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:c7e15c80f17b5f67ff58217cc314ac49bd28cfe49e2b8ca0c5682fdc4a7efce7
|
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 sha256:2de53dcb3ee4e13e390ed7fc2cb2b5ebfba796eb2275e3be62b0de5358a92508
|
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 sha256:17caf9d5782cd523194dc4cd34e56cdf909db81a566bbef7cbd8c858a34f3fe2
|
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 sha256:10a7887d6b4e9ab070e5287ab7206d0dcc85510c107141500fe19ee9c9131187
|
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:a1296f661c0186856404bfab321588f651622cf10f20699fb3533149305f17ad
|
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:ff74138205755bce38bd1bd9875c6c045ff1c6f0ea6da20c8a628756883c7179
|
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:b51c4c89b0caaa72a872724373981c6b8075ed36230b2868421a8a00b0a3fdb7
|
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 sha256:4fc984656e3890fe88d20962b94768c87acd5e03e3a0a90142b93bb164b6f90a
|
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": 3.
|
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": 8.881390584911924e-05,
|
2767 |
"loss": 0.3322,
|
2768 |
"step": 230000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2769 |
}
|
2770 |
],
|
2771 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.9999914894341324,
|
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": 8.881390584911924e-05,
|
2767 |
"loss": 0.3322,
|
2768 |
"step": 230000
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 3.92,
|
2772 |
+
"learning_rate": 8.859570143798174e-05,
|
2773 |
+
"loss": 0.3325,
|
2774 |
+
"step": 230500
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 3.93,
|
2778 |
+
"learning_rate": 8.837741219074127e-05,
|
2779 |
+
"loss": 0.3324,
|
2780 |
+
"step": 231000
|
2781 |
+
},
|
2782 |
+
{
|
2783 |
+
"epoch": 3.94,
|
2784 |
+
"learning_rate": 8.815904026182456e-05,
|
2785 |
+
"loss": 0.3322,
|
2786 |
+
"step": 231500
|
2787 |
+
},
|
2788 |
+
{
|
2789 |
+
"epoch": 3.95,
|
2790 |
+
"learning_rate": 8.794058780647441e-05,
|
2791 |
+
"loss": 0.3319,
|
2792 |
+
"step": 232000
|
2793 |
+
},
|
2794 |
+
{
|
2795 |
+
"epoch": 3.96,
|
2796 |
+
"learning_rate": 8.772205698072836e-05,
|
2797 |
+
"loss": 0.3324,
|
2798 |
+
"step": 232500
|
2799 |
+
},
|
2800 |
+
{
|
2801 |
+
"epoch": 3.97,
|
2802 |
+
"learning_rate": 8.750432451851294e-05,
|
2803 |
+
"loss": 0.3322,
|
2804 |
+
"step": 233000
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 3.97,
|
2808 |
+
"learning_rate": 8.728564371508559e-05,
|
2809 |
+
"loss": 0.332,
|
2810 |
+
"step": 233500
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 3.98,
|
2814 |
+
"learning_rate": 8.706732858104335e-05,
|
2815 |
+
"loss": 0.3322,
|
2816 |
+
"step": 234000
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 3.99,
|
2820 |
+
"learning_rate": 8.684850626123223e-05,
|
2821 |
+
"loss": 0.3323,
|
2822 |
+
"step": 234500
|
2823 |
+
},
|
2824 |
+
{
|
2825 |
+
"epoch": 4.0,
|
2826 |
+
"learning_rate": 8.66296163494292e-05,
|
2827 |
+
"loss": 0.3321,
|
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 sha256:2de53dcb3ee4e13e390ed7fc2cb2b5ebfba796eb2275e3be62b0de5358a92508
|
3 |
size 201355195
|