aleegis12 commited on
Commit
31d9ebc
·
verified ·
1 Parent(s): 6c34086

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 sha256:481563ab13b96a2de82b86d46148c8bcf2ac9f73a43d5a74a4b79118232e391a
3
  size 42487072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722bc3d4f538eee8c4a74dbe4a1eaf86f63d202c34738dcb542a487aa613767c
3
  size 42487072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:973dce70c2e001988d19644a28fb9f7255d5d785928f68ed9f2a7930741fccb1
3
  size 21735354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd6e95155e83793501d80cb2cf1b723d9713dc2e2d23563f836039f5de200d6
3
  size 21735354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:889b72d75cbad3f140ef557feb72852251d2151e74b7f8526d42c352b93432f6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2e66c2c009662e0eee7db74ff3a35272b2dc75982c972f42fe3befffe76f3e5
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": 2.2692179679870605,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.6615214994487321,
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": 96.011,
1090
  "eval_steps_per_second": 24.128,
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": 5454912804618240.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.2532453536987305,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.8820286659316428,
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": 96.011,
1090
  "eval_steps_per_second": 24.128,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.6659316427783903,
1095
+ "grad_norm": 3.6759140491485596,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 9.4823,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.6703417861080485,
1102
+ "grad_norm": 3.4207842350006104,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 9.5271,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.6747519294377067,
1109
+ "grad_norm": 3.703519582748413,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 9.8302,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.679162072767365,
1116
+ "grad_norm": 3.2789928913116455,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 9.6278,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.6835722160970231,
1123
+ "grad_norm": 2.9552910327911377,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 9.5895,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.6879823594266814,
1130
+ "grad_norm": 2.9568581581115723,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 9.5088,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.6923925027563396,
1137
+ "grad_norm": 2.9085640907287598,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 9.5415,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.6968026460859978,
1144
+ "grad_norm": 2.9179465770721436,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 9.4631,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.701212789415656,
1151
+ "grad_norm": 2.654332160949707,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 9.02,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.7056229327453142,
1158
+ "grad_norm": 2.8916449546813965,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 9.6744,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.7100330760749725,
1165
+ "grad_norm": 2.5509328842163086,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 9.5784,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.7144432194046306,
1172
+ "grad_norm": 2.656136989593506,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 9.4054,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.7188533627342889,
1179
+ "grad_norm": 2.6057004928588867,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 9.543,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.7232635060639471,
1186
+ "grad_norm": 2.974360942840576,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 9.578,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.7276736493936052,
1193
+ "grad_norm": 2.5843842029571533,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 9.5427,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.7320837927232635,
1200
+ "grad_norm": 2.5783538818359375,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 9.4709,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.7364939360529217,
1207
+ "grad_norm": 2.44590425491333,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 9.4573,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.74090407938258,
1214
+ "grad_norm": 2.5670814514160156,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 9.5009,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.7453142227122381,
1221
+ "grad_norm": 2.6164445877075195,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 9.7775,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.7497243660418964,
1228
+ "grad_norm": 2.614750623703003,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 9.4587,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.7541345093715546,
1235
+ "grad_norm": 2.6944541931152344,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 9.5405,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.7585446527012127,
1242
+ "grad_norm": 2.5363221168518066,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 9.4638,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.762954796030871,
1249
+ "grad_norm": 2.5635743141174316,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 9.5558,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.7673649393605292,
1256
+ "grad_norm": 2.5865283012390137,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 9.2366,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.7717750826901875,
1263
+ "grad_norm": 2.468916177749634,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 9.3768,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.7761852260198456,
1270
+ "grad_norm": 2.4861855506896973,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 9.4156,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.7805953693495039,
1277
+ "grad_norm": 2.5258901119232178,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 9.2959,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.7850055126791621,
1284
+ "grad_norm": 2.4535820484161377,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 9.5271,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.7894156560088202,
1291
+ "grad_norm": 2.4277803897857666,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 9.3665,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.7938257993384785,
1298
+ "grad_norm": 2.5256242752075195,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 9.341,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.7982359426681367,
1305
+ "grad_norm": 2.6025824546813965,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 9.8123,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.802646085997795,
1312
+ "grad_norm": 2.4343557357788086,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 9.4829,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.8070562293274531,
1319
+ "grad_norm": 2.5988001823425293,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 9.7153,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.8114663726571113,
1326
+ "grad_norm": 2.562573194503784,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 9.485,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.8158765159867696,
1333
+ "grad_norm": 2.454115629196167,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 9.3411,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.8202866593164277,
1340
+ "grad_norm": 2.6099281311035156,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 9.4701,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.824696802646086,
1347
+ "grad_norm": 2.6781437397003174,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 9.8366,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.8291069459757442,
1354
+ "grad_norm": 2.4233927726745605,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 9.5856,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.8335170893054025,
1361
+ "grad_norm": 2.722417116165161,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 9.6465,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.8379272326350606,
1368
+ "grad_norm": 2.6799838542938232,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 9.821,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.8423373759647188,
1375
+ "grad_norm": 2.830326795578003,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 9.6341,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.8467475192943771,
1382
+ "grad_norm": 2.969053030014038,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 9.7395,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.8511576626240352,
1389
+ "grad_norm": 3.2237770557403564,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 9.9695,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.8555678059536935,
1396
+ "grad_norm": 3.5367090702056885,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 9.6035,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.8599779492833517,
1403
+ "grad_norm": 3.7807130813598633,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 9.526,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.86438809261301,
1410
+ "grad_norm": 3.813859224319458,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 9.2044,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.8687982359426681,
1417
+ "grad_norm": 4.019887447357178,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 9.0055,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.8732083792723263,
1424
+ "grad_norm": 4.306025981903076,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 9.0699,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.8776185226019846,
1431
+ "grad_norm": 5.382304668426514,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 8.8738,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.8820286659316428,
1438
+ "grad_norm": 6.224758148193359,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 8.9482,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.8820286659316428,
1445
+ "eval_loss": 2.2532453536987305,
1446
+ "eval_runtime": 3.9946,
1447
+ "eval_samples_per_second": 95.63,
1448
+ "eval_steps_per_second": 24.033,
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": 7284189598580736.0,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null