CreatorPhan commited on
Commit
507c313
1 Parent(s): 3540d17

Upload folder using huggingface_hub (#2)

Browse files

- Upload folder using huggingface_hub (edb2131e1c3823ba72b1d279d10abad09a5f6533)

Files changed (4) hide show
  1. adapter_model.bin +1 -1
  2. optimizer.pt +1 -1
  3. scheduler.pt +1 -1
  4. trainer_state.json +603 -3
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5d07783590970cc01440af02efb30baf84be013f42d6e324dbec3f1211d5743
3
  size 39409357
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b39b2ac3c3f75772f547048fda7ecb323076b9689db7d79915bba156dc508f2f
3
  size 39409357
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bb4e74f21744cbd194fc93b7a41891675165b22a0068ad1db19aeac49015587
3
  size 78844421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c734ecaa394370ee4bcd94cc0b2ae016a26765122f3f76327b28c23f96a22732
3
  size 78844421
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49d3e390b4500e3448050a2123ac7e837c199dcd6015f166fda34e0372e32849
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d8dcaf05375bb59f736a94e8f8b03d33cdc87bc02411e6527a29996e0a68b3b
3
  size 627
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.1173184357541899,
5
  "eval_steps": 500,
6
- "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1207,13 +1207,613 @@
1207
  "learning_rate": 0.0001441340782122905,
1208
  "loss": 1.9591,
1209
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1210
  }
1211
  ],
1212
  "logging_steps": 1,
1213
  "max_steps": 716,
1214
  "num_train_epochs": 4,
1215
  "save_steps": 100,
1216
- "total_flos": 1.0290223796256768e+17,
1217
  "trial_name": null,
1218
  "trial_params": null
1219
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.675977653631285,
5
  "eval_steps": 500,
6
+ "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1207
  "learning_rate": 0.0001441340782122905,
1208
  "loss": 1.9591,
1209
  "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 1.12,
1213
+ "learning_rate": 0.00014385474860335195,
1214
+ "loss": 1.8722,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 1.13,
1219
+ "learning_rate": 0.00014357541899441342,
1220
+ "loss": 1.8535,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 1.13,
1225
+ "learning_rate": 0.00014329608938547488,
1226
+ "loss": 1.8676,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 1.14,
1231
+ "learning_rate": 0.00014301675977653632,
1232
+ "loss": 1.8976,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 1.15,
1237
+ "learning_rate": 0.00014273743016759776,
1238
+ "loss": 1.7723,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 1.15,
1243
+ "learning_rate": 0.00014245810055865923,
1244
+ "loss": 1.8165,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 1.16,
1249
+ "learning_rate": 0.00014217877094972067,
1250
+ "loss": 1.7811,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 1.16,
1255
+ "learning_rate": 0.00014189944134078214,
1256
+ "loss": 1.908,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 1.17,
1261
+ "learning_rate": 0.00014162011173184357,
1262
+ "loss": 1.7663,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 1.17,
1267
+ "learning_rate": 0.00014134078212290501,
1268
+ "loss": 1.6779,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 1.18,
1273
+ "learning_rate": 0.0001410614525139665,
1274
+ "loss": 1.9039,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 1.18,
1279
+ "learning_rate": 0.00014078212290502795,
1280
+ "loss": 1.8033,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 1.19,
1285
+ "learning_rate": 0.00014050279329608939,
1286
+ "loss": 1.8251,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 1.2,
1291
+ "learning_rate": 0.00014022346368715085,
1292
+ "loss": 1.8505,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 1.2,
1297
+ "learning_rate": 0.0001399441340782123,
1298
+ "loss": 1.8147,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 1.21,
1303
+ "learning_rate": 0.00013966480446927376,
1304
+ "loss": 1.8419,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 1.21,
1309
+ "learning_rate": 0.0001393854748603352,
1310
+ "loss": 1.8401,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 1.22,
1315
+ "learning_rate": 0.00013910614525139664,
1316
+ "loss": 1.8912,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 1.22,
1321
+ "learning_rate": 0.0001388268156424581,
1322
+ "loss": 1.7548,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 1.23,
1327
+ "learning_rate": 0.00013854748603351957,
1328
+ "loss": 1.8741,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 1.23,
1333
+ "learning_rate": 0.000138268156424581,
1334
+ "loss": 1.9549,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 1.24,
1339
+ "learning_rate": 0.00013798882681564248,
1340
+ "loss": 1.9093,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 1.25,
1345
+ "learning_rate": 0.00013770949720670392,
1346
+ "loss": 1.7896,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 1.25,
1351
+ "learning_rate": 0.00013743016759776538,
1352
+ "loss": 1.8491,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 1.26,
1357
+ "learning_rate": 0.00013715083798882682,
1358
+ "loss": 1.7851,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 1.26,
1363
+ "learning_rate": 0.00013687150837988826,
1364
+ "loss": 1.6992,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 1.27,
1369
+ "learning_rate": 0.00013659217877094973,
1370
+ "loss": 1.9765,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 1.27,
1375
+ "learning_rate": 0.00013631284916201117,
1376
+ "loss": 1.8179,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 1.28,
1381
+ "learning_rate": 0.00013603351955307263,
1382
+ "loss": 1.8548,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 1.28,
1387
+ "learning_rate": 0.0001357541899441341,
1388
+ "loss": 1.8843,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 1.29,
1393
+ "learning_rate": 0.00013547486033519554,
1394
+ "loss": 1.9105,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 1.3,
1399
+ "learning_rate": 0.00013519553072625698,
1400
+ "loss": 1.8748,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 1.3,
1405
+ "learning_rate": 0.00013491620111731844,
1406
+ "loss": 1.7976,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 1.31,
1411
+ "learning_rate": 0.00013463687150837988,
1412
+ "loss": 1.7369,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 1.31,
1417
+ "learning_rate": 0.00013435754189944135,
1418
+ "loss": 1.7808,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 1.32,
1423
+ "learning_rate": 0.0001340782122905028,
1424
+ "loss": 1.8385,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 1.32,
1429
+ "learning_rate": 0.00013379888268156423,
1430
+ "loss": 1.8295,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 1.33,
1435
+ "learning_rate": 0.00013351955307262572,
1436
+ "loss": 1.757,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 1.34,
1441
+ "learning_rate": 0.00013324022346368716,
1442
+ "loss": 1.7904,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 1.34,
1447
+ "learning_rate": 0.0001329608938547486,
1448
+ "loss": 1.7632,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 1.35,
1453
+ "learning_rate": 0.00013268156424581007,
1454
+ "loss": 1.7867,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 1.35,
1459
+ "learning_rate": 0.0001324022346368715,
1460
+ "loss": 1.8259,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 1.36,
1465
+ "learning_rate": 0.00013212290502793297,
1466
+ "loss": 1.6655,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.36,
1471
+ "learning_rate": 0.0001318435754189944,
1472
+ "loss": 1.6848,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 1.37,
1477
+ "learning_rate": 0.00013156424581005585,
1478
+ "loss": 1.7931,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 1.37,
1483
+ "learning_rate": 0.00013128491620111732,
1484
+ "loss": 1.7868,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 1.38,
1489
+ "learning_rate": 0.00013100558659217879,
1490
+ "loss": 1.7732,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 1.39,
1495
+ "learning_rate": 0.00013072625698324022,
1496
+ "loss": 1.7851,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 1.39,
1501
+ "learning_rate": 0.0001304469273743017,
1502
+ "loss": 1.7406,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 1.4,
1507
+ "learning_rate": 0.00013016759776536313,
1508
+ "loss": 1.5853,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 1.4,
1513
+ "learning_rate": 0.0001298882681564246,
1514
+ "loss": 1.8271,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 1.41,
1519
+ "learning_rate": 0.00012960893854748604,
1520
+ "loss": 1.6054,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 1.41,
1525
+ "learning_rate": 0.00012932960893854748,
1526
+ "loss": 1.6884,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 1.42,
1531
+ "learning_rate": 0.00012905027932960894,
1532
+ "loss": 1.7333,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 1.42,
1537
+ "learning_rate": 0.00012877094972067038,
1538
+ "loss": 1.803,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 1.43,
1543
+ "learning_rate": 0.00012849162011173185,
1544
+ "loss": 1.63,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 1.44,
1549
+ "learning_rate": 0.00012821229050279331,
1550
+ "loss": 1.8023,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 1.44,
1555
+ "learning_rate": 0.00012793296089385475,
1556
+ "loss": 1.762,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 1.45,
1561
+ "learning_rate": 0.00012765363128491622,
1562
+ "loss": 1.7565,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 1.45,
1567
+ "learning_rate": 0.00012737430167597766,
1568
+ "loss": 1.5937,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 1.46,
1573
+ "learning_rate": 0.0001270949720670391,
1574
+ "loss": 1.7208,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 1.46,
1579
+ "learning_rate": 0.00012681564245810057,
1580
+ "loss": 1.8097,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 1.47,
1585
+ "learning_rate": 0.000126536312849162,
1586
+ "loss": 1.7042,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 1.47,
1591
+ "learning_rate": 0.00012625698324022347,
1592
+ "loss": 1.7892,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 1.48,
1597
+ "learning_rate": 0.00012597765363128494,
1598
+ "loss": 1.752,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 1.49,
1603
+ "learning_rate": 0.00012569832402234638,
1604
+ "loss": 1.7333,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 1.49,
1609
+ "learning_rate": 0.00012541899441340784,
1610
+ "loss": 1.7492,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 1.5,
1615
+ "learning_rate": 0.00012513966480446928,
1616
+ "loss": 1.818,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 1.5,
1621
+ "learning_rate": 0.00012486033519553072,
1622
+ "loss": 1.7146,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 1.51,
1627
+ "learning_rate": 0.0001245810055865922,
1628
+ "loss": 1.7958,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 1.51,
1633
+ "learning_rate": 0.00012430167597765363,
1634
+ "loss": 1.7212,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 1.52,
1639
+ "learning_rate": 0.0001240223463687151,
1640
+ "loss": 1.8835,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 1.53,
1645
+ "learning_rate": 0.00012374301675977656,
1646
+ "loss": 1.7486,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 1.53,
1651
+ "learning_rate": 0.000123463687150838,
1652
+ "loss": 1.8103,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 1.54,
1657
+ "learning_rate": 0.00012318435754189944,
1658
+ "loss": 1.7557,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 1.54,
1663
+ "learning_rate": 0.0001229050279329609,
1664
+ "loss": 1.6198,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 1.55,
1669
+ "learning_rate": 0.00012262569832402235,
1670
+ "loss": 1.6971,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 1.55,
1675
+ "learning_rate": 0.0001223463687150838,
1676
+ "loss": 1.668,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 1.56,
1681
+ "learning_rate": 0.00012206703910614525,
1682
+ "loss": 1.8795,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 1.56,
1687
+ "learning_rate": 0.0001217877094972067,
1688
+ "loss": 1.6412,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 1.57,
1693
+ "learning_rate": 0.00012150837988826816,
1694
+ "loss": 1.7497,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 1.58,
1699
+ "learning_rate": 0.00012122905027932962,
1700
+ "loss": 1.5577,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 1.58,
1705
+ "learning_rate": 0.00012094972067039108,
1706
+ "loss": 1.8049,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 1.59,
1711
+ "learning_rate": 0.00012067039106145253,
1712
+ "loss": 1.6834,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 1.59,
1717
+ "learning_rate": 0.00012039106145251397,
1718
+ "loss": 1.7978,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 1.6,
1723
+ "learning_rate": 0.00012011173184357542,
1724
+ "loss": 1.6558,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 1.6,
1729
+ "learning_rate": 0.00011983240223463687,
1730
+ "loss": 1.7561,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 1.61,
1735
+ "learning_rate": 0.00011955307262569833,
1736
+ "loss": 1.6807,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 1.61,
1741
+ "learning_rate": 0.00011927374301675978,
1742
+ "loss": 1.6937,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 1.62,
1747
+ "learning_rate": 0.00011899441340782122,
1748
+ "loss": 1.6591,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 1.63,
1753
+ "learning_rate": 0.0001187150837988827,
1754
+ "loss": 1.6771,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 1.63,
1759
+ "learning_rate": 0.00011843575418994415,
1760
+ "loss": 1.7743,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 1.64,
1765
+ "learning_rate": 0.00011815642458100559,
1766
+ "loss": 1.5857,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 1.64,
1771
+ "learning_rate": 0.00011787709497206705,
1772
+ "loss": 1.6999,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 1.65,
1777
+ "learning_rate": 0.0001175977653631285,
1778
+ "loss": 1.5661,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 1.65,
1783
+ "learning_rate": 0.00011731843575418995,
1784
+ "loss": 1.7235,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 1.66,
1789
+ "learning_rate": 0.0001170391061452514,
1790
+ "loss": 1.607,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 1.66,
1795
+ "learning_rate": 0.00011675977653631284,
1796
+ "loss": 1.68,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 1.67,
1801
+ "learning_rate": 0.0001164804469273743,
1802
+ "loss": 1.6938,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 1.68,
1807
+ "learning_rate": 0.00011620111731843578,
1808
+ "loss": 1.6315,
1809
+ "step": 300
1810
  }
1811
  ],
1812
  "logging_steps": 1,
1813
  "max_steps": 716,
1814
  "num_train_epochs": 4,
1815
  "save_steps": 100,
1816
+ "total_flos": 1.5369996759656448e+17,
1817
  "trial_name": null,
1818
  "trial_params": null
1819
  }