lesso commited on
Commit
17e2fbf
·
verified ·
1 Parent(s): 3ac042e

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:a1da8e4244ee2f29a6dd33b2b3f28a7b7a5fe10e585143763c29826ce9bfeddb
3
  size 100690288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40db45d3d9a9857f9142fd99bf12f5de7d021ad0bb07bf1624cb1fb9f89b67d6
3
  size 100690288
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1ea54593dd06c791a2c63a2fc1d0d901d7dd3db312a2f7aee789fcfe12cf21f
3
  size 51344890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfab43f9e4c386aa90887de7268be690d2c532b1ba0c242d927c8830c5ac66ae
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:d47344633e98a7e34880dcd6bf08f83d6265edf432ca9c24660ea237b07925a4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a23a0688584fbad5072f2472656b5a3972761d27e8aae70de57e12639dc777
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faf4b7c5498ae4c4e5a296fe320aca480fc4724dd9eaa1c7badb2de02f26fafb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c6d837152cc4853064add4c61272c62a18db4bbfe14e332929026ad210cee2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.7836493253707886,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.5474452554744526,
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": 12.353,
1090
  "eval_steps_per_second": 3.088,
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": 3484840800288768.0,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 1.7836493253707886,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.7299270072992701,
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": 12.353,
1090
  "eval_steps_per_second": 3.088,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.551094890510949,
1095
+ "grad_norm": 2.173349142074585,
1096
+ "learning_rate": 2.6073157894736845e-05,
1097
+ "loss": 3.5216,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.5547445255474452,
1102
+ "grad_norm": 1.9568188190460205,
1103
+ "learning_rate": 2.554105263157895e-05,
1104
+ "loss": 3.414,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.5583941605839416,
1109
+ "grad_norm": 2.049314022064209,
1110
+ "learning_rate": 2.5008947368421052e-05,
1111
+ "loss": 3.1854,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.5620437956204379,
1116
+ "grad_norm": 1.8505172729492188,
1117
+ "learning_rate": 2.447684210526316e-05,
1118
+ "loss": 3.7311,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.5656934306569343,
1123
+ "grad_norm": 1.7153427600860596,
1124
+ "learning_rate": 2.3944736842105262e-05,
1125
+ "loss": 3.1837,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.5693430656934306,
1130
+ "grad_norm": 1.6411361694335938,
1131
+ "learning_rate": 2.341263157894737e-05,
1132
+ "loss": 3.521,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.572992700729927,
1137
+ "grad_norm": 1.6039944887161255,
1138
+ "learning_rate": 2.2880526315789475e-05,
1139
+ "loss": 3.4806,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.5766423357664233,
1144
+ "grad_norm": 1.678540587425232,
1145
+ "learning_rate": 2.234842105263158e-05,
1146
+ "loss": 3.1553,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.5802919708029197,
1151
+ "grad_norm": 1.57163405418396,
1152
+ "learning_rate": 2.1816315789473685e-05,
1153
+ "loss": 4.0207,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.583941605839416,
1158
+ "grad_norm": 1.9761027097702026,
1159
+ "learning_rate": 2.128421052631579e-05,
1160
+ "loss": 3.7772,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.5875912408759124,
1165
+ "grad_norm": 2.047546863555908,
1166
+ "learning_rate": 2.0752105263157895e-05,
1167
+ "loss": 3.4518,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.5912408759124088,
1172
+ "grad_norm": 1.9257515668869019,
1173
+ "learning_rate": 2.0220000000000003e-05,
1174
+ "loss": 3.3506,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.5948905109489051,
1179
+ "grad_norm": 2.5686001777648926,
1180
+ "learning_rate": 1.9687894736842104e-05,
1181
+ "loss": 3.4314,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.5985401459854015,
1186
+ "grad_norm": 1.6636919975280762,
1187
+ "learning_rate": 1.9155789473684213e-05,
1188
+ "loss": 3.6784,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.6021897810218978,
1193
+ "grad_norm": 1.5030348300933838,
1194
+ "learning_rate": 1.8623684210526314e-05,
1195
+ "loss": 3.0561,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.6058394160583942,
1200
+ "grad_norm": 1.5657211542129517,
1201
+ "learning_rate": 1.8091578947368423e-05,
1202
+ "loss": 2.7246,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.6094890510948905,
1207
+ "grad_norm": 1.5702214241027832,
1208
+ "learning_rate": 1.7559473684210528e-05,
1209
+ "loss": 2.7973,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.6131386861313869,
1214
+ "grad_norm": 1.8857451677322388,
1215
+ "learning_rate": 1.7027368421052632e-05,
1216
+ "loss": 3.6129,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.6167883211678832,
1221
+ "grad_norm": 1.5984008312225342,
1222
+ "learning_rate": 1.6495263157894737e-05,
1223
+ "loss": 3.2637,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.6204379562043796,
1228
+ "grad_norm": 1.8663055896759033,
1229
+ "learning_rate": 1.5963157894736842e-05,
1230
+ "loss": 3.5648,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.6240875912408759,
1235
+ "grad_norm": 2.12020206451416,
1236
+ "learning_rate": 1.5431052631578947e-05,
1237
+ "loss": 4.199,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.6277372262773723,
1242
+ "grad_norm": 1.8056983947753906,
1243
+ "learning_rate": 1.4898947368421052e-05,
1244
+ "loss": 3.4812,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.6313868613138686,
1249
+ "grad_norm": 1.6429282426834106,
1250
+ "learning_rate": 1.4366842105263159e-05,
1251
+ "loss": 3.5187,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.635036496350365,
1256
+ "grad_norm": 1.8332836627960205,
1257
+ "learning_rate": 1.3834736842105265e-05,
1258
+ "loss": 3.9151,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.6386861313868614,
1263
+ "grad_norm": 1.760815143585205,
1264
+ "learning_rate": 1.3302631578947369e-05,
1265
+ "loss": 3.1158,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.6423357664233577,
1270
+ "grad_norm": 1.793931484222412,
1271
+ "learning_rate": 1.2770526315789475e-05,
1272
+ "loss": 3.2062,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.6459854014598541,
1277
+ "grad_norm": 1.727136254310608,
1278
+ "learning_rate": 1.223842105263158e-05,
1279
+ "loss": 3.2026,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.6496350364963503,
1284
+ "grad_norm": 2.5563066005706787,
1285
+ "learning_rate": 1.1706315789473685e-05,
1286
+ "loss": 4.4599,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.6532846715328468,
1291
+ "grad_norm": 1.7797980308532715,
1292
+ "learning_rate": 1.117421052631579e-05,
1293
+ "loss": 3.446,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.656934306569343,
1298
+ "grad_norm": 1.8188791275024414,
1299
+ "learning_rate": 1.0642105263157895e-05,
1300
+ "loss": 3.7353,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.6605839416058394,
1305
+ "grad_norm": 1.6830250024795532,
1306
+ "learning_rate": 1.0110000000000001e-05,
1307
+ "loss": 3.3371,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.6642335766423357,
1312
+ "grad_norm": 2.488910675048828,
1313
+ "learning_rate": 9.577894736842106e-06,
1314
+ "loss": 4.4411,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.6678832116788321,
1319
+ "grad_norm": 1.7048317193984985,
1320
+ "learning_rate": 9.045789473684211e-06,
1321
+ "loss": 3.4593,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.6715328467153284,
1326
+ "grad_norm": 2.0829358100891113,
1327
+ "learning_rate": 8.513684210526316e-06,
1328
+ "loss": 4.0263,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.6751824817518248,
1333
+ "grad_norm": 2.3267061710357666,
1334
+ "learning_rate": 7.981578947368421e-06,
1335
+ "loss": 3.8797,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.6788321167883211,
1340
+ "grad_norm": 2.366909980773926,
1341
+ "learning_rate": 7.449473684210526e-06,
1342
+ "loss": 3.7547,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.6824817518248175,
1347
+ "grad_norm": 2.0214099884033203,
1348
+ "learning_rate": 6.917368421052633e-06,
1349
+ "loss": 4.1961,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.6861313868613139,
1354
+ "grad_norm": 3.4042675495147705,
1355
+ "learning_rate": 6.385263157894738e-06,
1356
+ "loss": 4.0792,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.6897810218978102,
1361
+ "grad_norm": 2.2859408855438232,
1362
+ "learning_rate": 5.8531578947368425e-06,
1363
+ "loss": 4.2271,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.6934306569343066,
1368
+ "grad_norm": 3.462792158126831,
1369
+ "learning_rate": 5.321052631578947e-06,
1370
+ "loss": 5.6922,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.6970802919708029,
1375
+ "grad_norm": 2.6065616607666016,
1376
+ "learning_rate": 4.788947368421053e-06,
1377
+ "loss": 4.1072,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.7007299270072993,
1382
+ "grad_norm": 2.6013782024383545,
1383
+ "learning_rate": 4.256842105263158e-06,
1384
+ "loss": 3.5596,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.7043795620437956,
1389
+ "grad_norm": 3.0235507488250732,
1390
+ "learning_rate": 3.724736842105263e-06,
1391
+ "loss": 3.9284,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.708029197080292,
1396
+ "grad_norm": 3.959134340286255,
1397
+ "learning_rate": 3.192631578947369e-06,
1398
+ "loss": 3.8374,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.7116788321167883,
1403
+ "grad_norm": 4.039380073547363,
1404
+ "learning_rate": 2.6605263157894737e-06,
1405
+ "loss": 4.4352,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.7153284671532847,
1410
+ "grad_norm": 5.668715953826904,
1411
+ "learning_rate": 2.128421052631579e-06,
1412
+ "loss": 3.3006,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.718978102189781,
1417
+ "grad_norm": 7.316230773925781,
1418
+ "learning_rate": 1.5963157894736844e-06,
1419
+ "loss": 3.4598,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.7226277372262774,
1424
+ "grad_norm": 5.929181098937988,
1425
+ "learning_rate": 1.0642105263157895e-06,
1426
+ "loss": 3.8279,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.7262773722627737,
1431
+ "grad_norm": 8.298709869384766,
1432
+ "learning_rate": 5.321052631578948e-07,
1433
+ "loss": 5.2993,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.7299270072992701,
1438
+ "grad_norm": 10.71786880493164,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 5.1007,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.7299270072992701,
1445
+ "eval_loss": 1.7919894456863403,
1446
+ "eval_runtime": 8.7871,
1447
+ "eval_samples_per_second": 13.201,
1448
+ "eval_steps_per_second": 3.3,
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": 4684012345884672.0,
1479
  "train_batch_size": 4,
1480
  "trial_name": null,
1481
  "trial_params": null