alchemist69 commited on
Commit
0197283
·
verified ·
1 Parent(s): 19e2f57

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:e5351f6ac3f23d156b082737654ec541a7169a3a6f659eae0693d3689d89441c
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9d06c66b35e42fa8e7f6078a8848793711cf1fdd03307f4047d69a5e847258
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcc3c144bfe8a0ecd7e44e448a3375120db3337c7584c8f11c4608d95f12e193
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1740623369ed9722bd948a1d524f380ffe189be88911a763d754222511c059c
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c103485edcdb33f74f455c971472dfffb5f2342d7f56b292a976f9ac7ccb0b9d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f29902632d5f0fa0e598a0430a1bf358f9eb1976fd443aad55248fa75d62d72e
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": 10.335372924804688,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 1.8018018018018018,
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": 449.015,
1090
  "eval_steps_per_second": 112.254,
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": 16718655258624.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 10.335372924804688,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 2.4024024024024024,
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": 449.015,
1090
  "eval_steps_per_second": 112.254,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 1.8138138138138138,
1095
+ "grad_norm": 0.08203451335430145,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 10.0847,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 1.825825825825826,
1102
+ "grad_norm": 0.10485396534204483,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 10.4735,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 1.8378378378378377,
1109
+ "grad_norm": 0.08351816236972809,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 10.376,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 1.84984984984985,
1116
+ "grad_norm": 0.08282805979251862,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 10.4858,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 1.8618618618618619,
1123
+ "grad_norm": 0.06912698596715927,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 10.4977,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 1.8738738738738738,
1130
+ "grad_norm": 0.05990024656057358,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 10.1305,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 1.885885885885886,
1137
+ "grad_norm": 0.09366833418607712,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 10.4212,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 1.8978978978978978,
1144
+ "grad_norm": 0.08317462354898453,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 10.2669,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 1.90990990990991,
1151
+ "grad_norm": 0.06542299687862396,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 10.5,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 1.921921921921922,
1158
+ "grad_norm": 0.11974980682134628,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 10.2073,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 1.9339339339339339,
1165
+ "grad_norm": 0.12192590534687042,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 10.3949,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 1.945945945945946,
1172
+ "grad_norm": 0.18741394579410553,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 10.462,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 1.9579579579579578,
1179
+ "grad_norm": 0.21047306060791016,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 10.4403,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 1.96996996996997,
1186
+ "grad_norm": 0.09633217006921768,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 10.4283,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 1.981981981981982,
1193
+ "grad_norm": 0.09279535710811615,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 10.5016,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 1.993993993993994,
1200
+ "grad_norm": 0.1264590471982956,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 10.232,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 2.006006006006006,
1207
+ "grad_norm": 0.5660918951034546,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 17.5015,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 2.018018018018018,
1214
+ "grad_norm": 0.07636700570583344,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 10.3312,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 2.03003003003003,
1221
+ "grad_norm": 0.08472772687673569,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 10.4095,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 2.042042042042042,
1228
+ "grad_norm": 0.07472264766693115,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 10.1201,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 2.054054054054054,
1235
+ "grad_norm": 0.06900706142187119,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 10.7351,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 2.066066066066066,
1242
+ "grad_norm": 0.09336791932582855,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 10.1279,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 2.078078078078078,
1249
+ "grad_norm": 0.07351528853178024,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 10.4047,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 2.09009009009009,
1256
+ "grad_norm": 0.1067480817437172,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 10.1926,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 2.1021021021021022,
1263
+ "grad_norm": 0.10185723751783371,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 10.4406,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 2.114114114114114,
1270
+ "grad_norm": 0.07974503189325333,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 10.3356,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 2.126126126126126,
1277
+ "grad_norm": 0.10168915241956711,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 10.429,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 2.138138138138138,
1284
+ "grad_norm": 0.0855264887213707,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 10.4118,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 2.15015015015015,
1291
+ "grad_norm": 0.06459216773509979,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 10.4516,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 2.1621621621621623,
1298
+ "grad_norm": 0.08227691799402237,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 10.3692,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 2.174174174174174,
1305
+ "grad_norm": 0.08134052157402039,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 10.0423,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 2.186186186186186,
1312
+ "grad_norm": 0.1169663667678833,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 10.2857,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 2.1981981981981984,
1319
+ "grad_norm": 0.11807834357023239,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 10.3408,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 2.21021021021021,
1326
+ "grad_norm": 0.13462962210178375,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 10.8249,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 2.2222222222222223,
1333
+ "grad_norm": 0.17719753086566925,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 10.001,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 2.234234234234234,
1340
+ "grad_norm": 0.18614676594734192,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 10.4575,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 2.2462462462462462,
1347
+ "grad_norm": 0.12907378375530243,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 10.2002,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 2.2582582582582584,
1354
+ "grad_norm": 0.10864003747701645,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 10.0162,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 2.27027027027027,
1361
+ "grad_norm": 0.08046580106019974,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 10.5991,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 2.2822822822822824,
1368
+ "grad_norm": 0.06014268472790718,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 10.2142,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 2.294294294294294,
1375
+ "grad_norm": 0.07127836346626282,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 10.2936,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 2.3063063063063063,
1382
+ "grad_norm": 0.07464353740215302,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 10.4045,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 2.3183183183183185,
1389
+ "grad_norm": 0.08217864483594894,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 10.3816,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 2.33033033033033,
1396
+ "grad_norm": 0.052305858582258224,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 10.0796,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 2.3423423423423424,
1403
+ "grad_norm": 0.07987543940544128,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 10.6084,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 2.3543543543543546,
1410
+ "grad_norm": 0.10201536864042282,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 10.3774,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 2.3663663663663663,
1417
+ "grad_norm": 0.08694560825824738,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 10.5723,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 2.3783783783783785,
1424
+ "grad_norm": 0.07485759258270264,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 10.2715,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 2.3903903903903903,
1431
+ "grad_norm": 0.09124989062547684,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 9.9672,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 2.4024024024024024,
1438
+ "grad_norm": 0.10986769944429398,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 10.7202,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 2.4024024024024024,
1445
+ "eval_loss": 10.33564281463623,
1446
+ "eval_runtime": 0.3116,
1447
+ "eval_samples_per_second": 449.315,
1448
+ "eval_steps_per_second": 112.329,
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": 22282244456448.0,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null