prxy5608 commited on
Commit
9e16bb8
·
verified ·
1 Parent(s): c30e363

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89f25e2994783015276422fd12146519d8cc036584321a5558a2cd6b1b25d725
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b495907bd8157c29bbb94953fa7261e8e7a6fccad958076bcabaa7095baa12
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05c53664ccedf5c334c81019b038b89179db0badffa04289f1e2db60956fe2df
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1930406d881ae3dbb7d79c26739d52be98017cb6077840ea930c67fa11909e70
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dab8b7d3da17403063f54164f52322ab901ca8bd9de68df84f5796b9924a523
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ca9291e7d2ace3b5da3a713dc519411230aad600e302a7fcfdb0f124d46f1f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.44540271162986755,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.8595988538681948,
5
  "eval_steps": 50,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1089,6 +1089,364 @@
1089
  "eval_samples_per_second": 9.268,
1090
  "eval_steps_per_second": 2.333,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -1103,7 +1461,7 @@
1103
  "early_stopping_threshold": 0.0
1104
  },
1105
  "attributes": {
1106
- "early_stopping_patience_counter": 0
1107
  }
1108
  },
1109
  "TrainerControl": {
@@ -1112,12 +1470,12 @@
1112
  "should_evaluate": false,
1113
  "should_log": false,
1114
  "should_save": true,
1115
- "should_training_stop": false
1116
  },
1117
  "attributes": {}
1118
  }
1119
  },
1120
- "total_flos": 3.307416021400289e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 0.44540271162986755,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.146131805157593,
5
  "eval_steps": 50,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1089
  "eval_samples_per_second": 9.268,
1090
  "eval_steps_per_second": 2.333,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.8653295128939829,
1095
+ "grad_norm": 0.8964242935180664,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 0.4643,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.8710601719197708,
1102
+ "grad_norm": 0.824439287185669,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 0.3892,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.8767908309455588,
1109
+ "grad_norm": 0.7776252627372742,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 0.4145,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.8825214899713467,
1116
+ "grad_norm": 0.9371297359466553,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 0.5634,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.8882521489971347,
1123
+ "grad_norm": 1.0299814939498901,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 0.4847,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.8939828080229226,
1130
+ "grad_norm": 1.4246488809585571,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 0.6393,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.8997134670487106,
1137
+ "grad_norm": 0.7245753407478333,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 0.4044,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.9054441260744985,
1144
+ "grad_norm": 0.7005698680877686,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 0.4756,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.9111747851002865,
1151
+ "grad_norm": 0.8856043219566345,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 0.5241,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.9169054441260746,
1158
+ "grad_norm": 0.7303268909454346,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 0.4489,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.9226361031518625,
1165
+ "grad_norm": 0.7562816739082336,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 0.3839,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.9283667621776505,
1172
+ "grad_norm": 0.8168535828590393,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 0.4504,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.9340974212034384,
1179
+ "grad_norm": 1.0767041444778442,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 0.6333,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.9398280802292264,
1186
+ "grad_norm": 1.0518041849136353,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 0.3752,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.9455587392550143,
1193
+ "grad_norm": 1.162166953086853,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 0.4307,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.9512893982808023,
1200
+ "grad_norm": 1.3328009843826294,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 0.5075,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.9570200573065902,
1207
+ "grad_norm": 0.9067739248275757,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 0.4621,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.9627507163323782,
1214
+ "grad_norm": 0.9629002213478088,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 0.4683,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.9684813753581661,
1221
+ "grad_norm": 0.9616539478302002,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 0.5045,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.9742120343839542,
1228
+ "grad_norm": 1.5788521766662598,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 0.353,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.9799426934097422,
1235
+ "grad_norm": 1.116830825805664,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 0.5412,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.9856733524355301,
1242
+ "grad_norm": 1.3788104057312012,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 0.3874,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.9914040114613181,
1249
+ "grad_norm": 0.8184030652046204,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 0.591,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.997134670487106,
1256
+ "grad_norm": 0.849399209022522,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 0.353,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 1.002865329512894,
1263
+ "grad_norm": 2.4538636207580566,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 0.7994,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 1.008595988538682,
1270
+ "grad_norm": 0.49595823884010315,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 0.5555,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 1.0143266475644699,
1277
+ "grad_norm": 0.5643259882926941,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 0.6956,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 1.0200573065902578,
1284
+ "grad_norm": 0.8207282423973083,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 0.5886,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 1.0257879656160458,
1291
+ "grad_norm": 0.6101379990577698,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 0.7186,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 1.0315186246418337,
1298
+ "grad_norm": 0.6199820041656494,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 0.6548,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 1.0372492836676217,
1305
+ "grad_norm": 0.6589621901512146,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 0.608,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 1.0429799426934097,
1312
+ "grad_norm": 0.8309704661369324,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 0.3727,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 1.0487106017191976,
1319
+ "grad_norm": 0.7659175992012024,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 0.352,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 1.0544412607449858,
1326
+ "grad_norm": 0.9337642788887024,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 0.473,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 1.0601719197707737,
1333
+ "grad_norm": 1.664469599723816,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 0.1855,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 1.0659025787965617,
1340
+ "grad_norm": 0.8137052059173584,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 0.2174,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 1.0716332378223496,
1347
+ "grad_norm": 6.241861343383789,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 0.4824,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 1.0773638968481376,
1354
+ "grad_norm": 1.8748527765274048,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 0.2882,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 1.0830945558739256,
1361
+ "grad_norm": 4.546536445617676,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 0.4016,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 1.0888252148997135,
1368
+ "grad_norm": 3.190882444381714,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 0.3463,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 1.0945558739255015,
1375
+ "grad_norm": 0.5799930691719055,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 0.2081,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 1.1002865329512894,
1382
+ "grad_norm": 0.46898940205574036,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 0.1307,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 1.1060171919770774,
1389
+ "grad_norm": 1.3466490507125854,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 0.4705,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 1.1117478510028653,
1396
+ "grad_norm": 0.7763919830322266,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 0.4452,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 1.1174785100286533,
1403
+ "grad_norm": 0.6729264259338379,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 0.2995,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 1.1232091690544412,
1410
+ "grad_norm": 0.6211886405944824,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 0.2793,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 1.1289398280802292,
1417
+ "grad_norm": 0.6557769775390625,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 0.2858,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 1.1346704871060171,
1424
+ "grad_norm": 0.7445409297943115,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 0.3551,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 1.140401146131805,
1431
+ "grad_norm": 0.6006184220314026,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 0.3054,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 1.146131805157593,
1438
+ "grad_norm": 0.6899487972259521,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.4284,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 1.146131805157593,
1445
+ "eval_loss": 0.45417553186416626,
1446
+ "eval_runtime": 31.4756,
1447
+ "eval_samples_per_second": 9.341,
1448
+ "eval_steps_per_second": 2.351,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
1461
  "early_stopping_threshold": 0.0
1462
  },
1463
  "attributes": {
1464
+ "early_stopping_patience_counter": 1
1465
  }
1466
  },
1467
  "TrainerControl": {
 
1470
  "should_evaluate": false,
1471
  "should_log": false,
1472
  "should_save": true,
1473
+ "should_training_stop": true
1474
  },
1475
  "attributes": {}
1476
  }
1477
  },
1478
+ "total_flos": 4.341690643827917e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null