0x1202 commited on
Commit
de66d38
1 Parent(s): feba65e

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:a18a1b14748d8b4db7db74a142e1902d53a3e2bd03c119f29ddb6f3abbd02604
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f64519c99b2c312cb1f57d9107d425128afc361f0f2925f0060b09b555564fa
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2aadffe177a513af10bd3ba9bc1059364dd7ec579f109342e9b4b2ec194fb520
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8a1b598f31c8449eb58f8d6bc777721909d28519352e3e36317113d7a3d945
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1a12c05fdd0239884b6dbc91fa003ab5c9eb48317a39524098ff9406f6c0ee2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13f1cb76d2fd1cb8c08c6c4fdc62917f4648b9e462f5576ed11de46a9b2ac3c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e70710c409284f74d525f8db5cfaccc22a8afd29416f19c595da9242ec92d936
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe157715eb8e05b3bab2a7f2fafac33705dc4a1a9dd7f6d860c3a7f9597d78bb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.9701613783836365,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.08042221663734607,
5
  "eval_steps": 25,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1113,6 +1113,372 @@
1113
  "eval_samples_per_second": 7.141,
1114
  "eval_steps_per_second": 7.141,
1115
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1116
  }
1117
  ],
1118
  "logging_steps": 1,
@@ -1136,12 +1502,12 @@
1136
  "should_evaluate": false,
1137
  "should_log": false,
1138
  "should_save": true,
1139
- "should_training_stop": false
1140
  },
1141
  "attributes": {}
1142
  }
1143
  },
1144
- "total_flos": 2.0881258502632243e+17,
1145
  "train_batch_size": 1,
1146
  "trial_name": null,
1147
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9611303806304932,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.10722962218312809,
5
  "eval_steps": 25,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1113
  "eval_samples_per_second": 7.141,
1114
  "eval_steps_per_second": 7.141,
1115
  "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 0.08095836474826171,
1119
+ "grad_norm": 5.198462009429932,
1120
+ "learning_rate": 4.659698863221513e-05,
1121
+ "loss": 24.5072,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 0.08149451285917735,
1126
+ "grad_norm": 4.549412250518799,
1127
+ "learning_rate": 4.481448235912671e-05,
1128
+ "loss": 26.2581,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 0.08203066097009298,
1133
+ "grad_norm": 4.362401485443115,
1134
+ "learning_rate": 4.306073275629044e-05,
1135
+ "loss": 27.6788,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 0.08256680908100864,
1140
+ "grad_norm": 5.346713066101074,
1141
+ "learning_rate": 4.133621928133665e-05,
1142
+ "loss": 30.5177,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 0.08310295719192427,
1147
+ "grad_norm": 4.8502702713012695,
1148
+ "learning_rate": 3.964141339903026e-05,
1149
+ "loss": 27.5227,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 0.08363910530283991,
1154
+ "grad_norm": 4.808586120605469,
1155
+ "learning_rate": 3.797677845237696e-05,
1156
+ "loss": 30.8657,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 0.08417525341375555,
1161
+ "grad_norm": 4.663094997406006,
1162
+ "learning_rate": 3.634276953594982e-05,
1163
+ "loss": 29.7888,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 0.08471140152467119,
1168
+ "grad_norm": 5.056007385253906,
1169
+ "learning_rate": 3.473983337147118e-05,
1170
+ "loss": 29.6446,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 0.08524754963558683,
1175
+ "grad_norm": 4.635434150695801,
1176
+ "learning_rate": 3.316840818568315e-05,
1177
+ "loss": 29.1428,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 0.08578369774650248,
1182
+ "grad_norm": 4.840639591217041,
1183
+ "learning_rate": 3.162892359054098e-05,
1184
+ "loss": 29.1692,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 0.08631984585741811,
1189
+ "grad_norm": 4.706408977508545,
1190
+ "learning_rate": 3.0121800465761293e-05,
1191
+ "loss": 30.8735,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 0.08685599396833375,
1196
+ "grad_norm": 4.438312530517578,
1197
+ "learning_rate": 2.8647450843757897e-05,
1198
+ "loss": 29.7526,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 0.08739214207924939,
1203
+ "grad_norm": 4.957245349884033,
1204
+ "learning_rate": 2.7206277796996144e-05,
1205
+ "loss": 31.258,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 0.08792829019016503,
1210
+ "grad_norm": 4.573652267456055,
1211
+ "learning_rate": 2.5798675327796993e-05,
1212
+ "loss": 30.8789,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 0.08846443830108067,
1217
+ "grad_norm": 4.697335243225098,
1218
+ "learning_rate": 2.4425028260620715e-05,
1219
+ "loss": 30.2755,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 0.08900058641199632,
1224
+ "grad_norm": 4.690494060516357,
1225
+ "learning_rate": 2.3085712136859668e-05,
1226
+ "loss": 29.9391,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 0.08953673452291196,
1231
+ "grad_norm": 4.9841694831848145,
1232
+ "learning_rate": 2.178109311216913e-05,
1233
+ "loss": 27.8766,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 0.0900728826338276,
1238
+ "grad_norm": 5.224708557128906,
1239
+ "learning_rate": 2.0511527856363912e-05,
1240
+ "loss": 29.0932,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 0.09060903074474323,
1245
+ "grad_norm": 4.802592754364014,
1246
+ "learning_rate": 1.927736345590839e-05,
1247
+ "loss": 30.957,
1248
+ "step": 169
1249
+ },
1250
+ {
1251
+ "epoch": 0.09114517885565887,
1252
+ "grad_norm": 4.843587398529053,
1253
+ "learning_rate": 1.8078937319026654e-05,
1254
+ "loss": 30.3239,
1255
+ "step": 170
1256
+ },
1257
+ {
1258
+ "epoch": 0.09168132696657452,
1259
+ "grad_norm": 4.917239665985107,
1260
+ "learning_rate": 1.6916577083458228e-05,
1261
+ "loss": 30.4517,
1262
+ "step": 171
1263
+ },
1264
+ {
1265
+ "epoch": 0.09221747507749016,
1266
+ "grad_norm": 4.622511863708496,
1267
+ "learning_rate": 1.579060052688548e-05,
1268
+ "loss": 29.1561,
1269
+ "step": 172
1270
+ },
1271
+ {
1272
+ "epoch": 0.0927536231884058,
1273
+ "grad_norm": 5.174027919769287,
1274
+ "learning_rate": 1.4701315480056164e-05,
1275
+ "loss": 28.5216,
1276
+ "step": 173
1277
+ },
1278
+ {
1279
+ "epoch": 0.09328977129932144,
1280
+ "grad_norm": 5.131156921386719,
1281
+ "learning_rate": 1.3649019742625623e-05,
1282
+ "loss": 30.5295,
1283
+ "step": 174
1284
+ },
1285
+ {
1286
+ "epoch": 0.09382591941023707,
1287
+ "grad_norm": 5.090980052947998,
1288
+ "learning_rate": 1.2634001001741373e-05,
1289
+ "loss": 30.1167,
1290
+ "step": 175
1291
+ },
1292
+ {
1293
+ "epoch": 0.09382591941023707,
1294
+ "eval_loss": 0.961780846118927,
1295
+ "eval_runtime": 7.0068,
1296
+ "eval_samples_per_second": 7.136,
1297
+ "eval_steps_per_second": 7.136,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 0.09436206752115271,
1302
+ "grad_norm": 5.299232006072998,
1303
+ "learning_rate": 1.1656536753392287e-05,
1304
+ "loss": 29.9242,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 0.09489821563206836,
1309
+ "grad_norm": 5.412871837615967,
1310
+ "learning_rate": 1.0716894226543953e-05,
1311
+ "loss": 31.6097,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 0.095434363742984,
1316
+ "grad_norm": 5.443716526031494,
1317
+ "learning_rate": 9.815330310080887e-06,
1318
+ "loss": 32.2806,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 0.09597051185389964,
1323
+ "grad_norm": 5.2226080894470215,
1324
+ "learning_rate": 8.952091482575824e-06,
1325
+ "loss": 32.0395,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 0.09650665996481528,
1330
+ "grad_norm": 5.585422039031982,
1331
+ "learning_rate": 8.127413744904804e-06,
1332
+ "loss": 32.5046,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 0.09704280807573092,
1337
+ "grad_norm": 5.256342887878418,
1338
+ "learning_rate": 7.34152255572697e-06,
1339
+ "loss": 29.7976,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 0.09757895618664657,
1344
+ "grad_norm": 5.678742408752441,
1345
+ "learning_rate": 6.594632769846353e-06,
1346
+ "loss": 31.166,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 0.0981151042975622,
1351
+ "grad_norm": 5.608844757080078,
1352
+ "learning_rate": 5.886948579472778e-06,
1353
+ "loss": 31.462,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 0.09865125240847784,
1358
+ "grad_norm": 5.735723495483398,
1359
+ "learning_rate": 5.218663458397715e-06,
1360
+ "loss": 32.3888,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 0.09918740051939348,
1365
+ "grad_norm": 5.686238765716553,
1366
+ "learning_rate": 4.589960109100444e-06,
1367
+ "loss": 32.2446,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 0.09972354863030912,
1372
+ "grad_norm": 6.456745147705078,
1373
+ "learning_rate": 4.001010412799138e-06,
1374
+ "loss": 31.8302,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 0.10025969674122476,
1379
+ "grad_norm": 6.2624192237854,
1380
+ "learning_rate": 3.451975382460109e-06,
1381
+ "loss": 32.1222,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 0.10079584485214041,
1386
+ "grad_norm": 6.031360149383545,
1387
+ "learning_rate": 2.9430051187785962e-06,
1388
+ "loss": 30.3575,
1389
+ "step": 188
1390
+ },
1391
+ {
1392
+ "epoch": 0.10133199296305605,
1393
+ "grad_norm": 6.787166595458984,
1394
+ "learning_rate": 2.4742387691426445e-06,
1395
+ "loss": 33.5298,
1396
+ "step": 189
1397
+ },
1398
+ {
1399
+ "epoch": 0.10186814107397169,
1400
+ "grad_norm": 7.786647796630859,
1401
+ "learning_rate": 2.0458044895916513e-06,
1402
+ "loss": 33.5317,
1403
+ "step": 190
1404
+ },
1405
+ {
1406
+ "epoch": 0.10240428918488732,
1407
+ "grad_norm": 7.0574631690979,
1408
+ "learning_rate": 1.6578194097797258e-06,
1409
+ "loss": 30.7742,
1410
+ "step": 191
1411
+ },
1412
+ {
1413
+ "epoch": 0.10294043729580296,
1414
+ "grad_norm": 7.725040912628174,
1415
+ "learning_rate": 1.3103896009537207e-06,
1416
+ "loss": 31.2916,
1417
+ "step": 192
1418
+ },
1419
+ {
1420
+ "epoch": 0.1034765854067186,
1421
+ "grad_norm": 8.722898483276367,
1422
+ "learning_rate": 1.0036100469542786e-06,
1423
+ "loss": 33.509,
1424
+ "step": 193
1425
+ },
1426
+ {
1427
+ "epoch": 0.10401273351763425,
1428
+ "grad_norm": 9.124086380004883,
1429
+ "learning_rate": 7.375646182482875e-07,
1430
+ "loss": 32.766,
1431
+ "step": 194
1432
+ },
1433
+ {
1434
+ "epoch": 0.10454888162854989,
1435
+ "grad_norm": 12.139370918273926,
1436
+ "learning_rate": 5.123260489995229e-07,
1437
+ "loss": 35.1079,
1438
+ "step": 195
1439
+ },
1440
+ {
1441
+ "epoch": 0.10508502973946553,
1442
+ "grad_norm": 13.486305236816406,
1443
+ "learning_rate": 3.2795591718381975e-07,
1444
+ "loss": 33.708,
1445
+ "step": 196
1446
+ },
1447
+ {
1448
+ "epoch": 0.10562117785038116,
1449
+ "grad_norm": 15.585397720336914,
1450
+ "learning_rate": 1.8450462775428942e-07,
1451
+ "loss": 35.6728,
1452
+ "step": 197
1453
+ },
1454
+ {
1455
+ "epoch": 0.1061573259612968,
1456
+ "grad_norm": 17.088029861450195,
1457
+ "learning_rate": 8.201139886109264e-08,
1458
+ "loss": 33.6193,
1459
+ "step": 198
1460
+ },
1461
+ {
1462
+ "epoch": 0.10669347407221245,
1463
+ "grad_norm": 17.898561477661133,
1464
+ "learning_rate": 2.0504251129649374e-08,
1465
+ "loss": 27.5111,
1466
+ "step": 199
1467
+ },
1468
+ {
1469
+ "epoch": 0.10722962218312809,
1470
+ "grad_norm": 28.369626998901367,
1471
+ "learning_rate": 0.0,
1472
+ "loss": 21.8853,
1473
+ "step": 200
1474
+ },
1475
+ {
1476
+ "epoch": 0.10722962218312809,
1477
+ "eval_loss": 0.9611303806304932,
1478
+ "eval_runtime": 7.0035,
1479
+ "eval_samples_per_second": 7.139,
1480
+ "eval_steps_per_second": 7.139,
1481
+ "step": 200
1482
  }
1483
  ],
1484
  "logging_steps": 1,
 
1502
  "should_evaluate": false,
1503
  "should_log": false,
1504
  "should_save": true,
1505
+ "should_training_stop": true
1506
  },
1507
  "attributes": {}
1508
  }
1509
  },
1510
+ "total_flos": 2.784601741716357e+17,
1511
  "train_batch_size": 1,
1512
  "trial_name": null,
1513
  "trial_params": null