Training in progress, step 275, 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:
|
3 |
size 838904832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d6c9e9fde3bf761964ce0a1096daf1a2f902a2ec3817c338700dd0fdb422b7b
|
3 |
size 838904832
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c44e3e00e2ab4d12e4e2b2418ce9291412c0dade8841637f3f38586085364aea
|
3 |
+
size 421458386
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cecdcf6d8c7c779a0c31f47b4cfa05311ab6c9a135282cd57f3efb2ff76f57b
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cd2eafba86db0126a84de125a9a439f555cacfcb5b82fd7e6af07740e165b9d
|
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": 1.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1507,13 +1507,163 @@
|
|
1507 |
"learning_rate": 0.0002,
|
1508 |
"loss": 0.3503,
|
1509 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1510 |
}
|
1511 |
],
|
1512 |
"logging_steps": 1,
|
1513 |
-
"max_steps":
|
1514 |
-
"num_train_epochs":
|
1515 |
"save_steps": 25,
|
1516 |
-
"total_flos":
|
1517 |
"trial_name": null,
|
1518 |
"trial_params": null
|
1519 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.1,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 275,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1507 |
"learning_rate": 0.0002,
|
1508 |
"loss": 0.3503,
|
1509 |
"step": 250
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 1.0,
|
1513 |
+
"learning_rate": 0.0002,
|
1514 |
+
"loss": 0.6092,
|
1515 |
+
"step": 251
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 1.01,
|
1519 |
+
"learning_rate": 0.0002,
|
1520 |
+
"loss": 0.5481,
|
1521 |
+
"step": 252
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 1.01,
|
1525 |
+
"learning_rate": 0.0002,
|
1526 |
+
"loss": 0.5902,
|
1527 |
+
"step": 253
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 1.02,
|
1531 |
+
"learning_rate": 0.0002,
|
1532 |
+
"loss": 0.4603,
|
1533 |
+
"step": 254
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 1.02,
|
1537 |
+
"learning_rate": 0.0002,
|
1538 |
+
"loss": 0.5344,
|
1539 |
+
"step": 255
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 1.02,
|
1543 |
+
"learning_rate": 0.0002,
|
1544 |
+
"loss": 0.5136,
|
1545 |
+
"step": 256
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 1.03,
|
1549 |
+
"learning_rate": 0.0002,
|
1550 |
+
"loss": 0.5304,
|
1551 |
+
"step": 257
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 1.03,
|
1555 |
+
"learning_rate": 0.0002,
|
1556 |
+
"loss": 0.4625,
|
1557 |
+
"step": 258
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.04,
|
1561 |
+
"learning_rate": 0.0002,
|
1562 |
+
"loss": 0.4841,
|
1563 |
+
"step": 259
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 1.04,
|
1567 |
+
"learning_rate": 0.0002,
|
1568 |
+
"loss": 0.4548,
|
1569 |
+
"step": 260
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 1.04,
|
1573 |
+
"learning_rate": 0.0002,
|
1574 |
+
"loss": 0.4686,
|
1575 |
+
"step": 261
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 1.05,
|
1579 |
+
"learning_rate": 0.0002,
|
1580 |
+
"loss": 0.4717,
|
1581 |
+
"step": 262
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 1.05,
|
1585 |
+
"learning_rate": 0.0002,
|
1586 |
+
"loss": 0.4775,
|
1587 |
+
"step": 263
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 1.06,
|
1591 |
+
"learning_rate": 0.0002,
|
1592 |
+
"loss": 0.503,
|
1593 |
+
"step": 264
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 1.06,
|
1597 |
+
"learning_rate": 0.0002,
|
1598 |
+
"loss": 0.4712,
|
1599 |
+
"step": 265
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 1.06,
|
1603 |
+
"learning_rate": 0.0002,
|
1604 |
+
"loss": 0.4782,
|
1605 |
+
"step": 266
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 1.07,
|
1609 |
+
"learning_rate": 0.0002,
|
1610 |
+
"loss": 0.4649,
|
1611 |
+
"step": 267
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 1.07,
|
1615 |
+
"learning_rate": 0.0002,
|
1616 |
+
"loss": 0.4758,
|
1617 |
+
"step": 268
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 1.08,
|
1621 |
+
"learning_rate": 0.0002,
|
1622 |
+
"loss": 0.4192,
|
1623 |
+
"step": 269
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 1.08,
|
1627 |
+
"learning_rate": 0.0002,
|
1628 |
+
"loss": 0.4511,
|
1629 |
+
"step": 270
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.08,
|
1633 |
+
"learning_rate": 0.0002,
|
1634 |
+
"loss": 0.4572,
|
1635 |
+
"step": 271
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 1.09,
|
1639 |
+
"learning_rate": 0.0002,
|
1640 |
+
"loss": 0.4277,
|
1641 |
+
"step": 272
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 1.09,
|
1645 |
+
"learning_rate": 0.0002,
|
1646 |
+
"loss": 0.4366,
|
1647 |
+
"step": 273
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 1.1,
|
1651 |
+
"learning_rate": 0.0002,
|
1652 |
+
"loss": 0.403,
|
1653 |
+
"step": 274
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 1.1,
|
1657 |
+
"learning_rate": 0.0002,
|
1658 |
+
"loss": 0.4161,
|
1659 |
+
"step": 275
|
1660 |
}
|
1661 |
],
|
1662 |
"logging_steps": 1,
|
1663 |
+
"max_steps": 500,
|
1664 |
+
"num_train_epochs": 2,
|
1665 |
"save_steps": 25,
|
1666 |
+
"total_flos": 3.327201233842176e+16,
|
1667 |
"trial_name": null,
|
1668 |
"trial_params": null
|
1669 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf8ae64e171536bf78dc95ca36df03d7f40620336c1b55d8bd15bbd85cdd8bf5
|
3 |
size 4600
|