Azamorn commited on
Commit
8ffde91
1 Parent(s): 04af1da

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. model.safetensors +1 -1
  2. optimizer.pt +1 -1
  3. scheduler.pt +1 -1
  4. trainer_state.json +603 -3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c158b28744f13168b014d5cf922deca9738e6809ab54db7e8affc8232fcb3974
3
  size 1615784368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c97e63770e3735813765be2c9ba1d4ed42ce9f6d5cb1fe6436b55911b8fb122a
3
  size 1615784368
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9332add6073f65b7e3a08cc193bb303da7205dba8c332784ee758e46bc804da6
3
  size 3231643962
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1065d6ac0bb1bbe0b5d374b2d9de7bd167bcfd8d9ab60bcd6fb1e468ea7dc8c8
3
  size 3231643962
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45925f2efb7989009db479896dcd4dc450d8b946cbe8f7080ca846dee0a898df
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da2ce3420af021e22f607bef056bacad267b44e24aab62c3270b61d3493433c9
3
  size 1064
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.2,
5
  "eval_steps": 500,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1207,6 +1207,606 @@
1207
  "learning_rate": 0.0003799519807923169,
1208
  "loss": 1.9875,
1209
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1210
  }
1211
  ],
1212
  "logging_steps": 5,
@@ -1214,7 +1814,7 @@
1214
  "num_input_tokens_seen": 0,
1215
  "num_train_epochs": 5,
1216
  "save_steps": 500,
1217
- "total_flos": 1.974401690333184e+16,
1218
  "train_batch_size": 8,
1219
  "trial_name": null,
1220
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.8,
5
  "eval_steps": 500,
6
+ "global_step": 1500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1207
  "learning_rate": 0.0003799519807923169,
1208
  "loss": 1.9875,
1209
  "step": 1000
1210
+ },
1211
+ {
1212
+ "epoch": 1.21,
1213
+ "learning_rate": 0.00037935174069627856,
1214
+ "loss": 2.0543,
1215
+ "step": 1005
1216
+ },
1217
+ {
1218
+ "epoch": 1.21,
1219
+ "learning_rate": 0.0003787515006002401,
1220
+ "loss": 2.1018,
1221
+ "step": 1010
1222
+ },
1223
+ {
1224
+ "epoch": 1.22,
1225
+ "learning_rate": 0.00037815126050420167,
1226
+ "loss": 2.1016,
1227
+ "step": 1015
1228
+ },
1229
+ {
1230
+ "epoch": 1.22,
1231
+ "learning_rate": 0.00037755102040816323,
1232
+ "loss": 2.0779,
1233
+ "step": 1020
1234
+ },
1235
+ {
1236
+ "epoch": 1.23,
1237
+ "learning_rate": 0.0003769507803121249,
1238
+ "loss": 2.1172,
1239
+ "step": 1025
1240
+ },
1241
+ {
1242
+ "epoch": 1.24,
1243
+ "learning_rate": 0.00037635054021608645,
1244
+ "loss": 2.0815,
1245
+ "step": 1030
1246
+ },
1247
+ {
1248
+ "epoch": 1.24,
1249
+ "learning_rate": 0.000375750300120048,
1250
+ "loss": 2.0598,
1251
+ "step": 1035
1252
+ },
1253
+ {
1254
+ "epoch": 1.25,
1255
+ "learning_rate": 0.00037515006002400956,
1256
+ "loss": 2.0456,
1257
+ "step": 1040
1258
+ },
1259
+ {
1260
+ "epoch": 1.25,
1261
+ "learning_rate": 0.00037454981992797123,
1262
+ "loss": 2.1081,
1263
+ "step": 1045
1264
+ },
1265
+ {
1266
+ "epoch": 1.26,
1267
+ "learning_rate": 0.0003739495798319328,
1268
+ "loss": 2.0235,
1269
+ "step": 1050
1270
+ },
1271
+ {
1272
+ "epoch": 1.27,
1273
+ "learning_rate": 0.00037334933973589434,
1274
+ "loss": 2.0866,
1275
+ "step": 1055
1276
+ },
1277
+ {
1278
+ "epoch": 1.27,
1279
+ "learning_rate": 0.0003727490996398559,
1280
+ "loss": 2.0599,
1281
+ "step": 1060
1282
+ },
1283
+ {
1284
+ "epoch": 1.28,
1285
+ "learning_rate": 0.00037214885954381757,
1286
+ "loss": 2.0281,
1287
+ "step": 1065
1288
+ },
1289
+ {
1290
+ "epoch": 1.28,
1291
+ "learning_rate": 0.0003715486194477791,
1292
+ "loss": 2.0481,
1293
+ "step": 1070
1294
+ },
1295
+ {
1296
+ "epoch": 1.29,
1297
+ "learning_rate": 0.0003709483793517407,
1298
+ "loss": 2.0223,
1299
+ "step": 1075
1300
+ },
1301
+ {
1302
+ "epoch": 1.3,
1303
+ "learning_rate": 0.0003703481392557023,
1304
+ "loss": 2.0303,
1305
+ "step": 1080
1306
+ },
1307
+ {
1308
+ "epoch": 1.3,
1309
+ "learning_rate": 0.0003697478991596639,
1310
+ "loss": 2.13,
1311
+ "step": 1085
1312
+ },
1313
+ {
1314
+ "epoch": 1.31,
1315
+ "learning_rate": 0.00036914765906362546,
1316
+ "loss": 2.1372,
1317
+ "step": 1090
1318
+ },
1319
+ {
1320
+ "epoch": 1.31,
1321
+ "learning_rate": 0.000368547418967587,
1322
+ "loss": 2.0192,
1323
+ "step": 1095
1324
+ },
1325
+ {
1326
+ "epoch": 1.32,
1327
+ "learning_rate": 0.00036794717887154863,
1328
+ "loss": 2.0754,
1329
+ "step": 1100
1330
+ },
1331
+ {
1332
+ "epoch": 1.33,
1333
+ "learning_rate": 0.00036734693877551024,
1334
+ "loss": 2.123,
1335
+ "step": 1105
1336
+ },
1337
+ {
1338
+ "epoch": 1.33,
1339
+ "learning_rate": 0.0003667466986794718,
1340
+ "loss": 2.0884,
1341
+ "step": 1110
1342
+ },
1343
+ {
1344
+ "epoch": 1.34,
1345
+ "learning_rate": 0.00036614645858343335,
1346
+ "loss": 2.0835,
1347
+ "step": 1115
1348
+ },
1349
+ {
1350
+ "epoch": 1.34,
1351
+ "learning_rate": 0.00036554621848739496,
1352
+ "loss": 2.0276,
1353
+ "step": 1120
1354
+ },
1355
+ {
1356
+ "epoch": 1.35,
1357
+ "learning_rate": 0.0003649459783913566,
1358
+ "loss": 2.0106,
1359
+ "step": 1125
1360
+ },
1361
+ {
1362
+ "epoch": 1.36,
1363
+ "learning_rate": 0.00036434573829531813,
1364
+ "loss": 1.9971,
1365
+ "step": 1130
1366
+ },
1367
+ {
1368
+ "epoch": 1.36,
1369
+ "learning_rate": 0.0003637454981992797,
1370
+ "loss": 1.9734,
1371
+ "step": 1135
1372
+ },
1373
+ {
1374
+ "epoch": 1.37,
1375
+ "learning_rate": 0.0003631452581032413,
1376
+ "loss": 2.0989,
1377
+ "step": 1140
1378
+ },
1379
+ {
1380
+ "epoch": 1.37,
1381
+ "learning_rate": 0.0003625450180072029,
1382
+ "loss": 2.0539,
1383
+ "step": 1145
1384
+ },
1385
+ {
1386
+ "epoch": 1.38,
1387
+ "learning_rate": 0.00036194477791116447,
1388
+ "loss": 1.9613,
1389
+ "step": 1150
1390
+ },
1391
+ {
1392
+ "epoch": 1.39,
1393
+ "learning_rate": 0.000361344537815126,
1394
+ "loss": 2.0324,
1395
+ "step": 1155
1396
+ },
1397
+ {
1398
+ "epoch": 1.39,
1399
+ "learning_rate": 0.00036074429771908764,
1400
+ "loss": 2.0144,
1401
+ "step": 1160
1402
+ },
1403
+ {
1404
+ "epoch": 1.4,
1405
+ "learning_rate": 0.00036014405762304925,
1406
+ "loss": 2.0124,
1407
+ "step": 1165
1408
+ },
1409
+ {
1410
+ "epoch": 1.4,
1411
+ "learning_rate": 0.0003595438175270108,
1412
+ "loss": 2.0638,
1413
+ "step": 1170
1414
+ },
1415
+ {
1416
+ "epoch": 1.41,
1417
+ "learning_rate": 0.00035894357743097236,
1418
+ "loss": 2.0049,
1419
+ "step": 1175
1420
+ },
1421
+ {
1422
+ "epoch": 1.42,
1423
+ "learning_rate": 0.000358343337334934,
1424
+ "loss": 2.0731,
1425
+ "step": 1180
1426
+ },
1427
+ {
1428
+ "epoch": 1.42,
1429
+ "learning_rate": 0.0003577430972388956,
1430
+ "loss": 2.0804,
1431
+ "step": 1185
1432
+ },
1433
+ {
1434
+ "epoch": 1.43,
1435
+ "learning_rate": 0.00035714285714285714,
1436
+ "loss": 2.0652,
1437
+ "step": 1190
1438
+ },
1439
+ {
1440
+ "epoch": 1.43,
1441
+ "learning_rate": 0.00035654261704681875,
1442
+ "loss": 1.9836,
1443
+ "step": 1195
1444
+ },
1445
+ {
1446
+ "epoch": 1.44,
1447
+ "learning_rate": 0.0003559423769507803,
1448
+ "loss": 2.0288,
1449
+ "step": 1200
1450
+ },
1451
+ {
1452
+ "epoch": 1.45,
1453
+ "learning_rate": 0.0003553421368547419,
1454
+ "loss": 1.9811,
1455
+ "step": 1205
1456
+ },
1457
+ {
1458
+ "epoch": 1.45,
1459
+ "learning_rate": 0.0003547418967587035,
1460
+ "loss": 1.9923,
1461
+ "step": 1210
1462
+ },
1463
+ {
1464
+ "epoch": 1.46,
1465
+ "learning_rate": 0.0003541416566626651,
1466
+ "loss": 2.0066,
1467
+ "step": 1215
1468
+ },
1469
+ {
1470
+ "epoch": 1.46,
1471
+ "learning_rate": 0.00035354141656662665,
1472
+ "loss": 1.992,
1473
+ "step": 1220
1474
+ },
1475
+ {
1476
+ "epoch": 1.47,
1477
+ "learning_rate": 0.00035294117647058826,
1478
+ "loss": 2.0675,
1479
+ "step": 1225
1480
+ },
1481
+ {
1482
+ "epoch": 1.48,
1483
+ "learning_rate": 0.0003523409363745498,
1484
+ "loss": 2.0066,
1485
+ "step": 1230
1486
+ },
1487
+ {
1488
+ "epoch": 1.48,
1489
+ "learning_rate": 0.0003517406962785114,
1490
+ "loss": 2.0111,
1491
+ "step": 1235
1492
+ },
1493
+ {
1494
+ "epoch": 1.49,
1495
+ "learning_rate": 0.000351140456182473,
1496
+ "loss": 1.9843,
1497
+ "step": 1240
1498
+ },
1499
+ {
1500
+ "epoch": 1.49,
1501
+ "learning_rate": 0.0003505402160864346,
1502
+ "loss": 2.0322,
1503
+ "step": 1245
1504
+ },
1505
+ {
1506
+ "epoch": 1.5,
1507
+ "learning_rate": 0.00034993997599039615,
1508
+ "loss": 2.0266,
1509
+ "step": 1250
1510
+ },
1511
+ {
1512
+ "epoch": 1.51,
1513
+ "learning_rate": 0.00034933973589435776,
1514
+ "loss": 2.0346,
1515
+ "step": 1255
1516
+ },
1517
+ {
1518
+ "epoch": 1.51,
1519
+ "learning_rate": 0.0003487394957983193,
1520
+ "loss": 1.9676,
1521
+ "step": 1260
1522
+ },
1523
+ {
1524
+ "epoch": 1.52,
1525
+ "learning_rate": 0.00034813925570228093,
1526
+ "loss": 2.0872,
1527
+ "step": 1265
1528
+ },
1529
+ {
1530
+ "epoch": 1.52,
1531
+ "learning_rate": 0.0003475390156062425,
1532
+ "loss": 1.9265,
1533
+ "step": 1270
1534
+ },
1535
+ {
1536
+ "epoch": 1.53,
1537
+ "learning_rate": 0.0003469387755102041,
1538
+ "loss": 2.0074,
1539
+ "step": 1275
1540
+ },
1541
+ {
1542
+ "epoch": 1.54,
1543
+ "learning_rate": 0.00034633853541416566,
1544
+ "loss": 2.0108,
1545
+ "step": 1280
1546
+ },
1547
+ {
1548
+ "epoch": 1.54,
1549
+ "learning_rate": 0.00034573829531812727,
1550
+ "loss": 1.9766,
1551
+ "step": 1285
1552
+ },
1553
+ {
1554
+ "epoch": 1.55,
1555
+ "learning_rate": 0.0003451380552220889,
1556
+ "loss": 1.9319,
1557
+ "step": 1290
1558
+ },
1559
+ {
1560
+ "epoch": 1.55,
1561
+ "learning_rate": 0.00034453781512605044,
1562
+ "loss": 2.0803,
1563
+ "step": 1295
1564
+ },
1565
+ {
1566
+ "epoch": 1.56,
1567
+ "learning_rate": 0.000343937575030012,
1568
+ "loss": 2.0196,
1569
+ "step": 1300
1570
+ },
1571
+ {
1572
+ "epoch": 1.57,
1573
+ "learning_rate": 0.0003433373349339736,
1574
+ "loss": 2.0166,
1575
+ "step": 1305
1576
+ },
1577
+ {
1578
+ "epoch": 1.57,
1579
+ "learning_rate": 0.0003427370948379352,
1580
+ "loss": 2.0094,
1581
+ "step": 1310
1582
+ },
1583
+ {
1584
+ "epoch": 1.58,
1585
+ "learning_rate": 0.0003421368547418968,
1586
+ "loss": 1.9954,
1587
+ "step": 1315
1588
+ },
1589
+ {
1590
+ "epoch": 1.58,
1591
+ "learning_rate": 0.00034153661464585833,
1592
+ "loss": 1.9782,
1593
+ "step": 1320
1594
+ },
1595
+ {
1596
+ "epoch": 1.59,
1597
+ "learning_rate": 0.00034093637454981994,
1598
+ "loss": 2.0126,
1599
+ "step": 1325
1600
+ },
1601
+ {
1602
+ "epoch": 1.6,
1603
+ "learning_rate": 0.00034033613445378155,
1604
+ "loss": 1.9949,
1605
+ "step": 1330
1606
+ },
1607
+ {
1608
+ "epoch": 1.6,
1609
+ "learning_rate": 0.0003397358943577431,
1610
+ "loss": 1.9744,
1611
+ "step": 1335
1612
+ },
1613
+ {
1614
+ "epoch": 1.61,
1615
+ "learning_rate": 0.00033913565426170467,
1616
+ "loss": 2.0246,
1617
+ "step": 1340
1618
+ },
1619
+ {
1620
+ "epoch": 1.61,
1621
+ "learning_rate": 0.0003385354141656663,
1622
+ "loss": 1.9461,
1623
+ "step": 1345
1624
+ },
1625
+ {
1626
+ "epoch": 1.62,
1627
+ "learning_rate": 0.0003379351740696279,
1628
+ "loss": 1.9792,
1629
+ "step": 1350
1630
+ },
1631
+ {
1632
+ "epoch": 1.63,
1633
+ "learning_rate": 0.00033733493397358945,
1634
+ "loss": 1.9813,
1635
+ "step": 1355
1636
+ },
1637
+ {
1638
+ "epoch": 1.63,
1639
+ "learning_rate": 0.000336734693877551,
1640
+ "loss": 2.0243,
1641
+ "step": 1360
1642
+ },
1643
+ {
1644
+ "epoch": 1.64,
1645
+ "learning_rate": 0.0003361344537815126,
1646
+ "loss": 1.9371,
1647
+ "step": 1365
1648
+ },
1649
+ {
1650
+ "epoch": 1.64,
1651
+ "learning_rate": 0.0003355342136854742,
1652
+ "loss": 2.0438,
1653
+ "step": 1370
1654
+ },
1655
+ {
1656
+ "epoch": 1.65,
1657
+ "learning_rate": 0.0003349339735894358,
1658
+ "loss": 1.9632,
1659
+ "step": 1375
1660
+ },
1661
+ {
1662
+ "epoch": 1.66,
1663
+ "learning_rate": 0.00033433373349339734,
1664
+ "loss": 2.0137,
1665
+ "step": 1380
1666
+ },
1667
+ {
1668
+ "epoch": 1.66,
1669
+ "learning_rate": 0.000333733493397359,
1670
+ "loss": 1.9849,
1671
+ "step": 1385
1672
+ },
1673
+ {
1674
+ "epoch": 1.67,
1675
+ "learning_rate": 0.00033313325330132056,
1676
+ "loss": 1.9578,
1677
+ "step": 1390
1678
+ },
1679
+ {
1680
+ "epoch": 1.67,
1681
+ "learning_rate": 0.0003325330132052821,
1682
+ "loss": 1.942,
1683
+ "step": 1395
1684
+ },
1685
+ {
1686
+ "epoch": 1.68,
1687
+ "learning_rate": 0.0003319327731092437,
1688
+ "loss": 1.9424,
1689
+ "step": 1400
1690
+ },
1691
+ {
1692
+ "epoch": 1.69,
1693
+ "learning_rate": 0.0003313325330132053,
1694
+ "loss": 2.0015,
1695
+ "step": 1405
1696
+ },
1697
+ {
1698
+ "epoch": 1.69,
1699
+ "learning_rate": 0.0003307322929171669,
1700
+ "loss": 2.0385,
1701
+ "step": 1410
1702
+ },
1703
+ {
1704
+ "epoch": 1.7,
1705
+ "learning_rate": 0.00033013205282112846,
1706
+ "loss": 2.019,
1707
+ "step": 1415
1708
+ },
1709
+ {
1710
+ "epoch": 1.7,
1711
+ "learning_rate": 0.00032953181272509,
1712
+ "loss": 1.99,
1713
+ "step": 1420
1714
+ },
1715
+ {
1716
+ "epoch": 1.71,
1717
+ "learning_rate": 0.0003289315726290516,
1718
+ "loss": 1.9583,
1719
+ "step": 1425
1720
+ },
1721
+ {
1722
+ "epoch": 1.72,
1723
+ "learning_rate": 0.00032833133253301324,
1724
+ "loss": 1.9645,
1725
+ "step": 1430
1726
+ },
1727
+ {
1728
+ "epoch": 1.72,
1729
+ "learning_rate": 0.0003277310924369748,
1730
+ "loss": 2.0095,
1731
+ "step": 1435
1732
+ },
1733
+ {
1734
+ "epoch": 1.73,
1735
+ "learning_rate": 0.00032713085234093635,
1736
+ "loss": 1.9755,
1737
+ "step": 1440
1738
+ },
1739
+ {
1740
+ "epoch": 1.73,
1741
+ "learning_rate": 0.00032653061224489796,
1742
+ "loss": 1.8859,
1743
+ "step": 1445
1744
+ },
1745
+ {
1746
+ "epoch": 1.74,
1747
+ "learning_rate": 0.00032593037214885957,
1748
+ "loss": 1.9807,
1749
+ "step": 1450
1750
+ },
1751
+ {
1752
+ "epoch": 1.75,
1753
+ "learning_rate": 0.00032533013205282113,
1754
+ "loss": 1.9688,
1755
+ "step": 1455
1756
+ },
1757
+ {
1758
+ "epoch": 1.75,
1759
+ "learning_rate": 0.0003247298919567827,
1760
+ "loss": 1.9898,
1761
+ "step": 1460
1762
+ },
1763
+ {
1764
+ "epoch": 1.76,
1765
+ "learning_rate": 0.0003241296518607443,
1766
+ "loss": 1.9136,
1767
+ "step": 1465
1768
+ },
1769
+ {
1770
+ "epoch": 1.76,
1771
+ "learning_rate": 0.0003235294117647059,
1772
+ "loss": 1.9058,
1773
+ "step": 1470
1774
+ },
1775
+ {
1776
+ "epoch": 1.77,
1777
+ "learning_rate": 0.00032292917166866747,
1778
+ "loss": 2.001,
1779
+ "step": 1475
1780
+ },
1781
+ {
1782
+ "epoch": 1.78,
1783
+ "learning_rate": 0.000322328931572629,
1784
+ "loss": 1.9529,
1785
+ "step": 1480
1786
+ },
1787
+ {
1788
+ "epoch": 1.78,
1789
+ "learning_rate": 0.00032172869147659063,
1790
+ "loss": 1.9859,
1791
+ "step": 1485
1792
+ },
1793
+ {
1794
+ "epoch": 1.79,
1795
+ "learning_rate": 0.00032112845138055224,
1796
+ "loss": 1.9973,
1797
+ "step": 1490
1798
+ },
1799
+ {
1800
+ "epoch": 1.79,
1801
+ "learning_rate": 0.0003205282112845138,
1802
+ "loss": 1.9371,
1803
+ "step": 1495
1804
+ },
1805
+ {
1806
+ "epoch": 1.8,
1807
+ "learning_rate": 0.0003199279711884754,
1808
+ "loss": 1.949,
1809
+ "step": 1500
1810
  }
1811
  ],
1812
  "logging_steps": 5,
 
1814
  "num_input_tokens_seen": 0,
1815
  "num_train_epochs": 5,
1816
  "save_steps": 500,
1817
+ "total_flos": 2.968978939416576e+16,
1818
  "train_batch_size": 8,
1819
  "trial_name": null,
1820
  "trial_params": null