aleegis09 commited on
Commit
db9b09c
·
verified ·
1 Parent(s): 99e5291

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 sha256:533818eecd922dff0635f36d17aeb0d0f10f0ee4450f7fe9d9493f11edbc7cb8
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcc6edd801735d2fb1f61fd03e4b4a0fb1eab0033549801138d5b70e86b1a51
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:021673b1c1192ea29039557030c62b0301b1c58b0d513a0d19e4bb34506a21d7
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9ebedb0f051553cfe9f481ec641f019f3a1eace2d8c206974cf7d37ef18328
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e1c3be782aeb28c42f6e840cb3dd0ae7f2e67cb50c1f822a6f52efbfb9a2d2a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2b674e14f5e49c08ca9b70b1ceae5828c76d6a365986cc18d4566c6f9045b7
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": 1.131042718887329,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.03365114974761638,
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": 23.233,
1090
  "eval_steps_per_second": 5.808,
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": 1.01030282919936e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.118039608001709,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.044868199663488505,
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": 23.233,
1090
  "eval_steps_per_second": 5.808,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.03387549074593382,
1095
+ "grad_norm": 0.8614676594734192,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 1.3554,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.03409983174425126,
1102
+ "grad_norm": 0.9027763605117798,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 1.3378,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.0343241727425687,
1109
+ "grad_norm": 0.9020812511444092,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 1.2763,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.03454851374088615,
1116
+ "grad_norm": 0.9730469584465027,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 1.3594,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.034772854739203586,
1123
+ "grad_norm": 1.0548874139785767,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 1.2592,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.03499719573752103,
1130
+ "grad_norm": 1.1751259565353394,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 1.3561,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.03522153673583847,
1137
+ "grad_norm": 1.040268898010254,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 1.1385,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.03544587773415592,
1144
+ "grad_norm": 1.034965991973877,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 1.1944,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.035670218732473356,
1151
+ "grad_norm": 1.005588412284851,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 1.152,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.0358945597307908,
1158
+ "grad_norm": 1.020017385482788,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 1.179,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.03611890072910824,
1165
+ "grad_norm": 1.0504347085952759,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 1.1554,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.03634324172742569,
1172
+ "grad_norm": 1.11807382106781,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 1.1324,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.03656758272574313,
1179
+ "grad_norm": 0.9994248747825623,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 1.1389,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.03679192372406057,
1186
+ "grad_norm": 0.9709587097167969,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 1.149,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.03701626472237801,
1193
+ "grad_norm": 1.1986273527145386,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 1.2284,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.03724060572069546,
1200
+ "grad_norm": 1.1978342533111572,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 1.1399,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.0374649467190129,
1207
+ "grad_norm": 1.1640859842300415,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 1.2051,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.03768928771733034,
1214
+ "grad_norm": 0.9959132075309753,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 1.0146,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.03791362871564778,
1221
+ "grad_norm": 1.102310061454773,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 0.9959,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.03813796971396523,
1228
+ "grad_norm": 1.1588571071624756,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 1.1923,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.03836231071228267,
1235
+ "grad_norm": 1.1732374429702759,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 1.1319,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.03858665171060011,
1242
+ "grad_norm": 1.260844349861145,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 1.0923,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.03881099270891755,
1249
+ "grad_norm": 1.2971606254577637,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 1.0556,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.039035333707235,
1256
+ "grad_norm": 1.2263072729110718,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 1.1448,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.03925967470555244,
1263
+ "grad_norm": 1.263629674911499,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 1.0225,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.03948401570386988,
1270
+ "grad_norm": 1.3652485609054565,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 1.2126,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.03970835670218732,
1277
+ "grad_norm": 1.244150161743164,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 0.925,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.03993269770050477,
1284
+ "grad_norm": 1.1341102123260498,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 1.018,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.04015703869882221,
1291
+ "grad_norm": 1.3381551504135132,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 1.1376,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.040381379697139654,
1298
+ "grad_norm": 1.3847415447235107,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 1.1043,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.04060572069545709,
1305
+ "grad_norm": 1.2933632135391235,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 0.9109,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.04083006169377454,
1312
+ "grad_norm": 1.4092001914978027,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 1.0101,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.04105440269209198,
1319
+ "grad_norm": 1.4717921018600464,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 1.092,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.041278743690409424,
1326
+ "grad_norm": 1.4898322820663452,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 1.003,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.04150308468872686,
1333
+ "grad_norm": 1.434329867362976,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 1.0782,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.04172742568704431,
1340
+ "grad_norm": 1.4739409685134888,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 1.0491,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.04195176668536175,
1347
+ "grad_norm": 1.649688959121704,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 1.2685,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.042176107683679194,
1354
+ "grad_norm": 1.5006073713302612,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 1.0353,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.04240044868199663,
1361
+ "grad_norm": 1.5449039936065674,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 1.0905,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.04262478968031408,
1368
+ "grad_norm": 1.6924413442611694,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 1.0539,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.04284913067863152,
1375
+ "grad_norm": 2.0756149291992188,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 1.3964,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.043073471676948964,
1382
+ "grad_norm": 1.9471677541732788,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 1.1528,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.0432978126752664,
1389
+ "grad_norm": 1.9654617309570312,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 1.1359,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.04352215367358385,
1396
+ "grad_norm": 2.175584554672241,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 1.0669,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.04374649467190129,
1403
+ "grad_norm": 1.6459085941314697,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 0.9547,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.043970835670218734,
1410
+ "grad_norm": 2.174954652786255,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 0.9913,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.044195176668536174,
1417
+ "grad_norm": 2.332949161529541,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 1.0769,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.04441951766685362,
1424
+ "grad_norm": 2.5872936248779297,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 0.8778,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.04464385866517106,
1431
+ "grad_norm": 2.374394655227661,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 0.8653,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.044868199663488505,
1438
+ "grad_norm": 3.0859851837158203,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.9303,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.044868199663488505,
1445
+ "eval_loss": 1.118039608001709,
1446
+ "eval_runtime": 323.451,
1447
+ "eval_samples_per_second": 23.212,
1448
+ "eval_steps_per_second": 5.803,
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": 1.34707043893248e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null