prxy5607 commited on
Commit
1c9f19f
·
verified ·
1 Parent(s): 16bd8c5

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:e46fa8353695cc95f2bc606ea274e5822379a8ac2248ad7438b8f32634e26a88
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee2f4f823dd2ef0079cae544764b51f345f6aaa965c274f09ff69b8a0ae2c9f2
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38d37b6d91fa2dc3ddc1501bfe619f5f409341d1e1d2e6af4b6882056e4bb595
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2387361e965fa58d0d419e001115de84cf81e17665c4dc4e663ff32a5a26147c
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69bc201d8a9ab4eddc14ed00b9c74bea4a8a72499b6aa80ae5c57ce8386d1675
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a071f235e1e13263efd511ea37cc9dcde0e3812ad9524a742c2ab3535acfd06
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": 10.259008407592773,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.11985617259288853,
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": 424.968,
1090
  "eval_steps_per_second": 106.242,
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": 16732599091200.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.256814956665039,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.15980823012385137,
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": 424.968,
1090
  "eval_steps_per_second": 106.242,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.1206552137435078,
1095
+ "grad_norm": 0.11307033151388168,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 10.2621,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.12145425489412705,
1102
+ "grad_norm": 0.1421271562576294,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 10.2639,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.1222532960447463,
1109
+ "grad_norm": 0.10157382488250732,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 10.2586,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.12305233719536555,
1116
+ "grad_norm": 0.10615262389183044,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 10.2631,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.12385137834598482,
1123
+ "grad_norm": 0.09729348868131638,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 10.2604,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.12465041949660408,
1130
+ "grad_norm": 0.10905560851097107,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 10.2613,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.12544946064722334,
1137
+ "grad_norm": 0.0928855687379837,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 10.2615,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.12624850179784258,
1144
+ "grad_norm": 0.09943735599517822,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 10.2599,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.12704754294846185,
1151
+ "grad_norm": 0.09758269786834717,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 10.2583,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.1278465840990811,
1158
+ "grad_norm": 0.09555096924304962,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 10.2635,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.12864562524970036,
1165
+ "grad_norm": 0.09856700897216797,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 10.2606,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.12944466640031962,
1172
+ "grad_norm": 0.08741050213575363,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 10.2602,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.13024370755093886,
1179
+ "grad_norm": 0.10356659442186356,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 10.2581,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.13104274870155813,
1186
+ "grad_norm": 0.09480134397745132,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 10.2614,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.1318417898521774,
1193
+ "grad_norm": 0.09263721853494644,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 10.2597,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.13264083100279664,
1200
+ "grad_norm": 0.11439311504364014,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 10.2593,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.1334398721534159,
1207
+ "grad_norm": 0.10179632157087326,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 10.2588,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.13423891330403515,
1214
+ "grad_norm": 0.09949158132076263,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 10.2581,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.1350379544546544,
1221
+ "grad_norm": 0.09866398572921753,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 10.2562,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.13583699560527368,
1228
+ "grad_norm": 0.09820633381605148,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 10.2578,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.13663603675589292,
1235
+ "grad_norm": 0.08538760989904404,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 10.2561,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.1374350779065122,
1242
+ "grad_norm": 0.08216796070337296,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 10.2581,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.13823411905713145,
1249
+ "grad_norm": 0.10514167696237564,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 10.2582,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.1390331602077507,
1256
+ "grad_norm": 0.08929797261953354,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 10.2597,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.13983220135836996,
1263
+ "grad_norm": 0.09239036589860916,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 10.2589,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.1406312425089892,
1270
+ "grad_norm": 0.10553207248449326,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 10.2562,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.14143028365960847,
1277
+ "grad_norm": 0.11806043237447739,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 10.2575,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.14222932481022774,
1284
+ "grad_norm": 0.09203515201807022,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 10.2604,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.14302836596084698,
1291
+ "grad_norm": 0.09313210844993591,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 10.2581,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.14382740711146624,
1298
+ "grad_norm": 0.0929274708032608,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 10.2603,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.1446264482620855,
1305
+ "grad_norm": 0.09198065102100372,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 10.2575,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.14542548941270475,
1312
+ "grad_norm": 0.09558261185884476,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 10.2574,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.14622453056332402,
1319
+ "grad_norm": 0.09891287982463837,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 10.2586,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.14702357171394326,
1326
+ "grad_norm": 0.11207792907953262,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 10.2582,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.14782261286456252,
1333
+ "grad_norm": 0.09039048105478287,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 10.2556,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.1486216540151818,
1340
+ "grad_norm": 0.10318996012210846,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 10.2554,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.14942069516580103,
1347
+ "grad_norm": 0.09999803453683853,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 10.2558,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.1502197363164203,
1354
+ "grad_norm": 0.10861246287822723,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 10.2547,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.15101877746703954,
1361
+ "grad_norm": 0.11095039546489716,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 10.2595,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.1518178186176588,
1368
+ "grad_norm": 0.0924580916762352,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 10.2557,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.15261685976827807,
1375
+ "grad_norm": 0.12392506003379822,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 10.2568,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.1534159009188973,
1382
+ "grad_norm": 0.10083447396755219,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 10.2556,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.15421494206951658,
1389
+ "grad_norm": 0.11406996101140976,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 10.2564,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.15501398322013585,
1396
+ "grad_norm": 0.1480221152305603,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 10.2585,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.1558130243707551,
1403
+ "grad_norm": 0.1505753993988037,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 10.2574,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.15661206552137436,
1410
+ "grad_norm": 0.13065196573734283,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 10.2604,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.1574111066719936,
1417
+ "grad_norm": 0.15071333944797516,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 10.2567,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.15821014782261286,
1424
+ "grad_norm": 0.14649927616119385,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 10.254,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.15900918897323213,
1431
+ "grad_norm": 0.16115695238113403,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 10.2606,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.15980823012385137,
1438
+ "grad_norm": 0.19387610256671906,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 10.2609,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.15980823012385137,
1445
+ "eval_loss": 10.256814956665039,
1446
+ "eval_runtime": 5.005,
1447
+ "eval_samples_per_second": 421.178,
1448
+ "eval_steps_per_second": 105.295,
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": 22310132121600.0,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null