Training in progress, step 125000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +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/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daead06784fb685f16c8cd4be230d8d1e8dd660dd5700ca1713745746b253381
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a9b9a0e6dbea60a29b35873e79df86e03ac39957f1d79a8fb01696f16dd7a7a
|
3 |
size 201355195
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80a02cadcec5c682098fb51c72819423b3b298e5b5aa6d3385fbd714d0c4fc53
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5854d9dbf36ad77035ed5ae9f2ad8400752412d52a59d432127a289bcdb92870
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71a5df795212331f8a72bb6b1b8d59c54cf39c25cb99cf42270bc77cf846323a
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ff854085e0575add7bd7f2cfc8b0c747606a6eb61e0b088b11274467b5a8b60
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aea1a007ce33ad976f43f5e7f08eba6020a053dd3d18f48f4f4aec4331ad991f
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3dff3950ce2609071b8b73f3435124844b2bbec72cd02ec4af651f73d9d4e56
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1446,6 +1446,66 @@
|
|
1446 |
"learning_rate": 0.00013104255439843306,
|
1447 |
"loss": 0.3479,
|
1448 |
"step": 120000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1449 |
}
|
1450 |
],
|
1451 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.127658488012868,
|
5 |
+
"global_step": 125000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1446 |
"learning_rate": 0.00013104255439843306,
|
1447 |
"loss": 0.3479,
|
1448 |
"step": 120000
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 2.05,
|
1452 |
+
"learning_rate": 0.00013089181235245484,
|
1453 |
+
"loss": 0.3476,
|
1454 |
+
"step": 120500
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 2.06,
|
1458 |
+
"learning_rate": 0.00013074056802483454,
|
1459 |
+
"loss": 0.348,
|
1460 |
+
"step": 121000
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 2.07,
|
1464 |
+
"learning_rate": 0.00013058882290829265,
|
1465 |
+
"loss": 0.3481,
|
1466 |
+
"step": 121500
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 2.08,
|
1470 |
+
"learning_rate": 0.00013043688348660256,
|
1471 |
+
"loss": 0.3482,
|
1472 |
+
"step": 122000
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 2.09,
|
1476 |
+
"learning_rate": 0.00013028414228420884,
|
1477 |
+
"loss": 0.3474,
|
1478 |
+
"step": 122500
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 2.09,
|
1482 |
+
"learning_rate": 0.0001301309047976313,
|
1483 |
+
"loss": 0.3478,
|
1484 |
+
"step": 123000
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 2.1,
|
1488 |
+
"learning_rate": 0.00012997717253926207,
|
1489 |
+
"loss": 0.3479,
|
1490 |
+
"step": 123500
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 2.11,
|
1494 |
+
"learning_rate": 0.00012982294702637649,
|
1495 |
+
"loss": 0.3473,
|
1496 |
+
"step": 124000
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 2.12,
|
1500 |
+
"learning_rate": 0.0001296682297811181,
|
1501 |
+
"loss": 0.3472,
|
1502 |
+
"step": 124500
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 2.13,
|
1506 |
+
"learning_rate": 0.00012951302233048365,
|
1507 |
+
"loss": 0.3475,
|
1508 |
+
"step": 125000
|
1509 |
}
|
1510 |
],
|
1511 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a9b9a0e6dbea60a29b35873e79df86e03ac39957f1d79a8fb01696f16dd7a7a
|
3 |
size 201355195
|