prxy5608 commited on
Commit
3767fd9
·
verified ·
1 Parent(s): aa3ef48

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 sha256:691990251070a41bf5f066f030a652895aaea37639f610746072b49260d13199
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa4e19cb797bc1ce42862d68529a2f670447b6562352b2ca26aacf4ff486a25
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef857ad8e55aecb2b571c2a7f400dacfb06afade9b1f01247244518de2234149
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e039f304c5e409b31732f16c5fa9acc304548d385095aade4e7a1eb899127973
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:f6654a0f0e1f5b10ff3a4b8ed159b8c5d9abb0424d4ecc5bc9d5958367a590e8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97012629b610fea1ea03c2ea69bab255a24907584d3536f56fbbed5d7a8f7e6e
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": 3.0220675468444824,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.18331805682859761,
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": 13.156,
1090
  "eval_steps_per_second": 3.294,
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": 2.274084219959378e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.987743616104126,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.2444240757714635,
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": 13.156,
1090
  "eval_steps_per_second": 3.294,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.18454017720745494,
1095
+ "grad_norm": 0.4195626676082611,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 0.7554,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.18576229758631224,
1102
+ "grad_norm": 0.6150102615356445,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 1.3267,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.18698441796516957,
1109
+ "grad_norm": 0.7452414631843567,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 1.941,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.1882065383440269,
1116
+ "grad_norm": 0.9951115250587463,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 2.4691,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.1894286587228842,
1123
+ "grad_norm": 0.9944890141487122,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 2.5678,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.19065077910174152,
1130
+ "grad_norm": 1.1375707387924194,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 3.3458,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.19187289948059885,
1137
+ "grad_norm": 1.1083483695983887,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 3.1322,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.19309501985945615,
1144
+ "grad_norm": 1.095042109489441,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 2.781,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.19431714023831348,
1151
+ "grad_norm": 1.104952335357666,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 3.3943,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.19553926061717078,
1158
+ "grad_norm": 1.120809555053711,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 2.9882,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.1967613809960281,
1165
+ "grad_norm": 1.2952760457992554,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 2.9083,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.19798350137488543,
1172
+ "grad_norm": 1.198663353919983,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 2.876,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.19920562175374273,
1179
+ "grad_norm": 1.2929059267044067,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 3.4454,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.20042774213260006,
1186
+ "grad_norm": 1.346503734588623,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 2.924,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.2016498625114574,
1193
+ "grad_norm": 1.4312586784362793,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 2.9343,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.2028719828903147,
1200
+ "grad_norm": 1.4486632347106934,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 2.8998,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.20409410326917202,
1207
+ "grad_norm": 1.4035813808441162,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 2.887,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.20531622364802934,
1214
+ "grad_norm": 1.5069820880889893,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 3.3534,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.20653834402688664,
1221
+ "grad_norm": 1.5212185382843018,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 2.6384,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.20776046440574397,
1228
+ "grad_norm": 1.528660535812378,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 3.0434,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.20898258478460127,
1235
+ "grad_norm": 1.4674322605133057,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 3.3418,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.2102047051634586,
1242
+ "grad_norm": 1.5975470542907715,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 3.0848,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.21142682554231593,
1249
+ "grad_norm": 1.6269925832748413,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 2.993,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.21264894592117323,
1256
+ "grad_norm": 1.6554043292999268,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 3.0981,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.21387106630003055,
1263
+ "grad_norm": 1.584195852279663,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 3.5192,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.21509318667888788,
1270
+ "grad_norm": 1.766545057296753,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 3.1068,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.21631530705774518,
1277
+ "grad_norm": 1.7419136762619019,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 3.2986,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.2175374274366025,
1284
+ "grad_norm": 1.8571009635925293,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 3.0767,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.2187595478154598,
1291
+ "grad_norm": 1.7573845386505127,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 3.3433,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.21998166819431714,
1298
+ "grad_norm": 1.8403384685516357,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 3.1656,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.22120378857317446,
1305
+ "grad_norm": 1.9133869409561157,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 3.1567,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.22242590895203176,
1312
+ "grad_norm": 1.8523482084274292,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 2.8504,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.2236480293308891,
1319
+ "grad_norm": 2.132965564727783,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 2.9624,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.22487014970974642,
1326
+ "grad_norm": 2.0413360595703125,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 3.2415,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.22609227008860372,
1333
+ "grad_norm": 2.027620315551758,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 3.3509,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.22731439046746105,
1340
+ "grad_norm": 2.044543743133545,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 3.4187,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.22853651084631837,
1347
+ "grad_norm": 2.186988115310669,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 3.2818,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.22975863122517567,
1354
+ "grad_norm": 2.2599527835845947,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 2.5928,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.230980751604033,
1361
+ "grad_norm": 2.46183705329895,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 3.0016,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.2322028719828903,
1368
+ "grad_norm": 2.4188575744628906,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 3.0226,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.23342499236174763,
1375
+ "grad_norm": 2.517937660217285,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 3.5165,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.23464711274060496,
1382
+ "grad_norm": 2.5210366249084473,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 3.6273,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.23586923311946226,
1389
+ "grad_norm": 2.5702767372131348,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 3.16,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.23709135349831958,
1396
+ "grad_norm": 2.6997509002685547,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 3.1602,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.2383134738771769,
1403
+ "grad_norm": 2.682856559753418,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 3.1307,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.2395355942560342,
1410
+ "grad_norm": 2.9833390712738037,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 3.7016,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.24075771463489154,
1417
+ "grad_norm": 2.958155632019043,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 3.1719,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.24197983501374887,
1424
+ "grad_norm": 3.055063486099243,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 2.9459,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.24320195539260617,
1431
+ "grad_norm": 3.382892370223999,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 3.2328,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.2444240757714635,
1438
+ "grad_norm": 4.183358669281006,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 3.4313,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.2444240757714635,
1445
+ "eval_loss": 2.987743616104126,
1446
+ "eval_runtime": 104.7391,
1447
+ "eval_samples_per_second": 13.157,
1448
+ "eval_steps_per_second": 3.294,
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": 3.0321122932791706e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null