Training in progress, step 99000
Browse files- .gitattributes +1 -0
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +17 -3
- log.txt +0 -0
- pytorch_model.bin +1 -1
- runs/Jan19_18-25-54_turing/events.out.tfevents.1674149167.turing.482470.1 +2 -2
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
log.txt filter=lfs diff=lfs merge=lfs -text
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 538943941
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb6e7c33c0689e6c3298ded6c7a90382868146c4308e6c82b556a0111b8b1259
|
3 |
size 538943941
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 269468281
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5eb3d7defb1c32bd6fc4a21ab99f020092d22e7be3eb53044a485f9035ce1b7
|
3 |
size 269468281
|
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:f8326297abcf2a1908b1a767fe60d17987a26f2c5604b81b26fa14b663ae5bff
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da692e8a61b0469d66a05ee87d5569d6a98e9a4d9ac49ff837bd9b7979d7ad48
|
3 |
size 557
|
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:eed58ddd784a948e5c48af7e5967f7f6677bd7d9091292c0e7d8f98ed90e5eb2
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.4165735244750977,
|
3 |
"best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-98500",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2764,11 +2764,25 @@
|
|
2764 |
"eval_samples_per_second": 298.894,
|
2765 |
"eval_steps_per_second": 37.375,
|
2766 |
"step": 98500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2767 |
}
|
2768 |
],
|
2769 |
"max_steps": 134550,
|
2770 |
"num_train_epochs": 15,
|
2771 |
-
"total_flos": 6.
|
2772 |
"trial_name": null,
|
2773 |
"trial_params": null
|
2774 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.4165735244750977,
|
3 |
"best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-98500",
|
4 |
+
"epoch": 11.03678660633106,
|
5 |
+
"global_step": 99000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2764 |
"eval_samples_per_second": 298.894,
|
2765 |
"eval_steps_per_second": 37.375,
|
2766 |
"step": 98500
|
2767 |
+
},
|
2768 |
+
{
|
2769 |
+
"epoch": 11.04,
|
2770 |
+
"learning_rate": 2.6448903753251582e-05,
|
2771 |
+
"loss": 1.4601,
|
2772 |
+
"step": 99000
|
2773 |
+
},
|
2774 |
+
{
|
2775 |
+
"epoch": 11.04,
|
2776 |
+
"eval_loss": 1.421845555305481,
|
2777 |
+
"eval_runtime": 35.8769,
|
2778 |
+
"eval_samples_per_second": 320.317,
|
2779 |
+
"eval_steps_per_second": 40.054,
|
2780 |
+
"step": 99000
|
2781 |
}
|
2782 |
],
|
2783 |
"max_steps": 134550,
|
2784 |
"num_train_epochs": 15,
|
2785 |
+
"total_flos": 6.863007182432229e+17,
|
2786 |
"trial_name": null,
|
2787 |
"trial_params": null
|
2788 |
}
|
log.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 269468281
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5eb3d7defb1c32bd6fc4a21ab99f020092d22e7be3eb53044a485f9035ce1b7
|
3 |
size 269468281
|
runs/Jan19_18-25-54_turing/events.out.tfevents.1674149167.turing.482470.1
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 sha256:5ac6e242fb32701c2853e60a0c367c9fdb56bc17ee59cc3d3f6a344a8a448fea
|
3 |
+
size 89985
|