Training in progress, step 651000
Browse files- 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 +39 -3
- pytorch_model.bin +1 -1
- runs/Jun03_20-07-36_5814eb69ea9a/events.out.tfevents.1685824428.5814eb69ea9a.704.0 +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 3871544599
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49722fb4525cdfb5db10b91cc9964d6d93d53a3f624d39e81da612430ad473a1
|
3 |
size 3871544599
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca9a9edb197fdbdf00385a4c3210b7e932baf72faf125a9727ef9e5c30f08804
|
3 |
size 1944201353
|
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:c0e68f9154824758e939f3f203bd07329f72d1b44231a034da24c8f1b729ad93
|
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:f803e795f13c2c61f76367562826b3d0d4c17b6383f5b4bcdb43021fd0dba972
|
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 sha256:2f3d07c5e6735b6a42b3fb3c809508eeb0916a9cf2438aa81c83c4bba3bf70b8
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -7782,11 +7782,47 @@
|
|
7782 |
"learning_rate": 2.7607930630074693e-07,
|
7783 |
"loss": 1.0151,
|
7784 |
"step": 648000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7785 |
}
|
7786 |
],
|
7787 |
"max_steps": 762960,
|
7788 |
"num_train_epochs": 20,
|
7789 |
-
"total_flos": 7.
|
7790 |
"trial_name": null,
|
7791 |
"trial_params": null
|
7792 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 17.065103647859413,
|
5 |
+
"global_step": 651000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7782 |
"learning_rate": 2.7607930630074693e-07,
|
7783 |
"loss": 1.0151,
|
7784 |
"step": 648000
|
7785 |
+
},
|
7786 |
+
{
|
7787 |
+
"epoch": 17.0,
|
7788 |
+
"learning_rate": 2.7373283880098636e-07,
|
7789 |
+
"loss": 1.0206,
|
7790 |
+
"step": 648500
|
7791 |
+
},
|
7792 |
+
{
|
7793 |
+
"epoch": 17.01,
|
7794 |
+
"learning_rate": 2.7139580785331824e-07,
|
7795 |
+
"loss": 0.9983,
|
7796 |
+
"step": 649000
|
7797 |
+
},
|
7798 |
+
{
|
7799 |
+
"epoch": 17.03,
|
7800 |
+
"learning_rate": 2.690682233637923e-07,
|
7801 |
+
"loss": 0.9983,
|
7802 |
+
"step": 649500
|
7803 |
+
},
|
7804 |
+
{
|
7805 |
+
"epoch": 17.04,
|
7806 |
+
"learning_rate": 2.6675009519841726e-07,
|
7807 |
+
"loss": 1.023,
|
7808 |
+
"step": 650000
|
7809 |
+
},
|
7810 |
+
{
|
7811 |
+
"epoch": 17.05,
|
7812 |
+
"learning_rate": 2.6444143318311964e-07,
|
7813 |
+
"loss": 1.0061,
|
7814 |
+
"step": 650500
|
7815 |
+
},
|
7816 |
+
{
|
7817 |
+
"epoch": 17.07,
|
7818 |
+
"learning_rate": 2.621422471037019e-07,
|
7819 |
+
"loss": 1.0198,
|
7820 |
+
"step": 651000
|
7821 |
}
|
7822 |
],
|
7823 |
"max_steps": 762960,
|
7824 |
"num_train_epochs": 20,
|
7825 |
+
"total_flos": 7.731104357603082e+17,
|
7826 |
"trial_name": null,
|
7827 |
"trial_params": null
|
7828 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca9a9edb197fdbdf00385a4c3210b7e932baf72faf125a9727ef9e5c30f08804
|
3 |
size 1944201353
|
runs/Jun03_20-07-36_5814eb69ea9a/events.out.tfevents.1685824428.5814eb69ea9a.704.0
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:dacfe16a4c0981146c418235b9967b5b1712f3ffaff1b3360c7304894f973112
|
3 |
+
size 12141
|