Training in progress, step 570000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +39 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Jun01_02-00-15_72d6bfb1a401/1685586378.6154885/events.out.tfevents.1685586378.72d6bfb1a401.2268.1 +3 -0
- runs/Jun01_02-00-15_72d6bfb1a401/events.out.tfevents.1685586378.72d6bfb1a401.2268.0 +3 -0
- training_args.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 3871544599
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d2f2d7d2cadbcd7aceb96a8defa15be9235cf2861e0762840aae2beea42ec13
|
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:b9b07757646176e92f8dcba8a0fbcd8bbbd32524a0ba9b8949cb9efe6972db82
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:682d8f5af9a928814c1aa2cae346952f943ae20f0591da8254fd1d084226fa01
|
3 |
+
size 14511
|
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:a5970b634b76e24683de44b37ff55f568f86fe0760701f4b9ffa126dee06d439
|
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:cc780bf13ad434a35e5ae2b895926fba6c88685df4820697e037e902660ebe70
|
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": 14.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -6810,11 +6810,47 @@
|
|
6810 |
"learning_rate": 7.72271099597614e-07,
|
6811 |
"loss": 1.0389,
|
6812 |
"step": 567000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6813 |
}
|
6814 |
],
|
6815 |
"max_steps": 762960,
|
6816 |
"num_train_epochs": 20,
|
6817 |
-
"total_flos": 6.
|
6818 |
"trial_name": null,
|
6819 |
"trial_params": null
|
6820 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 14.941795724067065,
|
5 |
+
"global_step": 570000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
6810 |
"learning_rate": 7.72271099597614e-07,
|
6811 |
"loss": 1.0389,
|
6812 |
"step": 567000
|
6813 |
+
},
|
6814 |
+
{
|
6815 |
+
"epoch": 14.88,
|
6816 |
+
"learning_rate": 7.685546472145017e-07,
|
6817 |
+
"loss": 1.0438,
|
6818 |
+
"step": 567500
|
6819 |
+
},
|
6820 |
+
{
|
6821 |
+
"epoch": 14.89,
|
6822 |
+
"learning_rate": 7.648603557785422e-07,
|
6823 |
+
"loss": 1.0359,
|
6824 |
+
"step": 568000
|
6825 |
+
},
|
6826 |
+
{
|
6827 |
+
"epoch": 14.9,
|
6828 |
+
"learning_rate": 7.6115856793579e-07,
|
6829 |
+
"loss": 1.0527,
|
6830 |
+
"step": 568500
|
6831 |
+
},
|
6832 |
+
{
|
6833 |
+
"epoch": 14.92,
|
6834 |
+
"learning_rate": 7.574715320461648e-07,
|
6835 |
+
"loss": 1.034,
|
6836 |
+
"step": 569000
|
6837 |
+
},
|
6838 |
+
{
|
6839 |
+
"epoch": 14.93,
|
6840 |
+
"learning_rate": 7.537844860442989e-07,
|
6841 |
+
"loss": 1.0461,
|
6842 |
+
"step": 569500
|
6843 |
+
},
|
6844 |
+
{
|
6845 |
+
"epoch": 14.94,
|
6846 |
+
"learning_rate": 7.50104841783765e-07,
|
6847 |
+
"loss": 1.0558,
|
6848 |
+
"step": 570000
|
6849 |
}
|
6850 |
],
|
6851 |
"max_steps": 762960,
|
6852 |
"num_train_epochs": 20,
|
6853 |
+
"total_flos": 6.839220162824847e+17,
|
6854 |
"trial_name": null,
|
6855 |
"trial_params": null
|
6856 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46b3a87459854f08d80f4fb8cbdd6dbf69afb36e65aeb8868750af0e1c3b25c3
|
3 |
size 3771
|
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:b9b07757646176e92f8dcba8a0fbcd8bbbd32524a0ba9b8949cb9efe6972db82
|
3 |
size 1944201353
|
runs/Jun01_02-00-15_72d6bfb1a401/1685586378.6154885/events.out.tfevents.1685586378.72d6bfb1a401.2268.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9551b3f358861a603b4ad3dd373c1de5b81224e41cd003794b30a06e5b1d93e3
|
3 |
+
size 6184
|
runs/Jun01_02-00-15_72d6bfb1a401/events.out.tfevents.1685586378.72d6bfb1a401.2268.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af84064e46c023b2e7c8f52a9f6ca52513f50bcd2868568b383555c16d38fda3
|
3 |
+
size 5421
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46b3a87459854f08d80f4fb8cbdd6dbf69afb36e65aeb8868750af0e1c3b25c3
|
3 |
size 3771
|