brixeus commited on
Commit
f3370e6
·
verified ·
1 Parent(s): dc77093

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 sha256:3b5c4c721fa9253c931faa80ca77c266a6026ff8c589ce0ff7dc94e5ad197359
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea95fe3dde4adce01b6941805b60a9338c0849794b0c97e4c2ef9af17a26ab39
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75122d33d5f1a39ca63f93bf46482abd76de497219072ee1599ab66fa0d80355
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1a0dc6a72b0391477a93444a3e03c4fcedf22a8ec0d19e8c8ba69a86f0016e
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff00dc559515a0d1f85451ec340e8d92f0b326f010d6394af24f97ecea7d08be
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e1a56e406d65b1dd87dd2e349008b07b33e19e0dcb89f69ba776d2079ed09c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f4002ee03f4202a6a410bde3375cd186d152ce129e8a177eb112bee1f18b1e2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac116b8169c53ab649a7f15f2f32735f2c71ec2f803f70de8c655a513ee9cfc
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7750892639160156,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.029884942969567167,
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": 13.927,
1090
  "eval_steps_per_second": 3.483,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -1117,7 +1475,7 @@
1117
  "attributes": {}
1118
  }
1119
  },
1120
- "total_flos": 2.13283302801408e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.760303020477295,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.039846590626089556,
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": 13.927,
1090
  "eval_steps_per_second": 3.483,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.030084175922697614,
1095
+ "grad_norm": 0.8313390016555786,
1096
+ "learning_rate": 7.107005538862646e-05,
1097
+ "loss": 1.5251,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.03028340887582806,
1102
+ "grad_norm": 0.6984227299690247,
1103
+ "learning_rate": 7.07041155014006e-05,
1104
+ "loss": 1.4523,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.03048264182895851,
1109
+ "grad_norm": 0.7919133305549622,
1110
+ "learning_rate": 7.033683215379002e-05,
1111
+ "loss": 1.6288,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.030681874782088957,
1116
+ "grad_norm": 0.8622307181358337,
1117
+ "learning_rate": 6.996822917828477e-05,
1118
+ "loss": 1.6547,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.030881107735219404,
1123
+ "grad_norm": 0.6328975558280945,
1124
+ "learning_rate": 6.959833049300377e-05,
1125
+ "loss": 1.2618,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.031080340688349854,
1130
+ "grad_norm": 0.7241643667221069,
1131
+ "learning_rate": 6.922716010014255e-05,
1132
+ "loss": 1.5949,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.0312795736414803,
1137
+ "grad_norm": 0.63180011510849,
1138
+ "learning_rate": 6.885474208441603e-05,
1139
+ "loss": 1.4086,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.03147880659461075,
1144
+ "grad_norm": 0.7782214879989624,
1145
+ "learning_rate": 6.848110061149556e-05,
1146
+ "loss": 1.6755,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.0316780395477412,
1151
+ "grad_norm": 0.7412595152854919,
1152
+ "learning_rate": 6.810625992644085e-05,
1153
+ "loss": 1.5487,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.03187727250087164,
1158
+ "grad_norm": 0.7262195348739624,
1159
+ "learning_rate": 6.773024435212678e-05,
1160
+ "loss": 1.5054,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.03207650545400209,
1165
+ "grad_norm": 0.6977418065071106,
1166
+ "learning_rate": 6.735307828766515e-05,
1167
+ "loss": 1.4481,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.03227573840713254,
1172
+ "grad_norm": 0.8268071413040161,
1173
+ "learning_rate": 6.697478620682137e-05,
1174
+ "loss": 1.5609,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.032474971360262984,
1179
+ "grad_norm": 0.7182347178459167,
1180
+ "learning_rate": 6.659539265642643e-05,
1181
+ "loss": 1.6529,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.032674204313393435,
1186
+ "grad_norm": 0.6928174495697021,
1187
+ "learning_rate": 6.621492225478414e-05,
1188
+ "loss": 1.5177,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.032873437266523885,
1193
+ "grad_norm": 0.7981646060943604,
1194
+ "learning_rate": 6.583339969007363e-05,
1195
+ "loss": 1.6601,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.03307267021965433,
1200
+ "grad_norm": 0.8732507228851318,
1201
+ "learning_rate": 6.545084971874738e-05,
1202
+ "loss": 1.6293,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.03327190317278478,
1207
+ "grad_norm": 0.7294723391532898,
1208
+ "learning_rate": 6.506729716392481e-05,
1209
+ "loss": 1.5132,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.03347113612591523,
1214
+ "grad_norm": 0.7707034945487976,
1215
+ "learning_rate": 6.468276691378155e-05,
1216
+ "loss": 1.6842,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.03367036907904567,
1221
+ "grad_norm": 0.7112640142440796,
1222
+ "learning_rate": 6.429728391993446e-05,
1223
+ "loss": 1.5651,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.03386960203217612,
1228
+ "grad_norm": 0.8815944194793701,
1229
+ "learning_rate": 6.391087319582264e-05,
1230
+ "loss": 1.9648,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.03406883498530657,
1235
+ "grad_norm": 0.8880531191825867,
1236
+ "learning_rate": 6.35235598150842e-05,
1237
+ "loss": 1.805,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.034268067938437015,
1242
+ "grad_norm": 0.7516195178031921,
1243
+ "learning_rate": 6.313536890992935e-05,
1244
+ "loss": 1.6364,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.034467300891567465,
1249
+ "grad_norm": 0.7268112301826477,
1250
+ "learning_rate": 6.274632566950967e-05,
1251
+ "loss": 1.7021,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.034666533844697915,
1256
+ "grad_norm": 0.7526605725288391,
1257
+ "learning_rate": 6.235645533828349e-05,
1258
+ "loss": 1.7656,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.03486576679782836,
1263
+ "grad_norm": 0.7969704270362854,
1264
+ "learning_rate": 6.19657832143779e-05,
1265
+ "loss": 1.7097,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.03506499975095881,
1270
+ "grad_norm": 0.8148013949394226,
1271
+ "learning_rate": 6.157433464794716e-05,
1272
+ "loss": 1.8028,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.03526423270408926,
1277
+ "grad_norm": 0.7393292188644409,
1278
+ "learning_rate": 6.118213503952779e-05,
1279
+ "loss": 1.7528,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.0354634656572197,
1284
+ "grad_norm": 0.8155067563056946,
1285
+ "learning_rate": 6.078920983839031e-05,
1286
+ "loss": 1.8142,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.03566269861035015,
1291
+ "grad_norm": 0.8007950186729431,
1292
+ "learning_rate": 6.0395584540887963e-05,
1293
+ "loss": 1.6058,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.0358619315634806,
1298
+ "grad_norm": 0.7950125336647034,
1299
+ "learning_rate": 6.0001284688802226e-05,
1300
+ "loss": 1.8424,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.036061164516611045,
1305
+ "grad_norm": 0.7428115010261536,
1306
+ "learning_rate": 5.960633586768543e-05,
1307
+ "loss": 1.6715,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.036260397469741495,
1312
+ "grad_norm": 0.8062713742256165,
1313
+ "learning_rate": 5.921076370520058e-05,
1314
+ "loss": 1.885,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.036459630422871946,
1319
+ "grad_norm": 0.8469149470329285,
1320
+ "learning_rate": 5.8814593869458455e-05,
1321
+ "loss": 1.7839,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.03665886337600239,
1326
+ "grad_norm": 0.7747473120689392,
1327
+ "learning_rate": 5.841785206735192e-05,
1328
+ "loss": 1.8037,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.03685809632913284,
1333
+ "grad_norm": 0.9092196822166443,
1334
+ "learning_rate": 5.8020564042888015e-05,
1335
+ "loss": 1.6015,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.03705732928226329,
1340
+ "grad_norm": 0.8225083351135254,
1341
+ "learning_rate": 5.762275557551727e-05,
1342
+ "loss": 1.7744,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.03725656223539373,
1347
+ "grad_norm": 0.8785688877105713,
1348
+ "learning_rate": 5.7224452478461064e-05,
1349
+ "loss": 1.9095,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.03745579518852418,
1354
+ "grad_norm": 0.8963973522186279,
1355
+ "learning_rate": 5.682568059703659e-05,
1356
+ "loss": 1.8677,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.03765502814165463,
1361
+ "grad_norm": 0.9210934638977051,
1362
+ "learning_rate": 5.642646580697973e-05,
1363
+ "loss": 1.9918,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.037854261094785076,
1368
+ "grad_norm": 1.1235376596450806,
1369
+ "learning_rate": 5.602683401276615e-05,
1370
+ "loss": 2.0277,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.038053494047915526,
1375
+ "grad_norm": 0.9675539135932922,
1376
+ "learning_rate": 5.562681114593028e-05,
1377
+ "loss": 2.0708,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.038252727001045976,
1382
+ "grad_norm": 0.9660516381263733,
1383
+ "learning_rate": 5.522642316338268e-05,
1384
+ "loss": 2.0641,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.03845195995417642,
1389
+ "grad_norm": 0.9473053812980652,
1390
+ "learning_rate": 5.482569604572576e-05,
1391
+ "loss": 2.0431,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.03865119290730687,
1396
+ "grad_norm": 0.8935657739639282,
1397
+ "learning_rate": 5.442465579556793e-05,
1398
+ "loss": 1.9439,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.03885042586043732,
1403
+ "grad_norm": 0.919715940952301,
1404
+ "learning_rate": 5.402332843583631e-05,
1405
+ "loss": 1.9152,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.03904965881356776,
1410
+ "grad_norm": 0.8705791234970093,
1411
+ "learning_rate": 5.3621740008088126e-05,
1412
+ "loss": 1.9256,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.03924889176669821,
1417
+ "grad_norm": 0.9605872631072998,
1418
+ "learning_rate": 5.321991657082097e-05,
1419
+ "loss": 1.9576,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.03944812471982866,
1424
+ "grad_norm": 0.9608198404312134,
1425
+ "learning_rate": 5.281788419778187e-05,
1426
+ "loss": 2.0148,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.039647357672959106,
1431
+ "grad_norm": 0.9603476524353027,
1432
+ "learning_rate": 5.2415668976275355e-05,
1433
+ "loss": 2.0684,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.039846590626089556,
1438
+ "grad_norm": 1.0739209651947021,
1439
+ "learning_rate": 5.201329700547076e-05,
1440
+ "loss": 1.8792,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.039846590626089556,
1445
+ "eval_loss": 1.760303020477295,
1446
+ "eval_runtime": 607.8397,
1447
+ "eval_samples_per_second": 13.908,
1448
+ "eval_steps_per_second": 3.478,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
1475
  "attributes": {}
1476
  }
1477
  },
1478
+ "total_flos": 2.84377737068544e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null