apwic commited on
Commit
2887757
1 Parent(s): 9e42980

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": 0.9429657794676806,
18
  "eval_overall_precision": 0.9370277078085643,
19
  "eval_overall_recall": 0.9489795918367347,
20
- "eval_runtime": 0.3027,
21
  "eval_samples": 170,
22
- "eval_samples_per_second": 561.588,
23
- "eval_steps_per_second": 9.91,
24
  "predict_LOCATION_f1": 0.9063097514340345,
25
  "predict_LOCATION_number": 261,
26
  "predict_LOCATION_precision": 0.9045801526717557,
@@ -38,12 +38,12 @@
38
  "predict_overall_f1": 0.9257849666983824,
39
  "predict_overall_precision": 0.916195856873823,
40
  "predict_overall_recall": 0.9355769230769231,
41
- "predict_runtime": 0.7455,
42
- "predict_samples_per_second": 570.07,
43
- "predict_steps_per_second": 9.389,
44
  "train_loss": 0.038009579268594586,
45
- "train_runtime": 536.2277,
46
  "train_samples": 1531,
47
- "train_samples_per_second": 285.513,
48
- "train_steps_per_second": 17.903
49
  }
 
17
  "eval_overall_f1": 0.9429657794676806,
18
  "eval_overall_precision": 0.9370277078085643,
19
  "eval_overall_recall": 0.9489795918367347,
20
+ "eval_runtime": 0.2978,
21
  "eval_samples": 170,
22
+ "eval_samples_per_second": 570.849,
23
+ "eval_steps_per_second": 10.074,
24
  "predict_LOCATION_f1": 0.9063097514340345,
25
  "predict_LOCATION_number": 261,
26
  "predict_LOCATION_precision": 0.9045801526717557,
 
38
  "predict_overall_f1": 0.9257849666983824,
39
  "predict_overall_precision": 0.916195856873823,
40
  "predict_overall_recall": 0.9355769230769231,
41
+ "predict_runtime": 0.7436,
42
+ "predict_samples_per_second": 571.536,
43
+ "predict_steps_per_second": 9.414,
44
  "train_loss": 0.038009579268594586,
45
+ "train_runtime": 541.6955,
46
  "train_samples": 1531,
47
+ "train_samples_per_second": 282.631,
48
+ "train_steps_per_second": 17.722
49
  }
eval_results.json CHANGED
@@ -17,8 +17,8 @@
17
  "eval_overall_f1": 0.9429657794676806,
18
  "eval_overall_precision": 0.9370277078085643,
19
  "eval_overall_recall": 0.9489795918367347,
20
- "eval_runtime": 0.3027,
21
  "eval_samples": 170,
22
- "eval_samples_per_second": 561.588,
23
- "eval_steps_per_second": 9.91
24
  }
 
17
  "eval_overall_f1": 0.9429657794676806,
18
  "eval_overall_precision": 0.9370277078085643,
19
  "eval_overall_recall": 0.9489795918367347,
20
+ "eval_runtime": 0.2978,
21
  "eval_samples": 170,
22
+ "eval_samples_per_second": 570.849,
23
+ "eval_steps_per_second": 10.074
24
  }
predict_results.json CHANGED
@@ -16,7 +16,7 @@
16
  "predict_overall_f1": 0.9257849666983824,
17
  "predict_overall_precision": 0.916195856873823,
18
  "predict_overall_recall": 0.9355769230769231,
19
- "predict_runtime": 0.7455,
20
- "predict_samples_per_second": 570.07,
21
- "predict_steps_per_second": 9.389
22
  }
 
16
  "predict_overall_f1": 0.9257849666983824,
17
  "predict_overall_precision": 0.916195856873823,
18
  "predict_overall_recall": 0.9355769230769231,
19
+ "predict_runtime": 0.7436,
20
+ "predict_samples_per_second": 571.536,
21
+ "predict_steps_per_second": 9.414
22
  }
runs/Jun04_10-51-07_a358b85c7679/events.out.tfevents.1717498822.a358b85c7679.633858.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9193bcbe2cb78b4eb900bb00e90ddb4ee7c917a80327701ea345dc3d6011e0
3
+ size 1305
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 100.0,
3
  "train_loss": 0.038009579268594586,
4
- "train_runtime": 536.2277,
5
  "train_samples": 1531,
6
- "train_samples_per_second": 285.513,
7
- "train_steps_per_second": 17.903
8
  }
 
1
  {
2
  "epoch": 100.0,
3
  "train_loss": 0.038009579268594586,
4
+ "train_runtime": 541.6955,
5
  "train_samples": 1531,
6
+ "train_samples_per_second": 282.631,
7
+ "train_steps_per_second": 17.722
8
  }
trainer_state.json CHANGED
@@ -34,9 +34,9 @@
34
  "eval_overall_f1": 0.2607561929595828,
35
  "eval_overall_precision": 0.26666666666666666,
36
  "eval_overall_recall": 0.25510204081632654,
37
- "eval_runtime": 0.2875,
38
- "eval_samples_per_second": 591.375,
39
- "eval_steps_per_second": 10.436,
40
  "step": 96
41
  },
42
  {
@@ -65,9 +65,9 @@
65
  "eval_overall_f1": 0.5707434052757793,
66
  "eval_overall_precision": 0.5384615384615384,
67
  "eval_overall_recall": 0.6071428571428571,
68
- "eval_runtime": 0.2882,
69
- "eval_samples_per_second": 589.783,
70
- "eval_steps_per_second": 10.408,
71
  "step": 192
72
  },
73
  {
@@ -96,9 +96,9 @@
96
  "eval_overall_f1": 0.8360049321824907,
97
  "eval_overall_precision": 0.8090692124105012,
98
  "eval_overall_recall": 0.8647959183673469,
99
- "eval_runtime": 0.2893,
100
- "eval_samples_per_second": 587.54,
101
- "eval_steps_per_second": 10.368,
102
  "step": 288
103
  },
104
  {
@@ -127,9 +127,9 @@
127
  "eval_overall_f1": 0.8378033205619412,
128
  "eval_overall_precision": 0.8388746803069054,
129
  "eval_overall_recall": 0.8367346938775511,
130
- "eval_runtime": 0.2987,
131
- "eval_samples_per_second": 569.056,
132
- "eval_steps_per_second": 10.042,
133
  "step": 384
134
  },
135
  {
@@ -158,9 +158,9 @@
158
  "eval_overall_f1": 0.8944723618090452,
159
  "eval_overall_precision": 0.8811881188118812,
160
  "eval_overall_recall": 0.9081632653061225,
161
- "eval_runtime": 0.2924,
162
- "eval_samples_per_second": 581.478,
163
- "eval_steps_per_second": 10.261,
164
  "step": 480
165
  },
166
  {
@@ -189,9 +189,9 @@
189
  "eval_overall_f1": 0.8650693568726356,
190
  "eval_overall_precision": 0.8553615960099751,
191
  "eval_overall_recall": 0.875,
192
- "eval_runtime": 0.2897,
193
- "eval_samples_per_second": 586.733,
194
- "eval_steps_per_second": 10.354,
195
  "step": 576
196
  },
197
  {
@@ -220,9 +220,9 @@
220
  "eval_overall_f1": 0.9172932330827067,
221
  "eval_overall_precision": 0.9014778325123153,
222
  "eval_overall_recall": 0.9336734693877551,
223
- "eval_runtime": 0.2893,
224
- "eval_samples_per_second": 587.658,
225
- "eval_steps_per_second": 10.37,
226
  "step": 672
227
  },
228
  {
@@ -251,9 +251,9 @@
251
  "eval_overall_f1": 0.9238578680203046,
252
  "eval_overall_precision": 0.9191919191919192,
253
  "eval_overall_recall": 0.9285714285714286,
254
- "eval_runtime": 0.2896,
255
- "eval_samples_per_second": 587.103,
256
- "eval_steps_per_second": 10.361,
257
  "step": 768
258
  },
259
  {
@@ -282,9 +282,9 @@
282
  "eval_overall_f1": 0.9143576826196474,
283
  "eval_overall_precision": 0.9029850746268657,
284
  "eval_overall_recall": 0.9260204081632653,
285
- "eval_runtime": 0.291,
286
- "eval_samples_per_second": 584.135,
287
- "eval_steps_per_second": 10.308,
288
  "step": 864
289
  },
290
  {
@@ -313,9 +313,9 @@
313
  "eval_overall_f1": 0.9168765743073048,
314
  "eval_overall_precision": 0.9054726368159204,
315
  "eval_overall_recall": 0.9285714285714286,
316
- "eval_runtime": 0.2894,
317
- "eval_samples_per_second": 587.422,
318
- "eval_steps_per_second": 10.366,
319
  "step": 960
320
  },
321
  {
@@ -344,9 +344,9 @@
344
  "eval_overall_f1": 0.940127388535032,
345
  "eval_overall_precision": 0.9389312977099237,
346
  "eval_overall_recall": 0.9413265306122449,
347
- "eval_runtime": 0.2886,
348
- "eval_samples_per_second": 588.966,
349
- "eval_steps_per_second": 10.394,
350
  "step": 1056
351
  },
352
  {
@@ -375,9 +375,9 @@
375
  "eval_overall_f1": 0.9236545682102628,
376
  "eval_overall_precision": 0.9066339066339066,
377
  "eval_overall_recall": 0.9413265306122449,
378
- "eval_runtime": 0.2882,
379
- "eval_samples_per_second": 589.933,
380
- "eval_steps_per_second": 10.411,
381
  "step": 1152
382
  },
383
  {
@@ -406,9 +406,9 @@
406
  "eval_overall_f1": 0.9215189873417722,
407
  "eval_overall_precision": 0.914572864321608,
408
  "eval_overall_recall": 0.9285714285714286,
409
- "eval_runtime": 0.2908,
410
- "eval_samples_per_second": 584.659,
411
- "eval_steps_per_second": 10.318,
412
  "step": 1248
413
  },
414
  {
@@ -437,9 +437,9 @@
437
  "eval_overall_f1": 0.9226869455006337,
438
  "eval_overall_precision": 0.9168765743073047,
439
  "eval_overall_recall": 0.9285714285714286,
440
- "eval_runtime": 0.2895,
441
- "eval_samples_per_second": 587.264,
442
- "eval_steps_per_second": 10.363,
443
  "step": 1344
444
  },
445
  {
@@ -468,9 +468,9 @@
468
  "eval_overall_f1": 0.9328263624841572,
469
  "eval_overall_precision": 0.9269521410579346,
470
  "eval_overall_recall": 0.9387755102040817,
471
- "eval_runtime": 0.2927,
472
- "eval_samples_per_second": 580.716,
473
- "eval_steps_per_second": 10.248,
474
  "step": 1440
475
  },
476
  {
@@ -499,9 +499,9 @@
499
  "eval_overall_f1": 0.9267676767676768,
500
  "eval_overall_precision": 0.9175,
501
  "eval_overall_recall": 0.9362244897959183,
502
- "eval_runtime": 0.2894,
503
- "eval_samples_per_second": 587.341,
504
- "eval_steps_per_second": 10.365,
505
  "step": 1536
506
  },
507
  {
@@ -530,9 +530,9 @@
530
  "eval_overall_f1": 0.929471032745592,
531
  "eval_overall_precision": 0.917910447761194,
532
  "eval_overall_recall": 0.9413265306122449,
533
- "eval_runtime": 0.2919,
534
- "eval_samples_per_second": 582.34,
535
- "eval_steps_per_second": 10.277,
536
  "step": 1632
537
  },
538
  {
@@ -561,9 +561,9 @@
561
  "eval_overall_f1": 0.928388746803069,
562
  "eval_overall_precision": 0.9307692307692308,
563
  "eval_overall_recall": 0.9260204081632653,
564
- "eval_runtime": 0.2872,
565
- "eval_samples_per_second": 591.978,
566
- "eval_steps_per_second": 10.447,
567
  "step": 1728
568
  },
569
  {
@@ -592,9 +592,9 @@
592
  "eval_overall_f1": 0.9480354879594423,
593
  "eval_overall_precision": 0.9420654911838791,
594
  "eval_overall_recall": 0.9540816326530612,
595
- "eval_runtime": 0.2833,
596
- "eval_samples_per_second": 600.027,
597
- "eval_steps_per_second": 10.589,
598
  "step": 1824
599
  },
600
  {
@@ -623,9 +623,9 @@
623
  "eval_overall_f1": 0.9267676767676768,
624
  "eval_overall_precision": 0.9175,
625
  "eval_overall_recall": 0.9362244897959183,
626
- "eval_runtime": 0.2939,
627
- "eval_samples_per_second": 578.495,
628
- "eval_steps_per_second": 10.209,
629
  "step": 1920
630
  },
631
  {
@@ -654,9 +654,9 @@
654
  "eval_overall_f1": 0.9348659003831418,
655
  "eval_overall_precision": 0.9360613810741688,
656
  "eval_overall_recall": 0.9336734693877551,
657
- "eval_runtime": 0.2912,
658
- "eval_samples_per_second": 583.82,
659
- "eval_steps_per_second": 10.303,
660
  "step": 2016
661
  },
662
  {
@@ -685,9 +685,9 @@
685
  "eval_overall_f1": 0.9304677623261693,
686
  "eval_overall_precision": 0.9223057644110275,
687
  "eval_overall_recall": 0.9387755102040817,
688
- "eval_runtime": 0.2852,
689
- "eval_samples_per_second": 596.115,
690
- "eval_steps_per_second": 10.52,
691
  "step": 2112
692
  },
693
  {
@@ -716,9 +716,9 @@
716
  "eval_overall_f1": 0.9417721518987343,
717
  "eval_overall_precision": 0.9346733668341709,
718
  "eval_overall_recall": 0.9489795918367347,
719
- "eval_runtime": 0.2847,
720
- "eval_samples_per_second": 597.072,
721
- "eval_steps_per_second": 10.537,
722
  "step": 2208
723
  },
724
  {
@@ -747,9 +747,9 @@
747
  "eval_overall_f1": 0.9417721518987343,
748
  "eval_overall_precision": 0.9346733668341709,
749
  "eval_overall_recall": 0.9489795918367347,
750
- "eval_runtime": 0.2944,
751
- "eval_samples_per_second": 577.418,
752
- "eval_steps_per_second": 10.19,
753
  "step": 2304
754
  },
755
  {
@@ -778,9 +778,9 @@
778
  "eval_overall_f1": 0.9351969504447268,
779
  "eval_overall_precision": 0.9316455696202531,
780
  "eval_overall_recall": 0.9387755102040817,
781
- "eval_runtime": 0.2868,
782
- "eval_samples_per_second": 592.669,
783
- "eval_steps_per_second": 10.459,
784
  "step": 2400
785
  },
786
  {
@@ -809,9 +809,9 @@
809
  "eval_overall_f1": 0.9390862944162437,
810
  "eval_overall_precision": 0.9343434343434344,
811
  "eval_overall_recall": 0.9438775510204082,
812
- "eval_runtime": 0.2852,
813
- "eval_samples_per_second": 596.048,
814
- "eval_steps_per_second": 10.518,
815
  "step": 2496
816
  },
817
  {
@@ -840,9 +840,9 @@
840
  "eval_overall_f1": 0.9308176100628932,
841
  "eval_overall_precision": 0.9181141439205955,
842
  "eval_overall_recall": 0.9438775510204082,
843
- "eval_runtime": 0.2845,
844
- "eval_samples_per_second": 597.548,
845
- "eval_steps_per_second": 10.545,
846
  "step": 2592
847
  },
848
  {
@@ -871,9 +871,9 @@
871
  "eval_overall_f1": 0.9480354879594423,
872
  "eval_overall_precision": 0.9420654911838791,
873
  "eval_overall_recall": 0.9540816326530612,
874
- "eval_runtime": 0.2877,
875
- "eval_samples_per_second": 590.884,
876
- "eval_steps_per_second": 10.427,
877
  "step": 2688
878
  },
879
  {
@@ -902,9 +902,9 @@
902
  "eval_overall_f1": 0.9518987341772152,
903
  "eval_overall_precision": 0.9447236180904522,
904
  "eval_overall_recall": 0.9591836734693877,
905
- "eval_runtime": 0.2868,
906
- "eval_samples_per_second": 592.749,
907
- "eval_steps_per_second": 10.46,
908
  "step": 2784
909
  },
910
  {
@@ -933,9 +933,9 @@
933
  "eval_overall_f1": 0.9468354430379746,
934
  "eval_overall_precision": 0.9396984924623115,
935
  "eval_overall_recall": 0.9540816326530612,
936
- "eval_runtime": 0.2868,
937
- "eval_samples_per_second": 592.644,
938
- "eval_steps_per_second": 10.458,
939
  "step": 2880
940
  },
941
  {
@@ -964,9 +964,9 @@
964
  "eval_overall_f1": 0.9319899244332494,
965
  "eval_overall_precision": 0.9203980099502488,
966
  "eval_overall_recall": 0.9438775510204082,
967
- "eval_runtime": 0.289,
968
- "eval_samples_per_second": 588.215,
969
- "eval_steps_per_second": 10.38,
970
  "step": 2976
971
  },
972
  {
@@ -995,9 +995,9 @@
995
  "eval_overall_f1": 0.9355246523388117,
996
  "eval_overall_precision": 0.9273182957393483,
997
  "eval_overall_recall": 0.9438775510204082,
998
- "eval_runtime": 0.2918,
999
- "eval_samples_per_second": 582.529,
1000
- "eval_steps_per_second": 10.28,
1001
  "step": 3072
1002
  },
1003
  {
@@ -1026,9 +1026,9 @@
1026
  "eval_overall_f1": 0.9367088607594937,
1027
  "eval_overall_precision": 0.9296482412060302,
1028
  "eval_overall_recall": 0.9438775510204082,
1029
- "eval_runtime": 0.2871,
1030
- "eval_samples_per_second": 592.208,
1031
- "eval_steps_per_second": 10.451,
1032
  "step": 3168
1033
  },
1034
  {
@@ -1057,9 +1057,9 @@
1057
  "eval_overall_f1": 0.9390862944162437,
1058
  "eval_overall_precision": 0.9343434343434344,
1059
  "eval_overall_recall": 0.9438775510204082,
1060
- "eval_runtime": 0.2869,
1061
- "eval_samples_per_second": 592.499,
1062
- "eval_steps_per_second": 10.456,
1063
  "step": 3264
1064
  },
1065
  {
@@ -1088,9 +1088,9 @@
1088
  "eval_overall_f1": 0.9467005076142132,
1089
  "eval_overall_precision": 0.9419191919191919,
1090
  "eval_overall_recall": 0.951530612244898,
1091
- "eval_runtime": 0.286,
1092
- "eval_samples_per_second": 594.352,
1093
- "eval_steps_per_second": 10.489,
1094
  "step": 3360
1095
  },
1096
  {
@@ -1119,9 +1119,9 @@
1119
  "eval_overall_f1": 0.9531051964512041,
1120
  "eval_overall_precision": 0.947103274559194,
1121
  "eval_overall_recall": 0.9591836734693877,
1122
- "eval_runtime": 0.2873,
1123
- "eval_samples_per_second": 591.669,
1124
- "eval_steps_per_second": 10.441,
1125
  "step": 3456
1126
  },
1127
  {
@@ -1150,9 +1150,9 @@
1150
  "eval_overall_f1": 0.9443037974683544,
1151
  "eval_overall_precision": 0.9371859296482412,
1152
  "eval_overall_recall": 0.951530612244898,
1153
- "eval_runtime": 0.2862,
1154
- "eval_samples_per_second": 593.973,
1155
- "eval_steps_per_second": 10.482,
1156
  "step": 3552
1157
  },
1158
  {
@@ -1181,9 +1181,9 @@
1181
  "eval_overall_f1": 0.9279393173198484,
1182
  "eval_overall_precision": 0.9197994987468672,
1183
  "eval_overall_recall": 0.9362244897959183,
1184
- "eval_runtime": 0.2875,
1185
- "eval_samples_per_second": 591.343,
1186
- "eval_steps_per_second": 10.435,
1187
  "step": 3648
1188
  },
1189
  {
@@ -1212,9 +1212,9 @@
1212
  "eval_overall_f1": 0.9410288582183187,
1213
  "eval_overall_precision": 0.9259259259259259,
1214
  "eval_overall_recall": 0.9566326530612245,
1215
- "eval_runtime": 0.2889,
1216
- "eval_samples_per_second": 588.505,
1217
- "eval_steps_per_second": 10.385,
1218
  "step": 3744
1219
  },
1220
  {
@@ -1243,9 +1243,9 @@
1243
  "eval_overall_f1": 0.9433962264150944,
1244
  "eval_overall_precision": 0.9305210918114144,
1245
  "eval_overall_recall": 0.9566326530612245,
1246
- "eval_runtime": 0.2873,
1247
- "eval_samples_per_second": 591.774,
1248
- "eval_steps_per_second": 10.443,
1249
  "step": 3840
1250
  },
1251
  {
@@ -1274,9 +1274,9 @@
1274
  "eval_overall_f1": 0.9443037974683544,
1275
  "eval_overall_precision": 0.9371859296482412,
1276
  "eval_overall_recall": 0.951530612244898,
1277
- "eval_runtime": 0.2874,
1278
- "eval_samples_per_second": 591.444,
1279
- "eval_steps_per_second": 10.437,
1280
  "step": 3936
1281
  },
1282
  {
@@ -1305,9 +1305,9 @@
1305
  "eval_overall_f1": 0.9440203562340966,
1306
  "eval_overall_precision": 0.9416243654822335,
1307
  "eval_overall_recall": 0.9464285714285714,
1308
- "eval_runtime": 0.2866,
1309
- "eval_samples_per_second": 593.189,
1310
- "eval_steps_per_second": 10.468,
1311
  "step": 4032
1312
  },
1313
  {
@@ -1336,9 +1336,9 @@
1336
  "eval_overall_f1": 0.9455006337135614,
1337
  "eval_overall_precision": 0.9395465994962217,
1338
  "eval_overall_recall": 0.951530612244898,
1339
- "eval_runtime": 0.2889,
1340
- "eval_samples_per_second": 588.521,
1341
- "eval_steps_per_second": 10.386,
1342
  "step": 4128
1343
  },
1344
  {
@@ -1367,9 +1367,9 @@
1367
  "eval_overall_f1": 0.9377382465057178,
1368
  "eval_overall_precision": 0.9341772151898734,
1369
  "eval_overall_recall": 0.9413265306122449,
1370
- "eval_runtime": 0.2886,
1371
- "eval_samples_per_second": 589.07,
1372
- "eval_steps_per_second": 10.395,
1373
  "step": 4224
1374
  },
1375
  {
@@ -1398,9 +1398,9 @@
1398
  "eval_overall_f1": 0.9455006337135614,
1399
  "eval_overall_precision": 0.9395465994962217,
1400
  "eval_overall_recall": 0.951530612244898,
1401
- "eval_runtime": 0.2858,
1402
- "eval_samples_per_second": 594.841,
1403
- "eval_steps_per_second": 10.497,
1404
  "step": 4320
1405
  },
1406
  {
@@ -1429,9 +1429,9 @@
1429
  "eval_overall_f1": 0.9390862944162437,
1430
  "eval_overall_precision": 0.9343434343434344,
1431
  "eval_overall_recall": 0.9438775510204082,
1432
- "eval_runtime": 0.2884,
1433
- "eval_samples_per_second": 589.486,
1434
- "eval_steps_per_second": 10.403,
1435
  "step": 4416
1436
  },
1437
  {
@@ -1460,9 +1460,9 @@
1460
  "eval_overall_f1": 0.9390862944162437,
1461
  "eval_overall_precision": 0.9343434343434344,
1462
  "eval_overall_recall": 0.9438775510204082,
1463
- "eval_runtime": 0.285,
1464
- "eval_samples_per_second": 596.467,
1465
- "eval_steps_per_second": 10.526,
1466
  "step": 4512
1467
  },
1468
  {
@@ -1491,9 +1491,9 @@
1491
  "eval_overall_f1": 0.943109987357775,
1492
  "eval_overall_precision": 0.9348370927318296,
1493
  "eval_overall_recall": 0.951530612244898,
1494
- "eval_runtime": 0.2856,
1495
- "eval_samples_per_second": 595.237,
1496
- "eval_steps_per_second": 10.504,
1497
  "step": 4608
1498
  },
1499
  {
@@ -1522,9 +1522,9 @@
1522
  "eval_overall_f1": 0.9453621346886911,
1523
  "eval_overall_precision": 0.9417721518987342,
1524
  "eval_overall_recall": 0.9489795918367347,
1525
- "eval_runtime": 0.2876,
1526
- "eval_samples_per_second": 591.131,
1527
- "eval_steps_per_second": 10.432,
1528
  "step": 4704
1529
  },
1530
  {
@@ -1553,9 +1553,9 @@
1553
  "eval_overall_f1": 0.9426751592356687,
1554
  "eval_overall_precision": 0.9414758269720102,
1555
  "eval_overall_recall": 0.9438775510204082,
1556
- "eval_runtime": 0.2877,
1557
- "eval_samples_per_second": 590.925,
1558
- "eval_steps_per_second": 10.428,
1559
  "step": 4800
1560
  },
1561
  {
@@ -1584,9 +1584,9 @@
1584
  "eval_overall_f1": 0.9309462915601023,
1585
  "eval_overall_precision": 0.9333333333333333,
1586
  "eval_overall_recall": 0.9285714285714286,
1587
- "eval_runtime": 0.2844,
1588
- "eval_samples_per_second": 597.677,
1589
- "eval_steps_per_second": 10.547,
1590
  "step": 4896
1591
  },
1592
  {
@@ -1615,9 +1615,9 @@
1615
  "eval_overall_f1": 0.9389312977099236,
1616
  "eval_overall_precision": 0.9365482233502538,
1617
  "eval_overall_recall": 0.9413265306122449,
1618
- "eval_runtime": 0.2853,
1619
- "eval_samples_per_second": 595.839,
1620
- "eval_steps_per_second": 10.515,
1621
  "step": 4992
1622
  },
1623
  {
@@ -1646,9 +1646,9 @@
1646
  "eval_overall_f1": 0.9419191919191919,
1647
  "eval_overall_precision": 0.9325,
1648
  "eval_overall_recall": 0.951530612244898,
1649
- "eval_runtime": 0.2853,
1650
- "eval_samples_per_second": 595.767,
1651
- "eval_steps_per_second": 10.514,
1652
  "step": 5088
1653
  },
1654
  {
@@ -1677,9 +1677,9 @@
1677
  "eval_overall_f1": 0.9404309252217997,
1678
  "eval_overall_precision": 0.9345088161209067,
1679
  "eval_overall_recall": 0.9464285714285714,
1680
- "eval_runtime": 0.2861,
1681
- "eval_samples_per_second": 594.212,
1682
- "eval_steps_per_second": 10.486,
1683
  "step": 5184
1684
  },
1685
  {
@@ -1708,9 +1708,9 @@
1708
  "eval_overall_f1": 0.9417721518987343,
1709
  "eval_overall_precision": 0.9346733668341709,
1710
  "eval_overall_recall": 0.9489795918367347,
1711
- "eval_runtime": 0.2856,
1712
- "eval_samples_per_second": 595.161,
1713
- "eval_steps_per_second": 10.503,
1714
  "step": 5280
1715
  },
1716
  {
@@ -1739,9 +1739,9 @@
1739
  "eval_overall_f1": 0.9365482233502538,
1740
  "eval_overall_precision": 0.9318181818181818,
1741
  "eval_overall_recall": 0.9413265306122449,
1742
- "eval_runtime": 0.2859,
1743
- "eval_samples_per_second": 594.585,
1744
- "eval_steps_per_second": 10.493,
1745
  "step": 5376
1746
  },
1747
  {
@@ -1770,9 +1770,9 @@
1770
  "eval_overall_f1": 0.9296482412060302,
1771
  "eval_overall_precision": 0.9158415841584159,
1772
  "eval_overall_recall": 0.9438775510204082,
1773
- "eval_runtime": 0.2874,
1774
- "eval_samples_per_second": 591.525,
1775
- "eval_steps_per_second": 10.439,
1776
  "step": 5472
1777
  },
1778
  {
@@ -1801,9 +1801,9 @@
1801
  "eval_overall_f1": 0.9390862944162437,
1802
  "eval_overall_precision": 0.9343434343434344,
1803
  "eval_overall_recall": 0.9438775510204082,
1804
- "eval_runtime": 0.2854,
1805
- "eval_samples_per_second": 595.564,
1806
- "eval_steps_per_second": 10.51,
1807
  "step": 5568
1808
  },
1809
  {
@@ -1832,9 +1832,9 @@
1832
  "eval_overall_f1": 0.9456384323640962,
1833
  "eval_overall_precision": 0.9373433583959899,
1834
  "eval_overall_recall": 0.9540816326530612,
1835
- "eval_runtime": 0.2846,
1836
- "eval_samples_per_second": 597.225,
1837
- "eval_steps_per_second": 10.539,
1838
  "step": 5664
1839
  },
1840
  {
@@ -1863,9 +1863,9 @@
1863
  "eval_overall_f1": 0.9429657794676806,
1864
  "eval_overall_precision": 0.9370277078085643,
1865
  "eval_overall_recall": 0.9489795918367347,
1866
- "eval_runtime": 0.2844,
1867
- "eval_samples_per_second": 597.794,
1868
- "eval_steps_per_second": 10.549,
1869
  "step": 5760
1870
  },
1871
  {
@@ -1894,9 +1894,9 @@
1894
  "eval_overall_f1": 0.9456384323640962,
1895
  "eval_overall_precision": 0.9373433583959899,
1896
  "eval_overall_recall": 0.9540816326530612,
1897
- "eval_runtime": 0.2844,
1898
- "eval_samples_per_second": 597.741,
1899
- "eval_steps_per_second": 10.548,
1900
  "step": 5856
1901
  },
1902
  {
@@ -1925,9 +1925,9 @@
1925
  "eval_overall_f1": 0.9459119496855347,
1926
  "eval_overall_precision": 0.9330024813895782,
1927
  "eval_overall_recall": 0.9591836734693877,
1928
- "eval_runtime": 0.2854,
1929
- "eval_samples_per_second": 595.585,
1930
- "eval_steps_per_second": 10.51,
1931
  "step": 5952
1932
  },
1933
  {
@@ -1956,9 +1956,9 @@
1956
  "eval_overall_f1": 0.9457755359394704,
1957
  "eval_overall_precision": 0.9351620947630923,
1958
  "eval_overall_recall": 0.9566326530612245,
1959
- "eval_runtime": 0.2855,
1960
- "eval_samples_per_second": 595.41,
1961
- "eval_steps_per_second": 10.507,
1962
  "step": 6048
1963
  },
1964
  {
@@ -1987,9 +1987,9 @@
1987
  "eval_overall_f1": 0.9457755359394704,
1988
  "eval_overall_precision": 0.9351620947630923,
1989
  "eval_overall_recall": 0.9566326530612245,
1990
- "eval_runtime": 0.2867,
1991
- "eval_samples_per_second": 592.984,
1992
- "eval_steps_per_second": 10.464,
1993
  "step": 6144
1994
  },
1995
  {
@@ -2018,9 +2018,9 @@
2018
  "eval_overall_f1": 0.9593908629441624,
2019
  "eval_overall_precision": 0.9545454545454546,
2020
  "eval_overall_recall": 0.9642857142857143,
2021
- "eval_runtime": 0.2849,
2022
- "eval_samples_per_second": 596.763,
2023
- "eval_steps_per_second": 10.531,
2024
  "step": 6240
2025
  },
2026
  {
@@ -2049,9 +2049,9 @@
2049
  "eval_overall_f1": 0.9455006337135614,
2050
  "eval_overall_precision": 0.9395465994962217,
2051
  "eval_overall_recall": 0.951530612244898,
2052
- "eval_runtime": 0.286,
2053
- "eval_samples_per_second": 594.42,
2054
- "eval_steps_per_second": 10.49,
2055
  "step": 6336
2056
  },
2057
  {
@@ -2080,9 +2080,9 @@
2080
  "eval_overall_f1": 0.9517766497461929,
2081
  "eval_overall_precision": 0.946969696969697,
2082
  "eval_overall_recall": 0.9566326530612245,
2083
- "eval_runtime": 0.2845,
2084
- "eval_samples_per_second": 597.452,
2085
- "eval_steps_per_second": 10.543,
2086
  "step": 6432
2087
  },
2088
  {
@@ -2111,9 +2111,9 @@
2111
  "eval_overall_f1": 0.9456384323640962,
2112
  "eval_overall_precision": 0.9373433583959899,
2113
  "eval_overall_recall": 0.9540816326530612,
2114
- "eval_runtime": 0.2859,
2115
- "eval_samples_per_second": 594.629,
2116
- "eval_steps_per_second": 10.493,
2117
  "step": 6528
2118
  },
2119
  {
@@ -2142,9 +2142,9 @@
2142
  "eval_overall_f1": 0.9456384323640962,
2143
  "eval_overall_precision": 0.9373433583959899,
2144
  "eval_overall_recall": 0.9540816326530612,
2145
- "eval_runtime": 0.2853,
2146
- "eval_samples_per_second": 595.873,
2147
- "eval_steps_per_second": 10.515,
2148
  "step": 6624
2149
  },
2150
  {
@@ -2173,9 +2173,9 @@
2173
  "eval_overall_f1": 0.9407313997477933,
2174
  "eval_overall_precision": 0.9301745635910225,
2175
  "eval_overall_recall": 0.951530612244898,
2176
- "eval_runtime": 0.2853,
2177
- "eval_samples_per_second": 595.849,
2178
- "eval_steps_per_second": 10.515,
2179
  "step": 6720
2180
  },
2181
  {
@@ -2204,9 +2204,9 @@
2204
  "eval_overall_f1": 0.947103274559194,
2205
  "eval_overall_precision": 0.9353233830845771,
2206
  "eval_overall_recall": 0.9591836734693877,
2207
- "eval_runtime": 0.2857,
2208
- "eval_samples_per_second": 594.945,
2209
- "eval_steps_per_second": 10.499,
2210
  "step": 6816
2211
  },
2212
  {
@@ -2235,9 +2235,9 @@
2235
  "eval_overall_f1": 0.9456384323640962,
2236
  "eval_overall_precision": 0.9373433583959899,
2237
  "eval_overall_recall": 0.9540816326530612,
2238
- "eval_runtime": 0.2874,
2239
- "eval_samples_per_second": 591.423,
2240
- "eval_steps_per_second": 10.437,
2241
  "step": 6912
2242
  },
2243
  {
@@ -2266,9 +2266,9 @@
2266
  "eval_overall_f1": 0.9405815423514539,
2267
  "eval_overall_precision": 0.9323308270676691,
2268
  "eval_overall_recall": 0.9489795918367347,
2269
- "eval_runtime": 0.2875,
2270
- "eval_samples_per_second": 591.247,
2271
- "eval_steps_per_second": 10.434,
2272
  "step": 7008
2273
  },
2274
  {
@@ -2297,9 +2297,9 @@
2297
  "eval_overall_f1": 0.9390862944162437,
2298
  "eval_overall_precision": 0.9343434343434344,
2299
  "eval_overall_recall": 0.9438775510204082,
2300
- "eval_runtime": 0.2859,
2301
- "eval_samples_per_second": 594.654,
2302
- "eval_steps_per_second": 10.494,
2303
  "step": 7104
2304
  },
2305
  {
@@ -2328,9 +2328,9 @@
2328
  "eval_overall_f1": 0.9255989911727616,
2329
  "eval_overall_precision": 0.9152119700748129,
2330
  "eval_overall_recall": 0.9362244897959183,
2331
- "eval_runtime": 0.291,
2332
- "eval_samples_per_second": 584.169,
2333
- "eval_steps_per_second": 10.309,
2334
  "step": 7200
2335
  },
2336
  {
@@ -2359,9 +2359,9 @@
2359
  "eval_overall_f1": 0.9419191919191919,
2360
  "eval_overall_precision": 0.9325,
2361
  "eval_overall_recall": 0.951530612244898,
2362
- "eval_runtime": 0.2888,
2363
- "eval_samples_per_second": 588.564,
2364
- "eval_steps_per_second": 10.386,
2365
  "step": 7296
2366
  },
2367
  {
@@ -2390,9 +2390,9 @@
2390
  "eval_overall_f1": 0.9407313997477933,
2391
  "eval_overall_precision": 0.9301745635910225,
2392
  "eval_overall_recall": 0.951530612244898,
2393
- "eval_runtime": 0.2865,
2394
- "eval_samples_per_second": 593.392,
2395
- "eval_steps_per_second": 10.472,
2396
  "step": 7392
2397
  },
2398
  {
@@ -2421,9 +2421,9 @@
2421
  "eval_overall_f1": 0.9382093316519546,
2422
  "eval_overall_precision": 0.9276807980049875,
2423
  "eval_overall_recall": 0.9489795918367347,
2424
- "eval_runtime": 0.2878,
2425
- "eval_samples_per_second": 590.613,
2426
- "eval_steps_per_second": 10.423,
2427
  "step": 7488
2428
  },
2429
  {
@@ -2452,9 +2452,9 @@
2452
  "eval_overall_f1": 0.9404309252217997,
2453
  "eval_overall_precision": 0.9345088161209067,
2454
  "eval_overall_recall": 0.9464285714285714,
2455
- "eval_runtime": 0.2865,
2456
- "eval_samples_per_second": 593.452,
2457
- "eval_steps_per_second": 10.473,
2458
  "step": 7584
2459
  },
2460
  {
@@ -2483,9 +2483,9 @@
2483
  "eval_overall_f1": 0.9408805031446542,
2484
  "eval_overall_precision": 0.9280397022332506,
2485
  "eval_overall_recall": 0.9540816326530612,
2486
- "eval_runtime": 0.2856,
2487
- "eval_samples_per_second": 595.151,
2488
- "eval_steps_per_second": 10.503,
2489
  "step": 7680
2490
  },
2491
  {
@@ -2514,9 +2514,9 @@
2514
  "eval_overall_f1": 0.9494949494949495,
2515
  "eval_overall_precision": 0.94,
2516
  "eval_overall_recall": 0.9591836734693877,
2517
- "eval_runtime": 0.2881,
2518
- "eval_samples_per_second": 590.102,
2519
- "eval_steps_per_second": 10.414,
2520
  "step": 7776
2521
  },
2522
  {
@@ -2545,9 +2545,9 @@
2545
  "eval_overall_f1": 0.9380530973451328,
2546
  "eval_overall_precision": 0.9298245614035088,
2547
  "eval_overall_recall": 0.9464285714285714,
2548
- "eval_runtime": 0.2887,
2549
- "eval_samples_per_second": 588.941,
2550
- "eval_steps_per_second": 10.393,
2551
  "step": 7872
2552
  },
2553
  {
@@ -2576,9 +2576,9 @@
2576
  "eval_overall_f1": 0.94147582697201,
2577
  "eval_overall_precision": 0.9390862944162437,
2578
  "eval_overall_recall": 0.9438775510204082,
2579
- "eval_runtime": 0.2889,
2580
- "eval_samples_per_second": 588.437,
2581
- "eval_steps_per_second": 10.384,
2582
  "step": 7968
2583
  },
2584
  {
@@ -2607,9 +2607,9 @@
2607
  "eval_overall_f1": 0.9392405063291138,
2608
  "eval_overall_precision": 0.9321608040201005,
2609
  "eval_overall_recall": 0.9464285714285714,
2610
- "eval_runtime": 0.2858,
2611
- "eval_samples_per_second": 594.862,
2612
- "eval_steps_per_second": 10.498,
2613
  "step": 8064
2614
  },
2615
  {
@@ -2638,9 +2638,9 @@
2638
  "eval_overall_f1": 0.935361216730038,
2639
  "eval_overall_precision": 0.929471032745592,
2640
  "eval_overall_recall": 0.9413265306122449,
2641
- "eval_runtime": 0.2906,
2642
- "eval_samples_per_second": 585.065,
2643
- "eval_steps_per_second": 10.325,
2644
  "step": 8160
2645
  },
2646
  {
@@ -2669,9 +2669,9 @@
2669
  "eval_overall_f1": 0.9390862944162437,
2670
  "eval_overall_precision": 0.9343434343434344,
2671
  "eval_overall_recall": 0.9438775510204082,
2672
- "eval_runtime": 0.2913,
2673
- "eval_samples_per_second": 583.568,
2674
- "eval_steps_per_second": 10.298,
2675
  "step": 8256
2676
  },
2677
  {
@@ -2700,9 +2700,9 @@
2700
  "eval_overall_f1": 0.9417721518987343,
2701
  "eval_overall_precision": 0.9346733668341709,
2702
  "eval_overall_recall": 0.9489795918367347,
2703
- "eval_runtime": 0.2906,
2704
- "eval_samples_per_second": 584.911,
2705
- "eval_steps_per_second": 10.322,
2706
  "step": 8352
2707
  },
2708
  {
@@ -2731,9 +2731,9 @@
2731
  "eval_overall_f1": 0.9443037974683544,
2732
  "eval_overall_precision": 0.9371859296482412,
2733
  "eval_overall_recall": 0.951530612244898,
2734
- "eval_runtime": 0.2972,
2735
- "eval_samples_per_second": 571.995,
2736
- "eval_steps_per_second": 10.094,
2737
  "step": 8448
2738
  },
2739
  {
@@ -2762,9 +2762,9 @@
2762
  "eval_overall_f1": 0.9443037974683544,
2763
  "eval_overall_precision": 0.9371859296482412,
2764
  "eval_overall_recall": 0.951530612244898,
2765
- "eval_runtime": 0.2907,
2766
- "eval_samples_per_second": 584.758,
2767
- "eval_steps_per_second": 10.319,
2768
  "step": 8544
2769
  },
2770
  {
@@ -2793,9 +2793,9 @@
2793
  "eval_overall_f1": 0.943109987357775,
2794
  "eval_overall_precision": 0.9348370927318296,
2795
  "eval_overall_recall": 0.951530612244898,
2796
- "eval_runtime": 0.2905,
2797
- "eval_samples_per_second": 585.276,
2798
- "eval_steps_per_second": 10.328,
2799
  "step": 8640
2800
  },
2801
  {
@@ -2824,9 +2824,9 @@
2824
  "eval_overall_f1": 0.9417721518987343,
2825
  "eval_overall_precision": 0.9346733668341709,
2826
  "eval_overall_recall": 0.9489795918367347,
2827
- "eval_runtime": 0.2898,
2828
- "eval_samples_per_second": 586.56,
2829
- "eval_steps_per_second": 10.351,
2830
  "step": 8736
2831
  },
2832
  {
@@ -2855,9 +2855,9 @@
2855
  "eval_overall_f1": 0.9429657794676806,
2856
  "eval_overall_precision": 0.9370277078085643,
2857
  "eval_overall_recall": 0.9489795918367347,
2858
- "eval_runtime": 0.2936,
2859
- "eval_samples_per_second": 578.922,
2860
- "eval_steps_per_second": 10.216,
2861
  "step": 8832
2862
  },
2863
  {
@@ -2886,9 +2886,9 @@
2886
  "eval_overall_f1": 0.9380530973451328,
2887
  "eval_overall_precision": 0.9298245614035088,
2888
  "eval_overall_recall": 0.9464285714285714,
2889
- "eval_runtime": 0.2899,
2890
- "eval_samples_per_second": 586.429,
2891
- "eval_steps_per_second": 10.349,
2892
  "step": 8928
2893
  },
2894
  {
@@ -2917,9 +2917,9 @@
2917
  "eval_overall_f1": 0.9467005076142132,
2918
  "eval_overall_precision": 0.9419191919191919,
2919
  "eval_overall_recall": 0.951530612244898,
2920
- "eval_runtime": 0.2915,
2921
- "eval_samples_per_second": 583.255,
2922
- "eval_steps_per_second": 10.293,
2923
  "step": 9024
2924
  },
2925
  {
@@ -2948,9 +2948,9 @@
2948
  "eval_overall_f1": 0.949367088607595,
2949
  "eval_overall_precision": 0.9422110552763819,
2950
  "eval_overall_recall": 0.9566326530612245,
2951
- "eval_runtime": 0.2893,
2952
- "eval_samples_per_second": 587.53,
2953
- "eval_steps_per_second": 10.368,
2954
  "step": 9120
2955
  },
2956
  {
@@ -2979,9 +2979,9 @@
2979
  "eval_overall_f1": 0.9455006337135614,
2980
  "eval_overall_precision": 0.9395465994962217,
2981
  "eval_overall_recall": 0.951530612244898,
2982
- "eval_runtime": 0.2908,
2983
- "eval_samples_per_second": 584.627,
2984
- "eval_steps_per_second": 10.317,
2985
  "step": 9216
2986
  },
2987
  {
@@ -3010,9 +3010,9 @@
3010
  "eval_overall_f1": 0.9467005076142132,
3011
  "eval_overall_precision": 0.9419191919191919,
3012
  "eval_overall_recall": 0.951530612244898,
3013
- "eval_runtime": 0.2891,
3014
- "eval_samples_per_second": 587.978,
3015
- "eval_steps_per_second": 10.376,
3016
  "step": 9312
3017
  },
3018
  {
@@ -3041,9 +3041,9 @@
3041
  "eval_overall_f1": 0.9441624365482234,
3042
  "eval_overall_precision": 0.9393939393939394,
3043
  "eval_overall_recall": 0.9489795918367347,
3044
- "eval_runtime": 0.2903,
3045
- "eval_samples_per_second": 585.602,
3046
- "eval_steps_per_second": 10.334,
3047
  "step": 9408
3048
  },
3049
  {
@@ -3072,9 +3072,9 @@
3072
  "eval_overall_f1": 0.9441624365482234,
3073
  "eval_overall_precision": 0.9393939393939394,
3074
  "eval_overall_recall": 0.9489795918367347,
3075
- "eval_runtime": 0.2904,
3076
- "eval_samples_per_second": 585.452,
3077
- "eval_steps_per_second": 10.332,
3078
  "step": 9504
3079
  },
3080
  {
@@ -3103,9 +3103,9 @@
3103
  "eval_overall_f1": 0.9429657794676806,
3104
  "eval_overall_precision": 0.9370277078085643,
3105
  "eval_overall_recall": 0.9489795918367347,
3106
- "eval_runtime": 0.2939,
3107
- "eval_samples_per_second": 578.339,
3108
- "eval_steps_per_second": 10.206,
3109
  "step": 9600
3110
  },
3111
  {
@@ -3113,9 +3113,9 @@
3113
  "step": 9600,
3114
  "total_flos": 4315798421360676.0,
3115
  "train_loss": 0.038009579268594586,
3116
- "train_runtime": 536.2277,
3117
- "train_samples_per_second": 285.513,
3118
- "train_steps_per_second": 17.903
3119
  }
3120
  ],
3121
  "logging_steps": 500,
 
34
  "eval_overall_f1": 0.2607561929595828,
35
  "eval_overall_precision": 0.26666666666666666,
36
  "eval_overall_recall": 0.25510204081632654,
37
+ "eval_runtime": 0.2881,
38
+ "eval_samples_per_second": 590.049,
39
+ "eval_steps_per_second": 10.413,
40
  "step": 96
41
  },
42
  {
 
65
  "eval_overall_f1": 0.5707434052757793,
66
  "eval_overall_precision": 0.5384615384615384,
67
  "eval_overall_recall": 0.6071428571428571,
68
+ "eval_runtime": 0.2924,
69
+ "eval_samples_per_second": 581.441,
70
+ "eval_steps_per_second": 10.261,
71
  "step": 192
72
  },
73
  {
 
96
  "eval_overall_f1": 0.8360049321824907,
97
  "eval_overall_precision": 0.8090692124105012,
98
  "eval_overall_recall": 0.8647959183673469,
99
+ "eval_runtime": 0.2899,
100
+ "eval_samples_per_second": 586.468,
101
+ "eval_steps_per_second": 10.349,
102
  "step": 288
103
  },
104
  {
 
127
  "eval_overall_f1": 0.8378033205619412,
128
  "eval_overall_precision": 0.8388746803069054,
129
  "eval_overall_recall": 0.8367346938775511,
130
+ "eval_runtime": 0.2889,
131
+ "eval_samples_per_second": 588.524,
132
+ "eval_steps_per_second": 10.386,
133
  "step": 384
134
  },
135
  {
 
158
  "eval_overall_f1": 0.8944723618090452,
159
  "eval_overall_precision": 0.8811881188118812,
160
  "eval_overall_recall": 0.9081632653061225,
161
+ "eval_runtime": 0.2959,
162
+ "eval_samples_per_second": 574.566,
163
+ "eval_steps_per_second": 10.139,
164
  "step": 480
165
  },
166
  {
 
189
  "eval_overall_f1": 0.8650693568726356,
190
  "eval_overall_precision": 0.8553615960099751,
191
  "eval_overall_recall": 0.875,
192
+ "eval_runtime": 0.291,
193
+ "eval_samples_per_second": 584.164,
194
+ "eval_steps_per_second": 10.309,
195
  "step": 576
196
  },
197
  {
 
220
  "eval_overall_f1": 0.9172932330827067,
221
  "eval_overall_precision": 0.9014778325123153,
222
  "eval_overall_recall": 0.9336734693877551,
223
+ "eval_runtime": 0.2915,
224
+ "eval_samples_per_second": 583.232,
225
+ "eval_steps_per_second": 10.292,
226
  "step": 672
227
  },
228
  {
 
251
  "eval_overall_f1": 0.9238578680203046,
252
  "eval_overall_precision": 0.9191919191919192,
253
  "eval_overall_recall": 0.9285714285714286,
254
+ "eval_runtime": 0.286,
255
+ "eval_samples_per_second": 594.441,
256
+ "eval_steps_per_second": 10.49,
257
  "step": 768
258
  },
259
  {
 
282
  "eval_overall_f1": 0.9143576826196474,
283
  "eval_overall_precision": 0.9029850746268657,
284
  "eval_overall_recall": 0.9260204081632653,
285
+ "eval_runtime": 0.2906,
286
+ "eval_samples_per_second": 585.017,
287
+ "eval_steps_per_second": 10.324,
288
  "step": 864
289
  },
290
  {
 
313
  "eval_overall_f1": 0.9168765743073048,
314
  "eval_overall_precision": 0.9054726368159204,
315
  "eval_overall_recall": 0.9285714285714286,
316
+ "eval_runtime": 0.2883,
317
+ "eval_samples_per_second": 589.762,
318
+ "eval_steps_per_second": 10.408,
319
  "step": 960
320
  },
321
  {
 
344
  "eval_overall_f1": 0.940127388535032,
345
  "eval_overall_precision": 0.9389312977099237,
346
  "eval_overall_recall": 0.9413265306122449,
347
+ "eval_runtime": 0.2891,
348
+ "eval_samples_per_second": 588.067,
349
+ "eval_steps_per_second": 10.378,
350
  "step": 1056
351
  },
352
  {
 
375
  "eval_overall_f1": 0.9236545682102628,
376
  "eval_overall_precision": 0.9066339066339066,
377
  "eval_overall_recall": 0.9413265306122449,
378
+ "eval_runtime": 0.288,
379
+ "eval_samples_per_second": 590.347,
380
+ "eval_steps_per_second": 10.418,
381
  "step": 1152
382
  },
383
  {
 
406
  "eval_overall_f1": 0.9215189873417722,
407
  "eval_overall_precision": 0.914572864321608,
408
  "eval_overall_recall": 0.9285714285714286,
409
+ "eval_runtime": 0.2906,
410
+ "eval_samples_per_second": 585.089,
411
+ "eval_steps_per_second": 10.325,
412
  "step": 1248
413
  },
414
  {
 
437
  "eval_overall_f1": 0.9226869455006337,
438
  "eval_overall_precision": 0.9168765743073047,
439
  "eval_overall_recall": 0.9285714285714286,
440
+ "eval_runtime": 0.2899,
441
+ "eval_samples_per_second": 586.343,
442
+ "eval_steps_per_second": 10.347,
443
  "step": 1344
444
  },
445
  {
 
468
  "eval_overall_f1": 0.9328263624841572,
469
  "eval_overall_precision": 0.9269521410579346,
470
  "eval_overall_recall": 0.9387755102040817,
471
+ "eval_runtime": 0.2898,
472
+ "eval_samples_per_second": 586.551,
473
+ "eval_steps_per_second": 10.351,
474
  "step": 1440
475
  },
476
  {
 
499
  "eval_overall_f1": 0.9267676767676768,
500
  "eval_overall_precision": 0.9175,
501
  "eval_overall_recall": 0.9362244897959183,
502
+ "eval_runtime": 0.2901,
503
+ "eval_samples_per_second": 586.062,
504
+ "eval_steps_per_second": 10.342,
505
  "step": 1536
506
  },
507
  {
 
530
  "eval_overall_f1": 0.929471032745592,
531
  "eval_overall_precision": 0.917910447761194,
532
  "eval_overall_recall": 0.9413265306122449,
533
+ "eval_runtime": 0.2876,
534
+ "eval_samples_per_second": 591.072,
535
+ "eval_steps_per_second": 10.431,
536
  "step": 1632
537
  },
538
  {
 
561
  "eval_overall_f1": 0.928388746803069,
562
  "eval_overall_precision": 0.9307692307692308,
563
  "eval_overall_recall": 0.9260204081632653,
564
+ "eval_runtime": 0.2907,
565
+ "eval_samples_per_second": 584.85,
566
+ "eval_steps_per_second": 10.321,
567
  "step": 1728
568
  },
569
  {
 
592
  "eval_overall_f1": 0.9480354879594423,
593
  "eval_overall_precision": 0.9420654911838791,
594
  "eval_overall_recall": 0.9540816326530612,
595
+ "eval_runtime": 0.2873,
596
+ "eval_samples_per_second": 591.631,
597
+ "eval_steps_per_second": 10.441,
598
  "step": 1824
599
  },
600
  {
 
623
  "eval_overall_f1": 0.9267676767676768,
624
  "eval_overall_precision": 0.9175,
625
  "eval_overall_recall": 0.9362244897959183,
626
+ "eval_runtime": 0.2888,
627
+ "eval_samples_per_second": 588.684,
628
+ "eval_steps_per_second": 10.389,
629
  "step": 1920
630
  },
631
  {
 
654
  "eval_overall_f1": 0.9348659003831418,
655
  "eval_overall_precision": 0.9360613810741688,
656
  "eval_overall_recall": 0.9336734693877551,
657
+ "eval_runtime": 0.2899,
658
+ "eval_samples_per_second": 586.361,
659
+ "eval_steps_per_second": 10.348,
660
  "step": 2016
661
  },
662
  {
 
685
  "eval_overall_f1": 0.9304677623261693,
686
  "eval_overall_precision": 0.9223057644110275,
687
  "eval_overall_recall": 0.9387755102040817,
688
+ "eval_runtime": 0.2881,
689
+ "eval_samples_per_second": 590.144,
690
+ "eval_steps_per_second": 10.414,
691
  "step": 2112
692
  },
693
  {
 
716
  "eval_overall_f1": 0.9417721518987343,
717
  "eval_overall_precision": 0.9346733668341709,
718
  "eval_overall_recall": 0.9489795918367347,
719
+ "eval_runtime": 0.2873,
720
+ "eval_samples_per_second": 591.708,
721
+ "eval_steps_per_second": 10.442,
722
  "step": 2208
723
  },
724
  {
 
747
  "eval_overall_f1": 0.9417721518987343,
748
  "eval_overall_precision": 0.9346733668341709,
749
  "eval_overall_recall": 0.9489795918367347,
750
+ "eval_runtime": 0.29,
751
+ "eval_samples_per_second": 586.169,
752
+ "eval_steps_per_second": 10.344,
753
  "step": 2304
754
  },
755
  {
 
778
  "eval_overall_f1": 0.9351969504447268,
779
  "eval_overall_precision": 0.9316455696202531,
780
  "eval_overall_recall": 0.9387755102040817,
781
+ "eval_runtime": 0.2896,
782
+ "eval_samples_per_second": 587.085,
783
+ "eval_steps_per_second": 10.36,
784
  "step": 2400
785
  },
786
  {
 
809
  "eval_overall_f1": 0.9390862944162437,
810
  "eval_overall_precision": 0.9343434343434344,
811
  "eval_overall_recall": 0.9438775510204082,
812
+ "eval_runtime": 0.2876,
813
+ "eval_samples_per_second": 591.019,
814
+ "eval_steps_per_second": 10.43,
815
  "step": 2496
816
  },
817
  {
 
840
  "eval_overall_f1": 0.9308176100628932,
841
  "eval_overall_precision": 0.9181141439205955,
842
  "eval_overall_recall": 0.9438775510204082,
843
+ "eval_runtime": 0.2888,
844
+ "eval_samples_per_second": 588.616,
845
+ "eval_steps_per_second": 10.387,
846
  "step": 2592
847
  },
848
  {
 
871
  "eval_overall_f1": 0.9480354879594423,
872
  "eval_overall_precision": 0.9420654911838791,
873
  "eval_overall_recall": 0.9540816326530612,
874
+ "eval_runtime": 0.2881,
875
+ "eval_samples_per_second": 590.035,
876
+ "eval_steps_per_second": 10.412,
877
  "step": 2688
878
  },
879
  {
 
902
  "eval_overall_f1": 0.9518987341772152,
903
  "eval_overall_precision": 0.9447236180904522,
904
  "eval_overall_recall": 0.9591836734693877,
905
+ "eval_runtime": 0.2883,
906
+ "eval_samples_per_second": 589.601,
907
+ "eval_steps_per_second": 10.405,
908
  "step": 2784
909
  },
910
  {
 
933
  "eval_overall_f1": 0.9468354430379746,
934
  "eval_overall_precision": 0.9396984924623115,
935
  "eval_overall_recall": 0.9540816326530612,
936
+ "eval_runtime": 0.2898,
937
+ "eval_samples_per_second": 586.537,
938
+ "eval_steps_per_second": 10.351,
939
  "step": 2880
940
  },
941
  {
 
964
  "eval_overall_f1": 0.9319899244332494,
965
  "eval_overall_precision": 0.9203980099502488,
966
  "eval_overall_recall": 0.9438775510204082,
967
+ "eval_runtime": 0.2872,
968
+ "eval_samples_per_second": 591.827,
969
+ "eval_steps_per_second": 10.444,
970
  "step": 2976
971
  },
972
  {
 
995
  "eval_overall_f1": 0.9355246523388117,
996
  "eval_overall_precision": 0.9273182957393483,
997
  "eval_overall_recall": 0.9438775510204082,
998
+ "eval_runtime": 0.2888,
999
+ "eval_samples_per_second": 588.665,
1000
+ "eval_steps_per_second": 10.388,
1001
  "step": 3072
1002
  },
1003
  {
 
1026
  "eval_overall_f1": 0.9367088607594937,
1027
  "eval_overall_precision": 0.9296482412060302,
1028
  "eval_overall_recall": 0.9438775510204082,
1029
+ "eval_runtime": 0.2859,
1030
+ "eval_samples_per_second": 594.668,
1031
+ "eval_steps_per_second": 10.494,
1032
  "step": 3168
1033
  },
1034
  {
 
1057
  "eval_overall_f1": 0.9390862944162437,
1058
  "eval_overall_precision": 0.9343434343434344,
1059
  "eval_overall_recall": 0.9438775510204082,
1060
+ "eval_runtime": 0.2876,
1061
+ "eval_samples_per_second": 591.013,
1062
+ "eval_steps_per_second": 10.43,
1063
  "step": 3264
1064
  },
1065
  {
 
1088
  "eval_overall_f1": 0.9467005076142132,
1089
  "eval_overall_precision": 0.9419191919191919,
1090
  "eval_overall_recall": 0.951530612244898,
1091
+ "eval_runtime": 0.29,
1092
+ "eval_samples_per_second": 586.204,
1093
+ "eval_steps_per_second": 10.345,
1094
  "step": 3360
1095
  },
1096
  {
 
1119
  "eval_overall_f1": 0.9531051964512041,
1120
  "eval_overall_precision": 0.947103274559194,
1121
  "eval_overall_recall": 0.9591836734693877,
1122
+ "eval_runtime": 0.2853,
1123
+ "eval_samples_per_second": 595.846,
1124
+ "eval_steps_per_second": 10.515,
1125
  "step": 3456
1126
  },
1127
  {
 
1150
  "eval_overall_f1": 0.9443037974683544,
1151
  "eval_overall_precision": 0.9371859296482412,
1152
  "eval_overall_recall": 0.951530612244898,
1153
+ "eval_runtime": 0.2897,
1154
+ "eval_samples_per_second": 586.788,
1155
+ "eval_steps_per_second": 10.355,
1156
  "step": 3552
1157
  },
1158
  {
 
1181
  "eval_overall_f1": 0.9279393173198484,
1182
  "eval_overall_precision": 0.9197994987468672,
1183
  "eval_overall_recall": 0.9362244897959183,
1184
+ "eval_runtime": 0.2847,
1185
+ "eval_samples_per_second": 597.214,
1186
+ "eval_steps_per_second": 10.539,
1187
  "step": 3648
1188
  },
1189
  {
 
1212
  "eval_overall_f1": 0.9410288582183187,
1213
  "eval_overall_precision": 0.9259259259259259,
1214
  "eval_overall_recall": 0.9566326530612245,
1215
+ "eval_runtime": 0.2879,
1216
+ "eval_samples_per_second": 590.434,
1217
+ "eval_steps_per_second": 10.419,
1218
  "step": 3744
1219
  },
1220
  {
 
1243
  "eval_overall_f1": 0.9433962264150944,
1244
  "eval_overall_precision": 0.9305210918114144,
1245
  "eval_overall_recall": 0.9566326530612245,
1246
+ "eval_runtime": 0.2864,
1247
+ "eval_samples_per_second": 593.484,
1248
+ "eval_steps_per_second": 10.473,
1249
  "step": 3840
1250
  },
1251
  {
 
1274
  "eval_overall_f1": 0.9443037974683544,
1275
  "eval_overall_precision": 0.9371859296482412,
1276
  "eval_overall_recall": 0.951530612244898,
1277
+ "eval_runtime": 0.2927,
1278
+ "eval_samples_per_second": 580.719,
1279
+ "eval_steps_per_second": 10.248,
1280
  "step": 3936
1281
  },
1282
  {
 
1305
  "eval_overall_f1": 0.9440203562340966,
1306
  "eval_overall_precision": 0.9416243654822335,
1307
  "eval_overall_recall": 0.9464285714285714,
1308
+ "eval_runtime": 0.2862,
1309
+ "eval_samples_per_second": 594.05,
1310
+ "eval_steps_per_second": 10.483,
1311
  "step": 4032
1312
  },
1313
  {
 
1336
  "eval_overall_f1": 0.9455006337135614,
1337
  "eval_overall_precision": 0.9395465994962217,
1338
  "eval_overall_recall": 0.951530612244898,
1339
+ "eval_runtime": 0.2899,
1340
+ "eval_samples_per_second": 586.349,
1341
+ "eval_steps_per_second": 10.347,
1342
  "step": 4128
1343
  },
1344
  {
 
1367
  "eval_overall_f1": 0.9377382465057178,
1368
  "eval_overall_precision": 0.9341772151898734,
1369
  "eval_overall_recall": 0.9413265306122449,
1370
+ "eval_runtime": 0.293,
1371
+ "eval_samples_per_second": 580.26,
1372
+ "eval_steps_per_second": 10.24,
1373
  "step": 4224
1374
  },
1375
  {
 
1398
  "eval_overall_f1": 0.9455006337135614,
1399
  "eval_overall_precision": 0.9395465994962217,
1400
  "eval_overall_recall": 0.951530612244898,
1401
+ "eval_runtime": 0.293,
1402
+ "eval_samples_per_second": 580.259,
1403
+ "eval_steps_per_second": 10.24,
1404
  "step": 4320
1405
  },
1406
  {
 
1429
  "eval_overall_f1": 0.9390862944162437,
1430
  "eval_overall_precision": 0.9343434343434344,
1431
  "eval_overall_recall": 0.9438775510204082,
1432
+ "eval_runtime": 0.2938,
1433
+ "eval_samples_per_second": 578.698,
1434
+ "eval_steps_per_second": 10.212,
1435
  "step": 4416
1436
  },
1437
  {
 
1460
  "eval_overall_f1": 0.9390862944162437,
1461
  "eval_overall_precision": 0.9343434343434344,
1462
  "eval_overall_recall": 0.9438775510204082,
1463
+ "eval_runtime": 0.2947,
1464
+ "eval_samples_per_second": 576.944,
1465
+ "eval_steps_per_second": 10.181,
1466
  "step": 4512
1467
  },
1468
  {
 
1491
  "eval_overall_f1": 0.943109987357775,
1492
  "eval_overall_precision": 0.9348370927318296,
1493
  "eval_overall_recall": 0.951530612244898,
1494
+ "eval_runtime": 0.295,
1495
+ "eval_samples_per_second": 576.25,
1496
+ "eval_steps_per_second": 10.169,
1497
  "step": 4608
1498
  },
1499
  {
 
1522
  "eval_overall_f1": 0.9453621346886911,
1523
  "eval_overall_precision": 0.9417721518987342,
1524
  "eval_overall_recall": 0.9489795918367347,
1525
+ "eval_runtime": 0.2935,
1526
+ "eval_samples_per_second": 579.12,
1527
+ "eval_steps_per_second": 10.22,
1528
  "step": 4704
1529
  },
1530
  {
 
1553
  "eval_overall_f1": 0.9426751592356687,
1554
  "eval_overall_precision": 0.9414758269720102,
1555
  "eval_overall_recall": 0.9438775510204082,
1556
+ "eval_runtime": 0.2922,
1557
+ "eval_samples_per_second": 581.856,
1558
+ "eval_steps_per_second": 10.268,
1559
  "step": 4800
1560
  },
1561
  {
 
1584
  "eval_overall_f1": 0.9309462915601023,
1585
  "eval_overall_precision": 0.9333333333333333,
1586
  "eval_overall_recall": 0.9285714285714286,
1587
+ "eval_runtime": 0.2934,
1588
+ "eval_samples_per_second": 579.33,
1589
+ "eval_steps_per_second": 10.223,
1590
  "step": 4896
1591
  },
1592
  {
 
1615
  "eval_overall_f1": 0.9389312977099236,
1616
  "eval_overall_precision": 0.9365482233502538,
1617
  "eval_overall_recall": 0.9413265306122449,
1618
+ "eval_runtime": 0.2869,
1619
+ "eval_samples_per_second": 592.643,
1620
+ "eval_steps_per_second": 10.458,
1621
  "step": 4992
1622
  },
1623
  {
 
1646
  "eval_overall_f1": 0.9419191919191919,
1647
  "eval_overall_precision": 0.9325,
1648
  "eval_overall_recall": 0.951530612244898,
1649
+ "eval_runtime": 0.2894,
1650
+ "eval_samples_per_second": 587.459,
1651
+ "eval_steps_per_second": 10.367,
1652
  "step": 5088
1653
  },
1654
  {
 
1677
  "eval_overall_f1": 0.9404309252217997,
1678
  "eval_overall_precision": 0.9345088161209067,
1679
  "eval_overall_recall": 0.9464285714285714,
1680
+ "eval_runtime": 0.2896,
1681
+ "eval_samples_per_second": 586.963,
1682
+ "eval_steps_per_second": 10.358,
1683
  "step": 5184
1684
  },
1685
  {
 
1708
  "eval_overall_f1": 0.9417721518987343,
1709
  "eval_overall_precision": 0.9346733668341709,
1710
  "eval_overall_recall": 0.9489795918367347,
1711
+ "eval_runtime": 0.2875,
1712
+ "eval_samples_per_second": 591.392,
1713
+ "eval_steps_per_second": 10.436,
1714
  "step": 5280
1715
  },
1716
  {
 
1739
  "eval_overall_f1": 0.9365482233502538,
1740
  "eval_overall_precision": 0.9318181818181818,
1741
  "eval_overall_recall": 0.9413265306122449,
1742
+ "eval_runtime": 0.2866,
1743
+ "eval_samples_per_second": 593.098,
1744
+ "eval_steps_per_second": 10.466,
1745
  "step": 5376
1746
  },
1747
  {
 
1770
  "eval_overall_f1": 0.9296482412060302,
1771
  "eval_overall_precision": 0.9158415841584159,
1772
  "eval_overall_recall": 0.9438775510204082,
1773
+ "eval_runtime": 0.2857,
1774
+ "eval_samples_per_second": 595.043,
1775
+ "eval_steps_per_second": 10.501,
1776
  "step": 5472
1777
  },
1778
  {
 
1801
  "eval_overall_f1": 0.9390862944162437,
1802
  "eval_overall_precision": 0.9343434343434344,
1803
  "eval_overall_recall": 0.9438775510204082,
1804
+ "eval_runtime": 0.2901,
1805
+ "eval_samples_per_second": 586.05,
1806
+ "eval_steps_per_second": 10.342,
1807
  "step": 5568
1808
  },
1809
  {
 
1832
  "eval_overall_f1": 0.9456384323640962,
1833
  "eval_overall_precision": 0.9373433583959899,
1834
  "eval_overall_recall": 0.9540816326530612,
1835
+ "eval_runtime": 0.2861,
1836
+ "eval_samples_per_second": 594.197,
1837
+ "eval_steps_per_second": 10.486,
1838
  "step": 5664
1839
  },
1840
  {
 
1863
  "eval_overall_f1": 0.9429657794676806,
1864
  "eval_overall_precision": 0.9370277078085643,
1865
  "eval_overall_recall": 0.9489795918367347,
1866
+ "eval_runtime": 0.2886,
1867
+ "eval_samples_per_second": 589.138,
1868
+ "eval_steps_per_second": 10.397,
1869
  "step": 5760
1870
  },
1871
  {
 
1894
  "eval_overall_f1": 0.9456384323640962,
1895
  "eval_overall_precision": 0.9373433583959899,
1896
  "eval_overall_recall": 0.9540816326530612,
1897
+ "eval_runtime": 0.2868,
1898
+ "eval_samples_per_second": 592.725,
1899
+ "eval_steps_per_second": 10.46,
1900
  "step": 5856
1901
  },
1902
  {
 
1925
  "eval_overall_f1": 0.9459119496855347,
1926
  "eval_overall_precision": 0.9330024813895782,
1927
  "eval_overall_recall": 0.9591836734693877,
1928
+ "eval_runtime": 0.2904,
1929
+ "eval_samples_per_second": 585.445,
1930
+ "eval_steps_per_second": 10.331,
1931
  "step": 5952
1932
  },
1933
  {
 
1956
  "eval_overall_f1": 0.9457755359394704,
1957
  "eval_overall_precision": 0.9351620947630923,
1958
  "eval_overall_recall": 0.9566326530612245,
1959
+ "eval_runtime": 0.2876,
1960
+ "eval_samples_per_second": 591.049,
1961
+ "eval_steps_per_second": 10.43,
1962
  "step": 6048
1963
  },
1964
  {
 
1987
  "eval_overall_f1": 0.9457755359394704,
1988
  "eval_overall_precision": 0.9351620947630923,
1989
  "eval_overall_recall": 0.9566326530612245,
1990
+ "eval_runtime": 0.2872,
1991
+ "eval_samples_per_second": 591.94,
1992
+ "eval_steps_per_second": 10.446,
1993
  "step": 6144
1994
  },
1995
  {
 
2018
  "eval_overall_f1": 0.9593908629441624,
2019
  "eval_overall_precision": 0.9545454545454546,
2020
  "eval_overall_recall": 0.9642857142857143,
2021
+ "eval_runtime": 0.2897,
2022
+ "eval_samples_per_second": 586.882,
2023
+ "eval_steps_per_second": 10.357,
2024
  "step": 6240
2025
  },
2026
  {
 
2049
  "eval_overall_f1": 0.9455006337135614,
2050
  "eval_overall_precision": 0.9395465994962217,
2051
  "eval_overall_recall": 0.951530612244898,
2052
+ "eval_runtime": 0.2896,
2053
+ "eval_samples_per_second": 586.948,
2054
+ "eval_steps_per_second": 10.358,
2055
  "step": 6336
2056
  },
2057
  {
 
2080
  "eval_overall_f1": 0.9517766497461929,
2081
  "eval_overall_precision": 0.946969696969697,
2082
  "eval_overall_recall": 0.9566326530612245,
2083
+ "eval_runtime": 0.2906,
2084
+ "eval_samples_per_second": 584.957,
2085
+ "eval_steps_per_second": 10.323,
2086
  "step": 6432
2087
  },
2088
  {
 
2111
  "eval_overall_f1": 0.9456384323640962,
2112
  "eval_overall_precision": 0.9373433583959899,
2113
  "eval_overall_recall": 0.9540816326530612,
2114
+ "eval_runtime": 0.2858,
2115
+ "eval_samples_per_second": 594.88,
2116
+ "eval_steps_per_second": 10.498,
2117
  "step": 6528
2118
  },
2119
  {
 
2142
  "eval_overall_f1": 0.9456384323640962,
2143
  "eval_overall_precision": 0.9373433583959899,
2144
  "eval_overall_recall": 0.9540816326530612,
2145
+ "eval_runtime": 0.2869,
2146
+ "eval_samples_per_second": 592.632,
2147
+ "eval_steps_per_second": 10.458,
2148
  "step": 6624
2149
  },
2150
  {
 
2173
  "eval_overall_f1": 0.9407313997477933,
2174
  "eval_overall_precision": 0.9301745635910225,
2175
  "eval_overall_recall": 0.951530612244898,
2176
+ "eval_runtime": 0.2961,
2177
+ "eval_samples_per_second": 574.131,
2178
+ "eval_steps_per_second": 10.132,
2179
  "step": 6720
2180
  },
2181
  {
 
2204
  "eval_overall_f1": 0.947103274559194,
2205
  "eval_overall_precision": 0.9353233830845771,
2206
  "eval_overall_recall": 0.9591836734693877,
2207
+ "eval_runtime": 0.2878,
2208
+ "eval_samples_per_second": 590.741,
2209
+ "eval_steps_per_second": 10.425,
2210
  "step": 6816
2211
  },
2212
  {
 
2235
  "eval_overall_f1": 0.9456384323640962,
2236
  "eval_overall_precision": 0.9373433583959899,
2237
  "eval_overall_recall": 0.9540816326530612,
2238
+ "eval_runtime": 0.2868,
2239
+ "eval_samples_per_second": 592.807,
2240
+ "eval_steps_per_second": 10.461,
2241
  "step": 6912
2242
  },
2243
  {
 
2266
  "eval_overall_f1": 0.9405815423514539,
2267
  "eval_overall_precision": 0.9323308270676691,
2268
  "eval_overall_recall": 0.9489795918367347,
2269
+ "eval_runtime": 0.285,
2270
+ "eval_samples_per_second": 596.525,
2271
+ "eval_steps_per_second": 10.527,
2272
  "step": 7008
2273
  },
2274
  {
 
2297
  "eval_overall_f1": 0.9390862944162437,
2298
  "eval_overall_precision": 0.9343434343434344,
2299
  "eval_overall_recall": 0.9438775510204082,
2300
+ "eval_runtime": 0.2898,
2301
+ "eval_samples_per_second": 586.544,
2302
+ "eval_steps_per_second": 10.351,
2303
  "step": 7104
2304
  },
2305
  {
 
2328
  "eval_overall_f1": 0.9255989911727616,
2329
  "eval_overall_precision": 0.9152119700748129,
2330
  "eval_overall_recall": 0.9362244897959183,
2331
+ "eval_runtime": 0.2886,
2332
+ "eval_samples_per_second": 589.073,
2333
+ "eval_steps_per_second": 10.395,
2334
  "step": 7200
2335
  },
2336
  {
 
2359
  "eval_overall_f1": 0.9419191919191919,
2360
  "eval_overall_precision": 0.9325,
2361
  "eval_overall_recall": 0.951530612244898,
2362
+ "eval_runtime": 0.2848,
2363
+ "eval_samples_per_second": 597.003,
2364
+ "eval_steps_per_second": 10.535,
2365
  "step": 7296
2366
  },
2367
  {
 
2390
  "eval_overall_f1": 0.9407313997477933,
2391
  "eval_overall_precision": 0.9301745635910225,
2392
  "eval_overall_recall": 0.951530612244898,
2393
+ "eval_runtime": 0.2877,
2394
+ "eval_samples_per_second": 590.964,
2395
+ "eval_steps_per_second": 10.429,
2396
  "step": 7392
2397
  },
2398
  {
 
2421
  "eval_overall_f1": 0.9382093316519546,
2422
  "eval_overall_precision": 0.9276807980049875,
2423
  "eval_overall_recall": 0.9489795918367347,
2424
+ "eval_runtime": 0.2882,
2425
+ "eval_samples_per_second": 589.842,
2426
+ "eval_steps_per_second": 10.409,
2427
  "step": 7488
2428
  },
2429
  {
 
2452
  "eval_overall_f1": 0.9404309252217997,
2453
  "eval_overall_precision": 0.9345088161209067,
2454
  "eval_overall_recall": 0.9464285714285714,
2455
+ "eval_runtime": 0.2884,
2456
+ "eval_samples_per_second": 589.357,
2457
+ "eval_steps_per_second": 10.4,
2458
  "step": 7584
2459
  },
2460
  {
 
2483
  "eval_overall_f1": 0.9408805031446542,
2484
  "eval_overall_precision": 0.9280397022332506,
2485
  "eval_overall_recall": 0.9540816326530612,
2486
+ "eval_runtime": 0.2863,
2487
+ "eval_samples_per_second": 593.708,
2488
+ "eval_steps_per_second": 10.477,
2489
  "step": 7680
2490
  },
2491
  {
 
2514
  "eval_overall_f1": 0.9494949494949495,
2515
  "eval_overall_precision": 0.94,
2516
  "eval_overall_recall": 0.9591836734693877,
2517
+ "eval_runtime": 0.2885,
2518
+ "eval_samples_per_second": 589.3,
2519
+ "eval_steps_per_second": 10.399,
2520
  "step": 7776
2521
  },
2522
  {
 
2545
  "eval_overall_f1": 0.9380530973451328,
2546
  "eval_overall_precision": 0.9298245614035088,
2547
  "eval_overall_recall": 0.9464285714285714,
2548
+ "eval_runtime": 0.2895,
2549
+ "eval_samples_per_second": 587.126,
2550
+ "eval_steps_per_second": 10.361,
2551
  "step": 7872
2552
  },
2553
  {
 
2576
  "eval_overall_f1": 0.94147582697201,
2577
  "eval_overall_precision": 0.9390862944162437,
2578
  "eval_overall_recall": 0.9438775510204082,
2579
+ "eval_runtime": 0.2876,
2580
+ "eval_samples_per_second": 591.075,
2581
+ "eval_steps_per_second": 10.431,
2582
  "step": 7968
2583
  },
2584
  {
 
2607
  "eval_overall_f1": 0.9392405063291138,
2608
  "eval_overall_precision": 0.9321608040201005,
2609
  "eval_overall_recall": 0.9464285714285714,
2610
+ "eval_runtime": 0.2877,
2611
+ "eval_samples_per_second": 590.843,
2612
+ "eval_steps_per_second": 10.427,
2613
  "step": 8064
2614
  },
2615
  {
 
2638
  "eval_overall_f1": 0.935361216730038,
2639
  "eval_overall_precision": 0.929471032745592,
2640
  "eval_overall_recall": 0.9413265306122449,
2641
+ "eval_runtime": 0.2899,
2642
+ "eval_samples_per_second": 586.475,
2643
+ "eval_steps_per_second": 10.35,
2644
  "step": 8160
2645
  },
2646
  {
 
2669
  "eval_overall_f1": 0.9390862944162437,
2670
  "eval_overall_precision": 0.9343434343434344,
2671
  "eval_overall_recall": 0.9438775510204082,
2672
+ "eval_runtime": 0.2918,
2673
+ "eval_samples_per_second": 582.587,
2674
+ "eval_steps_per_second": 10.281,
2675
  "step": 8256
2676
  },
2677
  {
 
2700
  "eval_overall_f1": 0.9417721518987343,
2701
  "eval_overall_precision": 0.9346733668341709,
2702
  "eval_overall_recall": 0.9489795918367347,
2703
+ "eval_runtime": 0.2878,
2704
+ "eval_samples_per_second": 590.75,
2705
+ "eval_steps_per_second": 10.425,
2706
  "step": 8352
2707
  },
2708
  {
 
2731
  "eval_overall_f1": 0.9443037974683544,
2732
  "eval_overall_precision": 0.9371859296482412,
2733
  "eval_overall_recall": 0.951530612244898,
2734
+ "eval_runtime": 0.2906,
2735
+ "eval_samples_per_second": 585.01,
2736
+ "eval_steps_per_second": 10.324,
2737
  "step": 8448
2738
  },
2739
  {
 
2762
  "eval_overall_f1": 0.9443037974683544,
2763
  "eval_overall_precision": 0.9371859296482412,
2764
  "eval_overall_recall": 0.951530612244898,
2765
+ "eval_runtime": 0.2888,
2766
+ "eval_samples_per_second": 588.551,
2767
+ "eval_steps_per_second": 10.386,
2768
  "step": 8544
2769
  },
2770
  {
 
2793
  "eval_overall_f1": 0.943109987357775,
2794
  "eval_overall_precision": 0.9348370927318296,
2795
  "eval_overall_recall": 0.951530612244898,
2796
+ "eval_runtime": 0.2995,
2797
+ "eval_samples_per_second": 567.615,
2798
+ "eval_steps_per_second": 10.017,
2799
  "step": 8640
2800
  },
2801
  {
 
2824
  "eval_overall_f1": 0.9417721518987343,
2825
  "eval_overall_precision": 0.9346733668341709,
2826
  "eval_overall_recall": 0.9489795918367347,
2827
+ "eval_runtime": 0.2986,
2828
+ "eval_samples_per_second": 569.339,
2829
+ "eval_steps_per_second": 10.047,
2830
  "step": 8736
2831
  },
2832
  {
 
2855
  "eval_overall_f1": 0.9429657794676806,
2856
  "eval_overall_precision": 0.9370277078085643,
2857
  "eval_overall_recall": 0.9489795918367347,
2858
+ "eval_runtime": 0.2915,
2859
+ "eval_samples_per_second": 583.118,
2860
+ "eval_steps_per_second": 10.29,
2861
  "step": 8832
2862
  },
2863
  {
 
2886
  "eval_overall_f1": 0.9380530973451328,
2887
  "eval_overall_precision": 0.9298245614035088,
2888
  "eval_overall_recall": 0.9464285714285714,
2889
+ "eval_runtime": 0.2972,
2890
+ "eval_samples_per_second": 572.045,
2891
+ "eval_steps_per_second": 10.095,
2892
  "step": 8928
2893
  },
2894
  {
 
2917
  "eval_overall_f1": 0.9467005076142132,
2918
  "eval_overall_precision": 0.9419191919191919,
2919
  "eval_overall_recall": 0.951530612244898,
2920
+ "eval_runtime": 0.2975,
2921
+ "eval_samples_per_second": 571.462,
2922
+ "eval_steps_per_second": 10.085,
2923
  "step": 9024
2924
  },
2925
  {
 
2948
  "eval_overall_f1": 0.949367088607595,
2949
  "eval_overall_precision": 0.9422110552763819,
2950
  "eval_overall_recall": 0.9566326530612245,
2951
+ "eval_runtime": 0.295,
2952
+ "eval_samples_per_second": 576.241,
2953
+ "eval_steps_per_second": 10.169,
2954
  "step": 9120
2955
  },
2956
  {
 
2979
  "eval_overall_f1": 0.9455006337135614,
2980
  "eval_overall_precision": 0.9395465994962217,
2981
  "eval_overall_recall": 0.951530612244898,
2982
+ "eval_runtime": 0.2956,
2983
+ "eval_samples_per_second": 575.186,
2984
+ "eval_steps_per_second": 10.15,
2985
  "step": 9216
2986
  },
2987
  {
 
3010
  "eval_overall_f1": 0.9467005076142132,
3011
  "eval_overall_precision": 0.9419191919191919,
3012
  "eval_overall_recall": 0.951530612244898,
3013
+ "eval_runtime": 0.2943,
3014
+ "eval_samples_per_second": 577.594,
3015
+ "eval_steps_per_second": 10.193,
3016
  "step": 9312
3017
  },
3018
  {
 
3041
  "eval_overall_f1": 0.9441624365482234,
3042
  "eval_overall_precision": 0.9393939393939394,
3043
  "eval_overall_recall": 0.9489795918367347,
3044
+ "eval_runtime": 0.288,
3045
+ "eval_samples_per_second": 590.233,
3046
+ "eval_steps_per_second": 10.416,
3047
  "step": 9408
3048
  },
3049
  {
 
3072
  "eval_overall_f1": 0.9441624365482234,
3073
  "eval_overall_precision": 0.9393939393939394,
3074
  "eval_overall_recall": 0.9489795918367347,
3075
+ "eval_runtime": 0.2866,
3076
+ "eval_samples_per_second": 593.17,
3077
+ "eval_steps_per_second": 10.468,
3078
  "step": 9504
3079
  },
3080
  {
 
3103
  "eval_overall_f1": 0.9429657794676806,
3104
  "eval_overall_precision": 0.9370277078085643,
3105
  "eval_overall_recall": 0.9489795918367347,
3106
+ "eval_runtime": 0.2864,
3107
+ "eval_samples_per_second": 593.611,
3108
+ "eval_steps_per_second": 10.475,
3109
  "step": 9600
3110
  },
3111
  {
 
3113
  "step": 9600,
3114
  "total_flos": 4315798421360676.0,
3115
  "train_loss": 0.038009579268594586,
3116
+ "train_runtime": 541.6955,
3117
+ "train_samples_per_second": 282.631,
3118
+ "train_steps_per_second": 17.722
3119
  }
3120
  ],
3121
  "logging_steps": 500,