dq158 commited on
Commit
563dcbc
1 Parent(s): aa431f3

Training in progress, epoch 2, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcae599684a4fbbc309d29596a13d1f8e60c8669d4f351f311b7e665d723fa40
3
  size 3132668808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a891d3684c625b11ad2355f1e5ffa5ad093350cd5da2efac8dd2e8da30b22259
3
  size 3132668808
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72020de09af1159730a810cc5fea25580a0fc8159def1615cca3b3c80c1487c1
3
  size 6265677800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9437a36254b2c5cdaa07d8aa73cdb8e7dff0552234b948fd8f8d6d11b2289f2
3
  size 6265677800
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40625c746bfa84c1633ce1b215fe2e2c14d62ad791af8011ae10ef5e56dcfb97
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2f55ba368c38b65a890f3860852a11b796ef39484dde20b8682d6b6aaffcf7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a1a678710554b909b7044c4e7143bd849126d09514f3bc102b14b7bf0893c3f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6188a00a7d4fd320a7e276558cccd0933240ac43a9413145af237730e429faa2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 68219,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -842,13 +842,848 @@
842
  "eval_steps_per_second": 0.493,
843
  "eval_translation_length": 7761920,
844
  "step": 68219
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
845
  }
846
  ],
847
  "logging_steps": 500,
848
  "max_steps": 341095,
849
  "num_train_epochs": 5,
850
  "save_steps": 500,
851
- "total_flos": 3.144579296777994e+17,
852
  "trial_name": null,
853
  "trial_params": null
854
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
+ "global_step": 136438,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
842
  "eval_steps_per_second": 0.493,
843
  "eval_translation_length": 7761920,
844
  "step": 68219
845
+ },
846
+ {
847
+ "epoch": 1.0,
848
+ "learning_rate": 9.048308407381583e-05,
849
+ "loss": 2.9246,
850
+ "step": 68500
851
+ },
852
+ {
853
+ "epoch": 1.01,
854
+ "learning_rate": 9.034731799405654e-05,
855
+ "loss": 2.8047,
856
+ "step": 69000
857
+ },
858
+ {
859
+ "epoch": 1.02,
860
+ "learning_rate": 9.021069373680653e-05,
861
+ "loss": 2.8717,
862
+ "step": 69500
863
+ },
864
+ {
865
+ "epoch": 1.03,
866
+ "learning_rate": 9.007321420803e-05,
867
+ "loss": 2.8453,
868
+ "step": 70000
869
+ },
870
+ {
871
+ "epoch": 1.03,
872
+ "learning_rate": 8.993488233188263e-05,
873
+ "loss": 2.8545,
874
+ "step": 70500
875
+ },
876
+ {
877
+ "epoch": 1.04,
878
+ "learning_rate": 8.979570105064923e-05,
879
+ "loss": 2.7871,
880
+ "step": 71000
881
+ },
882
+ {
883
+ "epoch": 1.05,
884
+ "learning_rate": 8.965567332468128e-05,
885
+ "loss": 2.772,
886
+ "step": 71500
887
+ },
888
+ {
889
+ "epoch": 1.06,
890
+ "learning_rate": 8.951480213233397e-05,
891
+ "loss": 2.915,
892
+ "step": 72000
893
+ },
894
+ {
895
+ "epoch": 1.06,
896
+ "learning_rate": 8.937309046990271e-05,
897
+ "loss": 2.8076,
898
+ "step": 72500
899
+ },
900
+ {
901
+ "epoch": 1.07,
902
+ "learning_rate": 8.923054135155963e-05,
903
+ "loss": 2.693,
904
+ "step": 73000
905
+ },
906
+ {
907
+ "epoch": 1.08,
908
+ "learning_rate": 8.908715780928925e-05,
909
+ "loss": 2.8504,
910
+ "step": 73500
911
+ },
912
+ {
913
+ "epoch": 1.08,
914
+ "learning_rate": 8.89429428928241e-05,
915
+ "loss": 2.7593,
916
+ "step": 74000
917
+ },
918
+ {
919
+ "epoch": 1.09,
920
+ "learning_rate": 8.879789966957988e-05,
921
+ "loss": 2.7953,
922
+ "step": 74500
923
+ },
924
+ {
925
+ "epoch": 1.1,
926
+ "learning_rate": 8.865203122459008e-05,
927
+ "loss": 2.7169,
928
+ "step": 75000
929
+ },
930
+ {
931
+ "epoch": 1.11,
932
+ "learning_rate": 8.850534066044054e-05,
933
+ "loss": 2.6889,
934
+ "step": 75500
935
+ },
936
+ {
937
+ "epoch": 1.11,
938
+ "learning_rate": 8.835783109720333e-05,
939
+ "loss": 2.8703,
940
+ "step": 76000
941
+ },
942
+ {
943
+ "epoch": 1.12,
944
+ "learning_rate": 8.820950567237043e-05,
945
+ "loss": 2.8989,
946
+ "step": 76500
947
+ },
948
+ {
949
+ "epoch": 1.13,
950
+ "learning_rate": 8.806036754078701e-05,
951
+ "loss": 2.7834,
952
+ "step": 77000
953
+ },
954
+ {
955
+ "epoch": 1.14,
956
+ "learning_rate": 8.791041987458431e-05,
957
+ "loss": 2.84,
958
+ "step": 77500
959
+ },
960
+ {
961
+ "epoch": 1.14,
962
+ "learning_rate": 8.775966586311212e-05,
963
+ "loss": 2.6913,
964
+ "step": 78000
965
+ },
966
+ {
967
+ "epoch": 1.15,
968
+ "learning_rate": 8.760810871287108e-05,
969
+ "loss": 2.7712,
970
+ "step": 78500
971
+ },
972
+ {
973
+ "epoch": 1.16,
974
+ "learning_rate": 8.745575164744435e-05,
975
+ "loss": 2.8229,
976
+ "step": 79000
977
+ },
978
+ {
979
+ "epoch": 1.17,
980
+ "learning_rate": 8.730259790742906e-05,
981
+ "loss": 2.8877,
982
+ "step": 79500
983
+ },
984
+ {
985
+ "epoch": 1.17,
986
+ "learning_rate": 8.714865075036746e-05,
987
+ "loss": 2.7965,
988
+ "step": 80000
989
+ },
990
+ {
991
+ "epoch": 1.18,
992
+ "learning_rate": 8.699391345067759e-05,
993
+ "loss": 2.9252,
994
+ "step": 80500
995
+ },
996
+ {
997
+ "epoch": 1.19,
998
+ "learning_rate": 8.683838929958356e-05,
999
+ "loss": 2.8585,
1000
+ "step": 81000
1001
+ },
1002
+ {
1003
+ "epoch": 1.19,
1004
+ "learning_rate": 8.66820816050457e-05,
1005
+ "loss": 2.7542,
1006
+ "step": 81500
1007
+ },
1008
+ {
1009
+ "epoch": 1.2,
1010
+ "learning_rate": 8.652499369169005e-05,
1011
+ "loss": 2.8124,
1012
+ "step": 82000
1013
+ },
1014
+ {
1015
+ "epoch": 1.21,
1016
+ "learning_rate": 8.636712890073772e-05,
1017
+ "loss": 2.8251,
1018
+ "step": 82500
1019
+ },
1020
+ {
1021
+ "epoch": 1.22,
1022
+ "learning_rate": 8.62084905899339e-05,
1023
+ "loss": 2.7148,
1024
+ "step": 83000
1025
+ },
1026
+ {
1027
+ "epoch": 1.22,
1028
+ "learning_rate": 8.604908213347622e-05,
1029
+ "loss": 2.8276,
1030
+ "step": 83500
1031
+ },
1032
+ {
1033
+ "epoch": 1.23,
1034
+ "learning_rate": 8.58889069219432e-05,
1035
+ "loss": 2.8799,
1036
+ "step": 84000
1037
+ },
1038
+ {
1039
+ "epoch": 1.24,
1040
+ "learning_rate": 8.572796836222206e-05,
1041
+ "loss": 2.7959,
1042
+ "step": 84500
1043
+ },
1044
+ {
1045
+ "epoch": 1.25,
1046
+ "learning_rate": 8.556626987743621e-05,
1047
+ "loss": 2.756,
1048
+ "step": 85000
1049
+ },
1050
+ {
1051
+ "epoch": 1.25,
1052
+ "learning_rate": 8.54038149068725e-05,
1053
+ "loss": 2.8956,
1054
+ "step": 85500
1055
+ },
1056
+ {
1057
+ "epoch": 1.26,
1058
+ "learning_rate": 8.524060690590803e-05,
1059
+ "loss": 2.8619,
1060
+ "step": 86000
1061
+ },
1062
+ {
1063
+ "epoch": 1.27,
1064
+ "learning_rate": 8.507664934593668e-05,
1065
+ "loss": 2.8005,
1066
+ "step": 86500
1067
+ },
1068
+ {
1069
+ "epoch": 1.28,
1070
+ "learning_rate": 8.491194571429526e-05,
1071
+ "loss": 2.8213,
1072
+ "step": 87000
1073
+ },
1074
+ {
1075
+ "epoch": 1.28,
1076
+ "learning_rate": 8.474649951418936e-05,
1077
+ "loss": 2.8356,
1078
+ "step": 87500
1079
+ },
1080
+ {
1081
+ "epoch": 1.29,
1082
+ "learning_rate": 8.458031426461878e-05,
1083
+ "loss": 2.877,
1084
+ "step": 88000
1085
+ },
1086
+ {
1087
+ "epoch": 1.3,
1088
+ "learning_rate": 8.441339350030278e-05,
1089
+ "loss": 2.9189,
1090
+ "step": 88500
1091
+ },
1092
+ {
1093
+ "epoch": 1.3,
1094
+ "learning_rate": 8.424574077160476e-05,
1095
+ "loss": 2.8497,
1096
+ "step": 89000
1097
+ },
1098
+ {
1099
+ "epoch": 1.31,
1100
+ "learning_rate": 8.407735964445689e-05,
1101
+ "loss": 2.807,
1102
+ "step": 89500
1103
+ },
1104
+ {
1105
+ "epoch": 1.32,
1106
+ "learning_rate": 8.390825370028414e-05,
1107
+ "loss": 2.8745,
1108
+ "step": 90000
1109
+ },
1110
+ {
1111
+ "epoch": 1.33,
1112
+ "learning_rate": 8.373842653592818e-05,
1113
+ "loss": 2.8054,
1114
+ "step": 90500
1115
+ },
1116
+ {
1117
+ "epoch": 1.33,
1118
+ "learning_rate": 8.35678817635709e-05,
1119
+ "loss": 2.7019,
1120
+ "step": 91000
1121
+ },
1122
+ {
1123
+ "epoch": 1.34,
1124
+ "learning_rate": 8.339662301065747e-05,
1125
+ "loss": 2.8497,
1126
+ "step": 91500
1127
+ },
1128
+ {
1129
+ "epoch": 1.35,
1130
+ "learning_rate": 8.322465391981927e-05,
1131
+ "loss": 2.8442,
1132
+ "step": 92000
1133
+ },
1134
+ {
1135
+ "epoch": 1.36,
1136
+ "learning_rate": 8.30519781487964e-05,
1137
+ "loss": 2.7681,
1138
+ "step": 92500
1139
+ },
1140
+ {
1141
+ "epoch": 1.36,
1142
+ "learning_rate": 8.287859937035989e-05,
1143
+ "loss": 2.8219,
1144
+ "step": 93000
1145
+ },
1146
+ {
1147
+ "epoch": 1.37,
1148
+ "learning_rate": 8.270452127223352e-05,
1149
+ "loss": 2.8409,
1150
+ "step": 93500
1151
+ },
1152
+ {
1153
+ "epoch": 1.38,
1154
+ "learning_rate": 8.252974755701546e-05,
1155
+ "loss": 2.7358,
1156
+ "step": 94000
1157
+ },
1158
+ {
1159
+ "epoch": 1.39,
1160
+ "learning_rate": 8.235428194209947e-05,
1161
+ "loss": 2.6975,
1162
+ "step": 94500
1163
+ },
1164
+ {
1165
+ "epoch": 1.39,
1166
+ "learning_rate": 8.217812815959588e-05,
1167
+ "loss": 2.7972,
1168
+ "step": 95000
1169
+ },
1170
+ {
1171
+ "epoch": 1.4,
1172
+ "learning_rate": 8.200128995625211e-05,
1173
+ "loss": 2.8172,
1174
+ "step": 95500
1175
+ },
1176
+ {
1177
+ "epoch": 1.41,
1178
+ "learning_rate": 8.182377109337309e-05,
1179
+ "loss": 2.8309,
1180
+ "step": 96000
1181
+ },
1182
+ {
1183
+ "epoch": 1.41,
1184
+ "learning_rate": 8.164557534674122e-05,
1185
+ "loss": 2.9371,
1186
+ "step": 96500
1187
+ },
1188
+ {
1189
+ "epoch": 1.42,
1190
+ "learning_rate": 8.1466706506536e-05,
1191
+ "loss": 2.738,
1192
+ "step": 97000
1193
+ },
1194
+ {
1195
+ "epoch": 1.43,
1196
+ "learning_rate": 8.12871683772535e-05,
1197
+ "loss": 2.8989,
1198
+ "step": 97500
1199
+ },
1200
+ {
1201
+ "epoch": 1.44,
1202
+ "learning_rate": 8.110696477762538e-05,
1203
+ "loss": 2.7852,
1204
+ "step": 98000
1205
+ },
1206
+ {
1207
+ "epoch": 1.44,
1208
+ "learning_rate": 8.092609954053776e-05,
1209
+ "loss": 2.862,
1210
+ "step": 98500
1211
+ },
1212
+ {
1213
+ "epoch": 1.45,
1214
+ "learning_rate": 8.07445765129495e-05,
1215
+ "loss": 2.8234,
1216
+ "step": 99000
1217
+ },
1218
+ {
1219
+ "epoch": 1.46,
1220
+ "learning_rate": 8.056239955581064e-05,
1221
+ "loss": 2.844,
1222
+ "step": 99500
1223
+ },
1224
+ {
1225
+ "epoch": 1.47,
1226
+ "learning_rate": 8.037957254398004e-05,
1227
+ "loss": 2.7922,
1228
+ "step": 100000
1229
+ },
1230
+ {
1231
+ "epoch": 1.47,
1232
+ "learning_rate": 8.01960993661431e-05,
1233
+ "loss": 2.817,
1234
+ "step": 100500
1235
+ },
1236
+ {
1237
+ "epoch": 1.48,
1238
+ "learning_rate": 8.0011983924729e-05,
1239
+ "loss": 2.8955,
1240
+ "step": 101000
1241
+ },
1242
+ {
1243
+ "epoch": 1.49,
1244
+ "learning_rate": 7.982723013582772e-05,
1245
+ "loss": 2.8279,
1246
+ "step": 101500
1247
+ },
1248
+ {
1249
+ "epoch": 1.5,
1250
+ "learning_rate": 7.964184192910672e-05,
1251
+ "loss": 2.8259,
1252
+ "step": 102000
1253
+ },
1254
+ {
1255
+ "epoch": 1.5,
1256
+ "learning_rate": 7.94558232477274e-05,
1257
+ "loss": 2.9235,
1258
+ "step": 102500
1259
+ },
1260
+ {
1261
+ "epoch": 1.51,
1262
+ "learning_rate": 7.926917804826117e-05,
1263
+ "loss": 2.8261,
1264
+ "step": 103000
1265
+ },
1266
+ {
1267
+ "epoch": 1.52,
1268
+ "learning_rate": 7.908191030060532e-05,
1269
+ "loss": 2.7384,
1270
+ "step": 103500
1271
+ },
1272
+ {
1273
+ "epoch": 1.52,
1274
+ "learning_rate": 7.889402398789863e-05,
1275
+ "loss": 2.8064,
1276
+ "step": 104000
1277
+ },
1278
+ {
1279
+ "epoch": 1.53,
1280
+ "learning_rate": 7.870552310643656e-05,
1281
+ "loss": 2.8212,
1282
+ "step": 104500
1283
+ },
1284
+ {
1285
+ "epoch": 1.54,
1286
+ "learning_rate": 7.851641166558628e-05,
1287
+ "loss": 2.8605,
1288
+ "step": 105000
1289
+ },
1290
+ {
1291
+ "epoch": 1.55,
1292
+ "learning_rate": 7.832669368770149e-05,
1293
+ "loss": 2.7907,
1294
+ "step": 105500
1295
+ },
1296
+ {
1297
+ "epoch": 1.55,
1298
+ "learning_rate": 7.813637320803671e-05,
1299
+ "loss": 2.7278,
1300
+ "step": 106000
1301
+ },
1302
+ {
1303
+ "epoch": 1.56,
1304
+ "learning_rate": 7.794545427466153e-05,
1305
+ "loss": 2.7808,
1306
+ "step": 106500
1307
+ },
1308
+ {
1309
+ "epoch": 1.57,
1310
+ "learning_rate": 7.775394094837455e-05,
1311
+ "loss": 2.8643,
1312
+ "step": 107000
1313
+ },
1314
+ {
1315
+ "epoch": 1.58,
1316
+ "learning_rate": 7.756183730261694e-05,
1317
+ "loss": 2.738,
1318
+ "step": 107500
1319
+ },
1320
+ {
1321
+ "epoch": 1.58,
1322
+ "learning_rate": 7.736914742338577e-05,
1323
+ "loss": 2.7307,
1324
+ "step": 108000
1325
+ },
1326
+ {
1327
+ "epoch": 1.59,
1328
+ "learning_rate": 7.71758754091472e-05,
1329
+ "loss": 2.8986,
1330
+ "step": 108500
1331
+ },
1332
+ {
1333
+ "epoch": 1.6,
1334
+ "learning_rate": 7.698202537074926e-05,
1335
+ "loss": 2.7493,
1336
+ "step": 109000
1337
+ },
1338
+ {
1339
+ "epoch": 1.61,
1340
+ "learning_rate": 7.678760143133436e-05,
1341
+ "loss": 2.8837,
1342
+ "step": 109500
1343
+ },
1344
+ {
1345
+ "epoch": 1.61,
1346
+ "learning_rate": 7.659260772625176e-05,
1347
+ "loss": 2.778,
1348
+ "step": 110000
1349
+ },
1350
+ {
1351
+ "epoch": 1.62,
1352
+ "learning_rate": 7.639704840296936e-05,
1353
+ "loss": 2.8215,
1354
+ "step": 110500
1355
+ },
1356
+ {
1357
+ "epoch": 1.63,
1358
+ "learning_rate": 7.620092762098568e-05,
1359
+ "loss": 2.8389,
1360
+ "step": 111000
1361
+ },
1362
+ {
1363
+ "epoch": 1.63,
1364
+ "learning_rate": 7.600424955174132e-05,
1365
+ "loss": 2.8627,
1366
+ "step": 111500
1367
+ },
1368
+ {
1369
+ "epoch": 1.64,
1370
+ "learning_rate": 7.580701837853028e-05,
1371
+ "loss": 2.8321,
1372
+ "step": 112000
1373
+ },
1374
+ {
1375
+ "epoch": 1.65,
1376
+ "learning_rate": 7.560923829641088e-05,
1377
+ "loss": 2.9496,
1378
+ "step": 112500
1379
+ },
1380
+ {
1381
+ "epoch": 1.66,
1382
+ "learning_rate": 7.541091351211666e-05,
1383
+ "loss": 2.8576,
1384
+ "step": 113000
1385
+ },
1386
+ {
1387
+ "epoch": 1.66,
1388
+ "learning_rate": 7.521204824396678e-05,
1389
+ "loss": 2.7548,
1390
+ "step": 113500
1391
+ },
1392
+ {
1393
+ "epoch": 1.67,
1394
+ "learning_rate": 7.501264672177637e-05,
1395
+ "loss": 2.7738,
1396
+ "step": 114000
1397
+ },
1398
+ {
1399
+ "epoch": 1.68,
1400
+ "learning_rate": 7.481271318676662e-05,
1401
+ "loss": 2.8088,
1402
+ "step": 114500
1403
+ },
1404
+ {
1405
+ "epoch": 1.69,
1406
+ "learning_rate": 7.46122518914744e-05,
1407
+ "loss": 2.8243,
1408
+ "step": 115000
1409
+ },
1410
+ {
1411
+ "epoch": 1.69,
1412
+ "learning_rate": 7.441126709966203e-05,
1413
+ "loss": 2.6794,
1414
+ "step": 115500
1415
+ },
1416
+ {
1417
+ "epoch": 1.7,
1418
+ "learning_rate": 7.420976308622632e-05,
1419
+ "loss": 2.8277,
1420
+ "step": 116000
1421
+ },
1422
+ {
1423
+ "epoch": 1.71,
1424
+ "learning_rate": 7.400774413710793e-05,
1425
+ "loss": 2.8341,
1426
+ "step": 116500
1427
+ },
1428
+ {
1429
+ "epoch": 1.72,
1430
+ "learning_rate": 7.380521454920001e-05,
1431
+ "loss": 2.8003,
1432
+ "step": 117000
1433
+ },
1434
+ {
1435
+ "epoch": 1.72,
1436
+ "learning_rate": 7.360217863025687e-05,
1437
+ "loss": 2.724,
1438
+ "step": 117500
1439
+ },
1440
+ {
1441
+ "epoch": 1.73,
1442
+ "learning_rate": 7.33986406988024e-05,
1443
+ "loss": 2.829,
1444
+ "step": 118000
1445
+ },
1446
+ {
1447
+ "epoch": 1.74,
1448
+ "learning_rate": 7.319460508403811e-05,
1449
+ "loss": 2.812,
1450
+ "step": 118500
1451
+ },
1452
+ {
1453
+ "epoch": 1.74,
1454
+ "learning_rate": 7.299007612575117e-05,
1455
+ "loss": 2.8172,
1456
+ "step": 119000
1457
+ },
1458
+ {
1459
+ "epoch": 1.75,
1460
+ "learning_rate": 7.278505817422199e-05,
1461
+ "loss": 2.8063,
1462
+ "step": 119500
1463
+ },
1464
+ {
1465
+ "epoch": 1.76,
1466
+ "learning_rate": 7.257955559013181e-05,
1467
+ "loss": 2.8775,
1468
+ "step": 120000
1469
+ },
1470
+ {
1471
+ "epoch": 1.77,
1472
+ "learning_rate": 7.23735727444698e-05,
1473
+ "loss": 2.7225,
1474
+ "step": 120500
1475
+ },
1476
+ {
1477
+ "epoch": 1.77,
1478
+ "learning_rate": 7.216711401844028e-05,
1479
+ "loss": 2.7283,
1480
+ "step": 121000
1481
+ },
1482
+ {
1483
+ "epoch": 1.78,
1484
+ "learning_rate": 7.196018380336934e-05,
1485
+ "loss": 2.8786,
1486
+ "step": 121500
1487
+ },
1488
+ {
1489
+ "epoch": 1.79,
1490
+ "learning_rate": 7.175278650061156e-05,
1491
+ "loss": 2.7372,
1492
+ "step": 122000
1493
+ },
1494
+ {
1495
+ "epoch": 1.8,
1496
+ "learning_rate": 7.154492652145635e-05,
1497
+ "loss": 2.7176,
1498
+ "step": 122500
1499
+ },
1500
+ {
1501
+ "epoch": 1.8,
1502
+ "learning_rate": 7.133660828703414e-05,
1503
+ "loss": 2.8233,
1504
+ "step": 123000
1505
+ },
1506
+ {
1507
+ "epoch": 1.81,
1508
+ "learning_rate": 7.112783622822235e-05,
1509
+ "loss": 2.8269,
1510
+ "step": 123500
1511
+ },
1512
+ {
1513
+ "epoch": 1.82,
1514
+ "learning_rate": 7.091861478555114e-05,
1515
+ "loss": 2.8155,
1516
+ "step": 124000
1517
+ },
1518
+ {
1519
+ "epoch": 1.83,
1520
+ "learning_rate": 7.070894840910887e-05,
1521
+ "loss": 2.7793,
1522
+ "step": 124500
1523
+ },
1524
+ {
1525
+ "epoch": 1.83,
1526
+ "learning_rate": 7.049884155844762e-05,
1527
+ "loss": 2.8524,
1528
+ "step": 125000
1529
+ },
1530
+ {
1531
+ "epoch": 1.84,
1532
+ "learning_rate": 7.028829870248824e-05,
1533
+ "loss": 2.8373,
1534
+ "step": 125500
1535
+ },
1536
+ {
1537
+ "epoch": 1.85,
1538
+ "learning_rate": 7.007732431942529e-05,
1539
+ "loss": 2.8219,
1540
+ "step": 126000
1541
+ },
1542
+ {
1543
+ "epoch": 1.85,
1544
+ "learning_rate": 6.986592289663177e-05,
1545
+ "loss": 2.6958,
1546
+ "step": 126500
1547
+ },
1548
+ {
1549
+ "epoch": 1.86,
1550
+ "learning_rate": 6.965409893056375e-05,
1551
+ "loss": 2.8492,
1552
+ "step": 127000
1553
+ },
1554
+ {
1555
+ "epoch": 1.87,
1556
+ "learning_rate": 6.944185692666472e-05,
1557
+ "loss": 2.8947,
1558
+ "step": 127500
1559
+ },
1560
+ {
1561
+ "epoch": 1.88,
1562
+ "learning_rate": 6.922920139926964e-05,
1563
+ "loss": 2.8311,
1564
+ "step": 128000
1565
+ },
1566
+ {
1567
+ "epoch": 1.88,
1568
+ "learning_rate": 6.90161368715091e-05,
1569
+ "loss": 2.8389,
1570
+ "step": 128500
1571
+ },
1572
+ {
1573
+ "epoch": 1.89,
1574
+ "learning_rate": 6.880266787521298e-05,
1575
+ "loss": 2.7657,
1576
+ "step": 129000
1577
+ },
1578
+ {
1579
+ "epoch": 1.9,
1580
+ "learning_rate": 6.858879895081412e-05,
1581
+ "loss": 2.8388,
1582
+ "step": 129500
1583
+ },
1584
+ {
1585
+ "epoch": 1.91,
1586
+ "learning_rate": 6.837453464725174e-05,
1587
+ "loss": 2.8377,
1588
+ "step": 130000
1589
+ },
1590
+ {
1591
+ "epoch": 1.91,
1592
+ "learning_rate": 6.815987952187466e-05,
1593
+ "loss": 2.8376,
1594
+ "step": 130500
1595
+ },
1596
+ {
1597
+ "epoch": 1.92,
1598
+ "learning_rate": 6.794483814034439e-05,
1599
+ "loss": 2.7048,
1600
+ "step": 131000
1601
+ },
1602
+ {
1603
+ "epoch": 1.93,
1604
+ "learning_rate": 6.772941507653803e-05,
1605
+ "loss": 2.9014,
1606
+ "step": 131500
1607
+ },
1608
+ {
1609
+ "epoch": 1.93,
1610
+ "learning_rate": 6.751361491245093e-05,
1611
+ "loss": 2.7394,
1612
+ "step": 132000
1613
+ },
1614
+ {
1615
+ "epoch": 1.94,
1616
+ "learning_rate": 6.729744223809929e-05,
1617
+ "loss": 2.7723,
1618
+ "step": 132500
1619
+ },
1620
+ {
1621
+ "epoch": 1.95,
1622
+ "learning_rate": 6.708090165142255e-05,
1623
+ "loss": 2.8502,
1624
+ "step": 133000
1625
+ },
1626
+ {
1627
+ "epoch": 1.96,
1628
+ "learning_rate": 6.686399775818548e-05,
1629
+ "loss": 2.7521,
1630
+ "step": 133500
1631
+ },
1632
+ {
1633
+ "epoch": 1.96,
1634
+ "learning_rate": 6.664673517188036e-05,
1635
+ "loss": 2.8726,
1636
+ "step": 134000
1637
+ },
1638
+ {
1639
+ "epoch": 1.97,
1640
+ "learning_rate": 6.642911851362873e-05,
1641
+ "loss": 2.9264,
1642
+ "step": 134500
1643
+ },
1644
+ {
1645
+ "epoch": 1.98,
1646
+ "learning_rate": 6.621115241208316e-05,
1647
+ "loss": 2.8401,
1648
+ "step": 135000
1649
+ },
1650
+ {
1651
+ "epoch": 1.99,
1652
+ "learning_rate": 6.599284150332885e-05,
1653
+ "loss": 2.8706,
1654
+ "step": 135500
1655
+ },
1656
+ {
1657
+ "epoch": 1.99,
1658
+ "learning_rate": 6.57741904307849e-05,
1659
+ "loss": 2.886,
1660
+ "step": 136000
1661
+ },
1662
+ {
1663
+ "epoch": 2.0,
1664
+ "eval_bleu": 1.0,
1665
+ "eval_brevity_penalty": 1.0,
1666
+ "eval_length_ratio": 1.0,
1667
+ "eval_loss": 2.8930435180664062,
1668
+ "eval_precisions": [
1669
+ 1.0,
1670
+ 1.0,
1671
+ 1.0,
1672
+ 1.0
1673
+ ],
1674
+ "eval_reference_length": 7761920,
1675
+ "eval_runtime": 15438.142,
1676
+ "eval_samples_per_second": 0.982,
1677
+ "eval_steps_per_second": 0.491,
1678
+ "eval_translation_length": 7761920,
1679
+ "step": 136438
1680
  }
1681
  ],
1682
  "logging_steps": 500,
1683
  "max_steps": 341095,
1684
  "num_train_epochs": 5,
1685
  "save_steps": 500,
1686
+ "total_flos": 6.289158593555988e+17,
1687
  "trial_name": null,
1688
  "trial_params": null
1689
  }