eval_samples_per_second": 595.001,
1403
+ "eval_steps_per_second": 10.5,
1404
  "step": 4320
1405
  },
1406
  {
 
1429
  "eval_overall_f1": 0.9282178217821783,
1430
  "eval_overall_precision": 0.9213759213759214,
1431
  "eval_overall_recall": 0.9351620947630923,
1432
+ "eval_runtime": 0.2848,
1433
+ "eval_samples_per_second": 597.008,
1434
+ "eval_steps_per_second": 10.535,
1435
  "step": 4416
1436
  },
1437
  {
 
1460
  "eval_overall_f1": 0.9432098765432098,
1461
  "eval_overall_precision": 0.9339853300733496,
1462
  "eval_overall_recall": 0.9526184538653366,
1463
+ "eval_runtime": 0.283,
1464
+ "eval_samples_per_second": 600.766,
1465
+ "eval_steps_per_second": 10.602,
1466
  "step": 4512
1467
  },
1468
  {
 
1491
  "eval_overall_f1": 0.9392812887236679,
1492
  "eval_overall_precision": 0.9334975369458128,
1493
  "eval_overall_recall": 0.9451371571072319,
1494
+ "eval_runtime": 0.287,
1495
+ "eval_samples_per_second": 592.239,
1496
+ "eval_steps_per_second": 10.451,
1497
  "step": 4608
1498
  },
1499
  {
 
1522
  "eval_overall_f1": 0.9478908188585606,
1523
  "eval_overall_precision": 0.9432098765432099,
1524
  "eval_overall_recall": 0.9526184538653366,
1525
+ "eval_runtime": 0.3002,
1526
+ "eval_samples_per_second": 566.205,
1527
+ "eval_steps_per_second": 9.992,
1528
  "step": 4704
1529
  },
1530
  {
 
1553
  "eval_overall_f1": 0.9346485819975339,
1554
  "eval_overall_precision": 0.9243902439024391,
1555
  "eval_overall_recall": 0.9451371571072319,
1556
+ "eval_runtime": 0.2864,
1557
+ "eval_samples_per_second": 593.633,
1558
+ "eval_steps_per_second": 10.476,
1559
  "step": 4800
1560
  },
1561
  {
 
1584
  "eval_overall_f1": 0.9344870210135972,
1585
  "eval_overall_precision": 0.9264705882352942,
1586
  "eval_overall_recall": 0.942643391521197,
1587
+ "eval_runtime": 0.2864,
1588
+ "eval_samples_per_second": 593.597,
1589
+ "eval_steps_per_second": 10.475,
1590
  "step": 4896
1591
  },
1592
  {
 
1615
  "eval_overall_f1": 0.9297163995067818,
1616
  "eval_overall_precision": 0.9195121951219513,
1617
  "eval_overall_recall": 0.940149625935162,
1618
+ "eval_runtime": 0.2878,
1619
+ "eval_samples_per_second": 590.774,
1620
+ "eval_steps_per_second": 10.425,
1621
  "step": 4992
1622
  },
1623
  {
 
1646
  "eval_overall_f1": 0.9356435643564357,
1647
  "eval_overall_precision": 0.9287469287469288,
1648
  "eval_overall_recall": 0.942643391521197,
1649
+ "eval_runtime": 0.2877,
1650
+ "eval_samples_per_second": 590.819,
1651
+ "eval_steps_per_second": 10.426,
1652
  "step": 5088
1653
  },
1654
  {
 
1677
  "eval_overall_f1": 0.9326805385556914,
1678
  "eval_overall_precision": 0.9158653846153846,
1679
  "eval_overall_recall": 0.9501246882793017,
1680
+ "eval_runtime": 0.286,
1681
+ "eval_samples_per_second": 594.39,
1682
+ "eval_steps_per_second": 10.489,
1683
  "step": 5184
1684
  },
1685
  {
 
1708
  "eval_overall_f1": 0.9378109452736318,
1709
  "eval_overall_precision": 0.9354838709677419,
1710
  "eval_overall_recall": 0.940149625935162,
1711
+ "eval_runtime": 0.2846,
1712
+ "eval_samples_per_second": 597.26,
1713
+ "eval_steps_per_second": 10.54,
1714
  "step": 5280
1715
  },
1716
  {
 
1739
  "eval_overall_f1": 0.9379652605459058,
1740
  "eval_overall_precision": 0.9333333333333333,
1741
  "eval_overall_recall": 0.942643391521197,
1742
+ "eval_runtime": 0.2858,
1743
+ "eval_samples_per_second": 594.775,
1744
+ "eval_steps_per_second": 10.496,
1745
  "step": 5376
1746
  },
1747
  {
 
1770
  "eval_overall_f1": 0.9392812887236679,
1771
  "eval_overall_precision": 0.9334975369458128,
1772
  "eval_overall_recall": 0.9451371571072319,
1773
+ "eval_runtime": 0.2856,
1774
+ "eval_samples_per_second": 595.273,
1775
+ "eval_steps_per_second": 10.505,
1776
  "step": 5472
1777
  },
1778
  {
 
1801
  "eval_overall_f1": 0.9429280397022332,
1802
  "eval_overall_precision": 0.9382716049382716,
1803
  "eval_overall_recall": 0.9476309226932669,
1804
+ "eval_runtime": 0.2848,
1805
+ "eval_samples_per_second": 596.907,
1806
+ "eval_steps_per_second": 10.534,
1807
  "step": 5568
1808
  },
1809
  {
 
1832
  "eval_overall_f1": 0.9375,
1833
  "eval_overall_precision": 0.9398496240601504,
1834
  "eval_overall_recall": 0.9351620947630923,
1835
+ "eval_runtime": 0.2875,
1836
+ "eval_samples_per_second": 591.307,
1837
+ "eval_steps_per_second": 10.435,
1838
  "step": 5664
1839
  },
1840
  {
 
1863
  "eval_overall_f1": 0.9330024813895781,
1864
  "eval_overall_precision": 0.928395061728395,
1865
  "eval_overall_recall": 0.9376558603491272,
1866
+ "eval_runtime": 0.2878,
1867
+ "eval_samples_per_second": 590.651,
1868
+ "eval_steps_per_second": 10.423,
1869
  "step": 5760
1870
  },
1871
  {
 
1894
  "eval_overall_f1": 0.935,
1895
  "eval_overall_precision": 0.9373433583959899,
1896
  "eval_overall_recall": 0.9326683291770573,
1897
+ "eval_runtime": 0.2889,
1898
+ "eval_samples_per_second": 588.359,
1899
+ "eval_steps_per_second": 10.383,
1900
  "step": 5856
1901
  },
1902
  {
 
1925
  "eval_overall_f1": 0.9369592088998765,
1926
  "eval_overall_precision": 0.928921568627451,
1927
  "eval_overall_recall": 0.9451371571072319,
1928
+ "eval_runtime": 0.2873,
1929
+ "eval_samples_per_second": 591.665,
1930
+ "eval_steps_per_second": 10.441,
1931
  "step": 5952
1932
  },
1933
  {
 
1956
  "eval_overall_f1": 0.9442379182156134,
1957
  "eval_overall_precision": 0.9384236453201971,
1958
  "eval_overall_recall": 0.9501246882793017,
1959
+ "eval_runtime": 0.2847,
1960
+ "eval_samples_per_second": 597.174,
1961
+ "eval_steps_per_second": 10.538,
1962
  "step": 6048
1963
  },
1964
  {
 
1987
  "eval_overall_f1": 0.9440993788819876,
1988
  "eval_overall_precision": 0.9405940594059405,
1989
  "eval_overall_recall": 0.9476309226932669,
1990
+ "eval_runtime": 0.2842,
1991
+ "eval_samples_per_second": 598.224,
1992
+ "eval_steps_per_second": 10.557,
1993
  "step": 6144
1994
  },
1995
  {
 
2018
  "eval_overall_f1": 0.9356435643564357,
2019
  "eval_overall_precision": 0.9287469287469288,
2020
  "eval_overall_recall": 0.942643391521197,
2021
+ "eval_runtime": 0.2845,
2022
+ "eval_samples_per_second": 597.536,
2023
+ "eval_steps_per_second": 10.545,
2024
  "step": 6240
2025
  },
2026
  {
 
2049
  "eval_overall_f1": 0.9315068493150686,
2050
  "eval_overall_precision": 0.9303482587064676,
2051
  "eval_overall_recall": 0.9326683291770573,
2052
+ "eval_runtime": 0.2843,
2053
+ "eval_samples_per_second": 597.975,
2054
+ "eval_steps_per_second": 10.553,
2055
  "step": 6336
2056
  },
2057
  {
 
2080
  "eval_overall_f1": 0.9405940594059405,
2081
  "eval_overall_precision": 0.9336609336609336,
2082
  "eval_overall_recall": 0.9476309226932669,
2083
+ "eval_runtime": 0.2859,
2084
+ "eval_samples_per_second": 594.682,
2085
+ "eval_steps_per_second": 10.494,
2086
  "step": 6432
2087
  },
2088
  {
 
2111
  "eval_overall_f1": 0.9419035846724352,
2112
  "eval_overall_precision": 0.9338235294117647,
2113
  "eval_overall_recall": 0.9501246882793017,
2114
+ "eval_runtime": 0.2854,
2115
+ "eval_samples_per_second": 595.638,
2116
+ "eval_steps_per_second": 10.511,
2117
  "step": 6528
2118
  },
2119
  {
 
2142
  "eval_overall_f1": 0.9379652605459058,
2143
  "eval_overall_precision": 0.9333333333333333,
2144
  "eval_overall_recall": 0.942643391521197,
2145
+ "eval_runtime": 0.2862,
2146
+ "eval_samples_per_second": 594.072,
2147
+ "eval_steps_per_second": 10.484,
2148
  "step": 6624
2149
  },
2150
  {
 
2173
  "eval_overall_f1": 0.9392812887236679,
2174
  "eval_overall_precision": 0.9334975369458128,
2175
  "eval_overall_recall": 0.9451371571072319,
2176
+ "eval_runtime": 0.2866,
2177
+ "eval_samples_per_second": 593.127,
2178
+ "eval_steps_per_second": 10.467,
2179
  "step": 6720
2180
  },
2181
  {
 
2204
  "eval_overall_f1": 0.9344870210135972,
2205
  "eval_overall_precision": 0.9264705882352942,
2206
  "eval_overall_recall": 0.942643391521197,
2207
+ "eval_runtime": 0.2831,
2208
+ "eval_samples_per_second": 600.523,
2209
+ "eval_steps_per_second": 10.597,
2210
  "step": 6816
2211
  },
2212
  {
 
2235
  "eval_overall_f1": 0.9416149068322982,
2236
  "eval_overall_precision": 0.9381188118811881,
2237
  "eval_overall_recall": 0.9451371571072319,
2238
+ "eval_runtime": 0.2872,
2239
+ "eval_samples_per_second": 591.962,
2240
+ "eval_steps_per_second": 10.446,
2241
  "step": 6912
2242
  },
2243
  {
 
2266
  "eval_overall_f1": 0.9318463444857497,
2267
  "eval_overall_precision": 0.9261083743842364,
2268
  "eval_overall_recall": 0.9376558603491272,
2269
+ "eval_runtime": 0.2848,
2270
+ "eval_samples_per_second": 596.928,
2271
+ "eval_steps_per_second": 10.534,
2272
  "step": 7008
2273
  },
2274
  {
 
2297
  "eval_overall_f1": 0.9356435643564357,
2298
  "eval_overall_precision": 0.9287469287469288,
2299
  "eval_overall_recall": 0.942643391521197,
2300
+ "eval_runtime": 0.2875,
2301
+ "eval_samples_per_second": 591.305,
2302
+ "eval_steps_per_second": 10.435,
2303
  "step": 7104
2304
  },
2305
  {
 
2328
  "eval_overall_f1": 0.9257425742574258,
2329
  "eval_overall_precision": 0.918918918918919,
2330
  "eval_overall_recall": 0.9326683291770573,
2331
+ "eval_runtime": 0.2867,
2332
+ "eval_samples_per_second": 592.871,
2333
+ "eval_steps_per_second": 10.462,
2334
  "step": 7200
2335
  },
2336
  {
 
2359
  "eval_overall_f1": 0.9369592088998765,
2360
  "eval_overall_precision": 0.928921568627451,
2361
  "eval_overall_recall": 0.9451371571072319,
2362
+ "eval_runtime": 0.2872,
2363
+ "eval_samples_per_second": 591.918,
2364
+ "eval_steps_per_second": 10.446,
2365
  "step": 7296
2366
  },
2367
  {
 
2390
  "eval_overall_f1": 0.9391304347826087,
2391
  "eval_overall_precision": 0.9356435643564357,
2392
  "eval_overall_recall": 0.942643391521197,
2393
+ "eval_runtime": 0.2844,
2394
+ "eval_samples_per_second": 597.853,
2395
+ "eval_steps_per_second": 10.55,
2396
  "step": 7392
2397
  },
2398
  {
 
2421
  "eval_overall_f1": 0.9293680297397771,
2422
  "eval_overall_precision": 0.9236453201970444,
2423
  "eval_overall_recall": 0.9351620947630923,
2424
+ "eval_runtime": 0.2859,
2425
+ "eval_samples_per_second": 594.623,
2426
+ "eval_steps_per_second": 10.493,
2427
  "step": 7488
2428
  },
2429
  {
 
2452
  "eval_overall_f1": 0.9320148331273177,
2453
  "eval_overall_precision": 0.9240196078431373,
2454
  "eval_overall_recall": 0.940149625935162,
2455
+ "eval_runtime": 0.2852,
2456
+ "eval_samples_per_second": 596.158,
2457
+ "eval_steps_per_second": 10.52,
2458
  "step": 7584
2459
  },
2460
  {
 
2483
  "eval_overall_f1": 0.9356435643564357,
2484
  "eval_overall_precision": 0.9287469287469288,
2485
  "eval_overall_recall": 0.942643391521197,
2486
+ "eval_runtime": 0.2828,
2487
+ "eval_samples_per_second": 601.1,
2488
+ "eval_steps_per_second": 10.608,
2489
  "step": 7680
2490
  },
2491
  {
 
2514
  "eval_overall_f1": 0.9344870210135972,
2515
  "eval_overall_precision": 0.9264705882352942,
2516
  "eval_overall_recall": 0.942643391521197,
2517
+ "eval_runtime": 0.2859,
2518
+ "eval_samples_per_second": 594.513,
2519
+ "eval_steps_per_second": 10.491,
2520
  "step": 7776
2521
  },
2522
  {
 
2545
  "eval_overall_f1": 0.9343246592317225,
2546
  "eval_overall_precision": 0.9285714285714286,
2547
  "eval_overall_recall": 0.940149625935162,
2548
+ "eval_runtime": 0.2865,
2549
+ "eval_samples_per_second": 593.316,
2550
+ "eval_steps_per_second": 10.47,
2551
  "step": 7872
2552
  },
2553
  {
 
2576
  "eval_overall_f1": 0.9392812887236679,
2577
  "eval_overall_precision": 0.9334975369458128,
2578
  "eval_overall_recall": 0.9451371571072319,
2579
+ "eval_runtime": 0.2854,
2580
+ "eval_samples_per_second": 595.652,
2581
+ "eval_steps_per_second": 10.512,
2582
  "step": 7968
2583
  },
2584
  {
 
2607
  "eval_overall_f1": 0.9391304347826087,
2608
  "eval_overall_precision": 0.9356435643564357,
2609
  "eval_overall_recall": 0.942643391521197,
2610
+ "eval_runtime": 0.2843,
2611
+ "eval_samples_per_second": 597.939,
2612
+ "eval_steps_per_second": 10.552,
2613
  "step": 8064
2614
  },
2615
  {
 
2638
  "eval_overall_f1": 0.9405940594059405,
2639
  "eval_overall_precision": 0.9336609336609336,
2640
  "eval_overall_recall": 0.9476309226932669,
2641
+ "eval_runtime": 0.2872,
2642
+ "eval_samples_per_second": 591.847,
2643
+ "eval_steps_per_second": 10.444,
2644
  "step": 8160
2645
  },
2646
  {
 
2669
  "eval_overall_f1": 0.9343246592317225,
2670
  "eval_overall_precision": 0.9285714285714286,
2671
  "eval_overall_recall": 0.940149625935162,
2672
+ "eval_runtime": 0.2852,
2673
+ "eval_samples_per_second": 596.122,
2674
+ "eval_steps_per_second": 10.52,
2675
  "step": 8256
2676
  },
2677
  {
 
2700
  "eval_overall_f1": 0.9429280397022332,
2701
  "eval_overall_precision": 0.9382716049382716,
2702
  "eval_overall_recall": 0.9476309226932669,
2703
+ "eval_runtime": 0.2882,
2704
+ "eval_samples_per_second": 589.847,
2705
+ "eval_steps_per_second": 10.409,
2706
  "step": 8352
2707
  },
2708
  {
 
2731
  "eval_overall_f1": 0.9366459627329192,
2732
  "eval_overall_precision": 0.9331683168316832,
2733
  "eval_overall_recall": 0.940149625935162,
2734
+ "eval_runtime": 0.2865,
2735
+ "eval_samples_per_second": 593.348,
2736
+ "eval_steps_per_second": 10.471,
2737
  "step": 8448
2738
  },
2739
  {
 
2762
  "eval_overall_f1": 0.9356435643564357,
2763
  "eval_overall_precision": 0.9287469287469288,
2764
  "eval_overall_recall": 0.942643391521197,
2765
+ "eval_runtime": 0.2851,
2766
+ "eval_samples_per_second": 596.36,
2767
+ "eval_steps_per_second": 10.524,
2768
  "step": 8544
2769
  },
2770
  {
 
2793
  "eval_overall_f1": 0.9417596034696407,
2794
  "eval_overall_precision": 0.9359605911330049,
2795
  "eval_overall_recall": 0.9476309226932669,
2796
+ "eval_runtime": 0.2848,
2797
+ "eval_samples_per_second": 596.83,
2798
+ "eval_steps_per_second": 10.532,
2799
  "step": 8640
2800
  },
2801
  {
 
2824
  "eval_overall_f1": 0.9356435643564357,
2825
  "eval_overall_precision": 0.9287469287469288,
2826
  "eval_overall_recall": 0.942643391521197,
2827
+ "eval_runtime": 0.2853,
2828
+ "eval_samples_per_second": 595.914,
2829
+ "eval_steps_per_second": 10.516,
2830
  "step": 8736
2831
  },
2832
  {
 
2855
  "eval_overall_f1": 0.9368029739776952,
2856
  "eval_overall_precision": 0.9310344827586207,
2857
  "eval_overall_recall": 0.942643391521197,
2858
+ "eval_runtime": 0.2877,
2859
+ "eval_samples_per_second": 590.936,
2860
+ "eval_steps_per_second": 10.428,
2861
  "step": 8832
2862
  },
2863
  {
 
2886
  "eval_overall_f1": 0.9368029739776952,
2887
  "eval_overall_precision": 0.9310344827586207,
2888
  "eval_overall_recall": 0.942643391521197,
2889
+ "eval_runtime": 0.2934,
2890
+ "eval_samples_per_second": 579.374,
2891
+ "eval_steps_per_second": 10.224,
2892
  "step": 8928
2893
  },
2894
  {
 
2917
  "eval_overall_f1": 0.9392812887236679,
2918
  "eval_overall_precision": 0.9334975369458128,
2919
  "eval_overall_recall": 0.9451371571072319,
2920
+ "eval_runtime": 0.2941,
2921
+ "eval_samples_per_second": 578.014,
2922
+ "eval_steps_per_second": 10.2,
2923
  "step": 9024
2924
  },
2925
  {
 
2948
  "eval_overall_f1": 0.9344870210135972,
2949
  "eval_overall_precision": 0.9264705882352942,
2950
  "eval_overall_recall": 0.942643391521197,
2951
+ "eval_runtime": 0.2917,
2952
+ "eval_samples_per_second": 582.839,
2953
+ "eval_steps_per_second": 10.285,
2954
  "step": 9120
2955
  },
2956
  {
 
2979
  "eval_overall_f1": 0.9333333333333333,
2980
  "eval_overall_precision": 0.9242053789731052,
2981
  "eval_overall_recall": 0.942643391521197,
2982
+ "eval_runtime": 0.2967,
2983
+ "eval_samples_per_second": 572.951,
2984
+ "eval_steps_per_second": 10.111,
2985
  "step": 9216
2986
  },
2987
  {
 
3010
  "eval_overall_f1": 0.9356435643564357,
3011
  "eval_overall_precision": 0.9287469287469288,
3012
  "eval_overall_recall": 0.942643391521197,
3013
+ "eval_runtime": 0.2925,
3014
+ "eval_samples_per_second": 581.238,
3015
+ "eval_steps_per_second": 10.257,
3016
  "step": 9312
3017
  },
3018
  {
 
3041
  "eval_overall_f1": 0.9368029739776952,
3042
  "eval_overall_precision": 0.9310344827586207,
3043
  "eval_overall_recall": 0.942643391521197,
3044
+ "eval_runtime": 0.2925,
3045
+ "eval_samples_per_second": 581.127,
3046
+ "eval_steps_per_second": 10.255,
3047
  "step": 9408
3048
  },
3049
  {
 
3072
  "eval_overall_f1": 0.9368029739776952,
3073
  "eval_overall_precision": 0.9310344827586207,
3074
  "eval_overall_recall": 0.942643391521197,
3075
+ "eval_runtime": 0.2921,
3076
+ "eval_samples_per_second": 582.043,
3077
+ "eval_steps_per_second": 10.271,
3078
  "step": 9504
3079
  },
3080
  {
 
3103
  "eval_overall_f1": 0.9368029739776952,
3104
  "eval_overall_precision": 0.9310344827586207,
3105
  "eval_overall_recall": 0.942643391521197,
3106
+ "eval_runtime": 0.2907,
3107
+ "eval_samples_per_second": 584.734,
3108
+ "eval_steps_per_second": 10.319,
3109
  "step": 9600
3110
  },
3111
  {
 
3113
  "step": 9600,
3114
  "total_flos": 4208466347875278.0,
3115
  "train_loss": 0.03755435147012273,
3116
+ "train_runtime": 532.4294,
3117
+ "train_samples_per_second": 287.55,
3118
+ "train_steps_per_second": 18.031
3119
  }
3120
  ],
3121
  "logging_steps": 500,