magatex commited on
Commit
83f2db8
·
verified ·
1 Parent(s): 095e506

Training in progress, step 190, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b8c80c5b549785e595a6edded231302dc9fc7eb612dcee3581a10a67613d048
3
  size 188794608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4197823243285d91151e5193369a743a18bb5831f1e606de7cfdd4aa9505682
3
  size 188794608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69c608cb2b8bbffebbb5337c04a77b7b4b0b84c85657d208be0718283f227245
3
  size 377811346
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27902d987d923d811183b59010cf9f99b8ceade2c91a8416f467e78344dfc5c8
3
  size 377811346
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6861fc28c485cb3ef6288fd169e89f691e202481a632d4f2a2a8c13f43c26070
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56ff2e2b75ce612d72e9e8b2d041791a868be7d580cc9f1da80036ee48c96d1b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:445b7598993fe3a18f07b6ee10e450c957df6de162dc7729c132643a3ca6e545
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0717fa852ff14c4fb6ef3d8fb6e7d6c5b1e6b17d5f3ada276b0ae8e8648b64
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.21235010027885437,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.2430379746835443,
5
  "eval_steps": 25,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1113,6 +1113,294 @@
1113
  "eval_samples_per_second": 8.691,
1114
  "eval_steps_per_second": 8.691,
1115
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1116
  }
1117
  ],
1118
  "logging_steps": 1,
@@ -1136,12 +1424,12 @@
1136
  "should_evaluate": false,
1137
  "should_log": false,
1138
  "should_save": true,
1139
- "should_training_stop": false
1140
  },
1141
  "attributes": {}
1142
  }
1143
  },
1144
- "total_flos": 1.6427164989652992e+17,
1145
  "train_batch_size": 1,
1146
  "trial_name": null,
1147
  "trial_params": null
 
1
  {
2
  "best_metric": 0.21235010027885437,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.3078481012658228,
5
  "eval_steps": 25,
6
+ "global_step": 190,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1113
  "eval_samples_per_second": 8.691,
1114
  "eval_steps_per_second": 8.691,
1115
  "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 0.24465822784810126,
1119
+ "grad_norm": 11.316670417785645,
1120
+ "learning_rate": 1.9922179741796086e-05,
1121
+ "loss": 0.2515,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 0.24627848101265823,
1126
+ "grad_norm": 11.774153709411621,
1127
+ "learning_rate": 1.9438237813334586e-05,
1128
+ "loss": 0.1704,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 0.2478987341772152,
1133
+ "grad_norm": 6.292091369628906,
1134
+ "learning_rate": 1.8965008980117037e-05,
1135
+ "loss": 0.1084,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 0.24951898734177216,
1140
+ "grad_norm": 14.302482604980469,
1141
+ "learning_rate": 1.850263580385163e-05,
1142
+ "loss": 0.4959,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 0.25113924050632913,
1147
+ "grad_norm": 12.771811485290527,
1148
+ "learning_rate": 1.8051257575944925e-05,
1149
+ "loss": 0.2987,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 0.25275949367088607,
1154
+ "grad_norm": 16.40115737915039,
1155
+ "learning_rate": 1.7611010275539962e-05,
1156
+ "loss": 0.5615,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 0.254379746835443,
1161
+ "grad_norm": 13.117633819580078,
1162
+ "learning_rate": 1.718202652855205e-05,
1163
+ "loss": 0.3622,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 0.256,
1168
+ "grad_norm": 10.55799674987793,
1169
+ "learning_rate": 1.6764435567714794e-05,
1170
+ "loss": 0.3473,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 0.25762025316455694,
1175
+ "grad_norm": 7.9049763679504395,
1176
+ "learning_rate": 1.6358363193648352e-05,
1177
+ "loss": 0.2403,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 0.25924050632911394,
1182
+ "grad_norm": 11.420134544372559,
1183
+ "learning_rate": 1.5963931736961547e-05,
1184
+ "loss": 0.4369,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 0.2608607594936709,
1189
+ "grad_norm": 8.98204231262207,
1190
+ "learning_rate": 1.5581260021399396e-05,
1191
+ "loss": 0.2004,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 0.2624810126582279,
1196
+ "grad_norm": 7.689177513122559,
1197
+ "learning_rate": 1.5210463328047095e-05,
1198
+ "loss": 0.1891,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 0.2641012658227848,
1203
+ "grad_norm": 10.6261568069458,
1204
+ "learning_rate": 1.4851653360601179e-05,
1205
+ "loss": 0.2807,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 0.26572151898734175,
1210
+ "grad_norm": 7.932508945465088,
1211
+ "learning_rate": 1.4504938211718489e-05,
1212
+ "loss": 0.2299,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 0.26734177215189875,
1217
+ "grad_norm": 23.33995819091797,
1218
+ "learning_rate": 1.4170422330452816e-05,
1219
+ "loss": 0.3367,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 0.2689620253164557,
1224
+ "grad_norm": 10.17355728149414,
1225
+ "learning_rate": 1.384820649078939e-05,
1226
+ "loss": 0.2386,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 0.2705822784810127,
1231
+ "grad_norm": 12.60328197479248,
1232
+ "learning_rate": 1.3538387761286303e-05,
1233
+ "loss": 0.2627,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 0.2722025316455696,
1238
+ "grad_norm": 9.619555473327637,
1239
+ "learning_rate": 1.3241059475832373e-05,
1240
+ "loss": 0.2167,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 0.27382278481012656,
1245
+ "grad_norm": 5.489387512207031,
1246
+ "learning_rate": 1.2956311205529943e-05,
1247
+ "loss": 0.1933,
1248
+ "step": 169
1249
+ },
1250
+ {
1251
+ "epoch": 0.27544303797468356,
1252
+ "grad_norm": 15.453241348266602,
1253
+ "learning_rate": 1.268422873171136e-05,
1254
+ "loss": 0.1648,
1255
+ "step": 170
1256
+ },
1257
+ {
1258
+ "epoch": 0.2770632911392405,
1259
+ "grad_norm": 37.87616729736328,
1260
+ "learning_rate": 1.2424894020096997e-05,
1261
+ "loss": 0.5199,
1262
+ "step": 171
1263
+ },
1264
+ {
1265
+ "epoch": 0.2786835443037975,
1266
+ "grad_norm": 15.486174583435059,
1267
+ "learning_rate": 1.217838519610291e-05,
1268
+ "loss": 0.7258,
1269
+ "step": 172
1270
+ },
1271
+ {
1272
+ "epoch": 0.28030379746835443,
1273
+ "grad_norm": 15.361915588378906,
1274
+ "learning_rate": 1.1944776521305213e-05,
1275
+ "loss": 0.266,
1276
+ "step": 173
1277
+ },
1278
+ {
1279
+ "epoch": 0.28192405063291137,
1280
+ "grad_norm": 10.4679594039917,
1281
+ "learning_rate": 1.1724138371068603e-05,
1282
+ "loss": 0.3238,
1283
+ "step": 174
1284
+ },
1285
+ {
1286
+ "epoch": 0.28354430379746837,
1287
+ "grad_norm": 15.89462947845459,
1288
+ "learning_rate": 1.1516537213345519e-05,
1289
+ "loss": 0.3613,
1290
+ "step": 175
1291
+ },
1292
+ {
1293
+ "epoch": 0.28354430379746837,
1294
+ "eval_loss": 0.17382794618606567,
1295
+ "eval_runtime": 5.7564,
1296
+ "eval_samples_per_second": 8.686,
1297
+ "eval_steps_per_second": 8.686,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 0.2851645569620253,
1302
+ "grad_norm": 11.57437515258789,
1303
+ "learning_rate": 1.1322035588652484e-05,
1304
+ "loss": 0.31,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 0.2867848101265823,
1309
+ "grad_norm": 11.174723625183105,
1310
+ "learning_rate": 1.1140692091229556e-05,
1311
+ "loss": 0.423,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 0.28840506329113924,
1316
+ "grad_norm": 7.6294026374816895,
1317
+ "learning_rate": 1.0972561351388622e-05,
1318
+ "loss": 0.3503,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 0.2900253164556962,
1323
+ "grad_norm": 8.027375221252441,
1324
+ "learning_rate": 1.0817694019055866e-05,
1325
+ "loss": 0.2998,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 0.2916455696202532,
1330
+ "grad_norm": 10.243330955505371,
1331
+ "learning_rate": 1.0676136748513286e-05,
1332
+ "loss": 0.2555,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 0.2932658227848101,
1337
+ "grad_norm": 21.219587326049805,
1338
+ "learning_rate": 1.0547932184343948e-05,
1339
+ "loss": 0.4385,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 0.2948860759493671,
1344
+ "grad_norm": 7.321977615356445,
1345
+ "learning_rate": 1.043311894858519e-05,
1346
+ "loss": 0.2346,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 0.29650632911392405,
1351
+ "grad_norm": 9.628911972045898,
1352
+ "learning_rate": 1.033173162909358e-05,
1353
+ "loss": 0.2849,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 0.298126582278481,
1358
+ "grad_norm": 7.442295551300049,
1359
+ "learning_rate": 1.0243800769125222e-05,
1360
+ "loss": 0.146,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 0.299746835443038,
1365
+ "grad_norm": 5.40734338760376,
1366
+ "learning_rate": 1.0169352858134525e-05,
1367
+ "loss": 0.1266,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 0.3013670886075949,
1372
+ "grad_norm": 6.042978763580322,
1373
+ "learning_rate": 1.0108410323794131e-05,
1374
+ "loss": 0.167,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 0.3029873417721519,
1379
+ "grad_norm": 7.91204309463501,
1380
+ "learning_rate": 1.0060991525238538e-05,
1381
+ "loss": 0.174,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 0.30460759493670886,
1386
+ "grad_norm": 10.424847602844238,
1387
+ "learning_rate": 1.0027110747533332e-05,
1388
+ "loss": 0.3899,
1389
+ "step": 188
1390
+ },
1391
+ {
1392
+ "epoch": 0.3062278481012658,
1393
+ "grad_norm": 11.064706802368164,
1394
+ "learning_rate": 1.0006778197371774e-05,
1395
+ "loss": 0.2932,
1396
+ "step": 189
1397
+ },
1398
+ {
1399
+ "epoch": 0.3078481012658228,
1400
+ "grad_norm": 18.252004623413086,
1401
+ "learning_rate": 1e-05,
1402
+ "loss": 0.8028,
1403
+ "step": 190
1404
  }
1405
  ],
1406
  "logging_steps": 1,
 
1424
  "should_evaluate": false,
1425
  "should_log": false,
1426
  "should_save": true,
1427
+ "should_training_stop": true
1428
  },
1429
  "attributes": {}
1430
  }
1431
  },
1432
+ "total_flos": 2.080310468542464e+17,
1433
  "train_batch_size": 1,
1434
  "trial_name": null,
1435
  "trial_params": null