prxy5605 commited on
Commit
05bb7ff
·
verified ·
1 Parent(s): 59ebee4

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:c9edf81ca71690d9e70e91bb16cc2f715f082493919b56a04496803f5291139a
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bef3a28fb6ac0869134f439af1d19f8c3c959afd85dd0176277b8b5b5a24aa5b
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4945a78c500c3f0ce5f658e3e74e5eec709cc11e5afbf95ee42f276e743060f8
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87eef7e58a0394d309b0d5f5b5a0d68b6a79890f7cd97bcdf702b1e55290dd79
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9f46d1bc63914618d070571551b5e3d6e5bdac38ac757b8d953f640b87c03de
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5c5e9f72e8119bf1a0295061b0e87d36a63ef424bbc1116678537f0d29828c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
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": 0.40268826484680176,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.6968641114982579,
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": 12.661,
1090
  "eval_steps_per_second": 6.348,
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": 2.0293204473544704e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3997976779937744,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.9291521486643438,
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": 12.661,
1090
  "eval_steps_per_second": 6.348,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.7015098722415796,
1095
+ "grad_norm": 0.07464893162250519,
1096
+ "learning_rate": 1.7197048550474643e-05,
1097
+ "loss": 0.3232,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.7061556329849012,
1102
+ "grad_norm": 0.08017167448997498,
1103
+ "learning_rate": 1.6543469682057106e-05,
1104
+ "loss": 0.3353,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.710801393728223,
1109
+ "grad_norm": 0.08147679269313812,
1110
+ "learning_rate": 1.5900081996875083e-05,
1111
+ "loss": 0.3782,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.7154471544715447,
1116
+ "grad_norm": 0.08076490461826324,
1117
+ "learning_rate": 1.526708147705013e-05,
1118
+ "loss": 0.3868,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.7200929152148664,
1123
+ "grad_norm": 0.08399955183267593,
1124
+ "learning_rate": 1.4644660940672627e-05,
1125
+ "loss": 0.3969,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.7247386759581882,
1130
+ "grad_norm": 0.08693921566009521,
1131
+ "learning_rate": 1.4033009983067452e-05,
1132
+ "loss": 0.4041,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.7293844367015099,
1137
+ "grad_norm": 0.0896611288189888,
1138
+ "learning_rate": 1.3432314919041478e-05,
1139
+ "loss": 0.4216,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.7340301974448316,
1144
+ "grad_norm": 0.0846104696393013,
1145
+ "learning_rate": 1.2842758726130283e-05,
1146
+ "loss": 0.3874,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.7386759581881533,
1151
+ "grad_norm": 0.08544657379388809,
1152
+ "learning_rate": 1.22645209888614e-05,
1153
+ "loss": 0.3941,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.743321718931475,
1158
+ "grad_norm": 0.08604080229997635,
1159
+ "learning_rate": 1.1697777844051105e-05,
1160
+ "loss": 0.3877,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.7479674796747967,
1165
+ "grad_norm": 0.08604735136032104,
1166
+ "learning_rate": 1.1142701927151456e-05,
1167
+ "loss": 0.4023,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.7526132404181185,
1172
+ "grad_norm": 0.09132889658212662,
1173
+ "learning_rate": 1.0599462319663905e-05,
1174
+ "loss": 0.4295,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.7572590011614402,
1179
+ "grad_norm": 0.08961532264947891,
1180
+ "learning_rate": 1.006822449763537e-05,
1181
+ "loss": 0.4456,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.7619047619047619,
1186
+ "grad_norm": 0.0899558812379837,
1187
+ "learning_rate": 9.549150281252633e-06,
1188
+ "loss": 0.4357,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.7665505226480837,
1193
+ "grad_norm": 0.09272517263889313,
1194
+ "learning_rate": 9.042397785550405e-06,
1195
+ "loss": 0.3921,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.7711962833914053,
1200
+ "grad_norm": 0.09419538080692291,
1201
+ "learning_rate": 8.548121372247918e-06,
1202
+ "loss": 0.4672,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.775842044134727,
1207
+ "grad_norm": 0.08942130208015442,
1208
+ "learning_rate": 8.066471602728803e-06,
1209
+ "loss": 0.3797,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.7804878048780488,
1214
+ "grad_norm": 0.09228953719139099,
1215
+ "learning_rate": 7.597595192178702e-06,
1216
+ "loss": 0.4493,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.7851335656213705,
1221
+ "grad_norm": 0.09137838333845139,
1222
+ "learning_rate": 7.1416349648943894e-06,
1223
+ "loss": 0.4106,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.7897793263646922,
1228
+ "grad_norm": 0.09273667633533478,
1229
+ "learning_rate": 6.698729810778065e-06,
1230
+ "loss": 0.4121,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.794425087108014,
1235
+ "grad_norm": 0.10233430564403534,
1236
+ "learning_rate": 6.269014643030213e-06,
1237
+ "loss": 0.4697,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.7990708478513356,
1242
+ "grad_norm": 0.10301274061203003,
1243
+ "learning_rate": 5.852620357053651e-06,
1244
+ "loss": 0.4373,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.8037166085946573,
1249
+ "grad_norm": 0.09646183997392654,
1250
+ "learning_rate": 5.449673790581611e-06,
1251
+ "loss": 0.4071,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.8083623693379791,
1256
+ "grad_norm": 0.10154817253351212,
1257
+ "learning_rate": 5.060297685041659e-06,
1258
+ "loss": 0.4147,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.8130081300813008,
1263
+ "grad_norm": 0.10103941708803177,
1264
+ "learning_rate": 4.684610648167503e-06,
1265
+ "loss": 0.4114,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.8176538908246226,
1270
+ "grad_norm": 0.11970110982656479,
1271
+ "learning_rate": 4.322727117869951e-06,
1272
+ "loss": 0.4216,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.8222996515679443,
1277
+ "grad_norm": 0.1059812530875206,
1278
+ "learning_rate": 3.974757327377981e-06,
1279
+ "loss": 0.454,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.826945412311266,
1284
+ "grad_norm": 0.10988090932369232,
1285
+ "learning_rate": 3.6408072716606346e-06,
1286
+ "loss": 0.4468,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.8315911730545877,
1291
+ "grad_norm": 0.10387331992387772,
1292
+ "learning_rate": 3.3209786751399187e-06,
1293
+ "loss": 0.4221,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.8362369337979094,
1298
+ "grad_norm": 0.10960014909505844,
1299
+ "learning_rate": 3.0153689607045845e-06,
1300
+ "loss": 0.42,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.8408826945412311,
1305
+ "grad_norm": 0.11195356398820877,
1306
+ "learning_rate": 2.724071220034158e-06,
1307
+ "loss": 0.3963,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.8455284552845529,
1312
+ "grad_norm": 0.11215968430042267,
1313
+ "learning_rate": 2.4471741852423237e-06,
1314
+ "loss": 0.4018,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.8501742160278746,
1319
+ "grad_norm": 0.11241415143013,
1320
+ "learning_rate": 2.1847622018482283e-06,
1321
+ "loss": 0.4417,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.8548199767711963,
1326
+ "grad_norm": 0.12183176726102829,
1327
+ "learning_rate": 1.9369152030840556e-06,
1328
+ "loss": 0.4913,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.859465737514518,
1333
+ "grad_norm": 0.12207108736038208,
1334
+ "learning_rate": 1.70370868554659e-06,
1335
+ "loss": 0.4369,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.8641114982578397,
1340
+ "grad_norm": 0.1466074436903,
1341
+ "learning_rate": 1.4852136862001764e-06,
1342
+ "loss": 0.4316,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.8687572590011614,
1347
+ "grad_norm": 0.12350435554981232,
1348
+ "learning_rate": 1.2814967607382432e-06,
1349
+ "loss": 0.3746,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.8734030197444832,
1354
+ "grad_norm": 0.11707568168640137,
1355
+ "learning_rate": 1.0926199633097157e-06,
1356
+ "loss": 0.3918,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.8780487804878049,
1361
+ "grad_norm": 0.1270454227924347,
1362
+ "learning_rate": 9.186408276168013e-07,
1363
+ "loss": 0.438,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.8826945412311266,
1368
+ "grad_norm": 0.13130007684230804,
1369
+ "learning_rate": 7.596123493895991e-07,
1370
+ "loss": 0.4472,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.8873403019744484,
1375
+ "grad_norm": 0.13625501096248627,
1376
+ "learning_rate": 6.15582970243117e-07,
1377
+ "loss": 0.4111,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.89198606271777,
1382
+ "grad_norm": 0.13939520716667175,
1383
+ "learning_rate": 4.865965629214819e-07,
1384
+ "loss": 0.4035,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.8966318234610917,
1389
+ "grad_norm": 0.13698220252990723,
1390
+ "learning_rate": 3.7269241793390085e-07,
1391
+ "loss": 0.3758,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.9012775842044135,
1396
+ "grad_norm": 0.1364782154560089,
1397
+ "learning_rate": 2.7390523158633554e-07,
1398
+ "loss": 0.3438,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.9059233449477352,
1403
+ "grad_norm": 0.1426156461238861,
1404
+ "learning_rate": 1.9026509541272275e-07,
1405
+ "loss": 0.358,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.9105691056910569,
1410
+ "grad_norm": 0.16729362308979034,
1411
+ "learning_rate": 1.2179748700879012e-07,
1412
+ "loss": 0.3907,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.9152148664343787,
1417
+ "grad_norm": 0.1714531034231186,
1418
+ "learning_rate": 6.852326227130834e-08,
1419
+ "loss": 0.4107,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.9198606271777003,
1424
+ "grad_norm": 0.17565472424030304,
1425
+ "learning_rate": 3.04586490452119e-08,
1426
+ "loss": 0.4421,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.924506387921022,
1431
+ "grad_norm": 0.20578788220882416,
1432
+ "learning_rate": 7.615242180436522e-09,
1433
+ "loss": 0.4513,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.9291521486643438,
1438
+ "grad_norm": 0.2563062310218811,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.4545,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.9291521486643438,
1445
+ "eval_loss": 0.3997976779937744,
1446
+ "eval_runtime": 28.6696,
1447
+ "eval_samples_per_second": 12.661,
1448
+ "eval_steps_per_second": 6.348,
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": 2.7046516781953843e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null