Training in progress, step 600000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- 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/Jun02_00-39-49_138e59608869/events.out.tfevents.1685668028.138e59608869.1307.0 +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 sha256:428a42c91913879b41a1c2803d998875b9da7f68b57269ba88572bd6d7ce4f64
|
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:b080b9b29f961ef52eafaad1999ae2f632518cab5bfbea3cab5786c34f1394b5
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a962056376cc55caa0509a94dce6afead45bd33809ddcfeee2f662b8cd813c4
|
3 |
+
size 14511
|
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:c222d234df96e58f4e769dcdcf413da5cbddf18b696f2ea0f7db071920b58233
|
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:ed4046b8b982634729686d6bf5e39b07e66c1d3c6391448d15bb8c916db29fc5
|
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,
|
@@ -7170,11 +7170,47 @@
|
|
7170 |
"learning_rate": 5.628747568951393e-07,
|
7171 |
"loss": 1.0314,
|
7172 |
"step": 597000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7173 |
}
|
7174 |
],
|
7175 |
"max_steps": 762960,
|
7176 |
"num_train_epochs": 20,
|
7177 |
-
"total_flos": 7.
|
7178 |
"trial_name": null,
|
7179 |
"trial_params": null
|
7180 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.728208784641033,
|
5 |
+
"global_step": 600000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7170 |
"learning_rate": 5.628747568951393e-07,
|
7171 |
"loss": 1.0314,
|
7172 |
"step": 597000
|
7173 |
+
},
|
7174 |
+
{
|
7175 |
+
"epoch": 15.66,
|
7176 |
+
"learning_rate": 5.596251846756392e-07,
|
7177 |
+
"loss": 1.0358,
|
7178 |
+
"step": 597500
|
7179 |
+
},
|
7180 |
+
{
|
7181 |
+
"epoch": 15.68,
|
7182 |
+
"learning_rate": 5.563838371869096e-07,
|
7183 |
+
"loss": 1.0075,
|
7184 |
+
"step": 598000
|
7185 |
+
},
|
7186 |
+
{
|
7187 |
+
"epoch": 15.69,
|
7188 |
+
"learning_rate": 5.531507281681564e-07,
|
7189 |
+
"loss": 1.027,
|
7190 |
+
"step": 598500
|
7191 |
+
},
|
7192 |
+
{
|
7193 |
+
"epoch": 15.7,
|
7194 |
+
"learning_rate": 5.499323127925932e-07,
|
7195 |
+
"loss": 1.0259,
|
7196 |
+
"step": 599000
|
7197 |
+
},
|
7198 |
+
{
|
7199 |
+
"epoch": 15.72,
|
7200 |
+
"learning_rate": 5.467221302031053e-07,
|
7201 |
+
"loss": 1.0216,
|
7202 |
+
"step": 599500
|
7203 |
+
},
|
7204 |
+
{
|
7205 |
+
"epoch": 15.73,
|
7206 |
+
"learning_rate": 5.435137855349992e-07,
|
7207 |
+
"loss": 1.0323,
|
7208 |
+
"step": 600000
|
7209 |
}
|
7210 |
],
|
7211 |
"max_steps": 762960,
|
7212 |
"num_train_epochs": 20,
|
7213 |
+
"total_flos": 7.169441382292193e+17,
|
7214 |
"trial_name": null,
|
7215 |
"trial_params": null
|
7216 |
}
|
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:b080b9b29f961ef52eafaad1999ae2f632518cab5bfbea3cab5786c34f1394b5
|
3 |
size 1944201353
|
runs/Jun02_00-39-49_138e59608869/events.out.tfevents.1685668028.138e59608869.1307.0
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 sha256:394490a971e3aa4fe7457345f302913ccbdb7dd358e0ce79b6cebace43b0f673
|
3 |
+
size 6381
|