Training in progress, step 215000
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:c9ed916a28299763f4397e23935a009d75b791bca8cae2516180ad74cce128eb
|
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 sha256:37a6b3063a7c0f5c4de3bd37e9626c20669ac84a57464e0aaabdf7b78ceaeeee
|
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 sha256:0a8b224864d8f712b40fd04f1ce954fc21b5f5ceee0de2961bd2d520a5aa5b93
|
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 sha256:7a74c44837ac9a412797ec51671b2bb2dcacfd4e27b77c1c9f4a9ddcc895b3bd
|
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 sha256:62db7ff40e7246a1bb8226344232d91015ee91ea3e5f207c1e2cfedb9ab5fdd6
|
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 sha256:89812625b70187307d1add35edb508e9ea3343ab14a0754a37c44518bad4b3ac
|
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 sha256:82935853a364d735e34f7f9913abc7c4bb65b609e5cb01baca76894fae530b27
|
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 sha256:8d9a535eb39471db0b2448d31926c76992045784a79340c118feaf3800cfc77e
|
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": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2526,6 +2526,66 @@
|
|
2526 |
"learning_rate": 9.744535194458411e-05,
|
2527 |
"loss": 0.3354,
|
2528 |
"step": 210000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2529 |
}
|
2530 |
],
|
2531 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.659568854733151,
|
5 |
+
"global_step": 215000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2526 |
"learning_rate": 9.744535194458411e-05,
|
2527 |
"loss": 0.3354,
|
2528 |
"step": 210000
|
2529 |
+
},
|
2530 |
+
{
|
2531 |
+
"epoch": 3.58,
|
2532 |
+
"learning_rate": 9.723229357085885e-05,
|
2533 |
+
"loss": 0.3354,
|
2534 |
+
"step": 210500
|
2535 |
+
},
|
2536 |
+
{
|
2537 |
+
"epoch": 3.59,
|
2538 |
+
"learning_rate": 9.701906512135297e-05,
|
2539 |
+
"loss": 0.3355,
|
2540 |
+
"step": 211000
|
2541 |
+
},
|
2542 |
+
{
|
2543 |
+
"epoch": 3.6,
|
2544 |
+
"learning_rate": 9.680566870054522e-05,
|
2545 |
+
"loss": 0.3348,
|
2546 |
+
"step": 211500
|
2547 |
+
},
|
2548 |
+
{
|
2549 |
+
"epoch": 3.61,
|
2550 |
+
"learning_rate": 9.659210641457217e-05,
|
2551 |
+
"loss": 0.3349,
|
2552 |
+
"step": 212000
|
2553 |
+
},
|
2554 |
+
{
|
2555 |
+
"epoch": 3.62,
|
2556 |
+
"learning_rate": 9.637838037120726e-05,
|
2557 |
+
"loss": 0.3346,
|
2558 |
+
"step": 212500
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 3.63,
|
2562 |
+
"learning_rate": 9.616449267984031e-05,
|
2563 |
+
"loss": 0.3346,
|
2564 |
+
"step": 213000
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 3.63,
|
2568 |
+
"learning_rate": 9.59504454514565e-05,
|
2569 |
+
"loss": 0.3343,
|
2570 |
+
"step": 213500
|
2571 |
+
},
|
2572 |
+
{
|
2573 |
+
"epoch": 3.64,
|
2574 |
+
"learning_rate": 9.573666936362591e-05,
|
2575 |
+
"loss": 0.3341,
|
2576 |
+
"step": 214000
|
2577 |
+
},
|
2578 |
+
{
|
2579 |
+
"epoch": 3.65,
|
2580 |
+
"learning_rate": 9.5522309708951e-05,
|
2581 |
+
"loss": 0.3344,
|
2582 |
+
"step": 214500
|
2583 |
+
},
|
2584 |
+
{
|
2585 |
+
"epoch": 3.66,
|
2586 |
+
"learning_rate": 9.53077968553459e-05,
|
2587 |
+
"loss": 0.3339,
|
2588 |
+
"step": 215000
|
2589 |
}
|
2590 |
],
|
2591 |
"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 sha256:37a6b3063a7c0f5c4de3bd37e9626c20669ac84a57464e0aaabdf7b78ceaeeee
|
3 |
size 201355195
|