Training in progress, step 205000
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 sha256:057ac8242ae4950ae4de98a5746b30f516df4b7518cc74d6574cc6f7fcdefb5e
|
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 sha256:934659f94181ad4485889c5bb5271f6abde3d6795ecad2cad53e9b5483beeb0c
|
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 sha256:7bba7d43c9a61a289cd501e039253d309aa0f0a11c66d9b2e4ddc188ad3926ea
|
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 sha256:945e7c48e91acce820b4cc0e2a26e74efc9078cce21e915fe39b92b44a546474
|
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:b73902f90aaa4cfa06def316316665fd72c3ae9a76abfe3c97bf72e6a2a5475c
|
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:e2efc8164ecfc550cc54d5de99ea69212d0d015234dc82eb30a01c07908a480a
|
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 sha256:58e0269ee26a6783448738682e5dbef14a04536fb974be83632d7cf11724cdee
|
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 sha256:33cc556ef29f305eab3b663a3f8e50dc2decd7bed4e9c691167b9175202a09e3
|
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,
|
@@ -2406,6 +2406,66 @@
|
|
2406 |
"learning_rate": 0.00010166214120820125,
|
2407 |
"loss": 0.3323,
|
2408 |
"step": 200000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2409 |
}
|
2410 |
],
|
2411 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.4893617021276597,
|
5 |
+
"global_step": 205000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2406 |
"learning_rate": 0.00010166214120820125,
|
2407 |
"loss": 0.3323,
|
2408 |
"step": 200000
|
2409 |
+
},
|
2410 |
+
{
|
2411 |
+
"epoch": 3.41,
|
2412 |
+
"learning_rate": 0.00010145333668004409,
|
2413 |
+
"loss": 0.3324,
|
2414 |
+
"step": 200500
|
2415 |
+
},
|
2416 |
+
{
|
2417 |
+
"epoch": 3.42,
|
2418 |
+
"learning_rate": 0.00010124390218327814,
|
2419 |
+
"loss": 0.3326,
|
2420 |
+
"step": 201000
|
2421 |
+
},
|
2422 |
+
{
|
2423 |
+
"epoch": 3.43,
|
2424 |
+
"learning_rate": 0.00010103425801777416,
|
2425 |
+
"loss": 0.3323,
|
2426 |
+
"step": 201500
|
2427 |
+
},
|
2428 |
+
{
|
2429 |
+
"epoch": 3.44,
|
2430 |
+
"learning_rate": 0.00010082482616197382,
|
2431 |
+
"loss": 0.3327,
|
2432 |
+
"step": 202000
|
2433 |
+
},
|
2434 |
+
{
|
2435 |
+
"epoch": 3.45,
|
2436 |
+
"learning_rate": 0.00010061518959485431,
|
2437 |
+
"loss": 0.3337,
|
2438 |
+
"step": 202500
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 3.46,
|
2442 |
+
"learning_rate": 0.00010040492965561988,
|
2443 |
+
"loss": 0.3332,
|
2444 |
+
"step": 203000
|
2445 |
+
},
|
2446 |
+
{
|
2447 |
+
"epoch": 3.46,
|
2448 |
+
"learning_rate": 0.00010019488945022819,
|
2449 |
+
"loss": 0.3338,
|
2450 |
+
"step": 203500
|
2451 |
+
},
|
2452 |
+
{
|
2453 |
+
"epoch": 3.47,
|
2454 |
+
"learning_rate": 9.998422920787449e-05,
|
2455 |
+
"loss": 0.3351,
|
2456 |
+
"step": 204000
|
2457 |
+
},
|
2458 |
+
{
|
2459 |
+
"epoch": 3.48,
|
2460 |
+
"learning_rate": 9.977337172924645e-05,
|
2461 |
+
"loss": 0.3355,
|
2462 |
+
"step": 204500
|
2463 |
+
},
|
2464 |
+
{
|
2465 |
+
"epoch": 3.49,
|
2466 |
+
"learning_rate": 9.956231909542228e-05,
|
2467 |
+
"loss": 0.3346,
|
2468 |
+
"step": 205000
|
2469 |
}
|
2470 |
],
|
2471 |
"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 sha256:934659f94181ad4485889c5bb5271f6abde3d6795ecad2cad53e9b5483beeb0c
|
3 |
size 201355195
|