aleegis11 commited on
Commit
2fc1d3a
·
verified ·
1 Parent(s): 3249cdf

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:f6bb0e1bb2fbf04140bfa58f64e579d4511edd2cd7d85d248a51df6e8bc6f55e
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8747b7e91cf4ef2dd00e376687afd06e9420173911513f0b31e856ce393f7cf8
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6f43ca0d40e6ff9498287df2fd04fd296ad1b6824907e04dce984b2d81a2cad
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a67cb5f7f554e503c100c4e9b9ed7e36327e6aa702f256fd00302d11f8d12465
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d11fd250d467037f6d5558c43ba391bc178b1a22aabba4062e8737df6fb0aed
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e077beffc4ca55658ec0d7b3523dc34328e8a5a2b2b85d50023355567c46f0
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": 2.1498870849609375,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.22099447513812154,
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": 33.996,
1090
  "eval_steps_per_second": 8.499,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -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": 4.088974578548736e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.142829656600952,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.2946593001841621,
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": 33.996,
1090
  "eval_steps_per_second": 8.499,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.22246777163904236,
1095
+ "grad_norm": 0.4497315287590027,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 2.1235,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.22394106813996317,
1102
+ "grad_norm": 0.48219621181488037,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 2.0459,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.225414364640884,
1109
+ "grad_norm": 0.4607875645160675,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 2.1236,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.22688766114180478,
1116
+ "grad_norm": 0.4888078272342682,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 2.0777,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.2283609576427256,
1123
+ "grad_norm": 0.5186671614646912,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 2.1288,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.22983425414364642,
1130
+ "grad_norm": 0.5025704503059387,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 1.9971,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.2313075506445672,
1137
+ "grad_norm": 0.4730200469493866,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 2.0245,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.23278084714548802,
1144
+ "grad_norm": 0.5410052537918091,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 2.042,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.23425414364640884,
1151
+ "grad_norm": 0.4994640648365021,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 1.9262,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.23572744014732966,
1158
+ "grad_norm": 0.49574676156044006,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 2.1671,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.23720073664825045,
1165
+ "grad_norm": 0.5467461943626404,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 2.248,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.23867403314917127,
1172
+ "grad_norm": 0.5036174654960632,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 2.114,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.24014732965009208,
1179
+ "grad_norm": 0.516216516494751,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 2.1475,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.2416206261510129,
1186
+ "grad_norm": 0.5705137252807617,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 2.3152,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.2430939226519337,
1193
+ "grad_norm": 0.5074183940887451,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 2.0175,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.2445672191528545,
1200
+ "grad_norm": 0.5196369290351868,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 2.0298,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.24604051565377533,
1207
+ "grad_norm": 0.5080201625823975,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 2.1187,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.24751381215469614,
1214
+ "grad_norm": 0.5384064316749573,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 2.1803,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.24898710865561693,
1221
+ "grad_norm": 0.5691060423851013,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 2.0255,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.2504604051565378,
1228
+ "grad_norm": 0.550330638885498,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 2.1137,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.25193370165745854,
1235
+ "grad_norm": 0.5306848883628845,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 2.1299,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.25340699815837936,
1242
+ "grad_norm": 0.5351966619491577,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 2.1293,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.2548802946593002,
1249
+ "grad_norm": 0.5528244972229004,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 2.1027,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.256353591160221,
1256
+ "grad_norm": 0.5488362312316895,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 2.1509,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.2578268876611418,
1263
+ "grad_norm": 0.5732300877571106,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 2.2063,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.25930018416206263,
1270
+ "grad_norm": 0.5619857907295227,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 2.2253,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.26077348066298345,
1277
+ "grad_norm": 0.5769329071044922,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 2.2133,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.2622467771639042,
1284
+ "grad_norm": 0.5814343690872192,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 2.154,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.263720073664825,
1291
+ "grad_norm": 0.6259899139404297,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 2.3186,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.26519337016574585,
1298
+ "grad_norm": 0.5869902968406677,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 2.2518,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.26666666666666666,
1305
+ "grad_norm": 0.6089134216308594,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 2.0913,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.2681399631675875,
1312
+ "grad_norm": 0.5955935716629028,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 2.1964,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.2696132596685083,
1319
+ "grad_norm": 0.5801297426223755,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 2.128,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.2710865561694291,
1326
+ "grad_norm": 0.606168270111084,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 2.248,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.27255985267034993,
1333
+ "grad_norm": 0.628900945186615,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 2.0947,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.2740331491712707,
1340
+ "grad_norm": 0.6443435549736023,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 2.1588,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.2755064456721915,
1347
+ "grad_norm": 0.6042181849479675,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 2.0953,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.27697974217311233,
1354
+ "grad_norm": 0.6067960858345032,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 2.2178,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.27845303867403315,
1361
+ "grad_norm": 0.6070239543914795,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 2.2549,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.27992633517495397,
1368
+ "grad_norm": 0.6234919428825378,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 2.1084,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.2813996316758748,
1375
+ "grad_norm": 0.6733989715576172,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 2.0763,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.2828729281767956,
1382
+ "grad_norm": 0.7105913758277893,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 2.2615,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.28434622467771636,
1389
+ "grad_norm": 0.718129575252533,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 2.3094,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.2858195211786372,
1396
+ "grad_norm": 0.6917638182640076,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 2.1456,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.287292817679558,
1403
+ "grad_norm": 0.7489725351333618,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 2.1397,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.2887661141804788,
1410
+ "grad_norm": 0.7198150157928467,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 2.1637,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.29023941068139963,
1417
+ "grad_norm": 0.758560299873352,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 2.221,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.29171270718232045,
1424
+ "grad_norm": 0.764299750328064,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 2.2446,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.29318600368324127,
1431
+ "grad_norm": 0.8316512703895569,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 2.1687,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.2946593001841621,
1438
+ "grad_norm": 1.0795071125030518,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 2.0839,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.2946593001841621,
1445
+ "eval_loss": 2.142829656600952,
1446
+ "eval_runtime": 33.6479,
1447
+ "eval_samples_per_second": 33.999,
1448
+ "eval_steps_per_second": 8.5,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
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": 5.456501850243072e+16,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null