bbytxt commited on
Commit
4b794d1
·
verified ·
1 Parent(s): f1b8664

Training in progress, step 198, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c6f3aa24168b71c9628440d794fa206a88b0495145f17593014b98b984af395
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0052f674b5b989b7e51a781a4f15851ec3f32e3586b8d9ef1f22e1ef3a68e416
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41496ce843b2c216cd36799535e5e2a16150bf235d7f28ebd8bdb3d2b3ea1373
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f68863f6d486cdc2e403957848fedc229d0aaa2c2ec06b7b519ecdea270903
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3374fbd9f3feb8b3ac5dd0adb18e52db5838363e3cdea6750536c35798bac81
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b20fe899728626ee3b5178061cbf7d8d85051401b8a1e2a0371a56215108e1b0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbb1d8f7e21777781b2c44c66c5c28a191402d70597a4267d9083ab0a88876d6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e08a48f9468574b807356455caef20217ebc0ffec3d9064993cbf9eabd4fc0
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.765149712562561,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 2.2727272727272725,
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 +1089,342 @@
1089
  "eval_samples_per_second": 55.913,
1090
  "eval_steps_per_second": 14.104,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -1112,12 +1448,12 @@
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": 1.156857214009344e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 0.765149712562561,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 3.0,
5
  "eval_steps": 50,
6
+ "global_step": 198,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1089
  "eval_samples_per_second": 55.913,
1090
  "eval_steps_per_second": 14.104,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 2.287878787878788,
1095
+ "grad_norm": 0.6109030246734619,
1096
+ "learning_rate": 1.4644660940672627e-05,
1097
+ "loss": 0.5784,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 2.303030303030303,
1102
+ "grad_norm": 0.6387854814529419,
1103
+ "learning_rate": 1.4058815806103542e-05,
1104
+ "loss": 0.625,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 2.3181818181818183,
1109
+ "grad_norm": 0.659665048122406,
1110
+ "learning_rate": 1.3483006802566544e-05,
1111
+ "loss": 0.6757,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 2.3333333333333335,
1116
+ "grad_norm": 0.6564140319824219,
1117
+ "learning_rate": 1.2917394717602121e-05,
1118
+ "loss": 0.6371,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 2.3484848484848486,
1123
+ "grad_norm": 0.6709268689155579,
1124
+ "learning_rate": 1.2362137491387432e-05,
1125
+ "loss": 0.6282,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 2.3636363636363638,
1130
+ "grad_norm": 0.6831066012382507,
1131
+ "learning_rate": 1.1817390172633403e-05,
1132
+ "loss": 0.6034,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 2.378787878787879,
1137
+ "grad_norm": 0.665997326374054,
1138
+ "learning_rate": 1.1283304875289336e-05,
1139
+ "loss": 0.568,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 2.393939393939394,
1144
+ "grad_norm": 0.6755225658416748,
1145
+ "learning_rate": 1.0760030736066951e-05,
1146
+ "loss": 0.5589,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 2.409090909090909,
1151
+ "grad_norm": 0.7002132534980774,
1152
+ "learning_rate": 1.024771387279585e-05,
1153
+ "loss": 0.5588,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 2.4242424242424243,
1158
+ "grad_norm": 0.716273307800293,
1159
+ "learning_rate": 9.746497343621857e-06,
1160
+ "loss": 0.5729,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 2.4393939393939394,
1165
+ "grad_norm": 0.717272162437439,
1166
+ "learning_rate": 9.256521107059834e-06,
1167
+ "loss": 0.5198,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 2.4545454545454546,
1172
+ "grad_norm": 0.7685539722442627,
1173
+ "learning_rate": 8.777921982911996e-06,
1174
+ "loss": 0.5231,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 2.4696969696969697,
1179
+ "grad_norm": 0.7818545699119568,
1180
+ "learning_rate": 8.310833614062651e-06,
1181
+ "loss": 0.4314,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 2.484848484848485,
1186
+ "grad_norm": 0.9245851039886475,
1187
+ "learning_rate": 7.85538642916015e-06,
1188
+ "loss": 0.3269,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 2.5,
1193
+ "grad_norm": 0.5567438006401062,
1194
+ "learning_rate": 7.4117076061961885e-06,
1195
+ "loss": 0.5873,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 2.515151515151515,
1200
+ "grad_norm": 0.5879104733467102,
1201
+ "learning_rate": 6.979921036993042e-06,
1202
+ "loss": 0.6398,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 2.5303030303030303,
1207
+ "grad_norm": 0.6203252077102661,
1208
+ "learning_rate": 6.5601472926081766e-06,
1209
+ "loss": 0.6471,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 2.5454545454545454,
1214
+ "grad_norm": 0.6278418302536011,
1215
+ "learning_rate": 6.152503589666425e-06,
1216
+ "loss": 0.6167,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 2.5606060606060606,
1221
+ "grad_norm": 0.6504820585250854,
1222
+ "learning_rate": 5.757103757628573e-06,
1223
+ "loss": 0.6541,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 2.5757575757575757,
1228
+ "grad_norm": 0.6489107012748718,
1229
+ "learning_rate": 5.374058207005944e-06,
1230
+ "loss": 0.6618,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 2.590909090909091,
1235
+ "grad_norm": 0.6700452566146851,
1236
+ "learning_rate": 5.0034738985296095e-06,
1237
+ "loss": 0.6294,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 2.606060606060606,
1242
+ "grad_norm": 0.651507556438446,
1243
+ "learning_rate": 4.645454313282965e-06,
1244
+ "loss": 0.5573,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 2.621212121212121,
1249
+ "grad_norm": 0.6590191721916199,
1250
+ "learning_rate": 4.3000994238058644e-06,
1251
+ "loss": 0.5596,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 2.6363636363636362,
1256
+ "grad_norm": 0.6777567863464355,
1257
+ "learning_rate": 3.967505666178556e-06,
1258
+ "loss": 0.5544,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 2.6515151515151514,
1263
+ "grad_norm": 0.691135585308075,
1264
+ "learning_rate": 3.647765913093132e-06,
1265
+ "loss": 0.5732,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 2.6666666666666665,
1270
+ "grad_norm": 0.7173659205436707,
1271
+ "learning_rate": 3.340969447919873e-06,
1272
+ "loss": 0.5273,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 2.6818181818181817,
1277
+ "grad_norm": 0.7347037196159363,
1278
+ "learning_rate": 3.0472019397761064e-06,
1279
+ "loss": 0.4899,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 2.6969696969696972,
1284
+ "grad_norm": 0.724153995513916,
1285
+ "learning_rate": 2.7665454196040664e-06,
1286
+ "loss": 0.4094,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 2.712121212121212,
1291
+ "grad_norm": 0.7561957836151123,
1292
+ "learning_rate": 2.4990782572647975e-06,
1293
+ "loss": 0.3645,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 2.7272727272727275,
1298
+ "grad_norm": 0.9447779059410095,
1299
+ "learning_rate": 2.2448751396543787e-06,
1300
+ "loss": 0.3088,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 2.742424242424242,
1305
+ "grad_norm": 0.519648551940918,
1306
+ "learning_rate": 2.004007049848461e-06,
1307
+ "loss": 0.5594,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 2.757575757575758,
1312
+ "grad_norm": 0.5930406451225281,
1313
+ "learning_rate": 1.7765412472811771e-06,
1314
+ "loss": 0.5954,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 2.7727272727272725,
1319
+ "grad_norm": 0.6299811601638794,
1320
+ "learning_rate": 1.5625412489637337e-06,
1321
+ "loss": 0.658,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 2.787878787878788,
1326
+ "grad_norm": 0.6249811053276062,
1327
+ "learning_rate": 1.3620668117481472e-06,
1328
+ "loss": 0.6387,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 2.8030303030303028,
1333
+ "grad_norm": 0.6202895641326904,
1334
+ "learning_rate": 1.1751739156407649e-06,
1335
+ "loss": 0.5981,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 2.8181818181818183,
1340
+ "grad_norm": 0.6588528156280518,
1341
+ "learning_rate": 1.0019147481706625e-06,
1342
+ "loss": 0.624,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 2.8333333333333335,
1347
+ "grad_norm": 0.6690031290054321,
1348
+ "learning_rate": 8.423376898168245e-07,
1349
+ "loss": 0.6368,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 2.8484848484848486,
1354
+ "grad_norm": 0.6783432364463806,
1355
+ "learning_rate": 6.964873004985717e-07,
1356
+ "loss": 0.6003,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 2.8636363636363638,
1361
+ "grad_norm": 0.6635212302207947,
1362
+ "learning_rate": 5.644043071326932e-07,
1363
+ "loss": 0.5507,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 2.878787878787879,
1368
+ "grad_norm": 0.6875348687171936,
1369
+ "learning_rate": 4.461255922609986e-07,
1370
+ "loss": 0.5495,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 2.893939393939394,
1375
+ "grad_norm": 0.6876786351203918,
1376
+ "learning_rate": 3.416841837512952e-07,
1377
+ "loss": 0.5434,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 2.909090909090909,
1382
+ "grad_norm": 0.7225180268287659,
1383
+ "learning_rate": 2.511092455747932e-07,
1384
+ "loss": 0.5445,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 2.9242424242424243,
1389
+ "grad_norm": 0.7289068698883057,
1390
+ "learning_rate": 1.7442606966242004e-07,
1391
+ "loss": 0.5363,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 2.9393939393939394,
1396
+ "grad_norm": 0.7535192370414734,
1397
+ "learning_rate": 1.1165606884234181e-07,
1398
+ "loss": 0.4994,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 2.9545454545454546,
1403
+ "grad_norm": 0.7919872403144836,
1404
+ "learning_rate": 6.281677086071303e-08,
1405
+ "loss": 0.4289,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 2.9696969696969697,
1410
+ "grad_norm": 1.0089852809906006,
1411
+ "learning_rate": 2.792181348726941e-08,
1412
+ "loss": 0.3698,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 2.984848484848485,
1417
+ "grad_norm": 0.6285845637321472,
1418
+ "learning_rate": 6.980940707146389e-09,
1419
+ "loss": 0.6425,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 3.0,
1424
+ "grad_norm": 0.8173950910568237,
1425
+ "learning_rate": 0.0,
1426
+ "loss": 0.5206,
1427
+ "step": 198
1428
  }
1429
  ],
1430
  "logging_steps": 1,
 
1448
  "should_evaluate": false,
1449
  "should_log": false,
1450
  "should_save": true,
1451
+ "should_training_stop": true
1452
  },
1453
  "attributes": {}
1454
  }
1455
  },
1456
+ "total_flos": 1.5266167953555456e+16,
1457
  "train_batch_size": 8,
1458
  "trial_name": null,
1459
  "trial_params": null