texanrangee commited on
Commit
b3ed7e8
·
verified ·
1 Parent(s): 24fd1be

Training in progress, step 1650, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d37e22ad9d6da6d8732f1a6b4e2b09b77b82394aa5619162ee36c25251a8741
3
  size 2126429216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:987c964caa043df61d6919d7c2fb1d162e69bf2662bf67d2c59428669f72381f
3
  size 2126429216
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6c2f4a14c87edf3c6405495bebe373bbdf5b29e71dc7f1a6ef5a99f4a627f4e
3
  size 4186608315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b37e7aaf8d81b1ba57561743bd5eeae0553e3a90edab65bb39440adcc7a0a27f
3
  size 4186608315
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da9f9471dfac42496c93461674c458d70747450b67bd8051b34eef16b9095ee5
3
  size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2d88a48b5cbc6899f701738d3c67dd40260b67e1a0aaf2bec52454e73d2f5a0
3
  size 14308
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:483163757d9ed2641ce9369f6fa7036be52ec0b0271d246796d9f4564400a1aa
3
  size 1256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15752b21f4d27e50797678708d53c344f05d78ca10445bdf5c130c9e5677dedc
3
  size 1256
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.45603886246681213,
3
- "best_model_checkpoint": "./output/checkpoint-1350",
4
- "epoch": 0.2781784463218628,
5
  "eval_steps": 150,
6
- "global_step": 1350,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1024,6 +1024,232 @@
1024
  "eval_samples_per_second": 5.738,
1025
  "eval_steps_per_second": 5.738,
1026
  "step": 1350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1027
  }
1028
  ],
1029
  "logging_steps": 10,
@@ -1043,7 +1269,7 @@
1043
  "attributes": {}
1044
  }
1045
  },
1046
- "total_flos": 1.55823168886186e+17,
1047
  "train_batch_size": 2,
1048
  "trial_name": null,
1049
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.4438916742801666,
3
+ "best_model_checkpoint": "./output/checkpoint-1650",
4
+ "epoch": 0.3399958788378323,
5
  "eval_steps": 150,
6
+ "global_step": 1650,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1024
  "eval_samples_per_second": 5.738,
1025
  "eval_steps_per_second": 5.738,
1026
  "step": 1350
1027
+ },
1028
+ {
1029
+ "epoch": 0.2802390274057284,
1030
+ "grad_norm": 2.083104372024536,
1031
+ "learning_rate": 8.455313244934327e-05,
1032
+ "loss": 0.4565,
1033
+ "step": 1360
1034
+ },
1035
+ {
1036
+ "epoch": 0.28229960848959407,
1037
+ "grad_norm": 2.56447434425354,
1038
+ "learning_rate": 8.432071702457255e-05,
1039
+ "loss": 0.451,
1040
+ "step": 1370
1041
+ },
1042
+ {
1043
+ "epoch": 0.2843601895734597,
1044
+ "grad_norm": 2.085458993911743,
1045
+ "learning_rate": 8.408689080955001e-05,
1046
+ "loss": 0.4213,
1047
+ "step": 1380
1048
+ },
1049
+ {
1050
+ "epoch": 0.28642077065732535,
1051
+ "grad_norm": 1.9079893827438354,
1052
+ "learning_rate": 8.38516634159555e-05,
1053
+ "loss": 0.4359,
1054
+ "step": 1390
1055
+ },
1056
+ {
1057
+ "epoch": 0.288481351741191,
1058
+ "grad_norm": 2.075544834136963,
1059
+ "learning_rate": 8.361504451306586e-05,
1060
+ "loss": 0.4213,
1061
+ "step": 1400
1062
+ },
1063
+ {
1064
+ "epoch": 0.2905419328250567,
1065
+ "grad_norm": 2.2827491760253906,
1066
+ "learning_rate": 8.337704382735743e-05,
1067
+ "loss": 0.4475,
1068
+ "step": 1410
1069
+ },
1070
+ {
1071
+ "epoch": 0.29260251390892233,
1072
+ "grad_norm": 2.024596929550171,
1073
+ "learning_rate": 8.313767114210618e-05,
1074
+ "loss": 0.4367,
1075
+ "step": 1420
1076
+ },
1077
+ {
1078
+ "epoch": 0.294663094992788,
1079
+ "grad_norm": 2.20805025100708,
1080
+ "learning_rate": 8.289693629698566e-05,
1081
+ "loss": 0.4871,
1082
+ "step": 1430
1083
+ },
1084
+ {
1085
+ "epoch": 0.2967236760766536,
1086
+ "grad_norm": 2.127082347869873,
1087
+ "learning_rate": 8.265484918766245e-05,
1088
+ "loss": 0.4295,
1089
+ "step": 1440
1090
+ },
1091
+ {
1092
+ "epoch": 0.29878425716051926,
1093
+ "grad_norm": 2.2700977325439453,
1094
+ "learning_rate": 8.241141976538945e-05,
1095
+ "loss": 0.4551,
1096
+ "step": 1450
1097
+ },
1098
+ {
1099
+ "epoch": 0.3008448382443849,
1100
+ "grad_norm": 2.066436767578125,
1101
+ "learning_rate": 8.216665803659673e-05,
1102
+ "loss": 0.459,
1103
+ "step": 1460
1104
+ },
1105
+ {
1106
+ "epoch": 0.30290541932825055,
1107
+ "grad_norm": 2.181267261505127,
1108
+ "learning_rate": 8.19205740624803e-05,
1109
+ "loss": 0.4472,
1110
+ "step": 1470
1111
+ },
1112
+ {
1113
+ "epoch": 0.3049660004121162,
1114
+ "grad_norm": 2.0297725200653076,
1115
+ "learning_rate": 8.167317795858853e-05,
1116
+ "loss": 0.4616,
1117
+ "step": 1480
1118
+ },
1119
+ {
1120
+ "epoch": 0.3070265814959819,
1121
+ "grad_norm": 2.2850377559661865,
1122
+ "learning_rate": 8.142447989440621e-05,
1123
+ "loss": 0.3857,
1124
+ "step": 1490
1125
+ },
1126
+ {
1127
+ "epoch": 0.30908716257984753,
1128
+ "grad_norm": 1.8588734865188599,
1129
+ "learning_rate": 8.117449009293671e-05,
1130
+ "loss": 0.4105,
1131
+ "step": 1500
1132
+ },
1133
+ {
1134
+ "epoch": 0.30908716257984753,
1135
+ "eval_loss": 0.44821813702583313,
1136
+ "eval_runtime": 87.3405,
1137
+ "eval_samples_per_second": 5.736,
1138
+ "eval_steps_per_second": 5.736,
1139
+ "step": 1500
1140
+ },
1141
+ {
1142
+ "epoch": 0.31114774366371317,
1143
+ "grad_norm": 2.5045533180236816,
1144
+ "learning_rate": 8.09232188302816e-05,
1145
+ "loss": 0.4094,
1146
+ "step": 1510
1147
+ },
1148
+ {
1149
+ "epoch": 0.3132083247475788,
1150
+ "grad_norm": 2.2157442569732666,
1151
+ "learning_rate": 8.067067643521836e-05,
1152
+ "loss": 0.4376,
1153
+ "step": 1520
1154
+ },
1155
+ {
1156
+ "epoch": 0.31526890583144446,
1157
+ "grad_norm": 2.1551907062530518,
1158
+ "learning_rate": 8.041687328877568e-05,
1159
+ "loss": 0.439,
1160
+ "step": 1530
1161
+ },
1162
+ {
1163
+ "epoch": 0.3173294869153101,
1164
+ "grad_norm": 2.4675521850585938,
1165
+ "learning_rate": 8.016181982380684e-05,
1166
+ "loss": 0.4301,
1167
+ "step": 1540
1168
+ },
1169
+ {
1170
+ "epoch": 0.31939006799917574,
1171
+ "grad_norm": 2.021408796310425,
1172
+ "learning_rate": 7.990552652456082e-05,
1173
+ "loss": 0.4087,
1174
+ "step": 1550
1175
+ },
1176
+ {
1177
+ "epoch": 0.32145064908304144,
1178
+ "grad_norm": 2.2375285625457764,
1179
+ "learning_rate": 7.964800392625131e-05,
1180
+ "loss": 0.4457,
1181
+ "step": 1560
1182
+ },
1183
+ {
1184
+ "epoch": 0.3235112301669071,
1185
+ "grad_norm": 1.749822974205017,
1186
+ "learning_rate": 7.938926261462369e-05,
1187
+ "loss": 0.4338,
1188
+ "step": 1570
1189
+ },
1190
+ {
1191
+ "epoch": 0.3255718112507727,
1192
+ "grad_norm": 3.428098201751709,
1193
+ "learning_rate": 7.912931322551983e-05,
1194
+ "loss": 0.4303,
1195
+ "step": 1580
1196
+ },
1197
+ {
1198
+ "epoch": 0.32763239233463837,
1199
+ "grad_norm": 2.574517250061035,
1200
+ "learning_rate": 7.8868166444441e-05,
1201
+ "loss": 0.4172,
1202
+ "step": 1590
1203
+ },
1204
+ {
1205
+ "epoch": 0.329692973418504,
1206
+ "grad_norm": 2.3150064945220947,
1207
+ "learning_rate": 7.86058330061085e-05,
1208
+ "loss": 0.3861,
1209
+ "step": 1600
1210
+ },
1211
+ {
1212
+ "epoch": 0.33175355450236965,
1213
+ "grad_norm": 2.194667339324951,
1214
+ "learning_rate": 7.834232369402252e-05,
1215
+ "loss": 0.4271,
1216
+ "step": 1610
1217
+ },
1218
+ {
1219
+ "epoch": 0.3338141355862353,
1220
+ "grad_norm": 1.9583488702774048,
1221
+ "learning_rate": 7.807764934001877e-05,
1222
+ "loss": 0.4881,
1223
+ "step": 1620
1224
+ },
1225
+ {
1226
+ "epoch": 0.335874716670101,
1227
+ "grad_norm": 2.448866605758667,
1228
+ "learning_rate": 7.781182082382326e-05,
1229
+ "loss": 0.4401,
1230
+ "step": 1630
1231
+ },
1232
+ {
1233
+ "epoch": 0.33793529775396663,
1234
+ "grad_norm": 3.26418399810791,
1235
+ "learning_rate": 7.754484907260515e-05,
1236
+ "loss": 0.4386,
1237
+ "step": 1640
1238
+ },
1239
+ {
1240
+ "epoch": 0.3399958788378323,
1241
+ "grad_norm": 2.1950979232788086,
1242
+ "learning_rate": 7.727674506052746e-05,
1243
+ "loss": 0.4084,
1244
+ "step": 1650
1245
+ },
1246
+ {
1247
+ "epoch": 0.3399958788378323,
1248
+ "eval_loss": 0.4438916742801666,
1249
+ "eval_runtime": 87.3442,
1250
+ "eval_samples_per_second": 5.736,
1251
+ "eval_steps_per_second": 5.736,
1252
+ "step": 1650
1253
  }
1254
  ],
1255
  "logging_steps": 10,
 
1269
  "attributes": {}
1270
  }
1271
  },
1272
+ "total_flos": 1.9057210082716877e+17,
1273
  "train_batch_size": 2,
1274
  "trial_name": null,
1275
  "trial_params": null