Training in progress, step 210000
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 sha256:38516ca0517e9c7bd41fc6158ae087a6a134bc2f0dd8c89f13752386bca97a63
|
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 sha256:6a63ed5615691b5a4420962dc27128e6f0d4753bfd9410a7b1a6cb622c4acbb5
|
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 sha256:5a7b9ac978a897533a1d78caa11e5297f0a94874bb93aaeed60274a7803c253d
|
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:d9cd11c5bacff161047696669bdb8c61b5441b53c0bd485fe06a6c941142e724
|
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 sha256:201bf8b89cfe750a906681c70ce5fcc90044ccfff90a7a74d8d20d43f92cd11c
|
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 sha256:927df4b0b2eb7b67c90634dcefcb8439b0df0747bad04d2776fd3935f5b131b8
|
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:c7065456e80f792ecf63d108cd10a4439c5d10426363e793cec85f5588f73d66
|
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:da455c6df82b96f0b604fd8d8cf8c2607892cf7ef66ee8eb4c9f7c2eee60e455
|
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,
|
@@ -2466,6 +2466,66 @@
|
|
2466 |
"learning_rate": 9.956400828538178e-05,
|
2467 |
"loss": 0.3358,
|
2468 |
"step": 205000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2469 |
}
|
2470 |
],
|
2471 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.5744631960579056,
|
5 |
+
"global_step": 210000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2466 |
"learning_rate": 9.956400828538178e-05,
|
2467 |
"loss": 0.3358,
|
2468 |
"step": 205000
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 3.5,
|
2472 |
+
"learning_rate": 9.935318679532955e-05,
|
2473 |
+
"loss": 0.3353,
|
2474 |
+
"step": 205500
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 3.51,
|
2478 |
+
"learning_rate": 9.914217506040476e-05,
|
2479 |
+
"loss": 0.3356,
|
2480 |
+
"step": 206000
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 3.51,
|
2484 |
+
"learning_rate": 9.893055172104751e-05,
|
2485 |
+
"loss": 0.3354,
|
2486 |
+
"step": 206500
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 3.52,
|
2490 |
+
"learning_rate": 9.871874154478737e-05,
|
2491 |
+
"loss": 0.3352,
|
2492 |
+
"step": 207000
|
2493 |
+
},
|
2494 |
+
{
|
2495 |
+
"epoch": 3.53,
|
2496 |
+
"learning_rate": 9.850674662210523e-05,
|
2497 |
+
"loss": 0.3349,
|
2498 |
+
"step": 207500
|
2499 |
+
},
|
2500 |
+
{
|
2501 |
+
"epoch": 3.54,
|
2502 |
+
"learning_rate": 9.829456904530539e-05,
|
2503 |
+
"loss": 0.3349,
|
2504 |
+
"step": 208000
|
2505 |
+
},
|
2506 |
+
{
|
2507 |
+
"epoch": 3.55,
|
2508 |
+
"learning_rate": 9.808263580357464e-05,
|
2509 |
+
"loss": 0.3351,
|
2510 |
+
"step": 208500
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 3.56,
|
2514 |
+
"learning_rate": 9.787052480668757e-05,
|
2515 |
+
"loss": 0.3352,
|
2516 |
+
"step": 209000
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 3.57,
|
2520 |
+
"learning_rate": 9.76578125405694e-05,
|
2521 |
+
"loss": 0.3355,
|
2522 |
+
"step": 209500
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 3.57,
|
2526 |
+
"learning_rate": 9.744535194458411e-05,
|
2527 |
+
"loss": 0.3354,
|
2528 |
+
"step": 210000
|
2529 |
}
|
2530 |
],
|
2531 |
"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 sha256:6a63ed5615691b5a4420962dc27128e6f0d4753bfd9410a7b1a6cb622c4acbb5
|
3 |
size 201355195
|