Training in progress, step 42500
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1001681601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91053d4d3e3b390ce4e87a97edfb861b40bace7ab4f51e7cf005100149aa856d
|
3 |
size 1001681601
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f209d5f1e005ac2c8016438fcabcd9b0dd6f2f1784f8b113fa45848f0a727656
|
3 |
size 551185105
|
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 sha256:599cb814e3e2df58e24bb701a32fb03968b997cef6772b1ee3a9736759891fa6
|
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:b5032a9b1721b340554f51a45dcc33a1f0778e8ba630efbe84fd9d17388b5a17
|
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,
|
@@ -510,11 +510,17 @@
|
|
510 |
"learning_rate": 4.5795454545454544e-09,
|
511 |
"loss": 0.0254,
|
512 |
"step": 42000
|
|
|
|
|
|
|
|
|
|
|
|
|
513 |
}
|
514 |
],
|
515 |
"max_steps": 44000,
|
516 |
"num_train_epochs": 1,
|
517 |
-
"total_flos": 4.
|
518 |
"trial_name": null,
|
519 |
"trial_params": null
|
520 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5765213380721127,
|
5 |
+
"global_step": 42500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
510 |
"learning_rate": 4.5795454545454544e-09,
|
511 |
"loss": 0.0254,
|
512 |
"step": 42000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.58,
|
516 |
+
"learning_rate": 3.443181818181818e-09,
|
517 |
+
"loss": 0.0232,
|
518 |
+
"step": 42500
|
519 |
}
|
520 |
],
|
521 |
"max_steps": 44000,
|
522 |
"num_train_epochs": 1,
|
523 |
+
"total_flos": 4.440729620525875e+16,
|
524 |
"trial_name": null,
|
525 |
"trial_params": null
|
526 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f209d5f1e005ac2c8016438fcabcd9b0dd6f2f1784f8b113fa45848f0a727656
|
3 |
size 551185105
|
runs/Nov05_07-57-57_0b25abb50174/events.out.tfevents.1667635297.0b25abb50174.23.0
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:cbbe9367f1a047a143b17cc2e8dc6651b0f3920dde8f52db3fbd3ef83092a57b
|
3 |
+
size 59150
|