aleegis12 commited on
Commit
6fddc7d
·
verified ·
1 Parent(s): 0a162c1

Training in progress, step 199, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:477098c696cce141f95d504739a1abc488709b661256b050a4eb4fa5b0a25c6a
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f628f8095e3ff6b778f702fd5f31827fcf1c044fae64128e1eceb3b91a716f53
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de7a7ef05abdb90bd4c5e441b562470164a1516fc5606729170d8e63a21fa251
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecde8577ff422e4bac5f27cf9dc22e5361bd06d26ccc77458508b011785ae445
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95c26739f741091431c98caeaceb8f8178d745090d36ee44eda925f069b8c439
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a15d00ee80c037f858cd0f5f3a9688c70186b6d99835aaeabc6f79ef1b3270
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6024df9f7fc953bd1f3238f4774d1358ed74064d69469cc1f759a5c66b2bc31a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da8d1cd3310f3335996ce6a573b953581485436b0327db23e64baad0e252b90
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.7408222556114197,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 2.2641509433962264,
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 +1089,349 @@
1089
  "eval_samples_per_second": 20.3,
1090
  "eval_steps_per_second": 5.075,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -1112,12 +1455,12 @@
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": 8.386348515852288e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 0.7408222556114197,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 3.0037735849056606,
5
  "eval_steps": 50,
6
+ "global_step": 199,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1089
  "eval_samples_per_second": 20.3,
1090
  "eval_steps_per_second": 5.075,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 2.279245283018868,
1095
+ "grad_norm": 0.0900016725063324,
1096
+ "learning_rate": 1.5088159095696363e-05,
1097
+ "loss": 0.7261,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 2.2943396226415094,
1102
+ "grad_norm": 0.0879833921790123,
1103
+ "learning_rate": 1.4498045898920987e-05,
1104
+ "loss": 0.7737,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 2.309433962264151,
1109
+ "grad_norm": 0.0888439267873764,
1110
+ "learning_rate": 1.3917741558976894e-05,
1111
+ "loss": 0.8468,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 2.3245283018867924,
1116
+ "grad_norm": 0.08833940327167511,
1117
+ "learning_rate": 1.3347406408508695e-05,
1118
+ "loss": 0.8344,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 2.339622641509434,
1123
+ "grad_norm": 0.0893007144331932,
1124
+ "learning_rate": 1.2787198025767416e-05,
1125
+ "loss": 0.8671,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 2.3547169811320754,
1130
+ "grad_norm": 0.09148311614990234,
1131
+ "learning_rate": 1.2237271191073268e-05,
1132
+ "loss": 0.8152,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 2.369811320754717,
1137
+ "grad_norm": 0.08719191700220108,
1138
+ "learning_rate": 1.1697777844051105e-05,
1139
+ "loss": 0.7792,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 2.3849056603773584,
1144
+ "grad_norm": 0.08977144211530685,
1145
+ "learning_rate": 1.1168867041651082e-05,
1146
+ "loss": 0.8237,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 2.4,
1151
+ "grad_norm": 0.08768357336521149,
1152
+ "learning_rate": 1.0650684916965559e-05,
1153
+ "loss": 0.7988,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 2.4150943396226414,
1158
+ "grad_norm": 0.09540558606386185,
1159
+ "learning_rate": 1.0143374638853891e-05,
1160
+ "loss": 0.7716,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 2.430188679245283,
1165
+ "grad_norm": 0.09125573188066483,
1166
+ "learning_rate": 9.647076372386194e-06,
1167
+ "loss": 0.6321,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 2.4452830188679244,
1172
+ "grad_norm": 0.08672156184911728,
1173
+ "learning_rate": 9.161927240117174e-06,
1174
+ "loss": 0.4545,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 2.460377358490566,
1179
+ "grad_norm": 0.09875945746898651,
1180
+ "learning_rate": 8.688061284200266e-06,
1181
+ "loss": 0.4589,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 2.4754716981132074,
1186
+ "grad_norm": 0.10423805564641953,
1187
+ "learning_rate": 8.225609429353187e-06,
1188
+ "loss": 0.3094,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 2.490566037735849,
1193
+ "grad_norm": 0.08814896643161774,
1194
+ "learning_rate": 7.774699446684608e-06,
1195
+ "loss": 0.4504,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 2.5056603773584905,
1200
+ "grad_norm": 0.0902533084154129,
1201
+ "learning_rate": 7.33545591839222e-06,
1202
+ "loss": 0.7704,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 2.520754716981132,
1207
+ "grad_norm": 0.09167639911174774,
1208
+ "learning_rate": 6.908000203341802e-06,
1209
+ "loss": 0.8008,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 2.5358490566037735,
1214
+ "grad_norm": 0.09046367555856705,
1215
+ "learning_rate": 6.4924504035369595e-06,
1216
+ "loss": 0.8095,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 2.550943396226415,
1221
+ "grad_norm": 0.08376239240169525,
1222
+ "learning_rate": 6.088921331488568e-06,
1223
+ "loss": 0.757,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 2.5660377358490565,
1228
+ "grad_norm": 0.08740371465682983,
1229
+ "learning_rate": 5.6975244784932876e-06,
1230
+ "loss": 0.8007,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 2.581132075471698,
1235
+ "grad_norm": 0.09353169798851013,
1236
+ "learning_rate": 5.318367983829392e-06,
1237
+ "loss": 0.8656,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 2.5962264150943395,
1242
+ "grad_norm": 0.08881575614213943,
1243
+ "learning_rate": 4.951556604879048e-06,
1244
+ "loss": 0.8279,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 2.611320754716981,
1249
+ "grad_norm": 0.08782421052455902,
1250
+ "learning_rate": 4.597191688184754e-06,
1251
+ "loss": 0.8102,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 2.6264150943396225,
1256
+ "grad_norm": 0.0832432433962822,
1257
+ "learning_rate": 4.255371141448272e-06,
1258
+ "loss": 0.7513,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 2.641509433962264,
1263
+ "grad_norm": 0.09003833681344986,
1264
+ "learning_rate": 3.9261894064796135e-06,
1265
+ "loss": 0.8039,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 2.6566037735849055,
1270
+ "grad_norm": 0.09630510956048965,
1271
+ "learning_rate": 3.6097374331037324e-06,
1272
+ "loss": 0.8917,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 2.671698113207547,
1277
+ "grad_norm": 0.0935402363538742,
1278
+ "learning_rate": 3.306102654031823e-06,
1279
+ "loss": 0.7349,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 2.6867924528301885,
1284
+ "grad_norm": 0.08503729850053787,
1285
+ "learning_rate": 3.0153689607045845e-06,
1286
+ "loss": 0.4879,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 2.70188679245283,
1291
+ "grad_norm": 0.08797931671142578,
1292
+ "learning_rate": 2.737616680113758e-06,
1293
+ "loss": 0.3676,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 2.7169811320754715,
1298
+ "grad_norm": 0.10298191010951996,
1299
+ "learning_rate": 2.4729225526085586e-06,
1300
+ "loss": 0.3408,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 2.732075471698113,
1305
+ "grad_norm": 0.09024152904748917,
1306
+ "learning_rate": 2.221359710692961e-06,
1307
+ "loss": 0.4402,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 2.7471698113207546,
1312
+ "grad_norm": 0.08372613787651062,
1313
+ "learning_rate": 1.9829976588200127e-06,
1314
+ "loss": 0.6655,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 2.7622641509433965,
1319
+ "grad_norm": 0.08602160960435867,
1320
+ "learning_rate": 1.757902254188254e-06,
1321
+ "loss": 0.7168,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 2.777358490566038,
1326
+ "grad_norm": 0.0913161188364029,
1327
+ "learning_rate": 1.5461356885461075e-06,
1328
+ "loss": 0.79,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 2.7924528301886795,
1333
+ "grad_norm": 0.08356758952140808,
1334
+ "learning_rate": 1.3477564710088098e-06,
1335
+ "loss": 0.7183,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 2.807547169811321,
1340
+ "grad_norm": 0.08513372391462326,
1341
+ "learning_rate": 1.1628194118929403e-06,
1342
+ "loss": 0.7988,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 2.8226415094339625,
1347
+ "grad_norm": 0.08387143164873123,
1348
+ "learning_rate": 9.913756075728087e-07,
1349
+ "loss": 0.7751,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 2.837735849056604,
1354
+ "grad_norm": 0.09250643849372864,
1355
+ "learning_rate": 8.3347242636303e-07,
1356
+ "loss": 0.8318,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 2.8528301886792455,
1361
+ "grad_norm": 0.08692506700754166,
1362
+ "learning_rate": 6.891534954310885e-07,
1363
+ "loss": 0.8021,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 2.867924528301887,
1368
+ "grad_norm": 0.09043704718351364,
1369
+ "learning_rate": 5.584586887435739e-07,
1370
+ "loss": 0.828,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 2.8830188679245285,
1375
+ "grad_norm": 0.09076353162527084,
1376
+ "learning_rate": 4.4142411604936597e-07,
1377
+ "loss": 0.8358,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 2.89811320754717,
1382
+ "grad_norm": 0.08935835212469101,
1383
+ "learning_rate": 3.380821129028489e-07,
1384
+ "loss": 0.6771,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 2.9132075471698116,
1389
+ "grad_norm": 0.09465920180082321,
1390
+ "learning_rate": 2.4846123172992954e-07,
1391
+ "loss": 0.5426,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 2.928301886792453,
1396
+ "grad_norm": 0.08488347381353378,
1397
+ "learning_rate": 1.725862339392259e-07,
1398
+ "loss": 0.4009,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 2.9433962264150946,
1403
+ "grad_norm": 0.09194852411746979,
1404
+ "learning_rate": 1.1047808308075058e-07,
1405
+ "loss": 0.361,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 2.958490566037736,
1410
+ "grad_norm": 0.10439339280128479,
1411
+ "learning_rate": 6.215393905388278e-08,
1412
+ "loss": 0.346,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 2.9735849056603776,
1417
+ "grad_norm": 0.09068372845649719,
1418
+ "learning_rate": 2.7627153366222013e-08,
1419
+ "loss": 0.4575,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 2.988679245283019,
1424
+ "grad_norm": 0.09443732351064682,
1425
+ "learning_rate": 6.907265444716648e-09,
1426
+ "loss": 0.9297,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 3.0037735849056606,
1431
+ "grad_norm": 0.2620779573917389,
1432
+ "learning_rate": 0.0,
1433
+ "loss": 0.9032,
1434
+ "step": 199
1435
  }
1436
  ],
1437
  "logging_steps": 1,
 
1455
  "should_evaluate": false,
1456
  "should_log": false,
1457
  "should_save": true,
1458
+ "should_training_stop": true
1459
  },
1460
  "attributes": {}
1461
  }
1462
  },
1463
+ "total_flos": 1.1106999927098573e+17,
1464
  "train_batch_size": 8,
1465
  "trial_name": null,
1466
  "trial_params": null