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:af01b5ca42520bcf619e023d4a16b5298aaa21dec9432e39d57a0c72c202ab9a
|
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 sha256:354a0aed676b29ec3760436e5b6c43c03cc9569f889c0b3b60a7749726eff99e
|
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 sha256:7e14ecc5beeebc62d444ee2189eaa9cdcc7f712888371458a0734a769c8606f9
|
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 sha256:3da12d484b890ae8d00ec81f880f5fcabe9fab18446a270662286922b1e88c62
|
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:ccafac50eaf81a2756a49700e4d5786269f5269edf292835f3f910779efbc3a3
|
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:d5b3f1141ef34f4da98944cd3ac205ef2d95d3e7571bb5e5867c779db9ce0e85
|
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 sha256:5570cbca9105b2caec7d33a540aca9f5afd3920d293c8c6ddfc4a69132c812c3
|
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 sha256:17870ec46d59ea66d97c4e19444a8e5193a2206169a62e6711fb724252fcfe69
|
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": 0.00010166506882009926,
|
2407 |
"loss": 0.3356,
|
2408 |
"step": 200000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2409 |
}
|
2410 |
],
|
2411 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.4893575373826606,
|
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": 0.00010166506882009926,
|
2407 |
"loss": 0.3356,
|
2408 |
"step": 200000
|
2409 |
+
},
|
2410 |
+
{
|
2411 |
+
"epoch": 3.41,
|
2412 |
+
"learning_rate": 0.00010145626726491797,
|
2413 |
+
"loss": 0.3363,
|
2414 |
+
"step": 200500
|
2415 |
+
},
|
2416 |
+
{
|
2417 |
+
"epoch": 3.42,
|
2418 |
+
"learning_rate": 0.00010124683571819103,
|
2419 |
+
"loss": 0.3363,
|
2420 |
+
"step": 201000
|
2421 |
+
},
|
2422 |
+
{
|
2423 |
+
"epoch": 3.43,
|
2424 |
+
"learning_rate": 0.00010103719447377321,
|
2425 |
+
"loss": 0.3363,
|
2426 |
+
"step": 201500
|
2427 |
+
},
|
2428 |
+
{
|
2429 |
+
"epoch": 3.44,
|
2430 |
+
"learning_rate": 0.00010082734560073903,
|
2431 |
+
"loss": 0.3358,
|
2432 |
+
"step": 202000
|
2433 |
+
},
|
2434 |
+
{
|
2435 |
+
"epoch": 3.45,
|
2436 |
+
"learning_rate": 0.00010061729117021209,
|
2437 |
+
"loss": 0.336,
|
2438 |
+
"step": 202500
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 3.46,
|
2442 |
+
"learning_rate": 0.00010040703325534484,
|
2443 |
+
"loss": 0.336,
|
2444 |
+
"step": 203000
|
2445 |
+
},
|
2446 |
+
{
|
2447 |
+
"epoch": 3.46,
|
2448 |
+
"learning_rate": 0.00010019657393129802,
|
2449 |
+
"loss": 0.3359,
|
2450 |
+
"step": 203500
|
2451 |
+
},
|
2452 |
+
{
|
2453 |
+
"epoch": 3.47,
|
2454 |
+
"learning_rate": 9.998591527522016e-05,
|
2455 |
+
"loss": 0.3357,
|
2456 |
+
"step": 204000
|
2457 |
+
},
|
2458 |
+
{
|
2459 |
+
"epoch": 3.48,
|
2460 |
+
"learning_rate": 9.977505936622718e-05,
|
2461 |
+
"loss": 0.3356,
|
2462 |
+
"step": 204500
|
2463 |
+
},
|
2464 |
+
{
|
2465 |
+
"epoch": 3.49,
|
2466 |
+
"learning_rate": 9.956400828538178e-05,
|
2467 |
+
"loss": 0.3358,
|
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 sha256:354a0aed676b29ec3760436e5b6c43c03cc9569f889c0b3b60a7749726eff99e
|
3 |
size 201355195
|