ancient41 commited on
Commit
dec129a
·
verified ·
1 Parent(s): b9ac75f

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 sha256:28c9e5add88542a9b0379d9a567201cb325d3f480b7a62b7772bdb5ccae0d7ad
3
  size 231448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d31cdc953ce821d1fd6be2d27707827920ed01f92a0c304040f38f02dc3c87
3
  size 231448
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e27125129ed7d922f66f969f9f1fb3dfedaa33e617a75abac80eb795cce3b503
3
  size 254576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe3600fa57b08c05d85f3d1dabf23d81d80c8ca41b78f67412d5bc564d2a70c9
3
  size 254576
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:379045d31812f60b642cd0b7529f47164a2e979132b52b9b61f505adf21e54d3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54af720f7bf8580da079dcfb45d2b5b7d13e804ae3856726f52fa0878015b852
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": 10.324746131896973,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.09752925877763328,
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": 463.195,
1090
  "eval_steps_per_second": 115.843,
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": 32559228518400.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.324122428894043,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.13003901170351106,
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": 463.195,
1090
  "eval_steps_per_second": 115.843,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.09817945383615084,
1095
+ "grad_norm": 0.1216152161359787,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 10.3272,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.0988296488946684,
1102
+ "grad_norm": 0.10398002713918686,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 10.3268,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.09947984395318596,
1109
+ "grad_norm": 0.11506969481706619,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 10.3285,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.10013003901170352,
1116
+ "grad_norm": 0.10437972098588943,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 10.3281,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.10078023407022106,
1123
+ "grad_norm": 0.10129734128713608,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 10.328,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.10143042912873862,
1130
+ "grad_norm": 0.11362939327955246,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 10.3251,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.10208062418725618,
1137
+ "grad_norm": 0.10383567959070206,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 10.3251,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.10273081924577374,
1144
+ "grad_norm": 0.10725058615207672,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 10.3275,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.1033810143042913,
1151
+ "grad_norm": 0.11777881532907486,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 10.3254,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.10403120936280884,
1158
+ "grad_norm": 0.10041073709726334,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 10.3268,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.1046814044213264,
1165
+ "grad_norm": 0.09719385951757431,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 10.3279,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.10533159947984395,
1172
+ "grad_norm": 0.09627390652894974,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 10.3275,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.10598179453836151,
1179
+ "grad_norm": 0.11505679041147232,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 10.3267,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.10663198959687907,
1186
+ "grad_norm": 0.0919860377907753,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 10.3235,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.10728218465539661,
1193
+ "grad_norm": 0.10943809896707535,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 10.3274,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.10793237971391417,
1200
+ "grad_norm": 0.09337712824344635,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 10.3284,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.10858257477243173,
1207
+ "grad_norm": 0.08571542054414749,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 10.3259,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.10923276983094929,
1214
+ "grad_norm": 0.10791494697332382,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 10.3239,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.10988296488946683,
1221
+ "grad_norm": 0.09137783199548721,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 10.3338,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.11053315994798439,
1228
+ "grad_norm": 0.09270033240318298,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 10.324,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.11118335500650195,
1235
+ "grad_norm": 0.09181763976812363,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 10.3258,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.11183355006501951,
1242
+ "grad_norm": 0.10405848920345306,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 10.3318,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.11248374512353707,
1249
+ "grad_norm": 0.09887488186359406,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 10.3328,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.11313394018205461,
1256
+ "grad_norm": 0.09410857409238815,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 10.3251,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.11378413524057217,
1263
+ "grad_norm": 0.09131878614425659,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 10.3203,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.11443433029908973,
1270
+ "grad_norm": 0.11112850904464722,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 10.326,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.11508452535760728,
1277
+ "grad_norm": 0.11711225658655167,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 10.3197,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.11573472041612484,
1284
+ "grad_norm": 0.07148018479347229,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 10.3266,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.11638491547464239,
1291
+ "grad_norm": 0.10184058547019958,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 10.3288,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.11703511053315994,
1298
+ "grad_norm": 0.14172475039958954,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 10.3263,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.1176853055916775,
1305
+ "grad_norm": 0.0866977646946907,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 10.3236,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.11833550065019506,
1312
+ "grad_norm": 0.09405398368835449,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 10.3329,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.11898569570871262,
1319
+ "grad_norm": 0.09134174883365631,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 10.3321,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.11963589076723016,
1326
+ "grad_norm": 0.10691911727190018,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 10.3323,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.12028608582574772,
1333
+ "grad_norm": 0.10940374433994293,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 10.3277,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.12093628088426528,
1340
+ "grad_norm": 0.10505640506744385,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 10.3221,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.12158647594278284,
1347
+ "grad_norm": 0.12675940990447998,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 10.3208,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.1222366710013004,
1354
+ "grad_norm": 0.15413792431354523,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 10.3214,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.12288686605981794,
1361
+ "grad_norm": 0.1255342662334442,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 10.3313,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.1235370611183355,
1368
+ "grad_norm": 0.179266557097435,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 10.3249,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.12418725617685306,
1375
+ "grad_norm": 0.17855946719646454,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 10.3213,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.12483745123537061,
1382
+ "grad_norm": 0.1523905098438263,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 10.3158,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.12548764629388817,
1389
+ "grad_norm": 0.17341147363185883,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 10.3153,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.12613784135240572,
1396
+ "grad_norm": 0.17141734063625336,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 10.3119,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.1267880364109233,
1403
+ "grad_norm": 0.22108782827854156,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 10.3104,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.12743823146944083,
1410
+ "grad_norm": 0.25344622135162354,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 10.32,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.12808842652795838,
1417
+ "grad_norm": 0.292223185300827,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 10.3095,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.12873862158647595,
1424
+ "grad_norm": 0.3518892228603363,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 10.2972,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.1293888166449935,
1431
+ "grad_norm": 0.35086145997047424,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 10.3082,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.13003901170351106,
1438
+ "grad_norm": 0.45979052782058716,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 10.3006,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.13003901170351106,
1445
+ "eval_loss": 10.324122428894043,
1446
+ "eval_runtime": 5.6129,
1447
+ "eval_samples_per_second": 461.613,
1448
+ "eval_steps_per_second": 115.448,
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": 43412304691200.0,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null