aleegis09 commited on
Commit
0345aa2
·
verified ·
1 Parent(s): 2377613

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 sha256:5a8743ff3aee01fc50a47b12b0e2eb99750d8495e46fb868deb22e70543b3fd8
3
  size 100690184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b4dfe474e56972bb8456570db1e42143a207cbe6ae114cc1fa6e7281691ab8
3
  size 100690184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9aa4b12b47e98891ae814d6e2c3d92239a90bb5c238cc901582bd706fa7e909a
3
  size 51344890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d915414c3da4a99b1b5037e246fe83cd961608269115879eb99d211d571c7189
3
  size 51344890
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcb24b9dcb77790e13558de49a235f4653dd4b103999ad6a6becc504ad068b28
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fdd2ab9c11702da426bb570b93f0c9ea499df5dca047a6183a5797f40bf0394
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": 2.129817247390747,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 1.0101010101010102,
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": 87.332,
1090
  "eval_steps_per_second": 22.008,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -1103,7 +1461,7 @@
1103
  "early_stopping_threshold": 0.0
1104
  },
1105
  "attributes": {
1106
- "early_stopping_patience_counter": 0
1107
  }
1108
  },
1109
  "TrainerControl": {
@@ -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": 1.1172169937584128e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 2.129817247390747,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.3468013468013469,
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": 87.332,
1090
  "eval_steps_per_second": 22.008,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 1.0168350168350169,
1095
+ "grad_norm": 35.46605682373047,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 9.02,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 1.0235690235690236,
1102
+ "grad_norm": 49.0546989440918,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 8.8339,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 1.0303030303030303,
1109
+ "grad_norm": 30.65929412841797,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 8.5788,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 1.037037037037037,
1116
+ "grad_norm": 44.25896072387695,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 8.1816,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 1.0437710437710437,
1123
+ "grad_norm": 99.33442687988281,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 7.829,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 1.0505050505050506,
1130
+ "grad_norm": 111.64092254638672,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 8.1602,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 1.0572390572390573,
1137
+ "grad_norm": 50.77913284301758,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 7.6392,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 1.063973063973064,
1144
+ "grad_norm": 108.10916900634766,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 7.8437,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 1.0707070707070707,
1151
+ "grad_norm": 45.10155487060547,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 7.446,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 1.0774410774410774,
1158
+ "grad_norm": 42.05150604248047,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 7.7714,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 1.0841750841750841,
1165
+ "grad_norm": 56.60260009765625,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 8.1302,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 1.0909090909090908,
1172
+ "grad_norm": 44.20862579345703,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 8.5648,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 1.0976430976430978,
1179
+ "grad_norm": 36.54599380493164,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 7.989,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 1.1043771043771045,
1186
+ "grad_norm": 81.98597717285156,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 8.0401,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 1.1111111111111112,
1193
+ "grad_norm": 40.687744140625,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 7.553,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 1.1178451178451179,
1200
+ "grad_norm": 36.427791595458984,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 7.5782,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 1.1245791245791246,
1207
+ "grad_norm": 45.611934661865234,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 7.5116,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 1.1313131313131313,
1214
+ "grad_norm": 47.503997802734375,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 7.1602,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 1.138047138047138,
1221
+ "grad_norm": 58.62235641479492,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 7.0491,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 1.144781144781145,
1228
+ "grad_norm": 52.05401611328125,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 8.0497,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 1.1515151515151516,
1235
+ "grad_norm": 47.182411193847656,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 9.016,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 1.1582491582491583,
1242
+ "grad_norm": 51.34718704223633,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 7.6707,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 1.164983164983165,
1249
+ "grad_norm": 64.08531188964844,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 7.7479,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 1.1717171717171717,
1256
+ "grad_norm": 62.90645980834961,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 6.7577,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 1.1784511784511784,
1263
+ "grad_norm": 54.919891357421875,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 6.3705,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 1.1851851851851851,
1270
+ "grad_norm": 55.40079116821289,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 7.2107,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 1.1919191919191918,
1277
+ "grad_norm": 68.25981140136719,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 6.3771,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 1.1986531986531987,
1284
+ "grad_norm": 65.10997772216797,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 9.1602,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 1.2053872053872055,
1291
+ "grad_norm": 60.717926025390625,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 9.6875,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 1.2121212121212122,
1298
+ "grad_norm": 71.13054656982422,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 7.9383,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 1.2188552188552189,
1305
+ "grad_norm": 70.5322265625,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 7.0618,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 1.2255892255892256,
1312
+ "grad_norm": 74.00837707519531,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 7.48,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 1.2323232323232323,
1319
+ "grad_norm": 87.33047485351562,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 8.2148,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 1.239057239057239,
1326
+ "grad_norm": 201.9131317138672,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 10.4071,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 1.2457912457912457,
1333
+ "grad_norm": 84.5881576538086,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 10.4813,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 1.2525252525252526,
1340
+ "grad_norm": 86.1329574584961,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 10.4515,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 1.2592592592592593,
1347
+ "grad_norm": 36.676177978515625,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 7.6659,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 1.265993265993266,
1354
+ "grad_norm": 34.234840393066406,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 7.1829,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 1.2727272727272727,
1361
+ "grad_norm": 69.66173553466797,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 8.3657,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 1.2794612794612794,
1368
+ "grad_norm": 31.290864944458008,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 7.9053,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 1.2861952861952861,
1375
+ "grad_norm": 72.21870422363281,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 7.9443,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 1.2929292929292928,
1382
+ "grad_norm": 38.420162200927734,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 8.5182,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 1.2996632996632997,
1389
+ "grad_norm": 40.208003997802734,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 8.3081,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 1.3063973063973064,
1396
+ "grad_norm": 40.76144027709961,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 7.4706,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 1.3131313131313131,
1403
+ "grad_norm": 61.534549713134766,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 8.1495,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 1.3198653198653199,
1410
+ "grad_norm": 50.20437240600586,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 7.4514,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 1.3265993265993266,
1417
+ "grad_norm": 44.8299560546875,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 7.7406,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 1.3333333333333333,
1424
+ "grad_norm": 49.02394104003906,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 7.6097,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 1.34006734006734,
1431
+ "grad_norm": 48.80705642700195,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 7.7851,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 1.3468013468013469,
1438
+ "grad_norm": 42.12969207763672,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 7.6933,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 1.3468013468013469,
1445
+ "eval_loss": 2.1342430114746094,
1446
+ "eval_runtime": 2.8623,
1447
+ "eval_samples_per_second": 87.342,
1448
+ "eval_steps_per_second": 22.01,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
1461
  "early_stopping_threshold": 0.0
1462
  },
1463
  "attributes": {
1464
+ "early_stopping_patience_counter": 1
1465
  }
1466
  },
1467
  "TrainerControl": {
 
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": 1.4897778920521728e+16,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null