prxy5608 commited on
Commit
95bdb47
·
verified ·
1 Parent(s): 3bc40ec

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 sha256:3c4540a07a63c44e3db6c6c5bf0e1a58489f5840d7435fee6063e0413c1262cc
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9a1a2e8bc612276d507c6d3619fda9190d6f596f746092e7943bb0a2104c198
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e4fb7b1a20953e43d5403d3b23ecaf355f406cc67b45ad86049db1468e33962
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c86e6f253400aba6bf8fe0ea1608f93041e250c84d9d2e1a3adeccad757d9c
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:371d010da09a2e78143e8d3dc2084ab741537c6f3efd62834a52bccd8a5d88a3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5010c2660515ae7b1d3645c067bc2f2ce9e2792faf64206fcc04a511b66bec76
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": 2.344456672668457,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.6160164271047228,
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": 9.011,
1090
  "eval_steps_per_second": 2.264,
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": 3.198048786941215e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.3414769172668457,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.8213552361396304,
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": 9.011,
1090
  "eval_steps_per_second": 2.264,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.6201232032854209,
1095
+ "grad_norm": 0.2805425524711609,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 2.3709,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.6242299794661191,
1102
+ "grad_norm": 0.309853732585907,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 2.429,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.6283367556468172,
1109
+ "grad_norm": 0.33582112193107605,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 2.3477,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.6324435318275154,
1116
+ "grad_norm": 0.29468798637390137,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 2.3359,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.6365503080082136,
1123
+ "grad_norm": 0.28757351636886597,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 2.3597,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.6406570841889117,
1130
+ "grad_norm": 0.27962955832481384,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 2.3355,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.6447638603696099,
1137
+ "grad_norm": 0.267606645822525,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 2.3099,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.648870636550308,
1144
+ "grad_norm": 0.257451593875885,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 2.3082,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.6529774127310062,
1151
+ "grad_norm": 0.26463115215301514,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 2.3496,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.6570841889117043,
1158
+ "grad_norm": 0.2509690225124359,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 2.2506,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.6611909650924025,
1165
+ "grad_norm": 0.2563090920448303,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 2.3512,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.6652977412731006,
1172
+ "grad_norm": 0.24937409162521362,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 2.3201,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.6694045174537988,
1179
+ "grad_norm": 0.24155984818935394,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 2.3305,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.6735112936344969,
1186
+ "grad_norm": 0.24877284467220306,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 2.2932,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.6776180698151951,
1193
+ "grad_norm": 0.2494582235813141,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 2.2714,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.6817248459958932,
1200
+ "grad_norm": 0.25818485021591187,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 2.2696,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.6858316221765913,
1207
+ "grad_norm": 0.2597648501396179,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 2.3384,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.6899383983572895,
1214
+ "grad_norm": 0.2583504617214203,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 2.2874,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.6940451745379876,
1221
+ "grad_norm": 0.25682592391967773,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 2.3395,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.6981519507186859,
1228
+ "grad_norm": 0.27451130747795105,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 2.2966,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.702258726899384,
1235
+ "grad_norm": 0.269361287355423,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 2.325,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.7063655030800822,
1242
+ "grad_norm": 0.2751413583755493,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 2.3112,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.7104722792607803,
1249
+ "grad_norm": 0.27977946400642395,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 2.2973,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.7145790554414785,
1256
+ "grad_norm": 0.27026399970054626,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 2.381,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.7186858316221766,
1263
+ "grad_norm": 0.28504830598831177,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 2.2967,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.7227926078028748,
1270
+ "grad_norm": 0.30635881423950195,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 2.276,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.7268993839835729,
1277
+ "grad_norm": 0.2944948077201843,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 2.2743,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.731006160164271,
1284
+ "grad_norm": 0.2819386422634125,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 2.2921,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.7351129363449692,
1291
+ "grad_norm": 0.296308696269989,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 2.3994,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.7392197125256673,
1298
+ "grad_norm": 0.304075688123703,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 2.271,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.7433264887063655,
1305
+ "grad_norm": 0.30602318048477173,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 2.3283,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.7474332648870636,
1312
+ "grad_norm": 0.303476482629776,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 2.3518,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.7515400410677618,
1319
+ "grad_norm": 0.30692949891090393,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 2.3687,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.75564681724846,
1326
+ "grad_norm": 0.32387521862983704,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 2.2876,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.7597535934291582,
1333
+ "grad_norm": 0.3372074365615845,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 2.3528,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.7638603696098563,
1340
+ "grad_norm": 0.3233869671821594,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 2.3374,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.7679671457905544,
1347
+ "grad_norm": 0.3280622661113739,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 2.3641,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.7720739219712526,
1354
+ "grad_norm": 0.32876065373420715,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 2.3269,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.7761806981519507,
1361
+ "grad_norm": 0.33632636070251465,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 2.2996,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.7802874743326489,
1368
+ "grad_norm": 0.3384513556957245,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 2.3976,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.784394250513347,
1375
+ "grad_norm": 0.3339103162288666,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 2.2832,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.7885010266940452,
1382
+ "grad_norm": 0.34259554743766785,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 2.3546,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.7926078028747433,
1389
+ "grad_norm": 0.3554518520832062,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 2.3662,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.7967145790554415,
1396
+ "grad_norm": 0.365813672542572,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 2.2609,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.8008213552361396,
1403
+ "grad_norm": 0.38189005851745605,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 2.4067,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.8049281314168378,
1410
+ "grad_norm": 0.3823890686035156,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 2.3932,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.8090349075975359,
1417
+ "grad_norm": 0.39428114891052246,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 2.3534,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.813141683778234,
1424
+ "grad_norm": 0.4303341805934906,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 2.39,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.8172484599589322,
1431
+ "grad_norm": 0.4249311089515686,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 2.4358,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.8213552361396304,
1438
+ "grad_norm": 0.5224833488464355,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 2.3921,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.8213552361396304,
1445
+ "eval_loss": 2.3414769172668457,
1446
+ "eval_runtime": 45.2628,
1447
+ "eval_samples_per_second": 9.058,
1448
+ "eval_steps_per_second": 2.276,
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": 4.2577795760101786e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null