Training in progress, step 460000
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 sha256:61aa4e9f023152bed2aa596934d5e42f40b173f755150e912b6614c279f88f16
|
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 sha256:0041fa71647d2cd9df59d7b5cff88993534ca01fdffe6c97ebff4b6b443fd0e2
|
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 sha256:224147acac4c428ab25416c74203a796fb9ba398217dbc0d6d069fb51d8ae70c
|
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 sha256:370b0b9e82367f81826a68fe4933489b6c24ac5c097045a65f60cebec12b46ac
|
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 sha256:61a702dfc1727eb7e283876e0762ff2705652ffe9ef399715ec19d685d2566e2
|
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 sha256:0660e813a1c8e30d9dae8ca6064cf65b21ce2bac86463a2844ddbc8735ffeaee
|
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 sha256:66e9cea135a1b298a0410e4005fc8f12b63c8c5ab8a3f244d8fe801da116fbca
|
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 sha256:583fe6059dd28557686d7204c7aab4790397f0b6c5f67be3ad8679928fd339be
|
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": 7.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -5466,6 +5466,66 @@
|
|
5466 |
"learning_rate": 1.2800833136321545e-05,
|
5467 |
"loss": 0.3189,
|
5468 |
"step": 455000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5469 |
}
|
5470 |
],
|
5471 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.829780172083642,
|
5 |
+
"global_step": 460000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
5466 |
"learning_rate": 1.2800833136321545e-05,
|
5467 |
"loss": 0.3189,
|
5468 |
"step": 455000
|
5469 |
+
},
|
5470 |
+
{
|
5471 |
+
"epoch": 7.75,
|
5472 |
+
"learning_rate": 1.2739702505431287e-05,
|
5473 |
+
"loss": 0.319,
|
5474 |
+
"step": 455500
|
5475 |
+
},
|
5476 |
+
{
|
5477 |
+
"epoch": 7.76,
|
5478 |
+
"learning_rate": 1.2679112536818441e-05,
|
5479 |
+
"loss": 0.319,
|
5480 |
+
"step": 456000
|
5481 |
+
},
|
5482 |
+
{
|
5483 |
+
"epoch": 7.77,
|
5484 |
+
"learning_rate": 1.2619186998186322e-05,
|
5485 |
+
"loss": 0.319,
|
5486 |
+
"step": 456500
|
5487 |
+
},
|
5488 |
+
{
|
5489 |
+
"epoch": 7.78,
|
5490 |
+
"learning_rate": 1.2559926480975791e-05,
|
5491 |
+
"loss": 0.3189,
|
5492 |
+
"step": 457000
|
5493 |
+
},
|
5494 |
+
{
|
5495 |
+
"epoch": 7.79,
|
5496 |
+
"learning_rate": 1.250144809522549e-05,
|
5497 |
+
"loss": 0.3188,
|
5498 |
+
"step": 457500
|
5499 |
+
},
|
5500 |
+
{
|
5501 |
+
"epoch": 7.8,
|
5502 |
+
"learning_rate": 1.2443633230865312e-05,
|
5503 |
+
"loss": 0.3188,
|
5504 |
+
"step": 458000
|
5505 |
+
},
|
5506 |
+
{
|
5507 |
+
"epoch": 7.8,
|
5508 |
+
"learning_rate": 1.2386368592745543e-05,
|
5509 |
+
"loss": 0.3189,
|
5510 |
+
"step": 458500
|
5511 |
+
},
|
5512 |
+
{
|
5513 |
+
"epoch": 7.81,
|
5514 |
+
"learning_rate": 1.232977127387103e-05,
|
5515 |
+
"loss": 0.319,
|
5516 |
+
"step": 459000
|
5517 |
+
},
|
5518 |
+
{
|
5519 |
+
"epoch": 7.82,
|
5520 |
+
"learning_rate": 1.2273841832834476e-05,
|
5521 |
+
"loss": 0.3189,
|
5522 |
+
"step": 459500
|
5523 |
+
},
|
5524 |
+
{
|
5525 |
+
"epoch": 7.83,
|
5526 |
+
"learning_rate": 1.2218580821636874e-05,
|
5527 |
+
"loss": 0.319,
|
5528 |
+
"step": 460000
|
5529 |
}
|
5530 |
],
|
5531 |
"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 sha256:0041fa71647d2cd9df59d7b5cff88993534ca01fdffe6c97ebff4b6b443fd0e2
|
3 |
size 201355195
|