Commit
•
8f65368
1
Parent(s):
c7b5a77
Training in progress, step 29058
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 +9 -3
- pytorch_model.bin +1 -1
- runs/Jun04_13-23-35_1c0366a2fd20/events.out.tfevents.1685885434.1c0366a2fd20.848.0 +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 6319689
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbd9a570f689690c9381a700f4e08f7d057250fad239bf0d7d3d166c4750c397
|
3 |
size 6319689
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1121737121
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2949de498c0f9afaeec2e192142e84b05021e91da60ad84d02e7a4c541c57fa6
|
3 |
size 1121737121
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3095a897d1ad5c84155b78f306cfbdfcda4139cf5d1a48de6af855a69e4c48c
|
3 |
size 14639
|
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 sha256:4a95c6d62da71cd9b73e2c211f3e49827560e0c4c60be12059c1f57b220ad397
|
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 sha256:0f9b2568ca412d775325fb85c1efef3ee291a975293265d1304937b578764801
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -186,11 +186,17 @@
|
|
186 |
"learning_rate": 1.3519952766297365e-05,
|
187 |
"loss": 1.5231,
|
188 |
"step": 28000
|
|
|
|
|
|
|
|
|
|
|
|
|
189 |
}
|
190 |
],
|
191 |
"max_steps": 86379,
|
192 |
"num_train_epochs": 1,
|
193 |
-
"total_flos": 5.
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|
196 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3364012086270969,
|
5 |
+
"global_step": 29058,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
186 |
"learning_rate": 1.3519952766297365e-05,
|
187 |
"loss": 1.5231,
|
188 |
"step": 28000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.34,
|
192 |
+
"learning_rate": 1.3288415008277476e-05,
|
193 |
+
"loss": 1.5052,
|
194 |
+
"step": 29000
|
195 |
}
|
196 |
],
|
197 |
"max_steps": 86379,
|
198 |
"num_train_epochs": 1,
|
199 |
+
"total_flos": 5.411313875209421e+16,
|
200 |
"trial_name": null,
|
201 |
"trial_params": null
|
202 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1121737121
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2949de498c0f9afaeec2e192142e84b05021e91da60ad84d02e7a4c541c57fa6
|
3 |
size 1121737121
|
runs/Jun04_13-23-35_1c0366a2fd20/events.out.tfevents.1685885434.1c0366a2fd20.848.0
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 sha256:45922adb686d3cebf6b88e743e80ff7158718fb2e10617b5a28ccbecfaa93722
|
3 |
+
size 5149
|