elsayedissa commited on
Commit
af12196
1 Parent(s): 42e75bc

Training in progress, step 5000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cabcd18d745237ccff0ec1f82242c3cf6523964b69f61c6d491e0dcca8c96bd7
3
  size 12347192855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ebdc8f8502de59db12cbd6f74f44cf507331eefc4bc7fc93ae569b26938c332
3
  size 12347192855
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6744d734b49bb04f2a83a82c65c40351e020bce2add378d9abffb9d286d369c7
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2075a86257ec508484067431dfc2b82755c9993736866d73c28a72f6c350d8ee
3
  size 6173655480
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9719089c9777993e0b77b3d1ee31f8b1880df71d36ecfa484ab6990dbdfc6a8
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17b958d3c797ddf47f3720fe16e38f3bfa12d5f3155d1ad3776ff9e233d3c79
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f950b784a3ad9098996d53ce7727828e81f8df26d9869581909648eda25b95a
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04555011d88c332ec4c78dcfb8c2b871c53c6597c7acc140e81255dc49c7e66
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:285522fdbcf7692ca0fd2c300f90f1d4ac21d59ac64354db24bfa3599d4d3173
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3cec5ec84fec7cef7ee38ef6273b1f5107ef84969b9aa4786aa92ac2e1831ef
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 0.7431560204762965,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-japanese-24h/checkpoint-3000",
4
- "epoch": 30.53435114503817,
5
- "global_step": 4000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -1002,11 +1002,260 @@
1002
  "eval_steps_per_second": 0.164,
1003
  "eval_wer": 0.7442688626752726,
1004
  "step": 4000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1005
  }
1006
  ],
1007
  "max_steps": 5000,
1008
  "num_train_epochs": 39,
1009
- "total_flos": 4.2176792328192e+20,
1010
  "trial_name": null,
1011
  "trial_params": null
1012
  }
 
1
  {
2
  "best_metric": 0.7431560204762965,
3
  "best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-japanese-24h/checkpoint-3000",
4
+ "epoch": 38.16793893129771,
5
+ "global_step": 5000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
1002
  "eval_steps_per_second": 0.164,
1003
  "eval_wer": 0.7442688626752726,
1004
  "step": 4000
1005
+ },
1006
+ {
1007
+ "epoch": 30.73,
1008
+ "learning_rate": 2.1755555555555556e-06,
1009
+ "loss": 0.0002,
1010
+ "step": 4025
1011
+ },
1012
+ {
1013
+ "epoch": 30.92,
1014
+ "learning_rate": 2.12e-06,
1015
+ "loss": 0.0002,
1016
+ "step": 4050
1017
+ },
1018
+ {
1019
+ "epoch": 31.11,
1020
+ "learning_rate": 2.064444444444445e-06,
1021
+ "loss": 0.0002,
1022
+ "step": 4075
1023
+ },
1024
+ {
1025
+ "epoch": 31.3,
1026
+ "learning_rate": 2.008888888888889e-06,
1027
+ "loss": 0.0002,
1028
+ "step": 4100
1029
+ },
1030
+ {
1031
+ "epoch": 31.49,
1032
+ "learning_rate": 1.9533333333333334e-06,
1033
+ "loss": 0.0002,
1034
+ "step": 4125
1035
+ },
1036
+ {
1037
+ "epoch": 31.68,
1038
+ "learning_rate": 1.8977777777777779e-06,
1039
+ "loss": 0.0002,
1040
+ "step": 4150
1041
+ },
1042
+ {
1043
+ "epoch": 31.87,
1044
+ "learning_rate": 1.8422222222222225e-06,
1045
+ "loss": 0.0002,
1046
+ "step": 4175
1047
+ },
1048
+ {
1049
+ "epoch": 32.06,
1050
+ "learning_rate": 1.7866666666666668e-06,
1051
+ "loss": 0.0002,
1052
+ "step": 4200
1053
+ },
1054
+ {
1055
+ "epoch": 32.25,
1056
+ "learning_rate": 1.7311111111111112e-06,
1057
+ "loss": 0.0002,
1058
+ "step": 4225
1059
+ },
1060
+ {
1061
+ "epoch": 32.44,
1062
+ "learning_rate": 1.675555555555556e-06,
1063
+ "loss": 0.0002,
1064
+ "step": 4250
1065
+ },
1066
+ {
1067
+ "epoch": 32.63,
1068
+ "learning_rate": 1.6200000000000002e-06,
1069
+ "loss": 0.0002,
1070
+ "step": 4275
1071
+ },
1072
+ {
1073
+ "epoch": 32.82,
1074
+ "learning_rate": 1.5644444444444446e-06,
1075
+ "loss": 0.0002,
1076
+ "step": 4300
1077
+ },
1078
+ {
1079
+ "epoch": 33.02,
1080
+ "learning_rate": 1.5088888888888889e-06,
1081
+ "loss": 0.0001,
1082
+ "step": 4325
1083
+ },
1084
+ {
1085
+ "epoch": 33.21,
1086
+ "learning_rate": 1.4533333333333335e-06,
1087
+ "loss": 0.0002,
1088
+ "step": 4350
1089
+ },
1090
+ {
1091
+ "epoch": 33.4,
1092
+ "learning_rate": 1.397777777777778e-06,
1093
+ "loss": 0.0002,
1094
+ "step": 4375
1095
+ },
1096
+ {
1097
+ "epoch": 33.59,
1098
+ "learning_rate": 1.3422222222222222e-06,
1099
+ "loss": 0.0002,
1100
+ "step": 4400
1101
+ },
1102
+ {
1103
+ "epoch": 33.78,
1104
+ "learning_rate": 1.286666666666667e-06,
1105
+ "loss": 0.0002,
1106
+ "step": 4425
1107
+ },
1108
+ {
1109
+ "epoch": 33.97,
1110
+ "learning_rate": 1.2311111111111112e-06,
1111
+ "loss": 0.0002,
1112
+ "step": 4450
1113
+ },
1114
+ {
1115
+ "epoch": 34.16,
1116
+ "learning_rate": 1.1755555555555556e-06,
1117
+ "loss": 0.0002,
1118
+ "step": 4475
1119
+ },
1120
+ {
1121
+ "epoch": 34.35,
1122
+ "learning_rate": 1.12e-06,
1123
+ "loss": 0.0002,
1124
+ "step": 4500
1125
+ },
1126
+ {
1127
+ "epoch": 34.54,
1128
+ "learning_rate": 1.0644444444444445e-06,
1129
+ "loss": 0.0001,
1130
+ "step": 4525
1131
+ },
1132
+ {
1133
+ "epoch": 34.73,
1134
+ "learning_rate": 1.008888888888889e-06,
1135
+ "loss": 0.0001,
1136
+ "step": 4550
1137
+ },
1138
+ {
1139
+ "epoch": 34.92,
1140
+ "learning_rate": 9.533333333333335e-07,
1141
+ "loss": 0.0002,
1142
+ "step": 4575
1143
+ },
1144
+ {
1145
+ "epoch": 35.11,
1146
+ "learning_rate": 8.977777777777778e-07,
1147
+ "loss": 0.0002,
1148
+ "step": 4600
1149
+ },
1150
+ {
1151
+ "epoch": 35.31,
1152
+ "learning_rate": 8.422222222222224e-07,
1153
+ "loss": 0.0001,
1154
+ "step": 4625
1155
+ },
1156
+ {
1157
+ "epoch": 35.5,
1158
+ "learning_rate": 7.866666666666667e-07,
1159
+ "loss": 0.0001,
1160
+ "step": 4650
1161
+ },
1162
+ {
1163
+ "epoch": 35.69,
1164
+ "learning_rate": 7.311111111111112e-07,
1165
+ "loss": 0.0002,
1166
+ "step": 4675
1167
+ },
1168
+ {
1169
+ "epoch": 35.88,
1170
+ "learning_rate": 6.755555555555555e-07,
1171
+ "loss": 0.0002,
1172
+ "step": 4700
1173
+ },
1174
+ {
1175
+ "epoch": 36.07,
1176
+ "learning_rate": 6.200000000000001e-07,
1177
+ "loss": 0.0001,
1178
+ "step": 4725
1179
+ },
1180
+ {
1181
+ "epoch": 36.26,
1182
+ "learning_rate": 5.644444444444445e-07,
1183
+ "loss": 0.0001,
1184
+ "step": 4750
1185
+ },
1186
+ {
1187
+ "epoch": 36.45,
1188
+ "learning_rate": 5.088888888888889e-07,
1189
+ "loss": 0.0002,
1190
+ "step": 4775
1191
+ },
1192
+ {
1193
+ "epoch": 36.64,
1194
+ "learning_rate": 4.533333333333334e-07,
1195
+ "loss": 0.0001,
1196
+ "step": 4800
1197
+ },
1198
+ {
1199
+ "epoch": 36.83,
1200
+ "learning_rate": 3.9777777777777783e-07,
1201
+ "loss": 0.0001,
1202
+ "step": 4825
1203
+ },
1204
+ {
1205
+ "epoch": 37.02,
1206
+ "learning_rate": 3.422222222222223e-07,
1207
+ "loss": 0.0001,
1208
+ "step": 4850
1209
+ },
1210
+ {
1211
+ "epoch": 37.21,
1212
+ "learning_rate": 2.866666666666667e-07,
1213
+ "loss": 0.0001,
1214
+ "step": 4875
1215
+ },
1216
+ {
1217
+ "epoch": 37.4,
1218
+ "learning_rate": 2.3111111111111112e-07,
1219
+ "loss": 0.0002,
1220
+ "step": 4900
1221
+ },
1222
+ {
1223
+ "epoch": 37.6,
1224
+ "learning_rate": 1.7555555555555558e-07,
1225
+ "loss": 0.0001,
1226
+ "step": 4925
1227
+ },
1228
+ {
1229
+ "epoch": 37.79,
1230
+ "learning_rate": 1.2000000000000002e-07,
1231
+ "loss": 0.0001,
1232
+ "step": 4950
1233
+ },
1234
+ {
1235
+ "epoch": 37.98,
1236
+ "learning_rate": 6.444444444444445e-08,
1237
+ "loss": 0.0001,
1238
+ "step": 4975
1239
+ },
1240
+ {
1241
+ "epoch": 38.17,
1242
+ "learning_rate": 8.88888888888889e-09,
1243
+ "loss": 0.0002,
1244
+ "step": 5000
1245
+ },
1246
+ {
1247
+ "epoch": 38.17,
1248
+ "eval_loss": 0.4200145900249481,
1249
+ "eval_runtime": 1710.8673,
1250
+ "eval_samples_per_second": 2.621,
1251
+ "eval_steps_per_second": 0.164,
1252
+ "eval_wer": 0.7449365679946583,
1253
+ "step": 5000
1254
  }
1255
  ],
1256
  "max_steps": 5000,
1257
  "num_train_epochs": 39,
1258
+ "total_flos": 5.27162132754432e+20,
1259
  "trial_name": null,
1260
  "trial_params": null
1261
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6744d734b49bb04f2a83a82c65c40351e020bce2add378d9abffb9d286d369c7
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2075a86257ec508484067431dfc2b82755c9993736866d73c28a72f6c350d8ee
3
  size 6173655480
runs/Jan28_23-42-14_gpu07.cyverse.org/events.out.tfevents.1674974582.gpu07.cyverse.org.94170.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e6183fac4cb12f0942d286f36bbc9314f13fcf6e7786a873e26691f74d646f8
3
- size 30796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c97e6b6b1a08d10339672bd5f22c401e8fe6577ecddd03c757d8fa052ac1e4
3
+ size 37394