Kasper7953
commited on
Commit
•
b2a115d
1
Parent(s):
7f41c81
Training in progress, step 20000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +23 -3
- pytorch_model.bin +1 -1
- runs/Mar11_11-28-52_b25631785753/events.out.tfevents.1678534153.b25631785753.957.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2847145157
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9c14fcf03954690bc27a3f30a2dbbe40c7912b604337f903af3065014a20bb6
|
3 |
size 2847145157
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ae783b21b6623aeda112e79f193e9782db553c4ca9d2a9034e69b514f9ce627
|
3 |
size 1524261149
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b144e855c26b4a67bcc8aef0343e18f9ba30802df282181b8e7f5a853ff30385
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:992bd69aa05735ea7d505c9759104a3121010dab24aad121f3e53003a994a4c6
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -450,11 +450,31 @@
|
|
450 |
"learning_rate": 3.5759256483285864e-05,
|
451 |
"loss": 2.2077,
|
452 |
"step": 19000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
453 |
}
|
454 |
],
|
455 |
"max_steps": 66710,
|
456 |
"num_train_epochs": 10,
|
457 |
-
"total_flos": 2.
|
458 |
"trial_name": null,
|
459 |
"trial_params": null
|
460 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.99805126667666,
|
5 |
+
"global_step": 20000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
450 |
"learning_rate": 3.5759256483285864e-05,
|
451 |
"loss": 2.2077,
|
452 |
"step": 19000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 2.92,
|
456 |
+
"learning_rate": 3.538450007495128e-05,
|
457 |
+
"loss": 2.1778,
|
458 |
+
"step": 19500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 2.94,
|
462 |
+
"eval_loss": 2.6352317333221436,
|
463 |
+
"eval_runtime": 210.4866,
|
464 |
+
"eval_samples_per_second": 16.78,
|
465 |
+
"eval_steps_per_second": 5.597,
|
466 |
+
"step": 19600
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 3.0,
|
470 |
+
"learning_rate": 3.50097436666167e-05,
|
471 |
+
"loss": 2.2016,
|
472 |
+
"step": 20000
|
473 |
}
|
474 |
],
|
475 |
"max_steps": 66710,
|
476 |
"num_train_epochs": 10,
|
477 |
+
"total_flos": 2.7207121225728e+16,
|
478 |
"trial_name": null,
|
479 |
"trial_params": null
|
480 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ae783b21b6623aeda112e79f193e9782db553c4ca9d2a9034e69b514f9ce627
|
3 |
size 1524261149
|
runs/Mar11_11-28-52_b25631785753/events.out.tfevents.1678534153.b25631785753.957.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9812e6240cbcc86c0c714b5f758155aef3e19b7b08af4a1d5bbf5ae7e134baec
|
3 |
+
size 8560
|