abaddon182 commited on
Commit
bc29b2a
·
verified ·
1 Parent(s): efc4ecb

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 sha256:1437b9909bf13979f2cc617831b310a876519161411deba071642fdb78ac8536
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b369fbdc646a4e9272dc26a4d61c5ae34c4e282c1c51024a1b2b54ed58c06a
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e25a59d17f33742689b8043b2938ab2495217f8df9fac15cf7ce73c6a5f2d2e
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c82861f1e46bc0fb56c0c32f11def11aa618c55d42654ff8a601db200071e5
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e2dde15ab52627a4bf798f86c82969e606b5d48d2c2a97f3f12009bc3e8535c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752fa870475fa4c57dd74cfafc9b3cc37e4e99fd74a4b4d849ab1a9075b933f8
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": 0.350641667842865,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 1.837920489296636,
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": 12.702,
1090
  "eval_steps_per_second": 3.221,
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": 2.292940639693701e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 0.350641667842865,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 2.452599388379205,
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": 12.702,
1090
  "eval_steps_per_second": 3.221,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 1.8501529051987768,
1095
+ "grad_norm": 0.34158000349998474,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 0.2468,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 1.8623853211009176,
1102
+ "grad_norm": 0.3191375732421875,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 0.232,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 1.8746177370030581,
1109
+ "grad_norm": 0.32770881056785583,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 0.233,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 1.8868501529051986,
1116
+ "grad_norm": 0.33779266476631165,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 0.2322,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 1.8990825688073394,
1123
+ "grad_norm": 0.3396666944026947,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 0.2165,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 1.9113149847094801,
1130
+ "grad_norm": 0.3281339108943939,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 0.2128,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 1.9235474006116209,
1137
+ "grad_norm": 0.3483438193798065,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 0.2169,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 1.9357798165137616,
1144
+ "grad_norm": 0.3689464032649994,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 0.2426,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 1.9480122324159022,
1151
+ "grad_norm": 0.36408838629722595,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 0.2115,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 1.9602446483180427,
1158
+ "grad_norm": 0.42640426754951477,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 0.25,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 1.9724770642201834,
1165
+ "grad_norm": 0.41972142457962036,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 0.2345,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 1.9847094801223242,
1172
+ "grad_norm": 0.3567162752151489,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 0.2214,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 1.996941896024465,
1179
+ "grad_norm": 0.5055474042892456,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 0.2929,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 2.0122324159021407,
1186
+ "grad_norm": 0.22303302586078644,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 0.2807,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 2.0244648318042815,
1193
+ "grad_norm": 0.26136767864227295,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 0.2843,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 2.036697247706422,
1200
+ "grad_norm": 0.2842232882976532,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 0.2911,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 2.0489296636085625,
1207
+ "grad_norm": 0.2708796262741089,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 0.2626,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 2.0611620795107033,
1214
+ "grad_norm": 0.2718449532985687,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 0.2543,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 2.073394495412844,
1221
+ "grad_norm": 0.29201751947402954,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 0.2759,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 2.085626911314985,
1228
+ "grad_norm": 0.29264751076698303,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 0.2276,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 2.0978593272171255,
1235
+ "grad_norm": 0.3177122175693512,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 0.2929,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 2.1100917431192663,
1242
+ "grad_norm": 0.2933153212070465,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 0.2456,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 2.1223241590214066,
1249
+ "grad_norm": 0.2777900695800781,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 0.1786,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 2.1345565749235473,
1256
+ "grad_norm": 0.2833649814128876,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 0.1785,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 2.146788990825688,
1263
+ "grad_norm": 0.30753934383392334,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 0.1887,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 2.159021406727829,
1270
+ "grad_norm": 0.3037162125110626,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 0.1883,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 2.1712538226299696,
1277
+ "grad_norm": 0.2993669807910919,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 0.1701,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 2.18348623853211,
1284
+ "grad_norm": 0.3263915479183197,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 0.1783,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 2.1957186544342506,
1291
+ "grad_norm": 0.3346138596534729,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 0.1764,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 2.2079510703363914,
1298
+ "grad_norm": 0.6663686633110046,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 0.2113,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 2.220183486238532,
1305
+ "grad_norm": 0.3060767948627472,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 0.1483,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 2.232415902140673,
1312
+ "grad_norm": 0.3507230579853058,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 0.1656,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 2.2446483180428136,
1319
+ "grad_norm": 0.3343973457813263,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 0.1368,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 2.2568807339449544,
1326
+ "grad_norm": 0.2353735864162445,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 0.2903,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 2.2691131498470947,
1333
+ "grad_norm": 0.25053614377975464,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 0.2484,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 2.2813455657492354,
1340
+ "grad_norm": 0.27156978845596313,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 0.2264,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 2.293577981651376,
1347
+ "grad_norm": 0.3115900158882141,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 0.3016,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 2.305810397553517,
1354
+ "grad_norm": 0.2937740683555603,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 0.2485,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 2.3180428134556577,
1361
+ "grad_norm": 0.3086647689342499,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 0.2503,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 2.330275229357798,
1368
+ "grad_norm": 0.26695045828819275,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 0.1979,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 2.3425076452599387,
1375
+ "grad_norm": 0.3203602135181427,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 0.2646,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 2.3547400611620795,
1382
+ "grad_norm": 0.3068872094154358,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 0.2138,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 2.36697247706422,
1389
+ "grad_norm": 0.3405860662460327,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 0.258,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 2.379204892966361,
1396
+ "grad_norm": 0.3421233296394348,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 0.2252,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 2.3914373088685017,
1403
+ "grad_norm": 0.319794625043869,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 0.1911,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 2.4036697247706424,
1410
+ "grad_norm": 0.3064125180244446,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 0.1772,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 2.4159021406727827,
1417
+ "grad_norm": 0.3086625337600708,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 0.1514,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 2.4281345565749235,
1424
+ "grad_norm": 0.3053826093673706,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 0.1626,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 2.4403669724770642,
1431
+ "grad_norm": 0.32307735085487366,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 0.177,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 2.452599388379205,
1438
+ "grad_norm": 0.31589850783348083,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.1692,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 2.452599388379205,
1445
+ "eval_loss": 0.35414132475852966,
1446
+ "eval_runtime": 10.8556,
1447
+ "eval_samples_per_second": 12.712,
1448
+ "eval_steps_per_second": 3.224,
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": 3.0547399969603584e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null