Training in progress, step 40000
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 402587859
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:350d6a20720d1fd74b8a8444079c82d9172cc3091a8b4988eb3fb998da8e5918
|
3 |
size 402587859
|
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 sha256:4f773931870d5ec210c2530416bfc2b566148c206899a79032c3f2237ad80aa1
|
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 sha256:8e1d6cdc250e7c41358abfc4778ade95046631664f9a9cd0e1d2397ae0eb957c
|
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:ed7ddbb3091468495d36c3725551bda154a5ec0d8b374fc8155ef56a8e8bf136
|
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:d1a882955bcb115cdc4953b3a7056dfd2e484f24ea2b374978a6232b7b1c5d7d
|
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 sha256:1307fb0c2ffb9c9e676064788a9a9bfb8168f46f22a121e60cb381f6b8ef60ba
|
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 sha256:418af25aec4bef7120d46157de233e64fab0b4e4ebe06ec15abb44056125efaf
|
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:a94c54fffa556051788f8ee2aca37f5e903913f8b9cc822ec4876aa0c66a1968
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -426,6 +426,66 @@
|
|
426 |
"learning_rate": 0.00014831522856104197,
|
427 |
"loss": 0.371,
|
428 |
"step": 35000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
429 |
}
|
430 |
],
|
431 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6808510638297872,
|
5 |
+
"global_step": 40000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
426 |
"learning_rate": 0.00014831522856104197,
|
427 |
"loss": 0.371,
|
428 |
"step": 35000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.6,
|
432 |
+
"learning_rate": 0.00014826693414700317,
|
433 |
+
"loss": 0.3714,
|
434 |
+
"step": 35500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.61,
|
438 |
+
"learning_rate": 0.00014821796596588483,
|
439 |
+
"loss": 0.3706,
|
440 |
+
"step": 36000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.62,
|
444 |
+
"learning_rate": 0.0001481683245009831,
|
445 |
+
"loss": 0.3702,
|
446 |
+
"step": 36500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.63,
|
450 |
+
"learning_rate": 0.00014811801024223922,
|
451 |
+
"loss": 0.3702,
|
452 |
+
"step": 37000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.64,
|
456 |
+
"learning_rate": 0.00014806712632996593,
|
457 |
+
"loss": 0.3695,
|
458 |
+
"step": 37500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.65,
|
462 |
+
"learning_rate": 0.00014801546932299877,
|
463 |
+
"loss": 0.3696,
|
464 |
+
"step": 38000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.66,
|
468 |
+
"learning_rate": 0.00014796314103080835,
|
469 |
+
"loss": 0.3694,
|
470 |
+
"step": 38500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.66,
|
474 |
+
"learning_rate": 0.00014791014196985377,
|
475 |
+
"loss": 0.3687,
|
476 |
+
"step": 39000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.67,
|
480 |
+
"learning_rate": 0.0001478564726632144,
|
481 |
+
"loss": 0.3689,
|
482 |
+
"step": 39500
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.68,
|
486 |
+
"learning_rate": 0.00014780224298665108,
|
487 |
+
"loss": 0.3684,
|
488 |
+
"step": 40000
|
489 |
}
|
490 |
],
|
491 |
"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 sha256:4f773931870d5ec210c2530416bfc2b566148c206899a79032c3f2237ad80aa1
|
3 |
size 201355195
|