aleegis12 commited on
Commit
b91e8eb
·
verified ·
1 Parent(s): 39c192f

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 sha256:404aaa67d2653d11bd8590572ef83c7c9a9ad430d4352f4bd6f6ea9f79eca65b
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34159bcd2aae300ac1d67acc7984416d776f34e27d62a1db87546037df40b9e3
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53f4147c7cc029be567dcc7ed797cc8f4dc45812dbc268e0efc0d6c0c7c63f50
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40770f6136a057dc388e7b3052eeb5ac67d4701e25703bc677b82b0f371af9bf
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ab27cb17c551347e3049be4bfe08b4da103ef36f18be9b54c92fd4980fd0e18
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbec201e00f7c2245bb06b5fd4f16da9b6e4f8e016ab71d2dbb2c0eab81b4876
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": 1.1526620388031006,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.09764035801464606,
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": 23.628,
1090
  "eval_steps_per_second": 5.907,
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": 8.59964222472192e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.133461594581604,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.13018714401952808,
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": 23.628,
1090
  "eval_steps_per_second": 5.907,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.0982912937347437,
1095
+ "grad_norm": 0.4425734877586365,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 1.2236,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.09894222945484134,
1102
+ "grad_norm": 0.4403512179851532,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 1.1551,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.09959316517493898,
1109
+ "grad_norm": 0.570582926273346,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 1.3521,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.10024410089503662,
1116
+ "grad_norm": 0.5874238610267639,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 1.2793,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.10089503661513426,
1123
+ "grad_norm": 0.5461292862892151,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 1.2977,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.1015459723352319,
1130
+ "grad_norm": 0.5610890984535217,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 1.2314,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.10219690805532954,
1137
+ "grad_norm": 0.5510687232017517,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 1.3269,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.10284784377542718,
1144
+ "grad_norm": 0.5707263946533203,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 1.2968,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.10349877949552481,
1151
+ "grad_norm": 0.5511327385902405,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 1.1913,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.10414971521562245,
1158
+ "grad_norm": 0.6073991656303406,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 1.2753,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.1048006509357201,
1165
+ "grad_norm": 0.5549350380897522,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 1.1356,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.10545158665581773,
1172
+ "grad_norm": 0.5595770478248596,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 1.2582,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.10610252237591537,
1179
+ "grad_norm": 0.5501592755317688,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 1.1934,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.10675345809601301,
1186
+ "grad_norm": 0.5635471940040588,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 1.3024,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.10740439381611067,
1193
+ "grad_norm": 0.58777916431427,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 1.3083,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.1080553295362083,
1200
+ "grad_norm": 0.5593265295028687,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 1.2539,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.10870626525630595,
1207
+ "grad_norm": 0.5832934379577637,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 1.1859,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.10935720097640358,
1214
+ "grad_norm": 0.5834015011787415,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 1.1431,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.11000813669650122,
1221
+ "grad_norm": 0.6024950742721558,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 1.2358,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.11065907241659886,
1228
+ "grad_norm": 0.6071770191192627,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 1.2181,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.1113100081366965,
1235
+ "grad_norm": 0.6048394441604614,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 1.0767,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.11196094385679414,
1242
+ "grad_norm": 0.6726189255714417,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 1.249,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.11261187957689178,
1249
+ "grad_norm": 0.7132400274276733,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 1.2503,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.11326281529698942,
1256
+ "grad_norm": 0.6905943751335144,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 1.1835,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.11391375101708706,
1263
+ "grad_norm": 0.7441547513008118,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 1.2597,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.1145646867371847,
1270
+ "grad_norm": 0.7429041862487793,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 1.1172,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.11521562245728234,
1277
+ "grad_norm": 0.8964692950248718,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 1.2033,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.11586655817737998,
1284
+ "grad_norm": 0.8569055199623108,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 1.1635,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.11651749389747762,
1291
+ "grad_norm": 1.0133323669433594,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 1.1023,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.11716842961757526,
1298
+ "grad_norm": 0.9354881644248962,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 1.0004,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.1178193653376729,
1305
+ "grad_norm": 1.00664222240448,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 1.2482,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.11847030105777054,
1312
+ "grad_norm": 1.1946007013320923,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 1.2571,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.11912123677786819,
1319
+ "grad_norm": 1.0512912273406982,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 1.0046,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.11977217249796583,
1326
+ "grad_norm": 1.241084337234497,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 1.0715,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.12042310821806347,
1333
+ "grad_norm": 1.242465615272522,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 0.9481,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.12107404393816111,
1340
+ "grad_norm": 1.2314049005508423,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 0.968,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.12172497965825875,
1347
+ "grad_norm": 1.4579668045043945,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 1.1622,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.12237591537835639,
1354
+ "grad_norm": 1.495545744895935,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 0.7595,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.12302685109845403,
1361
+ "grad_norm": 1.4693126678466797,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 1.0173,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.12367778681855167,
1368
+ "grad_norm": 1.4530022144317627,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 1.0035,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.12432872253864931,
1375
+ "grad_norm": 1.6730422973632812,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 0.9927,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.12497965825874695,
1382
+ "grad_norm": 1.35174560546875,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 0.9331,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.1256305939788446,
1389
+ "grad_norm": 1.5141745805740356,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 0.838,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.12628152969894224,
1396
+ "grad_norm": 1.8975859880447388,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 1.2921,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.12693246541903988,
1403
+ "grad_norm": 1.7575794458389282,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 1.0674,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.12758340113913752,
1410
+ "grad_norm": 1.9218443632125854,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 1.0992,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.12823433685923516,
1417
+ "grad_norm": 2.026832103729248,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 0.8491,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.1288852725793328,
1424
+ "grad_norm": 2.744027853012085,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 1.3356,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.12953620829943044,
1431
+ "grad_norm": 2.4693961143493652,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 1.1594,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.13018714401952808,
1438
+ "grad_norm": 5.269348621368408,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 1.5934,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.13018714401952808,
1445
+ "eval_loss": 1.133461594581604,
1446
+ "eval_runtime": 109.4849,
1447
+ "eval_samples_per_second": 23.638,
1448
+ "eval_steps_per_second": 5.909,
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": 1.146618963296256e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null