Hugging Face's logo

elsayedissa
/
wav2vec2-xls-r-300m-ar

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
arabic_speech_corpus
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
elsayedissa commited on
Commit
e2327c2
·
1 Parent(s): 157cd14

Training in progress, step 5000

Browse files
Files changed (7) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +2 -2
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +252 -3
  6. pytorch_model.bin +1 -1
  7. runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27258b0c1d06a9b5e61d8f927d63726deb3b0f232f363bb381e6603a2e047efd
3
  size 2524414853
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04ac14b396acc439a80242e3de2dde5c2c3cfe230aff038ac79cfc71137162a
3
  size 2524414853
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb9bb8d82c12f7963f345a3bc44171138b5cd9c15813fe124d03c8957cb8aa3d
3
  size 1262229869
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72797f1440dbbfd35bf83a8efb707c911377db12eea28703ebe830d181f4ed7f
3
  size 1262229869
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc101980f72fb94e34cbe7f2fcca59c7772750d7ccf19bcd551759aee050f696
3
- size 14639
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c34f160b4325fa8e05323d539226829df54c92e017ae64958c023e2dbecb9e
3
+ size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4eb4748670085a8091d197542279b737c13c5a3f63f48bc90750499483c77941
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e00e24b9ec2f00c6f283cf8c9dd0d87ed62551d6e0d1598b4aa9ff96f37c557
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 0.0693531029534856,
3
  "best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-3000",
4
- "epoch": 35.39823008849557,
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": 1.209,
1003
  "eval_wer": 0.07222288652397466,
1004
  "step": 4000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1005
  }
1006
  ],
1007
  "max_steps": 10000,
1008
  "num_train_epochs": 89,
1009
- "total_flos": 1.5768864774399195e+19,
1010
  "trial_name": null,
1011
  "trial_params": null
1012
  }
 
1
  {
2
  "best_metric": 0.0693531029534856,
3
  "best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-3000",
4
+ "epoch": 44.24778761061947,
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": 1.209,
1003
  "eval_wer": 0.07222288652397466,
1004
  "step": 4000
1005
+ },
1006
+ {
1007
+ "epoch": 35.62,
1008
+ "learning_rate": 0.00018868421052631575,
1009
+ "loss": 0.0222,
1010
+ "step": 4025
1011
+ },
1012
+ {
1013
+ "epoch": 35.84,
1014
+ "learning_rate": 0.00018789473684210524,
1015
+ "loss": 0.0206,
1016
+ "step": 4050
1017
+ },
1018
+ {
1019
+ "epoch": 36.06,
1020
+ "learning_rate": 0.00018710526315789475,
1021
+ "loss": 0.0196,
1022
+ "step": 4075
1023
+ },
1024
+ {
1025
+ "epoch": 36.28,
1026
+ "learning_rate": 0.0001863157894736842,
1027
+ "loss": 0.0186,
1028
+ "step": 4100
1029
+ },
1030
+ {
1031
+ "epoch": 36.5,
1032
+ "learning_rate": 0.00018552631578947368,
1033
+ "loss": 0.0178,
1034
+ "step": 4125
1035
+ },
1036
+ {
1037
+ "epoch": 36.73,
1038
+ "learning_rate": 0.00018473684210526314,
1039
+ "loss": 0.0159,
1040
+ "step": 4150
1041
+ },
1042
+ {
1043
+ "epoch": 36.95,
1044
+ "learning_rate": 0.00018394736842105262,
1045
+ "loss": 0.0249,
1046
+ "step": 4175
1047
+ },
1048
+ {
1049
+ "epoch": 37.17,
1050
+ "learning_rate": 0.00018315789473684208,
1051
+ "loss": 0.0258,
1052
+ "step": 4200
1053
+ },
1054
+ {
1055
+ "epoch": 37.39,
1056
+ "learning_rate": 0.00018236842105263156,
1057
+ "loss": 0.0202,
1058
+ "step": 4225
1059
+ },
1060
+ {
1061
+ "epoch": 37.61,
1062
+ "learning_rate": 0.00018157894736842105,
1063
+ "loss": 0.022,
1064
+ "step": 4250
1065
+ },
1066
+ {
1067
+ "epoch": 37.83,
1068
+ "learning_rate": 0.0001807894736842105,
1069
+ "loss": 0.0266,
1070
+ "step": 4275
1071
+ },
1072
+ {
1073
+ "epoch": 38.05,
1074
+ "learning_rate": 0.00017999999999999998,
1075
+ "loss": 0.0183,
1076
+ "step": 4300
1077
+ },
1078
+ {
1079
+ "epoch": 38.27,
1080
+ "learning_rate": 0.00017921052631578944,
1081
+ "loss": 0.0159,
1082
+ "step": 4325
1083
+ },
1084
+ {
1085
+ "epoch": 38.5,
1086
+ "learning_rate": 0.00017842105263157892,
1087
+ "loss": 0.0167,
1088
+ "step": 4350
1089
+ },
1090
+ {
1091
+ "epoch": 38.72,
1092
+ "learning_rate": 0.00017763157894736838,
1093
+ "loss": 0.0163,
1094
+ "step": 4375
1095
+ },
1096
+ {
1097
+ "epoch": 38.94,
1098
+ "learning_rate": 0.00017684210526315786,
1099
+ "loss": 0.0151,
1100
+ "step": 4400
1101
+ },
1102
+ {
1103
+ "epoch": 39.16,
1104
+ "learning_rate": 0.00017605263157894737,
1105
+ "loss": 0.0172,
1106
+ "step": 4425
1107
+ },
1108
+ {
1109
+ "epoch": 39.38,
1110
+ "learning_rate": 0.00017526315789473683,
1111
+ "loss": 0.0175,
1112
+ "step": 4450
1113
+ },
1114
+ {
1115
+ "epoch": 39.6,
1116
+ "learning_rate": 0.0001744736842105263,
1117
+ "loss": 0.0193,
1118
+ "step": 4475
1119
+ },
1120
+ {
1121
+ "epoch": 39.82,
1122
+ "learning_rate": 0.0001736842105263158,
1123
+ "loss": 0.0241,
1124
+ "step": 4500
1125
+ },
1126
+ {
1127
+ "epoch": 40.04,
1128
+ "learning_rate": 0.00017289473684210525,
1129
+ "loss": 0.0192,
1130
+ "step": 4525
1131
+ },
1132
+ {
1133
+ "epoch": 40.27,
1134
+ "learning_rate": 0.00017210526315789473,
1135
+ "loss": 0.019,
1136
+ "step": 4550
1137
+ },
1138
+ {
1139
+ "epoch": 40.49,
1140
+ "learning_rate": 0.0001713157894736842,
1141
+ "loss": 0.0138,
1142
+ "step": 4575
1143
+ },
1144
+ {
1145
+ "epoch": 40.71,
1146
+ "learning_rate": 0.00017052631578947367,
1147
+ "loss": 0.0158,
1148
+ "step": 4600
1149
+ },
1150
+ {
1151
+ "epoch": 40.93,
1152
+ "learning_rate": 0.00016973684210526313,
1153
+ "loss": 0.0181,
1154
+ "step": 4625
1155
+ },
1156
+ {
1157
+ "epoch": 41.15,
1158
+ "learning_rate": 0.0001689473684210526,
1159
+ "loss": 0.0167,
1160
+ "step": 4650
1161
+ },
1162
+ {
1163
+ "epoch": 41.37,
1164
+ "learning_rate": 0.00016815789473684207,
1165
+ "loss": 0.0214,
1166
+ "step": 4675
1167
+ },
1168
+ {
1169
+ "epoch": 41.59,
1170
+ "learning_rate": 0.00016736842105263155,
1171
+ "loss": 0.0184,
1172
+ "step": 4700
1173
+ },
1174
+ {
1175
+ "epoch": 41.81,
1176
+ "learning_rate": 0.00016657894736842103,
1177
+ "loss": 0.0166,
1178
+ "step": 4725
1179
+ },
1180
+ {
1181
+ "epoch": 42.04,
1182
+ "learning_rate": 0.00016578947368421052,
1183
+ "loss": 0.0128,
1184
+ "step": 4750
1185
+ },
1186
+ {
1187
+ "epoch": 42.26,
1188
+ "learning_rate": 0.000165,
1189
+ "loss": 0.0156,
1190
+ "step": 4775
1191
+ },
1192
+ {
1193
+ "epoch": 42.48,
1194
+ "learning_rate": 0.00016421052631578948,
1195
+ "loss": 0.0131,
1196
+ "step": 4800
1197
+ },
1198
+ {
1199
+ "epoch": 42.7,
1200
+ "learning_rate": 0.00016342105263157894,
1201
+ "loss": 0.0146,
1202
+ "step": 4825
1203
+ },
1204
+ {
1205
+ "epoch": 42.92,
1206
+ "learning_rate": 0.00016263157894736842,
1207
+ "loss": 0.0157,
1208
+ "step": 4850
1209
+ },
1210
+ {
1211
+ "epoch": 43.14,
1212
+ "learning_rate": 0.00016184210526315788,
1213
+ "loss": 0.0158,
1214
+ "step": 4875
1215
+ },
1216
+ {
1217
+ "epoch": 43.36,
1218
+ "learning_rate": 0.00016105263157894736,
1219
+ "loss": 0.0157,
1220
+ "step": 4900
1221
+ },
1222
+ {
1223
+ "epoch": 43.58,
1224
+ "learning_rate": 0.00016026315789473682,
1225
+ "loss": 0.0159,
1226
+ "step": 4925
1227
+ },
1228
+ {
1229
+ "epoch": 43.81,
1230
+ "learning_rate": 0.0001594736842105263,
1231
+ "loss": 0.0217,
1232
+ "step": 4950
1233
+ },
1234
+ {
1235
+ "epoch": 44.03,
1236
+ "learning_rate": 0.00015868421052631578,
1237
+ "loss": 0.0178,
1238
+ "step": 4975
1239
+ },
1240
+ {
1241
+ "epoch": 44.25,
1242
+ "learning_rate": 0.00015789473684210524,
1243
+ "loss": 0.0177,
1244
+ "step": 5000
1245
+ },
1246
+ {
1247
+ "epoch": 44.25,
1248
+ "eval_loss": 0.24588559567928314,
1249
+ "eval_runtime": 10.7371,
1250
+ "eval_samples_per_second": 9.313,
1251
+ "eval_steps_per_second": 1.211,
1252
+ "eval_wer": 0.07437522420184145,
1253
+ "step": 5000
1254
  }
1255
  ],
1256
  "max_steps": 10000,
1257
  "num_train_epochs": 89,
1258
+ "total_flos": 1.96951110785928e+19,
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:bb9bb8d82c12f7963f345a3bc44171138b5cd9c15813fe124d03c8957cb8aa3d
3
  size 1262229869
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72797f1440dbbfd35bf83a8efb707c911377db12eea28703ebe830d181f4ed7f
3
  size 1262229869
runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50fa134d7573be5c46508e873e8bb15f1862c32825a16d7b12c777045dccecb2
3
- size 31774
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0c176c61ff82428c1cfed0632db9bfe35c7927ea235840f13920ec7caf7126
3
+ size 38372