Training in progress, step 250, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 147770496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba114e5f887ed6bee28791b1206325155477c2e5560fb5a0fa2445b9a14ab670
|
| 3 |
size 147770496
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 295765866
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6a6eae1f8a74cb4e2ecfce996fe78d7c29b0d277b81ad12a68deb43452a9e39
|
| 3 |
size 295765866
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4da830074bb329feb347ddaab079f26d40e80efce113e07a9d3f4f756cfd5bbb
|
| 3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efeca56ff129fd1938154764e5eedeecbd5777ae5c87bc82a516810d01093718
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c859c36874bfac59ee5311bb46d04057167ce59e38d261dd16a448e0837fdf72
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca7fcff078dbdb0c1c6efcaf72bc4a9140c10cda16434ba2611620408aff6078
|
| 3 |
size 15024
|
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 sha256:9e6892bef9374493ad62f6ec1fe71e66e2ecb6a2a8c48a6591b2eb5cb1debcb4
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.1887668371200562,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1479,6 +1479,372 @@
|
|
| 1479 |
"eval_samples_per_second": 39.253,
|
| 1480 |
"eval_steps_per_second": 10.206,
|
| 1481 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1482 |
}
|
| 1483 |
],
|
| 1484 |
"logging_steps": 1,
|
|
@@ -1493,7 +1859,7 @@
|
|
| 1493 |
"early_stopping_threshold": 0.0
|
| 1494 |
},
|
| 1495 |
"attributes": {
|
| 1496 |
-
"early_stopping_patience_counter":
|
| 1497 |
}
|
| 1498 |
},
|
| 1499 |
"TrainerControl": {
|
|
@@ -1502,12 +1868,12 @@
|
|
| 1502 |
"should_evaluate": false,
|
| 1503 |
"should_log": false,
|
| 1504 |
"should_save": true,
|
| 1505 |
-
"should_training_stop":
|
| 1506 |
},
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
-
"total_flos":
|
| 1511 |
"train_batch_size": 1,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.1887668371200562,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 2.1522733387140165,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 250,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1479 |
"eval_samples_per_second": 39.253,
|
| 1480 |
"eval_steps_per_second": 10.206,
|
| 1481 |
"step": 200
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.7304277643260693,
|
| 1485 |
+
"grad_norm": 0.7049666047096252,
|
| 1486 |
+
"learning_rate": 6.854023410237687e-05,
|
| 1487 |
+
"loss": 0.8616,
|
| 1488 |
+
"step": 201
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 1.7390368576809254,
|
| 1492 |
+
"grad_norm": 0.7968461513519287,
|
| 1493 |
+
"learning_rate": 6.8234871662076e-05,
|
| 1494 |
+
"loss": 1.0514,
|
| 1495 |
+
"step": 202
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 1.7476459510357816,
|
| 1499 |
+
"grad_norm": 1.1434416770935059,
|
| 1500 |
+
"learning_rate": 6.792884061139813e-05,
|
| 1501 |
+
"loss": 0.8036,
|
| 1502 |
+
"step": 203
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.7562550443906377,
|
| 1506 |
+
"grad_norm": 1.7658017873764038,
|
| 1507 |
+
"learning_rate": 6.762215641067727e-05,
|
| 1508 |
+
"loss": 1.4673,
|
| 1509 |
+
"step": 204
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 1.7648641377454937,
|
| 1513 |
+
"grad_norm": 1.5402103662490845,
|
| 1514 |
+
"learning_rate": 6.731483455324374e-05,
|
| 1515 |
+
"loss": 1.3059,
|
| 1516 |
+
"step": 205
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 1.7734732311003496,
|
| 1520 |
+
"grad_norm": 1.1886134147644043,
|
| 1521 |
+
"learning_rate": 6.700689056464162e-05,
|
| 1522 |
+
"loss": 1.1953,
|
| 1523 |
+
"step": 206
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 1.7820823244552058,
|
| 1527 |
+
"grad_norm": 0.7550622224807739,
|
| 1528 |
+
"learning_rate": 6.66983400018443e-05,
|
| 1529 |
+
"loss": 1.0902,
|
| 1530 |
+
"step": 207
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.790691417810062,
|
| 1534 |
+
"grad_norm": 0.6886234283447266,
|
| 1535 |
+
"learning_rate": 6.638919845246859e-05,
|
| 1536 |
+
"loss": 1.019,
|
| 1537 |
+
"step": 208
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.799300511164918,
|
| 1541 |
+
"grad_norm": 0.8987452387809753,
|
| 1542 |
+
"learning_rate": 6.607948153398726e-05,
|
| 1543 |
+
"loss": 0.9793,
|
| 1544 |
+
"step": 209
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.807909604519774,
|
| 1548 |
+
"grad_norm": 1.0460529327392578,
|
| 1549 |
+
"learning_rate": 6.576920489294011e-05,
|
| 1550 |
+
"loss": 0.9404,
|
| 1551 |
+
"step": 210
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.81651869787463,
|
| 1555 |
+
"grad_norm": 1.1776190996170044,
|
| 1556 |
+
"learning_rate": 6.545838420414338e-05,
|
| 1557 |
+
"loss": 0.8875,
|
| 1558 |
+
"step": 211
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 1.825127791229486,
|
| 1562 |
+
"grad_norm": 1.31589674949646,
|
| 1563 |
+
"learning_rate": 6.514703516989805e-05,
|
| 1564 |
+
"loss": 0.9621,
|
| 1565 |
+
"step": 212
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 1.8337368845843423,
|
| 1569 |
+
"grad_norm": 1.11146879196167,
|
| 1570 |
+
"learning_rate": 6.483517351919646e-05,
|
| 1571 |
+
"loss": 0.8761,
|
| 1572 |
+
"step": 213
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 1.8423459779391984,
|
| 1576 |
+
"grad_norm": 0.8180311918258667,
|
| 1577 |
+
"learning_rate": 6.452281500692775e-05,
|
| 1578 |
+
"loss": 0.9426,
|
| 1579 |
+
"step": 214
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.8509550712940543,
|
| 1583 |
+
"grad_norm": 0.7222698330879211,
|
| 1584 |
+
"learning_rate": 6.420997541308195e-05,
|
| 1585 |
+
"loss": 0.625,
|
| 1586 |
+
"step": 215
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.8595641646489103,
|
| 1590 |
+
"grad_norm": 1.14591646194458,
|
| 1591 |
+
"learning_rate": 6.389667054195275e-05,
|
| 1592 |
+
"loss": 1.1073,
|
| 1593 |
+
"step": 216
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.8681732580037664,
|
| 1597 |
+
"grad_norm": 1.1335718631744385,
|
| 1598 |
+
"learning_rate": 6.358291622133912e-05,
|
| 1599 |
+
"loss": 1.2874,
|
| 1600 |
+
"step": 217
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.8767823513586226,
|
| 1604 |
+
"grad_norm": 0.9186055064201355,
|
| 1605 |
+
"learning_rate": 6.326872830174567e-05,
|
| 1606 |
+
"loss": 1.1502,
|
| 1607 |
+
"step": 218
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.8853914447134787,
|
| 1611 |
+
"grad_norm": 0.942480206489563,
|
| 1612 |
+
"learning_rate": 6.295412265558197e-05,
|
| 1613 |
+
"loss": 1.1254,
|
| 1614 |
+
"step": 219
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.8940005380683347,
|
| 1618 |
+
"grad_norm": 0.8674805760383606,
|
| 1619 |
+
"learning_rate": 6.263911517636063e-05,
|
| 1620 |
+
"loss": 1.103,
|
| 1621 |
+
"step": 220
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.9026096314231906,
|
| 1625 |
+
"grad_norm": 0.8475675582885742,
|
| 1626 |
+
"learning_rate": 6.232372177789439e-05,
|
| 1627 |
+
"loss": 1.0278,
|
| 1628 |
+
"step": 221
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.9112187247780468,
|
| 1632 |
+
"grad_norm": 0.7307541966438293,
|
| 1633 |
+
"learning_rate": 6.200795839349223e-05,
|
| 1634 |
+
"loss": 0.9875,
|
| 1635 |
+
"step": 222
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.919827818132903,
|
| 1639 |
+
"grad_norm": 0.7373369336128235,
|
| 1640 |
+
"learning_rate": 6.169184097515432e-05,
|
| 1641 |
+
"loss": 1.0035,
|
| 1642 |
+
"step": 223
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.928436911487759,
|
| 1646 |
+
"grad_norm": 0.6376901865005493,
|
| 1647 |
+
"learning_rate": 6.137538549276629e-05,
|
| 1648 |
+
"loss": 0.7809,
|
| 1649 |
+
"step": 224
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.937046004842615,
|
| 1653 |
+
"grad_norm": 0.6437143087387085,
|
| 1654 |
+
"learning_rate": 6.105860793329227e-05,
|
| 1655 |
+
"loss": 0.8046,
|
| 1656 |
+
"step": 225
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 1.937046004842615,
|
| 1660 |
+
"eval_loss": 1.1572624444961548,
|
| 1661 |
+
"eval_runtime": 1.2769,
|
| 1662 |
+
"eval_samples_per_second": 39.158,
|
| 1663 |
+
"eval_steps_per_second": 10.181,
|
| 1664 |
+
"step": 225
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.945655098197471,
|
| 1668 |
+
"grad_norm": 0.9029556512832642,
|
| 1669 |
+
"learning_rate": 6.074152429996749e-05,
|
| 1670 |
+
"loss": 0.9927,
|
| 1671 |
+
"step": 226
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.9542641915523271,
|
| 1675 |
+
"grad_norm": 0.8548585772514343,
|
| 1676 |
+
"learning_rate": 6.042415061148954e-05,
|
| 1677 |
+
"loss": 1.0187,
|
| 1678 |
+
"step": 227
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 1.9628732849071833,
|
| 1682 |
+
"grad_norm": 0.9854429960250854,
|
| 1683 |
+
"learning_rate": 6.010650290120936e-05,
|
| 1684 |
+
"loss": 0.8351,
|
| 1685 |
+
"step": 228
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 1.9714823782620394,
|
| 1689 |
+
"grad_norm": 1.5009618997573853,
|
| 1690 |
+
"learning_rate": 5.978859721632112e-05,
|
| 1691 |
+
"loss": 1.4645,
|
| 1692 |
+
"step": 229
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 1.9800914716168954,
|
| 1696 |
+
"grad_norm": 0.9327002763748169,
|
| 1697 |
+
"learning_rate": 5.947044961705153e-05,
|
| 1698 |
+
"loss": 1.0599,
|
| 1699 |
+
"step": 230
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 1.9887005649717513,
|
| 1703 |
+
"grad_norm": 0.6681526899337769,
|
| 1704 |
+
"learning_rate": 5.9152076175848594e-05,
|
| 1705 |
+
"loss": 0.9357,
|
| 1706 |
+
"step": 231
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 1.9973096583266075,
|
| 1710 |
+
"grad_norm": 0.8246638178825378,
|
| 1711 |
+
"learning_rate": 5.883349297656956e-05,
|
| 1712 |
+
"loss": 0.9124,
|
| 1713 |
+
"step": 232
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 2.0059187516814636,
|
| 1717 |
+
"grad_norm": 0.8793002963066101,
|
| 1718 |
+
"learning_rate": 5.851471611366842e-05,
|
| 1719 |
+
"loss": 1.1954,
|
| 1720 |
+
"step": 233
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 2.0145278450363198,
|
| 1724 |
+
"grad_norm": 0.7132886052131653,
|
| 1725 |
+
"learning_rate": 5.81957616913828e-05,
|
| 1726 |
+
"loss": 1.0198,
|
| 1727 |
+
"step": 234
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 2.0231369383911755,
|
| 1731 |
+
"grad_norm": 0.7113811373710632,
|
| 1732 |
+
"learning_rate": 5.7876645822920464e-05,
|
| 1733 |
+
"loss": 0.9339,
|
| 1734 |
+
"step": 235
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 2.0317460317460316,
|
| 1738 |
+
"grad_norm": 0.6471757888793945,
|
| 1739 |
+
"learning_rate": 5.75573846296452e-05,
|
| 1740 |
+
"loss": 0.9608,
|
| 1741 |
+
"step": 236
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 2.040355125100888,
|
| 1745 |
+
"grad_norm": 0.7370480298995972,
|
| 1746 |
+
"learning_rate": 5.7237994240262515e-05,
|
| 1747 |
+
"loss": 0.9259,
|
| 1748 |
+
"step": 237
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 2.048964218455744,
|
| 1752 |
+
"grad_norm": 0.7430047392845154,
|
| 1753 |
+
"learning_rate": 5.691849079000465e-05,
|
| 1754 |
+
"loss": 0.8468,
|
| 1755 |
+
"step": 238
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 2.0575733118106,
|
| 1759 |
+
"grad_norm": 0.6476728320121765,
|
| 1760 |
+
"learning_rate": 5.659889041981564e-05,
|
| 1761 |
+
"loss": 0.7466,
|
| 1762 |
+
"step": 239
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 2.066182405165456,
|
| 1766 |
+
"grad_norm": 1.0301920175552368,
|
| 1767 |
+
"learning_rate": 5.627920927553575e-05,
|
| 1768 |
+
"loss": 0.8599,
|
| 1769 |
+
"step": 240
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 2.074791498520312,
|
| 1773 |
+
"grad_norm": 0.6990707516670227,
|
| 1774 |
+
"learning_rate": 5.5959463507085866e-05,
|
| 1775 |
+
"loss": 0.6485,
|
| 1776 |
+
"step": 241
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 2.083400591875168,
|
| 1780 |
+
"grad_norm": 0.6740060448646545,
|
| 1781 |
+
"learning_rate": 5.563966926765163e-05,
|
| 1782 |
+
"loss": 0.6521,
|
| 1783 |
+
"step": 242
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 2.0920096852300243,
|
| 1787 |
+
"grad_norm": 0.7777407765388489,
|
| 1788 |
+
"learning_rate": 5.53198427128674e-05,
|
| 1789 |
+
"loss": 0.8288,
|
| 1790 |
+
"step": 243
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 2.1006187785848804,
|
| 1794 |
+
"grad_norm": 0.7086468935012817,
|
| 1795 |
+
"learning_rate": 5.500000000000001e-05,
|
| 1796 |
+
"loss": 0.6116,
|
| 1797 |
+
"step": 244
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 2.109227871939736,
|
| 1801 |
+
"grad_norm": 1.1495126485824585,
|
| 1802 |
+
"learning_rate": 5.468015728713262e-05,
|
| 1803 |
+
"loss": 1.2629,
|
| 1804 |
+
"step": 245
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 2.1178369652945923,
|
| 1808 |
+
"grad_norm": 1.1655594110488892,
|
| 1809 |
+
"learning_rate": 5.4360330732348377e-05,
|
| 1810 |
+
"loss": 1.1571,
|
| 1811 |
+
"step": 246
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 2.1264460586494485,
|
| 1815 |
+
"grad_norm": 1.0574018955230713,
|
| 1816 |
+
"learning_rate": 5.404053649291415e-05,
|
| 1817 |
+
"loss": 1.0127,
|
| 1818 |
+
"step": 247
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 2.1350551520043046,
|
| 1822 |
+
"grad_norm": 0.8099690675735474,
|
| 1823 |
+
"learning_rate": 5.372079072446427e-05,
|
| 1824 |
+
"loss": 0.9191,
|
| 1825 |
+
"step": 248
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 2.143664245359161,
|
| 1829 |
+
"grad_norm": 0.7748256325721741,
|
| 1830 |
+
"learning_rate": 5.340110958018438e-05,
|
| 1831 |
+
"loss": 0.86,
|
| 1832 |
+
"step": 249
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 2.1522733387140165,
|
| 1836 |
+
"grad_norm": 1.3335024118423462,
|
| 1837 |
+
"learning_rate": 5.308150920999537e-05,
|
| 1838 |
+
"loss": 0.9134,
|
| 1839 |
+
"step": 250
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 2.1522733387140165,
|
| 1843 |
+
"eval_loss": 1.1941081285476685,
|
| 1844 |
+
"eval_runtime": 1.2717,
|
| 1845 |
+
"eval_samples_per_second": 39.316,
|
| 1846 |
+
"eval_steps_per_second": 10.222,
|
| 1847 |
+
"step": 250
|
| 1848 |
}
|
| 1849 |
],
|
| 1850 |
"logging_steps": 1,
|
|
|
|
| 1859 |
"early_stopping_threshold": 0.0
|
| 1860 |
},
|
| 1861 |
"attributes": {
|
| 1862 |
+
"early_stopping_patience_counter": 1
|
| 1863 |
}
|
| 1864 |
},
|
| 1865 |
"TrainerControl": {
|
|
|
|
| 1868 |
"should_evaluate": false,
|
| 1869 |
"should_log": false,
|
| 1870 |
"should_save": true,
|
| 1871 |
+
"should_training_stop": true
|
| 1872 |
},
|
| 1873 |
"attributes": {}
|
| 1874 |
}
|
| 1875 |
},
|
| 1876 |
+
"total_flos": 5.3114226274310554e+17,
|
| 1877 |
"train_batch_size": 1,
|
| 1878 |
"trial_name": null,
|
| 1879 |
"trial_params": null
|