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 sha256:9e83e911431daddbb5fb07546fcd0ead35a24a9d92caf98379399cb3838b4b73
|
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:b64554b1d34db97dfdbb800052b39ab43a21dec4e876d8b88d7b75afdcefbe88
|
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:b87eefc0a506b1050cb06c38c784da5f6b4431ded291f8c7b8382ea602c6b00d
|
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 sha256:11d8f5d8f125cd22a6ad5c501ed968acc092a0af6afb6186ba7d3d4be0c715e3
|
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:d76923756bc10bf0153eff8cd1f84631296a2fa97d8a64a30bb5a36a533e1119
|
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:f6e0f0c845a4ed1511dd45a62a8a544c473a93c4a6e6df62309fc4f47cf7e634
|
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:e4eb1b41c7c061aff1a8cf4d4b29ca4f1b06eb8036887e7db173c41b67cce439
|
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:a29aa394da4020a18d0273538f9a534d932e35dbf12a0267366fecf45a649ba9
|
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": 9.744151840926749e-05,
|
2527 |
"loss": 0.3335,
|
2528 |
"step": 210000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2529 |
}
|
2530 |
],
|
2531 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.6595744680851063,
|
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": 9.744151840926749e-05,
|
2527 |
"loss": 0.3335,
|
2528 |
"step": 210000
|
2529 |
+
},
|
2530 |
+
{
|
2531 |
+
"epoch": 3.58,
|
2532 |
+
"learning_rate": 9.722888324889499e-05,
|
2533 |
+
"loss": 0.3332,
|
2534 |
+
"step": 210500
|
2535 |
+
},
|
2536 |
+
{
|
2537 |
+
"epoch": 3.59,
|
2538 |
+
"learning_rate": 9.701607872588813e-05,
|
2539 |
+
"loss": 0.3332,
|
2540 |
+
"step": 211000
|
2541 |
+
},
|
2542 |
+
{
|
2543 |
+
"epoch": 3.6,
|
2544 |
+
"learning_rate": 9.680267996842769e-05,
|
2545 |
+
"loss": 0.3333,
|
2546 |
+
"step": 211500
|
2547 |
+
},
|
2548 |
+
{
|
2549 |
+
"epoch": 3.61,
|
2550 |
+
"learning_rate": 9.658911537529946e-05,
|
2551 |
+
"loss": 0.3341,
|
2552 |
+
"step": 212000
|
2553 |
+
},
|
2554 |
+
{
|
2555 |
+
"epoch": 3.62,
|
2556 |
+
"learning_rate": 9.63753870542998e-05,
|
2557 |
+
"loss": 0.3335,
|
2558 |
+
"step": 212500
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 3.63,
|
2562 |
+
"learning_rate": 9.616235299374545e-05,
|
2563 |
+
"loss": 0.3334,
|
2564 |
+
"step": 213000
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 3.63,
|
2568 |
+
"learning_rate": 9.594830418065726e-05,
|
2569 |
+
"loss": 0.3337,
|
2570 |
+
"step": 213500
|
2571 |
+
},
|
2572 |
+
{
|
2573 |
+
"epoch": 3.64,
|
2574 |
+
"learning_rate": 9.573409796424543e-05,
|
2575 |
+
"loss": 0.3338,
|
2576 |
+
"step": 214000
|
2577 |
+
},
|
2578 |
+
{
|
2579 |
+
"epoch": 3.65,
|
2580 |
+
"learning_rate": 9.55197364586388e-05,
|
2581 |
+
"loss": 0.3331,
|
2582 |
+
"step": 214500
|
2583 |
+
},
|
2584 |
+
{
|
2585 |
+
"epoch": 3.66,
|
2586 |
+
"learning_rate": 9.530522177949888e-05,
|
2587 |
+
"loss": 0.3326,
|
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:b64554b1d34db97dfdbb800052b39ab43a21dec4e876d8b88d7b75afdcefbe88
|
3 |
size 201355195
|