Training in progress, step 405000
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 sha256:2f1e57f8f9a1efae4c3fff9c42809948cf75dc1570f267d47e623eb161dd90ee
|
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 sha256:56d8a8ee16945aec5749f9bb829babf6a82d396722df24142a2fb75543830090
|
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 sha256:8cbdacfd237218d949eb56551a47bd67e43ffe255054067bcabe7d224d04d23c
|
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:e605556925fadc203c4043dc72d59f7d1f09cea160de48a96ed16b00dc720636
|
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 sha256:45979078708e5c9a4206e00dc378863acf7f34dabb4d86e9d7220967ac3e4a90
|
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:d873f836ac16dbb44487dcb127bad8ae4c46c3950f90d6a110aaaf2117dbfabf
|
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 sha256:65dadf708547d192dd1a1f85344e17c1a7a89640d06852cd8566bd64ca2db817
|
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:d581f3d19e2392f3251f890758885d9382430882b8662a69148bae9c0818b614
|
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": 6.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -4806,6 +4806,66 @@
|
|
4806 |
"learning_rate": 2.340890806960229e-05,
|
4807 |
"loss": 0.3201,
|
4808 |
"step": 400000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4809 |
}
|
4810 |
],
|
4811 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.893609416090076,
|
5 |
+
"global_step": 405000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
4806 |
"learning_rate": 2.340890806960229e-05,
|
4807 |
"loss": 0.3201,
|
4808 |
"step": 400000
|
4809 |
+
},
|
4810 |
+
{
|
4811 |
+
"epoch": 6.82,
|
4812 |
+
"learning_rate": 2.327975361381488e-05,
|
4813 |
+
"loss": 0.3202,
|
4814 |
+
"step": 400500
|
4815 |
+
},
|
4816 |
+
{
|
4817 |
+
"epoch": 6.83,
|
4818 |
+
"learning_rate": 2.3151158963960426e-05,
|
4819 |
+
"loss": 0.3202,
|
4820 |
+
"step": 401000
|
4821 |
+
},
|
4822 |
+
{
|
4823 |
+
"epoch": 6.83,
|
4824 |
+
"learning_rate": 2.302312538921618e-05,
|
4825 |
+
"loss": 0.3201,
|
4826 |
+
"step": 401500
|
4827 |
+
},
|
4828 |
+
{
|
4829 |
+
"epoch": 6.84,
|
4830 |
+
"learning_rate": 2.2895654153221863e-05,
|
4831 |
+
"loss": 0.32,
|
4832 |
+
"step": 402000
|
4833 |
+
},
|
4834 |
+
{
|
4835 |
+
"epoch": 6.85,
|
4836 |
+
"learning_rate": 2.276874651406709e-05,
|
4837 |
+
"loss": 0.3197,
|
4838 |
+
"step": 402500
|
4839 |
+
},
|
4840 |
+
{
|
4841 |
+
"epoch": 6.86,
|
4842 |
+
"learning_rate": 2.2642655845309204e-05,
|
4843 |
+
"loss": 0.3199,
|
4844 |
+
"step": 403000
|
4845 |
+
},
|
4846 |
+
{
|
4847 |
+
"epoch": 6.87,
|
4848 |
+
"learning_rate": 2.2516878018406796e-05,
|
4849 |
+
"loss": 0.32,
|
4850 |
+
"step": 403500
|
4851 |
+
},
|
4852 |
+
{
|
4853 |
+
"epoch": 6.88,
|
4854 |
+
"learning_rate": 2.2391667526711484e-05,
|
4855 |
+
"loss": 0.3202,
|
4856 |
+
"step": 404000
|
4857 |
+
},
|
4858 |
+
{
|
4859 |
+
"epoch": 6.89,
|
4860 |
+
"learning_rate": 2.226702560600025e-05,
|
4861 |
+
"loss": 0.3198,
|
4862 |
+
"step": 404500
|
4863 |
+
},
|
4864 |
+
{
|
4865 |
+
"epoch": 6.89,
|
4866 |
+
"learning_rate": 2.2142953486438546e-05,
|
4867 |
+
"loss": 0.32,
|
4868 |
+
"step": 405000
|
4869 |
}
|
4870 |
],
|
4871 |
"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 sha256:56d8a8ee16945aec5749f9bb829babf6a82d396722df24142a2fb75543830090
|
3 |
size 201355195
|