Training in progress, step 603000
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 sha256:7924350aa7b0ef40f7d6a474f587570dc226790bf00568e9c23218d34efafea7
|
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:acc7529dd346c8ff89bc38de3cc978fb0d50b278e43d762a8fbf29f855a69d82
|
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:ad3efc4595cba42dc788a946613baf66398a880b736516f6252b4e2ec36e45f4
|
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 sha256:0ad14576306654137543f9b3dec4960f6960720151fa86c828eb19ca18bad036
|
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 sha256:4f4f9f9e3abf410947206d3cf2eb5386883eaf03ecc7793d5a1bdcda114c35e9
|
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,
|
@@ -7206,11 +7206,47 @@
|
|
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.
|
7214 |
"trial_name": null,
|
7215 |
"trial_params": null
|
7216 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.806849042161664,
|
5 |
+
"global_step": 603000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7206 |
"learning_rate": 5.435137855349992e-07,
|
7207 |
"loss": 1.0323,
|
7208 |
"step": 600000
|
7209 |
+
},
|
7210 |
+
{
|
7211 |
+
"epoch": 15.74,
|
7212 |
+
"learning_rate": 5.403137338895826e-07,
|
7213 |
+
"loss": 1.0327,
|
7214 |
+
"step": 600500
|
7215 |
+
},
|
7216 |
+
{
|
7217 |
+
"epoch": 15.75,
|
7218 |
+
"learning_rate": 5.371219888310187e-07,
|
7219 |
+
"loss": 1.0246,
|
7220 |
+
"step": 601000
|
7221 |
+
},
|
7222 |
+
{
|
7223 |
+
"epoch": 15.77,
|
7224 |
+
"learning_rate": 5.339449224256996e-07,
|
7225 |
+
"loss": 1.0293,
|
7226 |
+
"step": 601500
|
7227 |
+
},
|
7228 |
+
{
|
7229 |
+
"epoch": 15.78,
|
7230 |
+
"learning_rate": 5.307698144117793e-07,
|
7231 |
+
"loss": 1.0265,
|
7232 |
+
"step": 602000
|
7233 |
+
},
|
7234 |
+
{
|
7235 |
+
"epoch": 15.79,
|
7236 |
+
"learning_rate": 5.276030534388399e-07,
|
7237 |
+
"loss": 1.0233,
|
7238 |
+
"step": 602500
|
7239 |
+
},
|
7240 |
+
{
|
7241 |
+
"epoch": 15.81,
|
7242 |
+
"learning_rate": 5.244509613783047e-07,
|
7243 |
+
"loss": 1.0278,
|
7244 |
+
"step": 603000
|
7245 |
}
|
7246 |
],
|
7247 |
"max_steps": 762960,
|
7248 |
"num_train_epochs": 20,
|
7249 |
+
"total_flos": 7.202301206304522e+17,
|
7250 |
"trial_name": null,
|
7251 |
"trial_params": null
|
7252 |
}
|
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:acc7529dd346c8ff89bc38de3cc978fb0d50b278e43d762a8fbf29f855a69d82
|
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 sha256:1265043442cc0302fe0749ab56d51c593485dcf47695ebdeb2d3ec9e330da349
|
3 |
+
size 7341
|