Training in progress, step 235000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.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 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d600151dc2dc266e3557533538435d6b6db41f98fc5aa6d10559c061c6458e35
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:709c41fd920a30b5a951e08bd40afe2f5260f9bde88fa94e15affc485599e91a
|
3 |
size 201355195
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c66ba390217b4d8447f44b985cca85c06771f09c07202b467e662dc71fa21ab
|
3 |
size 14503
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2745d36262546e2bf6b0a91f0fe909f35ee1b9739bfa3dbde358e0e5923d6af
|
3 |
size 14503
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c374f032eb1444ba3eb771610b11e973907b7f2c7941d675cb2cd3ba1bda96fe
|
3 |
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7494f025c9489a3650d72192671a7856a518eec49568c888ed94680627392d60
|
3 |
size 14503
|
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:d574cf7fd4086a04a10f73de0750cb369688e3f2923b5738f0fdca60cb1b5848
|
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 sha256:963e0fa0db7794bff4c101c0c5894c49d07149ac9fe80c80cab49c8f45412658
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2766,6 +2766,66 @@
|
|
2766 |
"learning_rate": 8.88117242320186e-05,
|
2767 |
"loss": 0.3307,
|
2768 |
"step": 230000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2769 |
}
|
2770 |
],
|
2771 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 235000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2766 |
"learning_rate": 8.88117242320186e-05,
|
2767 |
"loss": 0.3307,
|
2768 |
"step": 230000
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 3.92,
|
2772 |
+
"learning_rate": 8.859351896185837e-05,
|
2773 |
+
"loss": 0.3311,
|
2774 |
+
"step": 230500
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 3.93,
|
2778 |
+
"learning_rate": 8.837522887713532e-05,
|
2779 |
+
"loss": 0.3306,
|
2780 |
+
"step": 231000
|
2781 |
+
},
|
2782 |
+
{
|
2783 |
+
"epoch": 3.94,
|
2784 |
+
"learning_rate": 8.815729295883665e-05,
|
2785 |
+
"loss": 0.3304,
|
2786 |
+
"step": 231500
|
2787 |
+
},
|
2788 |
+
{
|
2789 |
+
"epoch": 3.95,
|
2790 |
+
"learning_rate": 8.793883986796712e-05,
|
2791 |
+
"loss": 0.3305,
|
2792 |
+
"step": 232000
|
2793 |
+
},
|
2794 |
+
{
|
2795 |
+
"epoch": 3.96,
|
2796 |
+
"learning_rate": 8.772030842395313e-05,
|
2797 |
+
"loss": 0.3305,
|
2798 |
+
"step": 232500
|
2799 |
+
},
|
2800 |
+
{
|
2801 |
+
"epoch": 3.97,
|
2802 |
+
"learning_rate": 8.750170078361183e-05,
|
2803 |
+
"loss": 0.3303,
|
2804 |
+
"step": 233000
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 3.97,
|
2808 |
+
"learning_rate": 8.728301910451236e-05,
|
2809 |
+
"loss": 0.3304,
|
2810 |
+
"step": 233500
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 3.98,
|
2814 |
+
"learning_rate": 8.706426554495459e-05,
|
2815 |
+
"loss": 0.3303,
|
2816 |
+
"step": 234000
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 3.99,
|
2820 |
+
"learning_rate": 8.68458799786565e-05,
|
2821 |
+
"loss": 0.3303,
|
2822 |
+
"step": 234500
|
2823 |
+
},
|
2824 |
+
{
|
2825 |
+
"epoch": 4.0,
|
2826 |
+
"learning_rate": 8.662742711628061e-05,
|
2827 |
+
"loss": 0.3303,
|
2828 |
+
"step": 235000
|
2829 |
}
|
2830 |
],
|
2831 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:709c41fd920a30b5a951e08bd40afe2f5260f9bde88fa94e15affc485599e91a
|
3 |
size 201355195
|