ErrorAI commited on
Commit
ecb2ff7
·
verified ·
1 Parent(s): 9c9bbd1

Training in progress, step 237, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f57fed67a0a24032810adbe0e03ab8a7bf6dee246be2e490def9aa34d56def6
3
  size 25192496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c7840385f12fee7e74973749b9ba9470366178c241f0416b8d447a2249977c
3
  size 25192496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:388f822a50fd19459e4ab02c6bc13e74177d0578716f88456b8df9bfde914d13
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d186c5b450df85102e6f0d49946a662cbe5a139e38bac5221450562139d428d
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f29e05bcbde75ce27a9713f89d1d62332544e44f262dd85c2f7f43afaa9c494
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa75adfc30a7af2ef9a87d78b6749bb4f19e86bd670abdfb90a4c932cb27ed2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0950e2dffdf70f6969e672506b8287212d20b088ff729b93c9b723972fc5a09f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e6ec607bcb824b32dbf9532bd2490e6acd122f00ac7ed381d94679fcb4d357f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.7619047619047619,
5
  "eval_steps": 60,
6
- "global_step": 180,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1299,6 +1299,405 @@
1299
  "eval_samples_per_second": 68.347,
1300
  "eval_steps_per_second": 34.173,
1301
  "step": 180
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1302
  }
1303
  ],
1304
  "logging_steps": 1,
@@ -1313,12 +1712,12 @@
1313
  "should_evaluate": false,
1314
  "should_log": false,
1315
  "should_save": true,
1316
- "should_training_stop": false
1317
  },
1318
  "attributes": {}
1319
  }
1320
  },
1321
- "total_flos": 5374302643814400.0,
1322
  "train_batch_size": 2,
1323
  "trial_name": null,
1324
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0031746031746032,
5
  "eval_steps": 60,
6
+ "global_step": 237,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1299
  "eval_samples_per_second": 68.347,
1300
  "eval_steps_per_second": 34.173,
1301
  "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.7661375661375661,
1305
+ "grad_norm": 7.957937240600586,
1306
+ "learning_rate": 2.855918772175522e-05,
1307
+ "loss": 3.4826,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.7703703703703704,
1312
+ "grad_norm": 6.855284690856934,
1313
+ "learning_rate": 2.7597661864045233e-05,
1314
+ "loss": 3.4164,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.7746031746031746,
1319
+ "grad_norm": 5.783848285675049,
1320
+ "learning_rate": 2.6650003363154963e-05,
1321
+ "loss": 2.3278,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.7788359788359789,
1326
+ "grad_norm": 15.872426986694336,
1327
+ "learning_rate": 2.5716393725910215e-05,
1328
+ "loss": 3.0732,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.783068783068783,
1333
+ "grad_norm": 6.1523871421813965,
1334
+ "learning_rate": 2.47970117683313e-05,
1335
+ "loss": 2.9557,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.7873015873015873,
1340
+ "grad_norm": 8.40322494506836,
1341
+ "learning_rate": 2.389203358138419e-05,
1342
+ "loss": 3.7876,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.7915343915343915,
1347
+ "grad_norm": 6.189878463745117,
1348
+ "learning_rate": 2.3001632497253424e-05,
1349
+ "loss": 2.9313,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.7957671957671958,
1354
+ "grad_norm": 4.903008460998535,
1355
+ "learning_rate": 2.2125979056143364e-05,
1356
+ "loss": 1.6503,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.8,
1361
+ "grad_norm": 8.661479949951172,
1362
+ "learning_rate": 2.1265240973614486e-05,
1363
+ "loss": 3.0821,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.8042328042328042,
1368
+ "grad_norm": 5.910584926605225,
1369
+ "learning_rate": 2.0419583108460418e-05,
1370
+ "loss": 2.6028,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.8084656084656084,
1375
+ "grad_norm": 6.254149436950684,
1376
+ "learning_rate": 1.958916743113214e-05,
1377
+ "loss": 2.7991,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.8126984126984127,
1382
+ "grad_norm": 7.573146820068359,
1383
+ "learning_rate": 1.877415299271561e-05,
1384
+ "loss": 2.5724,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.816931216931217,
1389
+ "grad_norm": 5.690131187438965,
1390
+ "learning_rate": 1.7974695894468384e-05,
1391
+ "loss": 2.2762,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.8211640211640212,
1396
+ "grad_norm": 5.798933982849121,
1397
+ "learning_rate": 1.7190949257921196e-05,
1398
+ "loss": 2.1385,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.8253968253968254,
1403
+ "grad_norm": 7.621517658233643,
1404
+ "learning_rate": 1.642306319555027e-05,
1405
+ "loss": 2.5064,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.8296296296296296,
1410
+ "grad_norm": 7.2165350914001465,
1411
+ "learning_rate": 1.5671184782026106e-05,
1412
+ "loss": 2.7742,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.8338624338624339,
1417
+ "grad_norm": 6.8323211669921875,
1418
+ "learning_rate": 1.4935458026043959e-05,
1419
+ "loss": 2.869,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.8380952380952381,
1424
+ "grad_norm": 6.338479042053223,
1425
+ "learning_rate": 1.4216023842741455e-05,
1426
+ "loss": 2.9435,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.8423280423280424,
1431
+ "grad_norm": 6.278661727905273,
1432
+ "learning_rate": 1.3513020026709023e-05,
1433
+ "loss": 2.7868,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.8465608465608465,
1438
+ "grad_norm": 5.375467300415039,
1439
+ "learning_rate": 1.2826581225597767e-05,
1440
+ "loss": 2.6017,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.8507936507936508,
1445
+ "grad_norm": 7.244228839874268,
1446
+ "learning_rate": 1.2156838914330072e-05,
1447
+ "loss": 3.1561,
1448
+ "step": 201
1449
+ },
1450
+ {
1451
+ "epoch": 0.855026455026455,
1452
+ "grad_norm": 6.201519012451172,
1453
+ "learning_rate": 1.1503921369918091e-05,
1454
+ "loss": 2.5623,
1455
+ "step": 202
1456
+ },
1457
+ {
1458
+ "epoch": 0.8592592592592593,
1459
+ "grad_norm": 5.793484210968018,
1460
+ "learning_rate": 1.0867953646894525e-05,
1461
+ "loss": 2.8732,
1462
+ "step": 203
1463
+ },
1464
+ {
1465
+ "epoch": 0.8634920634920635,
1466
+ "grad_norm": 7.211161136627197,
1467
+ "learning_rate": 1.0249057553360742e-05,
1468
+ "loss": 3.4671,
1469
+ "step": 204
1470
+ },
1471
+ {
1472
+ "epoch": 0.8677248677248677,
1473
+ "grad_norm": 6.088332176208496,
1474
+ "learning_rate": 9.647351627656543e-06,
1475
+ "loss": 1.7759,
1476
+ "step": 205
1477
+ },
1478
+ {
1479
+ "epoch": 0.8719576719576719,
1480
+ "grad_norm": 6.6968488693237305,
1481
+ "learning_rate": 9.062951115656403e-06,
1482
+ "loss": 3.3001,
1483
+ "step": 206
1484
+ },
1485
+ {
1486
+ "epoch": 0.8761904761904762,
1487
+ "grad_norm": 5.636354446411133,
1488
+ "learning_rate": 8.495967948696192e-06,
1489
+ "loss": 2.7173,
1490
+ "step": 207
1491
+ },
1492
+ {
1493
+ "epoch": 0.8804232804232804,
1494
+ "grad_norm": 5.944347858428955,
1495
+ "learning_rate": 7.946510722134692e-06,
1496
+ "loss": 2.454,
1497
+ "step": 208
1498
+ },
1499
+ {
1500
+ "epoch": 0.8846560846560847,
1501
+ "grad_norm": 6.995573997497559,
1502
+ "learning_rate": 7.4146846745541506e-06,
1503
+ "loss": 3.2652,
1504
+ "step": 209
1505
+ },
1506
+ {
1507
+ "epoch": 0.8888888888888888,
1508
+ "grad_norm": 7.945988178253174,
1509
+ "learning_rate": 6.900591667603751e-06,
1510
+ "loss": 3.5859,
1511
+ "step": 210
1512
+ },
1513
+ {
1514
+ "epoch": 0.8931216931216931,
1515
+ "grad_norm": 5.948593616485596,
1516
+ "learning_rate": 6.40433016648988e-06,
1517
+ "loss": 2.3406,
1518
+ "step": 211
1519
+ },
1520
+ {
1521
+ "epoch": 0.8973544973544973,
1522
+ "grad_norm": 6.893688201904297,
1523
+ "learning_rate": 5.925995221116853e-06,
1524
+ "loss": 2.5966,
1525
+ "step": 212
1526
+ },
1527
+ {
1528
+ "epoch": 0.9015873015873016,
1529
+ "grad_norm": 6.056822776794434,
1530
+ "learning_rate": 5.465678447881828e-06,
1531
+ "loss": 3.1498,
1532
+ "step": 213
1533
+ },
1534
+ {
1535
+ "epoch": 0.9058201058201059,
1536
+ "grad_norm": 5.484859943389893,
1537
+ "learning_rate": 5.023468012127364e-06,
1538
+ "loss": 2.3254,
1539
+ "step": 214
1540
+ },
1541
+ {
1542
+ "epoch": 0.91005291005291,
1543
+ "grad_norm": 5.663562774658203,
1544
+ "learning_rate": 4.599448611254964e-06,
1545
+ "loss": 2.4197,
1546
+ "step": 215
1547
+ },
1548
+ {
1549
+ "epoch": 0.9142857142857143,
1550
+ "grad_norm": 7.122875690460205,
1551
+ "learning_rate": 4.193701458502807e-06,
1552
+ "loss": 3.4631,
1553
+ "step": 216
1554
+ },
1555
+ {
1556
+ "epoch": 0.9185185185185185,
1557
+ "grad_norm": 5.062466621398926,
1558
+ "learning_rate": 3.80630426739077e-06,
1559
+ "loss": 2.0242,
1560
+ "step": 217
1561
+ },
1562
+ {
1563
+ "epoch": 0.9227513227513228,
1564
+ "grad_norm": 6.852725505828857,
1565
+ "learning_rate": 3.4373312368358944e-06,
1566
+ "loss": 2.3947,
1567
+ "step": 218
1568
+ },
1569
+ {
1570
+ "epoch": 0.926984126984127,
1571
+ "grad_norm": 6.722269058227539,
1572
+ "learning_rate": 3.086853036940862e-06,
1573
+ "loss": 2.9278,
1574
+ "step": 219
1575
+ },
1576
+ {
1577
+ "epoch": 0.9312169312169312,
1578
+ "grad_norm": 7.214760780334473,
1579
+ "learning_rate": 2.754936795458485e-06,
1580
+ "loss": 2.5268,
1581
+ "step": 220
1582
+ },
1583
+ {
1584
+ "epoch": 0.9354497354497354,
1585
+ "grad_norm": 7.218380451202393,
1586
+ "learning_rate": 2.4416460849345123e-06,
1587
+ "loss": 2.9904,
1588
+ "step": 221
1589
+ },
1590
+ {
1591
+ "epoch": 0.9396825396825397,
1592
+ "grad_norm": 6.950320720672607,
1593
+ "learning_rate": 2.1470409105315283e-06,
1594
+ "loss": 2.7091,
1595
+ "step": 222
1596
+ },
1597
+ {
1598
+ "epoch": 0.9439153439153439,
1599
+ "grad_norm": 5.87589168548584,
1600
+ "learning_rate": 1.8711776985360308e-06,
1601
+ "loss": 2.4052,
1602
+ "step": 223
1603
+ },
1604
+ {
1605
+ "epoch": 0.9481481481481482,
1606
+ "grad_norm": 5.747050762176514,
1607
+ "learning_rate": 1.61410928555098e-06,
1608
+ "loss": 2.5603,
1609
+ "step": 224
1610
+ },
1611
+ {
1612
+ "epoch": 0.9523809523809523,
1613
+ "grad_norm": 6.162868976593018,
1614
+ "learning_rate": 1.3758849083759352e-06,
1615
+ "loss": 2.5383,
1616
+ "step": 225
1617
+ },
1618
+ {
1619
+ "epoch": 0.9566137566137566,
1620
+ "grad_norm": 6.223538875579834,
1621
+ "learning_rate": 1.1565501945766222e-06,
1622
+ "loss": 2.7093,
1623
+ "step": 226
1624
+ },
1625
+ {
1626
+ "epoch": 0.9608465608465608,
1627
+ "grad_norm": 6.424678802490234,
1628
+ "learning_rate": 9.56147153745779e-07,
1629
+ "loss": 2.2974,
1630
+ "step": 227
1631
+ },
1632
+ {
1633
+ "epoch": 0.9650793650793651,
1634
+ "grad_norm": 8.89910888671875,
1635
+ "learning_rate": 7.747141694570026e-07,
1636
+ "loss": 3.2458,
1637
+ "step": 228
1638
+ },
1639
+ {
1640
+ "epoch": 0.9693121693121693,
1641
+ "grad_norm": 5.710629463195801,
1642
+ "learning_rate": 6.122859919130974e-07,
1643
+ "loss": 3.1255,
1644
+ "step": 229
1645
+ },
1646
+ {
1647
+ "epoch": 0.9735449735449735,
1648
+ "grad_norm": 5.598289489746094,
1649
+ "learning_rate": 4.6889373129022085e-07,
1650
+ "loss": 2.3627,
1651
+ "step": 230
1652
+ },
1653
+ {
1654
+ "epoch": 0.9777777777777777,
1655
+ "grad_norm": 6.710612773895264,
1656
+ "learning_rate": 3.445648517793942e-07,
1657
+ "loss": 2.4085,
1658
+ "step": 231
1659
+ },
1660
+ {
1661
+ "epoch": 0.982010582010582,
1662
+ "grad_norm": 6.431200981140137,
1663
+ "learning_rate": 2.3932316632614416e-07,
1664
+ "loss": 2.8684,
1665
+ "step": 232
1666
+ },
1667
+ {
1668
+ "epoch": 0.9862433862433863,
1669
+ "grad_norm": 6.007854461669922,
1670
+ "learning_rate": 1.5318883206962842e-07,
1671
+ "loss": 2.7014,
1672
+ "step": 233
1673
+ },
1674
+ {
1675
+ "epoch": 0.9904761904761905,
1676
+ "grad_norm": 5.230172634124756,
1677
+ "learning_rate": 8.617834648185774e-08,
1678
+ "loss": 2.6608,
1679
+ "step": 234
1680
+ },
1681
+ {
1682
+ "epoch": 0.9947089947089947,
1683
+ "grad_norm": 6.711563587188721,
1684
+ "learning_rate": 3.8304544207945495e-08,
1685
+ "loss": 2.612,
1686
+ "step": 235
1687
+ },
1688
+ {
1689
+ "epoch": 0.9989417989417989,
1690
+ "grad_norm": 5.968123912811279,
1691
+ "learning_rate": 9.576594607807465e-09,
1692
+ "loss": 2.2378,
1693
+ "step": 236
1694
+ },
1695
+ {
1696
+ "epoch": 1.0031746031746032,
1697
+ "grad_norm": 6.985171318054199,
1698
+ "learning_rate": 0.0,
1699
+ "loss": 2.7958,
1700
+ "step": 237
1701
  }
1702
  ],
1703
  "logging_steps": 1,
 
1712
  "should_evaluate": false,
1713
  "should_log": false,
1714
  "should_save": true,
1715
+ "should_training_stop": true
1716
  },
1717
  "attributes": {}
1718
  }
1719
  },
1720
+ "total_flos": 7072432993075200.0,
1721
  "train_batch_size": 2,
1722
  "trial_name": null,
1723
  "trial_params": null