prxy5607 commited on
Commit
3ce3f91
·
verified ·
1 Parent(s): 26cb90e

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:ff4c7f1c8b481da52c557dc335ea1b34439c3fced1cd086fa49ee8a2e190a1ea
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6f75493f9265152b77c39a8f1363a86fb71ca790027b2c73a38734682c5ff9
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f80bd1b17b75665e1f84f983d9f78af1af104b0b752be25a9a76c68f029db2d2
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5632eaf4df7d428bb361b6b2d3740ee1ad48a5895b3f6aa91c541783b91a14a3
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed04707b07fc679dcc42c87501aeae7557a4fe0b810329b1453942c51e260e1c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37175c9ac6661ab80fd5474918bc5899a6fc60497f0fbb1f5bc3d13039fc7a8
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": 1.5240753889083862,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.34110289937464466,
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": 8.484,
1090
  "eval_steps_per_second": 2.129,
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": 3.351746514266358e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5209094285964966,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.4548038658328596,
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": 8.484,
1090
  "eval_steps_per_second": 2.129,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.343376918703809,
1095
+ "grad_norm": 1.2536038160324097,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 1.849,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.34565093803297325,
1102
+ "grad_norm": 0.6904004216194153,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 1.6794,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.3479249573621376,
1109
+ "grad_norm": 1.3438644409179688,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 1.8664,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.3501989766913019,
1116
+ "grad_norm": 0.4487466514110565,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 1.4681,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.35247299602046617,
1123
+ "grad_norm": 0.5591351985931396,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 2.0531,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.3547470153496305,
1130
+ "grad_norm": 0.4360477328300476,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 2.0392,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.35702103467879476,
1137
+ "grad_norm": 0.4868318736553192,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 1.5427,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.3592950540079591,
1144
+ "grad_norm": 0.5212265253067017,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 1.5689,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.36156907333712335,
1151
+ "grad_norm": 0.4803144335746765,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 1.9316,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.36384309266628767,
1158
+ "grad_norm": 0.529874324798584,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 1.6473,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.36611711199545194,
1165
+ "grad_norm": 0.4623226523399353,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 1.6669,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.36839113132461626,
1172
+ "grad_norm": 0.6224995851516724,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 1.7597,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.3706651506537806,
1179
+ "grad_norm": 0.5420475006103516,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 1.693,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.37293916998294485,
1186
+ "grad_norm": 0.59107506275177,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 1.7996,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.3752131893121092,
1193
+ "grad_norm": 0.6783829927444458,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 1.6573,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.37748720864127344,
1200
+ "grad_norm": 0.5627995133399963,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 1.3896,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.37976122797043776,
1207
+ "grad_norm": 0.6750528216362,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 1.7502,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.38203524729960203,
1214
+ "grad_norm": 0.5398040413856506,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 1.4908,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.38430926662876636,
1221
+ "grad_norm": 0.7093826532363892,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 1.2441,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.3865832859579306,
1228
+ "grad_norm": 0.8342501521110535,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 1.4289,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.38885730528709495,
1235
+ "grad_norm": 0.7612286806106567,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 1.6867,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.3911313246162592,
1242
+ "grad_norm": 0.684005081653595,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 1.5414,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.39340534394542354,
1249
+ "grad_norm": 0.99790358543396,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 1.2303,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.39567936327458786,
1256
+ "grad_norm": 0.9739305973052979,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 1.3257,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.3979533826037521,
1263
+ "grad_norm": 0.8710699677467346,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 1.6414,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.40022740193291645,
1270
+ "grad_norm": 0.8697039484977722,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 1.2693,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.4025014212620807,
1277
+ "grad_norm": 0.9100931882858276,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 1.4523,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.40477544059124504,
1284
+ "grad_norm": 1.463058352470398,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 1.019,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.4070494599204093,
1291
+ "grad_norm": 1.1174596548080444,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 1.3052,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.40932347924957363,
1298
+ "grad_norm": 1.2767281532287598,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 1.1493,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.4115974985787379,
1305
+ "grad_norm": 1.1020197868347168,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 1.2324,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.4138715179079022,
1312
+ "grad_norm": 0.9557793736457825,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 1.8658,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.4161455372370665,
1319
+ "grad_norm": 1.3657689094543457,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 2.0749,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.4184195565662308,
1326
+ "grad_norm": 0.6264777779579163,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 1.874,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.42069357589539513,
1333
+ "grad_norm": 0.46833235025405884,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 1.4518,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.4229675952245594,
1340
+ "grad_norm": 0.6169543862342834,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 1.6197,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.4252416145537237,
1347
+ "grad_norm": 0.5078561305999756,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 1.7556,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.427515633882888,
1354
+ "grad_norm": 0.42960596084594727,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 1.5463,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.4297896532120523,
1361
+ "grad_norm": 0.6596783399581909,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 1.652,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.4320636725412166,
1368
+ "grad_norm": 0.5691636800765991,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 1.6293,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.4343376918703809,
1375
+ "grad_norm": 0.6190604567527771,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 1.7883,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.43661171119954517,
1382
+ "grad_norm": 0.6815586686134338,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 1.493,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.4388857305287095,
1389
+ "grad_norm": 0.5660620927810669,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 1.5054,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.4411597498578738,
1396
+ "grad_norm": 0.7303324937820435,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 1.5502,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.4434337691870381,
1403
+ "grad_norm": 0.6283324360847473,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 1.5532,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.4457077885162024,
1410
+ "grad_norm": 0.610903799533844,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 1.6055,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.4479818078453667,
1417
+ "grad_norm": 0.7150243520736694,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 1.6843,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.450255827174531,
1424
+ "grad_norm": 0.7381975054740906,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 1.5914,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.45252984650369527,
1431
+ "grad_norm": 0.6399606466293335,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 1.4263,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.4548038658328596,
1438
+ "grad_norm": 1.1996755599975586,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 1.8604,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.4548038658328596,
1445
+ "eval_loss": 1.5209094285964966,
1446
+ "eval_runtime": 87.3641,
1447
+ "eval_samples_per_second": 8.482,
1448
+ "eval_steps_per_second": 2.129,
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": 4.475705555586908e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null