magatex commited on
Commit
bfd7deb
·
verified ·
1 Parent(s): dfc31a3

Training in progress, step 190, 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:b63bc9d574a1e345fc18c69107e6e6be6d868f3c4a2374ff6dca021fca856ecc
3
  size 100966336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343c1413ea61110e9ebf894c3ac3f0bf6fc2c2d0350e548b608a4ed6b9025375
3
  size 100966336
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe0c28bfe4d853a31d04be135ca4e997ab5a91e658ae11b8ad2911ff1fa9e4bc
3
  size 202110330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c531dcf5a32114e0a68282c25cf49d0edf1632e6ce8ee2da4834ef2a77d2d5
3
  size 202110330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30171f90f1f394c061f52ff83feba83fa242f21f32d0e16ee62eb252bde7bbbc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1748613d6fe579509e3840a49ac2fdd8a596903c8c8205b822e98ccf4ff543d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:445b7598993fe3a18f07b6ee10e450c957df6de162dc7729c132643a3ca6e545
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0717fa852ff14c4fb6ef3d8fb6e7d6c5b1e6b17d5f3ada276b0ae8e8648b64
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.0219863653182983,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 1.1214953271028036,
5
  "eval_steps": 25,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1113,6 +1113,294 @@
1113
  "eval_samples_per_second": 28.515,
1114
  "eval_steps_per_second": 3.992,
1115
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1116
  }
1117
  ],
1118
  "logging_steps": 1,
@@ -1136,12 +1424,12 @@
1136
  "should_evaluate": false,
1137
  "should_log": false,
1138
  "should_save": true,
1139
- "should_training_stop": false
1140
  },
1141
  "attributes": {}
1142
  }
1143
  },
1144
- "total_flos": 6.249320727497933e+16,
1145
  "train_batch_size": 8,
1146
  "trial_name": null,
1147
  "trial_params": null
 
1
  {
2
  "best_metric": 1.0219863653182983,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.4205607476635513,
5
  "eval_steps": 25,
6
+ "global_step": 190,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1113
  "eval_samples_per_second": 28.515,
1114
  "eval_steps_per_second": 3.992,
1115
  "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 1.1289719626168224,
1119
+ "grad_norm": 1.3583935499191284,
1120
+ "learning_rate": 1.9922179741796086e-05,
1121
+ "loss": 0.8198,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 1.1364485981308412,
1126
+ "grad_norm": 1.284717321395874,
1127
+ "learning_rate": 1.9438237813334586e-05,
1128
+ "loss": 0.7878,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 1.1439252336448598,
1133
+ "grad_norm": 1.3621183633804321,
1134
+ "learning_rate": 1.8965008980117037e-05,
1135
+ "loss": 0.9232,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 1.1514018691588785,
1140
+ "grad_norm": 1.6327229738235474,
1141
+ "learning_rate": 1.850263580385163e-05,
1142
+ "loss": 1.0294,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 1.158878504672897,
1147
+ "grad_norm": 1.386734127998352,
1148
+ "learning_rate": 1.8051257575944925e-05,
1149
+ "loss": 0.8834,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 1.1663551401869159,
1154
+ "grad_norm": 1.375533938407898,
1155
+ "learning_rate": 1.7611010275539962e-05,
1156
+ "loss": 0.9483,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 1.1738317757009347,
1161
+ "grad_norm": 1.242241382598877,
1162
+ "learning_rate": 1.718202652855205e-05,
1163
+ "loss": 0.8194,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 1.1813084112149532,
1168
+ "grad_norm": 1.247066617012024,
1169
+ "learning_rate": 1.6764435567714794e-05,
1170
+ "loss": 0.8326,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 1.188785046728972,
1175
+ "grad_norm": 1.4270540475845337,
1176
+ "learning_rate": 1.6358363193648352e-05,
1177
+ "loss": 0.8584,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 1.1962616822429906,
1182
+ "grad_norm": 1.225496768951416,
1183
+ "learning_rate": 1.5963931736961547e-05,
1184
+ "loss": 0.8475,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 1.2037383177570093,
1189
+ "grad_norm": 1.2226568460464478,
1190
+ "learning_rate": 1.5581260021399396e-05,
1191
+ "loss": 0.828,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 1.2112149532710281,
1196
+ "grad_norm": 1.387080192565918,
1197
+ "learning_rate": 1.5210463328047095e-05,
1198
+ "loss": 0.8902,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 1.2186915887850467,
1203
+ "grad_norm": 1.2809566259384155,
1204
+ "learning_rate": 1.4851653360601179e-05,
1205
+ "loss": 0.9188,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 1.2261682242990655,
1210
+ "grad_norm": 1.4872632026672363,
1211
+ "learning_rate": 1.4504938211718489e-05,
1212
+ "loss": 1.1853,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 1.233644859813084,
1217
+ "grad_norm": 1.3789664506912231,
1218
+ "learning_rate": 1.4170422330452816e-05,
1219
+ "loss": 0.9331,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 1.2411214953271028,
1224
+ "grad_norm": 1.7620553970336914,
1225
+ "learning_rate": 1.384820649078939e-05,
1226
+ "loss": 1.3851,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 1.2485981308411216,
1231
+ "grad_norm": 2.51485013961792,
1232
+ "learning_rate": 1.3538387761286303e-05,
1233
+ "loss": 1.7585,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 1.2560747663551401,
1238
+ "grad_norm": 1.4379189014434814,
1239
+ "learning_rate": 1.3241059475832373e-05,
1240
+ "loss": 0.9246,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 1.263551401869159,
1245
+ "grad_norm": 1.3618923425674438,
1246
+ "learning_rate": 1.2956311205529943e-05,
1247
+ "loss": 0.8608,
1248
+ "step": 169
1249
+ },
1250
+ {
1251
+ "epoch": 1.2710280373831775,
1252
+ "grad_norm": 1.3011233806610107,
1253
+ "learning_rate": 1.268422873171136e-05,
1254
+ "loss": 0.8322,
1255
+ "step": 170
1256
+ },
1257
+ {
1258
+ "epoch": 1.2785046728971963,
1259
+ "grad_norm": 1.5399248600006104,
1260
+ "learning_rate": 1.2424894020096997e-05,
1261
+ "loss": 0.7588,
1262
+ "step": 171
1263
+ },
1264
+ {
1265
+ "epoch": 1.2859813084112148,
1266
+ "grad_norm": 1.449872374534607,
1267
+ "learning_rate": 1.217838519610291e-05,
1268
+ "loss": 0.857,
1269
+ "step": 172
1270
+ },
1271
+ {
1272
+ "epoch": 1.2934579439252336,
1273
+ "grad_norm": 1.3477046489715576,
1274
+ "learning_rate": 1.1944776521305213e-05,
1275
+ "loss": 0.8627,
1276
+ "step": 173
1277
+ },
1278
+ {
1279
+ "epoch": 1.3009345794392524,
1280
+ "grad_norm": 1.3076852560043335,
1281
+ "learning_rate": 1.1724138371068603e-05,
1282
+ "loss": 0.9005,
1283
+ "step": 174
1284
+ },
1285
+ {
1286
+ "epoch": 1.308411214953271,
1287
+ "grad_norm": 1.294968843460083,
1288
+ "learning_rate": 1.1516537213345519e-05,
1289
+ "loss": 0.7639,
1290
+ "step": 175
1291
+ },
1292
+ {
1293
+ "epoch": 1.308411214953271,
1294
+ "eval_loss": 1.0100014209747314,
1295
+ "eval_runtime": 1.729,
1296
+ "eval_samples_per_second": 28.918,
1297
+ "eval_steps_per_second": 4.049,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 1.3158878504672897,
1302
+ "grad_norm": 1.3219696283340454,
1303
+ "learning_rate": 1.1322035588652484e-05,
1304
+ "loss": 0.7752,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 1.3233644859813083,
1309
+ "grad_norm": 1.1848926544189453,
1310
+ "learning_rate": 1.1140692091229556e-05,
1311
+ "loss": 0.7759,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 1.330841121495327,
1316
+ "grad_norm": 1.1485064029693604,
1317
+ "learning_rate": 1.0972561351388622e-05,
1318
+ "loss": 0.7454,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 1.3383177570093459,
1323
+ "grad_norm": 1.1740100383758545,
1324
+ "learning_rate": 1.0817694019055866e-05,
1325
+ "loss": 0.761,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 1.3457943925233644,
1330
+ "grad_norm": 1.3378069400787354,
1331
+ "learning_rate": 1.0676136748513286e-05,
1332
+ "loss": 0.8535,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 1.3532710280373832,
1337
+ "grad_norm": 1.2721531391143799,
1338
+ "learning_rate": 1.0547932184343948e-05,
1339
+ "loss": 0.8117,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 1.3607476635514018,
1344
+ "grad_norm": 1.255110740661621,
1345
+ "learning_rate": 1.043311894858519e-05,
1346
+ "loss": 0.8114,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 1.3682242990654205,
1351
+ "grad_norm": 1.184085726737976,
1352
+ "learning_rate": 1.033173162909358e-05,
1353
+ "loss": 0.7484,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 1.3757009345794393,
1358
+ "grad_norm": 1.2864772081375122,
1359
+ "learning_rate": 1.0243800769125222e-05,
1360
+ "loss": 0.8197,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 1.3831775700934579,
1365
+ "grad_norm": 1.3960767984390259,
1366
+ "learning_rate": 1.0169352858134525e-05,
1367
+ "loss": 0.8416,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 1.3906542056074767,
1372
+ "grad_norm": 1.6105817556381226,
1373
+ "learning_rate": 1.0108410323794131e-05,
1374
+ "loss": 0.8156,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 1.3981308411214952,
1379
+ "grad_norm": 1.4161114692687988,
1380
+ "learning_rate": 1.0060991525238538e-05,
1381
+ "loss": 0.8663,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 1.405607476635514,
1386
+ "grad_norm": 1.3891263008117676,
1387
+ "learning_rate": 1.0027110747533332e-05,
1388
+ "loss": 0.9249,
1389
+ "step": 188
1390
+ },
1391
+ {
1392
+ "epoch": 1.4130841121495328,
1393
+ "grad_norm": 1.4171258211135864,
1394
+ "learning_rate": 1.0006778197371774e-05,
1395
+ "loss": 0.837,
1396
+ "step": 189
1397
+ },
1398
+ {
1399
+ "epoch": 1.4205607476635513,
1400
+ "grad_norm": 1.4086953401565552,
1401
+ "learning_rate": 1e-05,
1402
+ "loss": 0.9393,
1403
+ "step": 190
1404
  }
1405
  ],
1406
  "logging_steps": 1,
 
1424
  "should_evaluate": false,
1425
  "should_log": false,
1426
  "should_save": true,
1427
+ "should_training_stop": true
1428
  },
1429
  "attributes": {}
1430
  }
1431
  },
1432
+ "total_flos": 7.916153511660749e+16,
1433
  "train_batch_size": 8,
1434
  "trial_name": null,
1435
  "trial_params": null