aleegis10 commited on
Commit
33858f9
·
verified ·
1 Parent(s): 5c41b8f

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 sha256:0d41b46e3dc69c9d5bc4a0acb4ca6faadcd708be28492c8e4e26b3cd38de665b
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5914cde98fe3f4de705608d6a03b04a97c8ccc4ad8967700ad64609a8e2a1398
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46a2317886eaedf6f7cdd51be8588fb5f4210b2f13ff1405116473d82eb85d12
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc89f5984374bad641ee00d3d2a8845f8300876c6caef5ca6072f1d5f6263a8
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:dcff93eca5f581c005e2920d4649b724eb22f5f6f13912e12c2f4832a3a33588
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bbc558b1d1973faabdab1367ab4a9e66f9de5a87f512a69abe95b7fb53b7307
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": 0.876602828502655,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.6920415224913494,
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": 33.868,
1090
  "eval_steps_per_second": 8.537,
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": 4.0821709602816e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8764411211013794,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.922722029988466,
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": 33.868,
1090
  "eval_steps_per_second": 8.537,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.6966551326412919,
1095
+ "grad_norm": 0.5587314367294312,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 0.8308,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.7012687427912342,
1102
+ "grad_norm": 0.5991786122322083,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 0.811,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.7058823529411765,
1109
+ "grad_norm": 0.6372523307800293,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 0.8988,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.7104959630911188,
1116
+ "grad_norm": 0.5904070138931274,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 0.7663,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.7151095732410612,
1123
+ "grad_norm": 0.6629855632781982,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 0.8405,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.7197231833910035,
1130
+ "grad_norm": 0.7020514607429504,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 0.7466,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.7243367935409458,
1137
+ "grad_norm": 0.7516071796417236,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 0.8422,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.7289504036908881,
1144
+ "grad_norm": 0.6631370782852173,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 0.8203,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.7335640138408305,
1151
+ "grad_norm": 0.6792702078819275,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 0.8205,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.7381776239907728,
1158
+ "grad_norm": 0.6027781367301941,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 0.7852,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.7427912341407151,
1165
+ "grad_norm": 0.6831485033035278,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 0.8057,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.7474048442906575,
1172
+ "grad_norm": 0.6506722569465637,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 0.8373,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.7520184544405998,
1179
+ "grad_norm": 0.6890047192573547,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 0.8209,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.7566320645905421,
1186
+ "grad_norm": 0.7230890989303589,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 0.8907,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.7612456747404844,
1193
+ "grad_norm": 0.6444016098976135,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 0.8346,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.7658592848904268,
1200
+ "grad_norm": 0.6376002430915833,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 0.8048,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.7704728950403691,
1207
+ "grad_norm": 0.6137439012527466,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 0.7729,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.7750865051903114,
1214
+ "grad_norm": 0.6272302865982056,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 0.8045,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.7797001153402537,
1221
+ "grad_norm": 0.7248494625091553,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 0.8487,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.7843137254901961,
1228
+ "grad_norm": 0.6824492812156677,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 0.902,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.7889273356401384,
1235
+ "grad_norm": 0.7295922040939331,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 0.8031,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.7935409457900807,
1242
+ "grad_norm": 0.6699785590171814,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 0.8685,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.798154555940023,
1249
+ "grad_norm": 0.6496451497077942,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 0.7844,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.8027681660899654,
1256
+ "grad_norm": 0.6744278073310852,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 0.8418,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.8073817762399077,
1263
+ "grad_norm": 0.8501985669136047,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 0.8889,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.81199538638985,
1270
+ "grad_norm": 0.6856309175491333,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 0.8822,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.8166089965397924,
1277
+ "grad_norm": 0.7461533546447754,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 0.9183,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.8212226066897347,
1284
+ "grad_norm": 0.6875928044319153,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 0.7756,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.825836216839677,
1291
+ "grad_norm": 0.6789725422859192,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 0.7496,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.8304498269896193,
1298
+ "grad_norm": 0.6839475035667419,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 0.7941,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.8350634371395617,
1305
+ "grad_norm": 0.6540483832359314,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 0.8801,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.839677047289504,
1312
+ "grad_norm": 0.7676746249198914,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 0.8604,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.8442906574394463,
1319
+ "grad_norm": 0.6954748630523682,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 0.9073,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.8489042675893888,
1326
+ "grad_norm": 0.6446994543075562,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 0.7591,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.8535178777393311,
1333
+ "grad_norm": 0.8935235142707825,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 0.9245,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.8581314878892734,
1340
+ "grad_norm": 0.8469705581665039,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 0.9271,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.8627450980392157,
1347
+ "grad_norm": 0.7198098301887512,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 0.7991,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.8673587081891581,
1354
+ "grad_norm": 0.8117537498474121,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 0.9371,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.8719723183391004,
1361
+ "grad_norm": 0.7335435152053833,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 0.8187,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.8765859284890427,
1368
+ "grad_norm": 0.8176902532577515,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 0.9177,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.881199538638985,
1375
+ "grad_norm": 0.7294403314590454,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 0.8463,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.8858131487889274,
1382
+ "grad_norm": 0.755285918712616,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 0.8997,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.8904267589388697,
1389
+ "grad_norm": 0.826835572719574,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 0.9857,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.895040369088812,
1396
+ "grad_norm": 0.7164878845214844,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 0.8354,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.8996539792387543,
1403
+ "grad_norm": 0.9040074944496155,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 0.9114,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.9042675893886967,
1410
+ "grad_norm": 1.003586769104004,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 0.955,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.908881199538639,
1417
+ "grad_norm": 0.8864195346832275,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 0.928,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.9134948096885813,
1424
+ "grad_norm": 0.9328382015228271,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 0.8566,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.9181084198385236,
1431
+ "grad_norm": 1.1644843816757202,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 0.8518,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.922722029988466,
1438
+ "grad_norm": 1.5909967422485352,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.9691,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.922722029988466,
1445
+ "eval_loss": 0.8764411211013794,
1446
+ "eval_runtime": 10.7916,
1447
+ "eval_samples_per_second": 33.823,
1448
+ "eval_steps_per_second": 8.525,
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": 5.4428946137088e+16,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null