dimasik2987 commited on
Commit
7ee7f1a
·
verified ·
1 Parent(s): ca0d2ad

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:b0af3362e5050348c9fe7cfd1669c35f9e1a185aad83648bf5871fb89f970a46
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f5def912d3dccf8c4643728da905e8539f0a4492f7fb1bb54f8ec4f7c11a95
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:036893d2331400fec25ee30c8ba795193d66e4ac79f0f8370738bfb7d42d6a6e
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c9a0b64c2ef10ff893a80a379cb9909b23774174e343370c23cd5f7906e15f
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4962cdd4d6fe7bbd8a356ab145053d68f77edb9ca256c73b44651c97475ec71
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6910ef0b410c22c046f09af0bade7aa9b7a83fa8cf192f599c7e03dcd5dd17
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01c5525f1d8420ca8a81a7fd2ec397a508131d03210dfd36c7ac5758b0e6313b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e88ef6a2716260516e17223973d6a3b0a4c88bf12c72ed47e80e6f2a6782fd
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.12110025435686111,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.03912873353332464,
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": 4.509,
1090
  "eval_steps_per_second": 1.129,
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": 1
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": 9.80234739426263e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.08230920881032944,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.052171644711099516,
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": 4.509,
1090
  "eval_steps_per_second": 1.129,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.039389591756880137,
1095
+ "grad_norm": 3.797510862350464,
1096
+ "learning_rate": 2.589263157894737e-05,
1097
+ "loss": 0.5013,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.03965044998043563,
1102
+ "grad_norm": 3.3140711784362793,
1103
+ "learning_rate": 2.536421052631579e-05,
1104
+ "loss": 0.4598,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.03991130820399113,
1109
+ "grad_norm": 1.1835687160491943,
1110
+ "learning_rate": 2.483578947368421e-05,
1111
+ "loss": 0.3732,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.040172166427546625,
1116
+ "grad_norm": 0.5971368551254272,
1117
+ "learning_rate": 2.430736842105263e-05,
1118
+ "loss": 0.3361,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.04043302465110213,
1123
+ "grad_norm": 0.7615634799003601,
1124
+ "learning_rate": 2.3778947368421052e-05,
1125
+ "loss": 0.317,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.040693882874657625,
1130
+ "grad_norm": 0.589562177658081,
1131
+ "learning_rate": 2.3250526315789473e-05,
1132
+ "loss": 0.3424,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.04095474109821312,
1137
+ "grad_norm": 0.5603517293930054,
1138
+ "learning_rate": 2.2722105263157894e-05,
1139
+ "loss": 0.3523,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.04121559932176862,
1144
+ "grad_norm": 0.6157901883125305,
1145
+ "learning_rate": 2.2193684210526316e-05,
1146
+ "loss": 0.3667,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.041476457545324114,
1151
+ "grad_norm": 0.5660136342048645,
1152
+ "learning_rate": 2.1665263157894737e-05,
1153
+ "loss": 0.2797,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.04173731576887962,
1158
+ "grad_norm": 0.5905348658561707,
1159
+ "learning_rate": 2.1136842105263158e-05,
1160
+ "loss": 0.3196,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.04199817399243511,
1165
+ "grad_norm": 0.6353060603141785,
1166
+ "learning_rate": 2.060842105263158e-05,
1167
+ "loss": 0.3449,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.04225903221599061,
1172
+ "grad_norm": 0.6922320127487183,
1173
+ "learning_rate": 2.008e-05,
1174
+ "loss": 0.3504,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.042519890439546106,
1179
+ "grad_norm": 0.5601292252540588,
1180
+ "learning_rate": 1.9551578947368422e-05,
1181
+ "loss": 0.3378,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.0427807486631016,
1186
+ "grad_norm": 0.5565058588981628,
1187
+ "learning_rate": 1.9023157894736843e-05,
1188
+ "loss": 0.3541,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.043041606886657105,
1193
+ "grad_norm": 0.5381285548210144,
1194
+ "learning_rate": 1.849473684210526e-05,
1195
+ "loss": 0.2956,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.0433024651102126,
1200
+ "grad_norm": 0.8170627951622009,
1201
+ "learning_rate": 1.7966315789473686e-05,
1202
+ "loss": 0.3399,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.0435633233337681,
1207
+ "grad_norm": 0.7445321083068848,
1208
+ "learning_rate": 1.7437894736842107e-05,
1209
+ "loss": 0.3516,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.043824181557323594,
1214
+ "grad_norm": 0.6222259998321533,
1215
+ "learning_rate": 1.6909473684210525e-05,
1216
+ "loss": 0.3152,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.04408503978087909,
1221
+ "grad_norm": 0.6484302878379822,
1222
+ "learning_rate": 1.638105263157895e-05,
1223
+ "loss": 0.3919,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.04434589800443459,
1228
+ "grad_norm": 0.6885114908218384,
1229
+ "learning_rate": 1.5852631578947368e-05,
1230
+ "loss": 0.3483,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.04460675622799009,
1235
+ "grad_norm": 0.6635403633117676,
1236
+ "learning_rate": 1.532421052631579e-05,
1237
+ "loss": 0.2702,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.044867614451545586,
1242
+ "grad_norm": 0.7835387587547302,
1243
+ "learning_rate": 1.4795789473684209e-05,
1244
+ "loss": 0.3227,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.04512847267510108,
1249
+ "grad_norm": 0.6229288578033447,
1250
+ "learning_rate": 1.4267368421052632e-05,
1251
+ "loss": 0.288,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.04538933089865658,
1256
+ "grad_norm": 0.7214296460151672,
1257
+ "learning_rate": 1.3738947368421053e-05,
1258
+ "loss": 0.358,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.045650189122212075,
1263
+ "grad_norm": 0.6343803405761719,
1264
+ "learning_rate": 1.3210526315789473e-05,
1265
+ "loss": 0.1716,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.04591104734576758,
1270
+ "grad_norm": 0.470270037651062,
1271
+ "learning_rate": 1.2682105263157896e-05,
1272
+ "loss": 0.0489,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.046171905569323074,
1277
+ "grad_norm": 0.3558203876018524,
1278
+ "learning_rate": 1.2153684210526315e-05,
1279
+ "loss": 0.0174,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.04643276379287857,
1284
+ "grad_norm": 0.4911562502384186,
1285
+ "learning_rate": 1.1625263157894737e-05,
1286
+ "loss": 0.0214,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.046693622016434067,
1291
+ "grad_norm": 0.5593497157096863,
1292
+ "learning_rate": 1.1096842105263158e-05,
1293
+ "loss": 0.022,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.04695448023998956,
1298
+ "grad_norm": 0.4090302288532257,
1299
+ "learning_rate": 1.0568421052631579e-05,
1300
+ "loss": 0.0197,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.047215338463545066,
1305
+ "grad_norm": 0.44141674041748047,
1306
+ "learning_rate": 1.004e-05,
1307
+ "loss": 0.013,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.04747619668710056,
1312
+ "grad_norm": 0.38881024718284607,
1313
+ "learning_rate": 9.511578947368422e-06,
1314
+ "loss": 0.0129,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.04773705491065606,
1319
+ "grad_norm": 0.3517584502696991,
1320
+ "learning_rate": 8.983157894736843e-06,
1321
+ "loss": 0.013,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.047997913134211555,
1326
+ "grad_norm": 0.30295777320861816,
1327
+ "learning_rate": 8.454736842105263e-06,
1328
+ "loss": 0.0068,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.04825877135776705,
1333
+ "grad_norm": 0.22888092696666718,
1334
+ "learning_rate": 7.926315789473684e-06,
1335
+ "loss": 0.0032,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.048519629581322554,
1340
+ "grad_norm": 0.24423319101333618,
1341
+ "learning_rate": 7.397894736842104e-06,
1342
+ "loss": 0.0032,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.04878048780487805,
1347
+ "grad_norm": 0.5701403021812439,
1348
+ "learning_rate": 6.8694736842105265e-06,
1349
+ "loss": 0.004,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.04904134602843355,
1354
+ "grad_norm": 0.7065002918243408,
1355
+ "learning_rate": 6.341052631578948e-06,
1356
+ "loss": 0.005,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.04930220425198904,
1361
+ "grad_norm": 0.642783522605896,
1362
+ "learning_rate": 5.812631578947368e-06,
1363
+ "loss": 0.004,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.04956306247554454,
1368
+ "grad_norm": 0.04088672995567322,
1369
+ "learning_rate": 5.2842105263157896e-06,
1370
+ "loss": 0.0003,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.04982392069910004,
1375
+ "grad_norm": 0.6026747822761536,
1376
+ "learning_rate": 4.755789473684211e-06,
1377
+ "loss": 0.0056,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.05008477892265554,
1382
+ "grad_norm": 0.15268850326538086,
1383
+ "learning_rate": 4.227368421052631e-06,
1384
+ "loss": 0.0015,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.050345637146211035,
1389
+ "grad_norm": 0.20319561660289764,
1390
+ "learning_rate": 3.698947368421052e-06,
1391
+ "loss": 0.0008,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.05060649536976653,
1396
+ "grad_norm": 0.938482403755188,
1397
+ "learning_rate": 3.170526315789474e-06,
1398
+ "loss": 0.0017,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.05086735359332203,
1403
+ "grad_norm": 0.10921061784029007,
1404
+ "learning_rate": 2.6421052631578948e-06,
1405
+ "loss": 0.0004,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.051128211816877524,
1410
+ "grad_norm": 0.25236430764198303,
1411
+ "learning_rate": 2.1136842105263157e-06,
1412
+ "loss": 0.002,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.05138907004043303,
1417
+ "grad_norm": 0.3114216923713684,
1418
+ "learning_rate": 1.585263157894737e-06,
1419
+ "loss": 0.0012,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.05164992826398852,
1424
+ "grad_norm": 0.4255119264125824,
1425
+ "learning_rate": 1.0568421052631578e-06,
1426
+ "loss": 0.0071,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.05191078648754402,
1431
+ "grad_norm": 0.18521125614643097,
1432
+ "learning_rate": 5.284210526315789e-07,
1433
+ "loss": 0.0005,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.052171644711099516,
1438
+ "grad_norm": 2.783665180206299,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.0279,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.052171644711099516,
1445
+ "eval_loss": 0.08230920881032944,
1446
+ "eval_runtime": 357.6332,
1447
+ "eval_samples_per_second": 4.513,
1448
+ "eval_steps_per_second": 1.13,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
1461
  "early_stopping_threshold": 0.0
1462
  },
1463
  "attributes": {
1464
+ "early_stopping_patience_counter": 0
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": 1.3057871528853504e+17,
1479
  "train_batch_size": 4,
1480
  "trial_name": null,
1481
  "trial_params": null