0x1202 commited on
Commit
5e059a2
·
verified ·
1 Parent(s): 623676b

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:dec6bf8f49f369eefb83dcacbbf00fa4059f824fb49bc13f502dc0e6528472b2
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77835b66136bbbc7690bcb128e3e4eb97602fe56b56cdb5c1b580887dd1d8d33
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c78fb449d24ddefaef121db0e9850c71250fab43dfa01a7ae6c7d94de032e384
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee4b659edf90ea182776fe8a5315a932ce64ddad99ad7b15f7ee5a2c6f8018a
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd24905c365684771848f29aa7309f0a0567630b6dd98b4ba064d55c47751b7b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dceab492eb55d5b625a66b337338737db8eda4331a3228103f2ce6c58d9452cf
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": 0.5096783638000488,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.07796257796257797,
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": 5.155,
1114
  "eval_steps_per_second": 0.722,
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": 2.5105929355237786e+17,
1145
  "train_batch_size": 8,
1146
  "trial_name": null,
1147
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.4919222295284271,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.10395010395010396,
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": 5.155,
1114
  "eval_steps_per_second": 0.722,
1115
  "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 0.07848232848232849,
1119
+ "grad_norm": 0.22046735882759094,
1120
+ "learning_rate": 4.659698863221513e-05,
1121
+ "loss": 0.3254,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 0.079002079002079,
1126
+ "grad_norm": 0.2166861742734909,
1127
+ "learning_rate": 4.481448235912671e-05,
1128
+ "loss": 0.4457,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 0.07952182952182953,
1133
+ "grad_norm": 0.2074378877878189,
1134
+ "learning_rate": 4.306073275629044e-05,
1135
+ "loss": 0.5091,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 0.08004158004158005,
1140
+ "grad_norm": 0.221967875957489,
1141
+ "learning_rate": 4.133621928133665e-05,
1142
+ "loss": 0.4409,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 0.08056133056133057,
1147
+ "grad_norm": 0.20840375125408173,
1148
+ "learning_rate": 3.964141339903026e-05,
1149
+ "loss": 0.4149,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 0.08108108108108109,
1154
+ "grad_norm": 0.23525193333625793,
1155
+ "learning_rate": 3.797677845237696e-05,
1156
+ "loss": 0.4934,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 0.0816008316008316,
1161
+ "grad_norm": 0.25270870327949524,
1162
+ "learning_rate": 3.634276953594982e-05,
1163
+ "loss": 0.5205,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 0.08212058212058213,
1168
+ "grad_norm": 0.22861601412296295,
1169
+ "learning_rate": 3.473983337147118e-05,
1170
+ "loss": 0.4039,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 0.08264033264033264,
1175
+ "grad_norm": 0.2319110780954361,
1176
+ "learning_rate": 3.316840818568315e-05,
1177
+ "loss": 0.4785,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 0.08316008316008316,
1182
+ "grad_norm": 0.22803109884262085,
1183
+ "learning_rate": 3.162892359054098e-05,
1184
+ "loss": 0.486,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 0.08367983367983368,
1189
+ "grad_norm": 0.24335117638111115,
1190
+ "learning_rate": 3.0121800465761293e-05,
1191
+ "loss": 0.4956,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 0.0841995841995842,
1196
+ "grad_norm": 0.23986086249351501,
1197
+ "learning_rate": 2.8647450843757897e-05,
1198
+ "loss": 0.566,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 0.08471933471933472,
1203
+ "grad_norm": 0.24391090869903564,
1204
+ "learning_rate": 2.7206277796996144e-05,
1205
+ "loss": 0.5142,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 0.08523908523908524,
1210
+ "grad_norm": 0.29568424820899963,
1211
+ "learning_rate": 2.5798675327796993e-05,
1212
+ "loss": 0.6023,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 0.08575883575883576,
1217
+ "grad_norm": 0.2564331591129303,
1218
+ "learning_rate": 2.4425028260620715e-05,
1219
+ "loss": 0.5528,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 0.08627858627858628,
1224
+ "grad_norm": 0.2405325472354889,
1225
+ "learning_rate": 2.3085712136859668e-05,
1226
+ "loss": 0.4999,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 0.0867983367983368,
1231
+ "grad_norm": 0.2567991018295288,
1232
+ "learning_rate": 2.178109311216913e-05,
1233
+ "loss": 0.5486,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 0.08731808731808732,
1238
+ "grad_norm": 0.2838067412376404,
1239
+ "learning_rate": 2.0511527856363912e-05,
1240
+ "loss": 0.5459,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 0.08783783783783784,
1245
+ "grad_norm": 0.2707315683364868,
1246
+ "learning_rate": 1.927736345590839e-05,
1247
+ "loss": 0.5376,
1248
+ "step": 169
1249
+ },
1250
+ {
1251
+ "epoch": 0.08835758835758836,
1252
+ "grad_norm": 0.26636192202568054,
1253
+ "learning_rate": 1.8078937319026654e-05,
1254
+ "loss": 0.535,
1255
+ "step": 170
1256
+ },
1257
+ {
1258
+ "epoch": 0.08887733887733888,
1259
+ "grad_norm": 0.26214924454689026,
1260
+ "learning_rate": 1.6916577083458228e-05,
1261
+ "loss": 0.5322,
1262
+ "step": 171
1263
+ },
1264
+ {
1265
+ "epoch": 0.0893970893970894,
1266
+ "grad_norm": 0.2562224566936493,
1267
+ "learning_rate": 1.579060052688548e-05,
1268
+ "loss": 0.5278,
1269
+ "step": 172
1270
+ },
1271
+ {
1272
+ "epoch": 0.08991683991683992,
1273
+ "grad_norm": 0.30574294924736023,
1274
+ "learning_rate": 1.4701315480056164e-05,
1275
+ "loss": 0.5209,
1276
+ "step": 173
1277
+ },
1278
+ {
1279
+ "epoch": 0.09043659043659044,
1280
+ "grad_norm": 0.3442355692386627,
1281
+ "learning_rate": 1.3649019742625623e-05,
1282
+ "loss": 0.5682,
1283
+ "step": 174
1284
+ },
1285
+ {
1286
+ "epoch": 0.09095634095634096,
1287
+ "grad_norm": 0.2936060428619385,
1288
+ "learning_rate": 1.2634001001741373e-05,
1289
+ "loss": 0.5359,
1290
+ "step": 175
1291
+ },
1292
+ {
1293
+ "epoch": 0.09095634095634096,
1294
+ "eval_loss": 0.4958566725254059,
1295
+ "eval_runtime": 10.7748,
1296
+ "eval_samples_per_second": 4.64,
1297
+ "eval_steps_per_second": 0.65,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 0.09147609147609148,
1302
+ "grad_norm": 0.34981048107147217,
1303
+ "learning_rate": 1.1656536753392287e-05,
1304
+ "loss": 0.543,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 0.091995841995842,
1309
+ "grad_norm": 0.38105377554893494,
1310
+ "learning_rate": 1.0716894226543953e-05,
1311
+ "loss": 0.573,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 0.09251559251559252,
1316
+ "grad_norm": 0.3455210328102112,
1317
+ "learning_rate": 9.815330310080887e-06,
1318
+ "loss": 0.4597,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 0.09303534303534304,
1323
+ "grad_norm": 0.388644814491272,
1324
+ "learning_rate": 8.952091482575824e-06,
1325
+ "loss": 0.5382,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 0.09355509355509356,
1330
+ "grad_norm": 0.3758420944213867,
1331
+ "learning_rate": 8.127413744904804e-06,
1332
+ "loss": 0.5452,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 0.09407484407484408,
1337
+ "grad_norm": 0.4773421585559845,
1338
+ "learning_rate": 7.34152255572697e-06,
1339
+ "loss": 0.5899,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 0.0945945945945946,
1344
+ "grad_norm": 0.3917699158191681,
1345
+ "learning_rate": 6.594632769846353e-06,
1346
+ "loss": 0.5736,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 0.09511434511434512,
1351
+ "grad_norm": 0.5945054292678833,
1352
+ "learning_rate": 5.886948579472778e-06,
1353
+ "loss": 0.629,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 0.09563409563409564,
1358
+ "grad_norm": 0.49390462040901184,
1359
+ "learning_rate": 5.218663458397715e-06,
1360
+ "loss": 0.5509,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 0.09615384615384616,
1365
+ "grad_norm": 0.4783254861831665,
1366
+ "learning_rate": 4.589960109100444e-06,
1367
+ "loss": 0.5791,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 0.09667359667359668,
1372
+ "grad_norm": 0.5506903529167175,
1373
+ "learning_rate": 4.001010412799138e-06,
1374
+ "loss": 0.52,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 0.0971933471933472,
1379
+ "grad_norm": 0.5402777194976807,
1380
+ "learning_rate": 3.451975382460109e-06,
1381
+ "loss": 0.6098,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 0.09771309771309772,
1386
+ "grad_norm": 0.6247908473014832,
1387
+ "learning_rate": 2.9430051187785962e-06,
1388
+ "loss": 0.5823,
1389
+ "step": 188
1390
+ },
1391
+ {
1392
+ "epoch": 0.09823284823284824,
1393
+ "grad_norm": 0.6075006723403931,
1394
+ "learning_rate": 2.4742387691426445e-06,
1395
+ "loss": 0.6047,
1396
+ "step": 189
1397
+ },
1398
+ {
1399
+ "epoch": 0.09875259875259876,
1400
+ "grad_norm": 0.6293641328811646,
1401
+ "learning_rate": 2.0458044895916513e-06,
1402
+ "loss": 0.648,
1403
+ "step": 190
1404
+ },
1405
+ {
1406
+ "epoch": 0.09927234927234928,
1407
+ "grad_norm": 0.656559944152832,
1408
+ "learning_rate": 1.6578194097797258e-06,
1409
+ "loss": 0.5545,
1410
+ "step": 191
1411
+ },
1412
+ {
1413
+ "epoch": 0.0997920997920998,
1414
+ "grad_norm": 0.6681039333343506,
1415
+ "learning_rate": 1.3103896009537207e-06,
1416
+ "loss": 0.6438,
1417
+ "step": 192
1418
+ },
1419
+ {
1420
+ "epoch": 0.10031185031185032,
1421
+ "grad_norm": 0.9185191988945007,
1422
+ "learning_rate": 1.0036100469542786e-06,
1423
+ "loss": 0.625,
1424
+ "step": 193
1425
+ },
1426
+ {
1427
+ "epoch": 0.10083160083160084,
1428
+ "grad_norm": 0.7245170474052429,
1429
+ "learning_rate": 7.375646182482875e-07,
1430
+ "loss": 0.6581,
1431
+ "step": 194
1432
+ },
1433
+ {
1434
+ "epoch": 0.10135135135135136,
1435
+ "grad_norm": 0.8444747924804688,
1436
+ "learning_rate": 5.123260489995229e-07,
1437
+ "loss": 0.7302,
1438
+ "step": 195
1439
+ },
1440
+ {
1441
+ "epoch": 0.10187110187110188,
1442
+ "grad_norm": 0.8954965472221375,
1443
+ "learning_rate": 3.2795591718381975e-07,
1444
+ "loss": 0.6679,
1445
+ "step": 196
1446
+ },
1447
+ {
1448
+ "epoch": 0.1023908523908524,
1449
+ "grad_norm": 0.9438778758049011,
1450
+ "learning_rate": 1.8450462775428942e-07,
1451
+ "loss": 0.6426,
1452
+ "step": 197
1453
+ },
1454
+ {
1455
+ "epoch": 0.10291060291060292,
1456
+ "grad_norm": 0.9339571595191956,
1457
+ "learning_rate": 8.201139886109264e-08,
1458
+ "loss": 0.7167,
1459
+ "step": 198
1460
+ },
1461
+ {
1462
+ "epoch": 0.10343035343035344,
1463
+ "grad_norm": 1.101068377494812,
1464
+ "learning_rate": 2.0504251129649374e-08,
1465
+ "loss": 0.7554,
1466
+ "step": 199
1467
+ },
1468
+ {
1469
+ "epoch": 0.10395010395010396,
1470
+ "grad_norm": 1.1291167736053467,
1471
+ "learning_rate": 0.0,
1472
+ "loss": 0.687,
1473
+ "step": 200
1474
+ },
1475
+ {
1476
+ "epoch": 0.10395010395010396,
1477
+ "eval_loss": 0.4919222295284271,
1478
+ "eval_runtime": 10.7529,
1479
+ "eval_samples_per_second": 4.65,
1480
+ "eval_steps_per_second": 0.651,
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": 3.350084764827648e+17,
1511
  "train_batch_size": 8,
1512
  "trial_name": null,
1513
  "trial_params": null