prxy5605 commited on
Commit
c2d7ea3
·
verified ·
1 Parent(s): dce97b3

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 sha256:8674c4857d86cff24cba072c2b541b830bc871f68c3dfa393082fecd1816b215
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2ef02ce27c8aad4dfa5798e2a99f1f0911ceb6149328fbf5c9f4c21434b4df
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43e9cb9ba608f95f54ae254d2f2110070fd2b10f727b39af981b94ccab5dc3d4
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f032622ff8918ccf32030b132b9e73354f023c481c9ec089372bf85f5f84a12b
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f561c8f873ea0b5dfb5639d1c4834359f395f862f04c10d1f68400083b0bed5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016b0a04bcf8b8804250e0f1db4d0cba5dfab4d4f62a8110c21ffa6c4bc4b65a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
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": 0.3925303518772125,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.09468202619536058,
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": 11.092,
1090
  "eval_steps_per_second": 5.546,
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": 2.3933441700318413e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.38890671730041504,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.1262427015938141,
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": 11.092,
1090
  "eval_steps_per_second": 5.546,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.09531323970332965,
1095
+ "grad_norm": 0.9829754829406738,
1096
+ "learning_rate": 1.7197048550474643e-05,
1097
+ "loss": 0.9275,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.09594445321129873,
1102
+ "grad_norm": 1.0895384550094604,
1103
+ "learning_rate": 1.6543469682057106e-05,
1104
+ "loss": 1.1512,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.09657566671926779,
1109
+ "grad_norm": 1.1453516483306885,
1110
+ "learning_rate": 1.5900081996875083e-05,
1111
+ "loss": 1.2615,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.09720688022723686,
1116
+ "grad_norm": 1.2454159259796143,
1117
+ "learning_rate": 1.526708147705013e-05,
1118
+ "loss": 1.4501,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.09783809373520594,
1123
+ "grad_norm": 1.273112177848816,
1124
+ "learning_rate": 1.4644660940672627e-05,
1125
+ "loss": 1.3519,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.098469307243175,
1130
+ "grad_norm": 1.3017650842666626,
1131
+ "learning_rate": 1.4033009983067452e-05,
1132
+ "loss": 1.4724,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.09910052075114407,
1137
+ "grad_norm": 1.2280182838439941,
1138
+ "learning_rate": 1.3432314919041478e-05,
1139
+ "loss": 1.2936,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.09973173425911315,
1144
+ "grad_norm": 1.365878701210022,
1145
+ "learning_rate": 1.2842758726130283e-05,
1146
+ "loss": 1.4915,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.10036294776708221,
1151
+ "grad_norm": 1.3801015615463257,
1152
+ "learning_rate": 1.22645209888614e-05,
1153
+ "loss": 1.4224,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.10099416127505129,
1158
+ "grad_norm": 1.328890085220337,
1159
+ "learning_rate": 1.1697777844051105e-05,
1160
+ "loss": 1.3808,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.10162537478302036,
1165
+ "grad_norm": 1.4287265539169312,
1166
+ "learning_rate": 1.1142701927151456e-05,
1167
+ "loss": 1.6477,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.10225658829098942,
1172
+ "grad_norm": 1.3774094581604004,
1173
+ "learning_rate": 1.0599462319663905e-05,
1174
+ "loss": 1.5419,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.1028878017989585,
1179
+ "grad_norm": 1.4486933946609497,
1180
+ "learning_rate": 1.006822449763537e-05,
1181
+ "loss": 1.5195,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.10351901530692757,
1186
+ "grad_norm": 1.4375733137130737,
1187
+ "learning_rate": 9.549150281252633e-06,
1188
+ "loss": 1.7109,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.10415022881489663,
1193
+ "grad_norm": 1.4317312240600586,
1194
+ "learning_rate": 9.042397785550405e-06,
1195
+ "loss": 1.4966,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.10478144232286571,
1200
+ "grad_norm": 1.5089269876480103,
1201
+ "learning_rate": 8.548121372247918e-06,
1202
+ "loss": 1.5649,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.10541265583083478,
1207
+ "grad_norm": 1.5436687469482422,
1208
+ "learning_rate": 8.066471602728803e-06,
1209
+ "loss": 1.6303,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.10604386933880385,
1214
+ "grad_norm": 1.5016186237335205,
1215
+ "learning_rate": 7.597595192178702e-06,
1216
+ "loss": 1.6437,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.10667508284677292,
1221
+ "grad_norm": 1.5110390186309814,
1222
+ "learning_rate": 7.1416349648943894e-06,
1223
+ "loss": 1.5768,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.107306296354742,
1228
+ "grad_norm": 1.5523266792297363,
1229
+ "learning_rate": 6.698729810778065e-06,
1230
+ "loss": 1.7035,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.10793750986271106,
1235
+ "grad_norm": 1.5230318307876587,
1236
+ "learning_rate": 6.269014643030213e-06,
1237
+ "loss": 1.5579,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.10856872337068013,
1242
+ "grad_norm": 1.508470892906189,
1243
+ "learning_rate": 5.852620357053651e-06,
1244
+ "loss": 1.5116,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.1091999368786492,
1249
+ "grad_norm": 1.504398226737976,
1250
+ "learning_rate": 5.449673790581611e-06,
1251
+ "loss": 1.4858,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.10983115038661827,
1256
+ "grad_norm": 1.4883153438568115,
1257
+ "learning_rate": 5.060297685041659e-06,
1258
+ "loss": 1.7057,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.11046236389458734,
1263
+ "grad_norm": 1.4853483438491821,
1264
+ "learning_rate": 4.684610648167503e-06,
1265
+ "loss": 1.5148,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.11109357740255642,
1270
+ "grad_norm": 1.553637981414795,
1271
+ "learning_rate": 4.322727117869951e-06,
1272
+ "loss": 1.6167,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.11172479091052548,
1277
+ "grad_norm": 1.578129529953003,
1278
+ "learning_rate": 3.974757327377981e-06,
1279
+ "loss": 1.5491,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.11235600441849455,
1284
+ "grad_norm": 1.5624874830245972,
1285
+ "learning_rate": 3.6408072716606346e-06,
1286
+ "loss": 1.6006,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.11298721792646363,
1291
+ "grad_norm": 1.5715187788009644,
1292
+ "learning_rate": 3.3209786751399187e-06,
1293
+ "loss": 1.6976,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.11361843143443269,
1298
+ "grad_norm": 1.6272014379501343,
1299
+ "learning_rate": 3.0153689607045845e-06,
1300
+ "loss": 1.6757,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.11424964494240177,
1305
+ "grad_norm": 1.546974539756775,
1306
+ "learning_rate": 2.724071220034158e-06,
1307
+ "loss": 1.5974,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.11488085845037084,
1312
+ "grad_norm": 1.6230578422546387,
1313
+ "learning_rate": 2.4471741852423237e-06,
1314
+ "loss": 1.6203,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.11551207195833992,
1319
+ "grad_norm": 1.5810596942901611,
1320
+ "learning_rate": 2.1847622018482283e-06,
1321
+ "loss": 1.5336,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.11614328546630898,
1326
+ "grad_norm": 1.7239481210708618,
1327
+ "learning_rate": 1.9369152030840556e-06,
1328
+ "loss": 1.676,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.11677449897427805,
1333
+ "grad_norm": 1.6532574892044067,
1334
+ "learning_rate": 1.70370868554659e-06,
1335
+ "loss": 1.8418,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.11740571248224713,
1340
+ "grad_norm": 1.6952757835388184,
1341
+ "learning_rate": 1.4852136862001764e-06,
1342
+ "loss": 1.5633,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.11803692599021619,
1347
+ "grad_norm": 1.7153465747833252,
1348
+ "learning_rate": 1.2814967607382432e-06,
1349
+ "loss": 1.6121,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.11866813949818526,
1354
+ "grad_norm": 1.8238195180892944,
1355
+ "learning_rate": 1.0926199633097157e-06,
1356
+ "loss": 1.8494,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.11929935300615434,
1361
+ "grad_norm": 1.7845555543899536,
1362
+ "learning_rate": 9.186408276168013e-07,
1363
+ "loss": 1.6834,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.1199305665141234,
1368
+ "grad_norm": 1.8193535804748535,
1369
+ "learning_rate": 7.596123493895991e-07,
1370
+ "loss": 1.624,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.12056178002209247,
1375
+ "grad_norm": 1.7187602519989014,
1376
+ "learning_rate": 6.15582970243117e-07,
1377
+ "loss": 1.6485,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.12119299353006155,
1382
+ "grad_norm": 1.9166899919509888,
1383
+ "learning_rate": 4.865965629214819e-07,
1384
+ "loss": 1.8563,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.12182420703803061,
1389
+ "grad_norm": 1.856611728668213,
1390
+ "learning_rate": 3.7269241793390085e-07,
1391
+ "loss": 1.7069,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.12245542054599969,
1396
+ "grad_norm": 1.9729714393615723,
1397
+ "learning_rate": 2.7390523158633554e-07,
1398
+ "loss": 1.6582,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.12308663405396876,
1403
+ "grad_norm": 1.8488212823867798,
1404
+ "learning_rate": 1.9026509541272275e-07,
1405
+ "loss": 1.5962,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.12371784756193782,
1410
+ "grad_norm": 1.8829165697097778,
1411
+ "learning_rate": 1.2179748700879012e-07,
1412
+ "loss": 1.6283,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.1243490610699069,
1417
+ "grad_norm": 2.0195155143737793,
1418
+ "learning_rate": 6.852326227130834e-08,
1419
+ "loss": 1.5913,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.12498027457787597,
1424
+ "grad_norm": 1.976454257965088,
1425
+ "learning_rate": 3.04586490452119e-08,
1426
+ "loss": 1.4226,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.12561148808584505,
1431
+ "grad_norm": 2.081446647644043,
1432
+ "learning_rate": 7.615242180436522e-09,
1433
+ "loss": 1.3406,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.1262427015938141,
1438
+ "grad_norm": 2.4766805171966553,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 1.5761,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.1262427015938141,
1445
+ "eval_loss": 0.38890671730041504,
1446
+ "eval_runtime": 240.7623,
1447
+ "eval_samples_per_second": 11.081,
1448
+ "eval_steps_per_second": 5.541,
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": 3.194703055064924e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null