0x1202 commited on
Commit
9397da4
·
verified ·
1 Parent(s): 876bd98

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 sha256:92ec4d3e1b50a4ff30e2bf1f05006f56ea3efd447c41d64d5623d87102449157
3
  size 100697728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d904635aafd7262fb48d82774a33f0c63581e73eacca262a5d8b05bb7237a3da
3
  size 100697728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:888b5e1a6607855d891c7bab38874bf60ffa824cef391e980c6ca0c206a9f735
3
  size 201541754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:396af0d89ed29d0664236084b68385ae8e41c5ba51925f56fd8e5625fb45dd04
3
  size 201541754
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f71b19c65eeaf96f89e07535f2c5affc99f8d23dd1cf5a7b0662cabc65ffe57d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b55ae87a977c230ca7cfec962e3d2a84a1ca4d96a78bc38cae6c48f9a8e480b8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e70710c409284f74d525f8db5cfaccc22a8afd29416f19c595da9242ec92d936
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe157715eb8e05b3bab2a7f2fafac33705dc4a1a9dd7f6d860c3a7f9597d78bb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.3069193363189697,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.26155187445510025,
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 +1113,372 @@
1113
  "eval_samples_per_second": 9.055,
1114
  "eval_steps_per_second": 1.268,
1115
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1116
  }
1117
  ],
1118
  "logging_steps": 1,
@@ -1136,12 +1502,12 @@
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": 1.174333336584192e+17,
1145
  "train_batch_size": 8,
1146
  "trial_name": null,
1147
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.21677221357822418,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.34873583260680036,
5
  "eval_steps": 25,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1113
  "eval_samples_per_second": 9.055,
1114
  "eval_steps_per_second": 1.268,
1115
  "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 0.2632955536181343,
1119
+ "grad_norm": 2.6976211071014404,
1120
+ "learning_rate": 4.659698863221513e-05,
1121
+ "loss": 0.9924,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 0.26503923278116825,
1126
+ "grad_norm": 2.4865119457244873,
1127
+ "learning_rate": 4.481448235912671e-05,
1128
+ "loss": 0.9836,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 0.2667829119442023,
1133
+ "grad_norm": 2.388842821121216,
1134
+ "learning_rate": 4.306073275629044e-05,
1135
+ "loss": 0.9307,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 0.26852659110723626,
1140
+ "grad_norm": 2.6463711261749268,
1141
+ "learning_rate": 4.133621928133665e-05,
1142
+ "loss": 0.9441,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 0.2702702702702703,
1147
+ "grad_norm": 3.185688018798828,
1148
+ "learning_rate": 3.964141339903026e-05,
1149
+ "loss": 1.5189,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 0.27201394943330426,
1154
+ "grad_norm": 2.5308520793914795,
1155
+ "learning_rate": 3.797677845237696e-05,
1156
+ "loss": 1.0876,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 0.2737576285963383,
1161
+ "grad_norm": 2.8542747497558594,
1162
+ "learning_rate": 3.634276953594982e-05,
1163
+ "loss": 1.1529,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 0.27550130775937226,
1168
+ "grad_norm": 2.9631950855255127,
1169
+ "learning_rate": 3.473983337147118e-05,
1170
+ "loss": 1.3245,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 0.2772449869224063,
1175
+ "grad_norm": 2.4584150314331055,
1176
+ "learning_rate": 3.316840818568315e-05,
1177
+ "loss": 1.1519,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 0.27898866608544026,
1182
+ "grad_norm": 1.8335541486740112,
1183
+ "learning_rate": 3.162892359054098e-05,
1184
+ "loss": 1.0986,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 0.2807323452484743,
1189
+ "grad_norm": 2.91326904296875,
1190
+ "learning_rate": 3.0121800465761293e-05,
1191
+ "loss": 1.215,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 0.28247602441150826,
1196
+ "grad_norm": 2.9668750762939453,
1197
+ "learning_rate": 2.8647450843757897e-05,
1198
+ "loss": 1.1686,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 0.2842197035745423,
1203
+ "grad_norm": 5.294821262359619,
1204
+ "learning_rate": 2.7206277796996144e-05,
1205
+ "loss": 2.1123,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 0.28596338273757627,
1210
+ "grad_norm": 2.0044138431549072,
1211
+ "learning_rate": 2.5798675327796993e-05,
1212
+ "loss": 1.032,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 0.2877070619006103,
1217
+ "grad_norm": 2.5393261909484863,
1218
+ "learning_rate": 2.4425028260620715e-05,
1219
+ "loss": 1.515,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 0.28945074106364427,
1224
+ "grad_norm": 2.9860572814941406,
1225
+ "learning_rate": 2.3085712136859668e-05,
1226
+ "loss": 1.3507,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 0.2911944202266783,
1231
+ "grad_norm": 2.4634785652160645,
1232
+ "learning_rate": 2.178109311216913e-05,
1233
+ "loss": 1.2136,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 0.29293809938971227,
1238
+ "grad_norm": 3.3339245319366455,
1239
+ "learning_rate": 2.0511527856363912e-05,
1240
+ "loss": 1.321,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 0.2946817785527463,
1245
+ "grad_norm": 2.1197123527526855,
1246
+ "learning_rate": 1.927736345590839e-05,
1247
+ "loss": 0.9253,
1248
+ "step": 169
1249
+ },
1250
+ {
1251
+ "epoch": 0.29642545771578027,
1252
+ "grad_norm": 3.588160753250122,
1253
+ "learning_rate": 1.8078937319026654e-05,
1254
+ "loss": 1.6052,
1255
+ "step": 170
1256
+ },
1257
+ {
1258
+ "epoch": 0.2981691368788143,
1259
+ "grad_norm": 2.9059865474700928,
1260
+ "learning_rate": 1.6916577083458228e-05,
1261
+ "loss": 1.4387,
1262
+ "step": 171
1263
+ },
1264
+ {
1265
+ "epoch": 0.2999128160418483,
1266
+ "grad_norm": 2.4765589237213135,
1267
+ "learning_rate": 1.579060052688548e-05,
1268
+ "loss": 1.382,
1269
+ "step": 172
1270
+ },
1271
+ {
1272
+ "epoch": 0.3016564952048823,
1273
+ "grad_norm": 2.4395883083343506,
1274
+ "learning_rate": 1.4701315480056164e-05,
1275
+ "loss": 1.0238,
1276
+ "step": 173
1277
+ },
1278
+ {
1279
+ "epoch": 0.30340017436791633,
1280
+ "grad_norm": 2.7470932006835938,
1281
+ "learning_rate": 1.3649019742625623e-05,
1282
+ "loss": 1.0419,
1283
+ "step": 174
1284
+ },
1285
+ {
1286
+ "epoch": 0.3051438535309503,
1287
+ "grad_norm": 1.5619500875473022,
1288
+ "learning_rate": 1.2634001001741373e-05,
1289
+ "loss": 0.8899,
1290
+ "step": 175
1291
+ },
1292
+ {
1293
+ "epoch": 0.3051438535309503,
1294
+ "eval_loss": 0.22784070670604706,
1295
+ "eval_runtime": 5.5215,
1296
+ "eval_samples_per_second": 9.055,
1297
+ "eval_steps_per_second": 1.268,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 0.30688753269398433,
1302
+ "grad_norm": 2.5386416912078857,
1303
+ "learning_rate": 1.1656536753392287e-05,
1304
+ "loss": 0.8694,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 0.3086312118570183,
1309
+ "grad_norm": 3.259190320968628,
1310
+ "learning_rate": 1.0716894226543953e-05,
1311
+ "loss": 1.0628,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 0.31037489102005233,
1316
+ "grad_norm": 1.8797160387039185,
1317
+ "learning_rate": 9.815330310080887e-06,
1318
+ "loss": 0.9535,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 0.3121185701830863,
1323
+ "grad_norm": 2.192770004272461,
1324
+ "learning_rate": 8.952091482575824e-06,
1325
+ "loss": 1.4844,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 0.31386224934612034,
1330
+ "grad_norm": 2.7970409393310547,
1331
+ "learning_rate": 8.127413744904804e-06,
1332
+ "loss": 1.439,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 0.3156059285091543,
1337
+ "grad_norm": 2.338233709335327,
1338
+ "learning_rate": 7.34152255572697e-06,
1339
+ "loss": 0.9264,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 0.31734960767218834,
1344
+ "grad_norm": 2.306898832321167,
1345
+ "learning_rate": 6.594632769846353e-06,
1346
+ "loss": 1.3452,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 0.3190932868352223,
1351
+ "grad_norm": 1.7065132856369019,
1352
+ "learning_rate": 5.886948579472778e-06,
1353
+ "loss": 0.6402,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 0.32083696599825634,
1358
+ "grad_norm": 2.7839744091033936,
1359
+ "learning_rate": 5.218663458397715e-06,
1360
+ "loss": 1.1321,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 0.3225806451612903,
1365
+ "grad_norm": 3.4941210746765137,
1366
+ "learning_rate": 4.589960109100444e-06,
1367
+ "loss": 1.2375,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 0.32432432432432434,
1372
+ "grad_norm": 2.152266502380371,
1373
+ "learning_rate": 4.001010412799138e-06,
1374
+ "loss": 0.9531,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 0.3260680034873583,
1379
+ "grad_norm": 3.6408121585845947,
1380
+ "learning_rate": 3.451975382460109e-06,
1381
+ "loss": 1.459,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 0.32781168265039234,
1386
+ "grad_norm": 1.6680314540863037,
1387
+ "learning_rate": 2.9430051187785962e-06,
1388
+ "loss": 0.9177,
1389
+ "step": 188
1390
+ },
1391
+ {
1392
+ "epoch": 0.3295553618134263,
1393
+ "grad_norm": 2.857945203781128,
1394
+ "learning_rate": 2.4742387691426445e-06,
1395
+ "loss": 1.4882,
1396
+ "step": 189
1397
+ },
1398
+ {
1399
+ "epoch": 0.33129904097646035,
1400
+ "grad_norm": 2.823565721511841,
1401
+ "learning_rate": 2.0458044895916513e-06,
1402
+ "loss": 1.6463,
1403
+ "step": 190
1404
+ },
1405
+ {
1406
+ "epoch": 0.3330427201394943,
1407
+ "grad_norm": 5.935178756713867,
1408
+ "learning_rate": 1.6578194097797258e-06,
1409
+ "loss": 1.3552,
1410
+ "step": 191
1411
+ },
1412
+ {
1413
+ "epoch": 0.33478639930252835,
1414
+ "grad_norm": 2.990522623062134,
1415
+ "learning_rate": 1.3103896009537207e-06,
1416
+ "loss": 1.763,
1417
+ "step": 192
1418
+ },
1419
+ {
1420
+ "epoch": 0.3365300784655623,
1421
+ "grad_norm": 2.7563226222991943,
1422
+ "learning_rate": 1.0036100469542786e-06,
1423
+ "loss": 1.8906,
1424
+ "step": 193
1425
+ },
1426
+ {
1427
+ "epoch": 0.33827375762859635,
1428
+ "grad_norm": 2.6643290519714355,
1429
+ "learning_rate": 7.375646182482875e-07,
1430
+ "loss": 1.5991,
1431
+ "step": 194
1432
+ },
1433
+ {
1434
+ "epoch": 0.3400174367916303,
1435
+ "grad_norm": 2.767608880996704,
1436
+ "learning_rate": 5.123260489995229e-07,
1437
+ "loss": 1.4336,
1438
+ "step": 195
1439
+ },
1440
+ {
1441
+ "epoch": 0.34176111595466435,
1442
+ "grad_norm": 2.827756643295288,
1443
+ "learning_rate": 3.2795591718381975e-07,
1444
+ "loss": 1.2425,
1445
+ "step": 196
1446
+ },
1447
+ {
1448
+ "epoch": 0.3435047951176983,
1449
+ "grad_norm": 2.2509312629699707,
1450
+ "learning_rate": 1.8450462775428942e-07,
1451
+ "loss": 1.4668,
1452
+ "step": 197
1453
+ },
1454
+ {
1455
+ "epoch": 0.34524847428073235,
1456
+ "grad_norm": 3.5071616172790527,
1457
+ "learning_rate": 8.201139886109264e-08,
1458
+ "loss": 1.2136,
1459
+ "step": 198
1460
+ },
1461
+ {
1462
+ "epoch": 0.3469921534437663,
1463
+ "grad_norm": 3.1070590019226074,
1464
+ "learning_rate": 2.0504251129649374e-08,
1465
+ "loss": 1.1762,
1466
+ "step": 199
1467
+ },
1468
+ {
1469
+ "epoch": 0.34873583260680036,
1470
+ "grad_norm": 5.442651748657227,
1471
+ "learning_rate": 0.0,
1472
+ "loss": 1.4769,
1473
+ "step": 200
1474
+ },
1475
+ {
1476
+ "epoch": 0.34873583260680036,
1477
+ "eval_loss": 0.21677221357822418,
1478
+ "eval_runtime": 5.5193,
1479
+ "eval_samples_per_second": 9.059,
1480
+ "eval_steps_per_second": 1.268,
1481
+ "step": 200
1482
  }
1483
  ],
1484
  "logging_steps": 1,
 
1502
  "should_evaluate": false,
1503
  "should_log": false,
1504
  "should_save": true,
1505
+ "should_training_stop": true
1506
  },
1507
  "attributes": {}
1508
  }
1509
  },
1510
+ "total_flos": 1.565777782112256e+17,
1511
  "train_batch_size": 8,
1512
  "trial_name": null,
1513
  "trial_params": null