Training in progress, step 588000
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 sha256:145c0a00858525cef13dcc730c322c7359bdba5e00e02a3bf89edf80af62f1d8
|
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 sha256:89037c61457d92a92d8a8114636f5328491a76d6f314d56f9e8167460609d7fc
|
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:a389ff9bc9613d90441220e05bbb320a7bc427029765d050e309eaa9aac6aafa
|
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 sha256:08f55b12f85aa59ff0112a71e308a0461d067a9b1044007a121298b913aae15f
|
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:eba0ddaa6d2944ea53fae500fd775fdda4313267c086c538c0c4de183f8c7838
|
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,
|
@@ -7026,11 +7026,47 @@
|
|
7026 |
"learning_rate": 6.432680070962052e-07,
|
7027 |
"loss": 1.0271,
|
7028 |
"step": 585000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7029 |
}
|
7030 |
],
|
7031 |
"max_steps": 762960,
|
7032 |
"num_train_epochs": 20,
|
7033 |
-
"total_flos": 7.
|
7034 |
"trial_name": null,
|
7035 |
"trial_params": null
|
7036 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.413637269190843,
|
5 |
+
"global_step": 588000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7026 |
"learning_rate": 6.432680070962052e-07,
|
7027 |
"loss": 1.0271,
|
7028 |
"step": 585000
|
7029 |
+
},
|
7030 |
+
{
|
7031 |
+
"epoch": 15.35,
|
7032 |
+
"learning_rate": 6.398253158795223e-07,
|
7033 |
+
"loss": 1.0367,
|
7034 |
+
"step": 585500
|
7035 |
+
},
|
7036 |
+
{
|
7037 |
+
"epoch": 15.36,
|
7038 |
+
"learning_rate": 6.363905094466666e-07,
|
7039 |
+
"loss": 1.0408,
|
7040 |
+
"step": 586000
|
7041 |
+
},
|
7042 |
+
{
|
7043 |
+
"epoch": 15.37,
|
7044 |
+
"learning_rate": 6.32963602356865e-07,
|
7045 |
+
"loss": 1.0184,
|
7046 |
+
"step": 586500
|
7047 |
+
},
|
7048 |
+
{
|
7049 |
+
"epoch": 15.39,
|
7050 |
+
"learning_rate": 6.295446091358618e-07,
|
7051 |
+
"loss": 1.0284,
|
7052 |
+
"step": 587000
|
7053 |
+
},
|
7054 |
+
{
|
7055 |
+
"epoch": 15.4,
|
7056 |
+
"learning_rate": 6.261335442758554e-07,
|
7057 |
+
"loss": 1.0337,
|
7058 |
+
"step": 587500
|
7059 |
+
},
|
7060 |
+
{
|
7061 |
+
"epoch": 15.41,
|
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": 7.037292973216481e+17,
|
7070 |
"trial_name": null,
|
7071 |
"trial_params": null
|
7072 |
}
|
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 sha256:89037c61457d92a92d8a8114636f5328491a76d6f314d56f9e8167460609d7fc
|
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:ba38c004c778b009546003c02c04bc43ef50ddeee326ffd3e18109395d615d18
|
3 |
+
size 11181
|