Training in progress, step 591000
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/Jun01_02-00-15_72d6bfb1a401/events.out.tfevents.1685586378.72d6bfb1a401.2268.0 +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:cc9ad53a3115139f361080abe79a9737051bc035a423bc59f9cc8d229a8e895a
|
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:eb3e0019bc999b90253f77b24ce40dc1e78a96ded902156b1cdea866c7ce4331
|
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 sha256:52330c0aa0d02fcb5799ed6e9cc612a980458016cf0a3f065d156f1aa64d865b
|
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 sha256:13ae0c12d6dffd3dc4ba83c4aefd7c6399f9d43d426c023af851822645281d9d
|
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:ec9b92b3a1b3f86b4bf4ceafccb75f91a766a16a540352fed8d3f4b4b3e97656
|
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": 15.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -7062,11 +7062,47 @@
|
|
7062 |
"learning_rate": 6.227372205429946e-07,
|
7063 |
"loss": 1.0273,
|
7064 |
"step": 588000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7065 |
}
|
7066 |
],
|
7067 |
"max_steps": 762960,
|
7068 |
"num_train_epochs": 20,
|
7069 |
-
"total_flos": 7.
|
7070 |
"trial_name": null,
|
7071 |
"trial_params": null
|
7072 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.492277526711474,
|
5 |
+
"global_step": 591000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7062 |
"learning_rate": 6.227372205429946e-07,
|
7063 |
"loss": 1.0273,
|
7064 |
"step": 588000
|
7065 |
+
},
|
7066 |
+
{
|
7067 |
+
"epoch": 15.43,
|
7068 |
+
"learning_rate": 6.193420398182335e-07,
|
7069 |
+
"loss": 1.0237,
|
7070 |
+
"step": 588500
|
7071 |
+
},
|
7072 |
+
{
|
7073 |
+
"epoch": 15.44,
|
7074 |
+
"learning_rate": 6.159548307004379e-07,
|
7075 |
+
"loss": 1.0253,
|
7076 |
+
"step": 589000
|
7077 |
+
},
|
7078 |
+
{
|
7079 |
+
"epoch": 15.45,
|
7080 |
+
"learning_rate": 6.125756075470824e-07,
|
7081 |
+
"loss": 1.0333,
|
7082 |
+
"step": 589500
|
7083 |
+
},
|
7084 |
+
{
|
7085 |
+
"epoch": 15.47,
|
7086 |
+
"learning_rate": 6.092043846817916e-07,
|
7087 |
+
"loss": 1.033,
|
7088 |
+
"step": 590000
|
7089 |
+
},
|
7090 |
+
{
|
7091 |
+
"epoch": 15.48,
|
7092 |
+
"learning_rate": 6.058411763942787e-07,
|
7093 |
+
"loss": 1.0371,
|
7094 |
+
"step": 590500
|
7095 |
+
},
|
7096 |
+
{
|
7097 |
+
"epoch": 15.49,
|
7098 |
+
"learning_rate": 6.024926992769612e-07,
|
7099 |
+
"loss": 1.0252,
|
7100 |
+
"step": 591000
|
7101 |
}
|
7102 |
],
|
7103 |
"max_steps": 762960,
|
7104 |
"num_train_epochs": 20,
|
7105 |
+
"total_flos": 7.070228286116659e+17,
|
7106 |
"trial_name": null,
|
7107 |
"trial_params": null
|
7108 |
}
|
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:eb3e0019bc999b90253f77b24ce40dc1e78a96ded902156b1cdea866c7ce4331
|
3 |
size 1944201353
|
runs/Jun01_02-00-15_72d6bfb1a401/events.out.tfevents.1685586378.72d6bfb1a401.2268.0
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 sha256:7e58b715a66e89807c52ea029fcbe06f9781357371c2f8198cbfab569dccf0ea
|
3 |
+
size 12141
|