Dmitriy007
commited on
Commit
•
7d73d56
1
Parent(s):
330b071
Training in progress, step 9000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +23 -3
- pytorch_model.bin +1 -1
- runs/Mar25_07-47-44_6e686009e3a0/events.out.tfevents.1679730482.6e686009e3a0.183.0 +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 2847145157
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d2f03fdda1ca39fde0c64317a67d40ff299e0a8045caf4dc17711409c358e20
|
3 |
size 2847145157
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53a37e89668ae10c59734590a0f0679c1da8a47db00622b7c14188b5f2f462f3
|
3 |
size 1524261149
|
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 sha256:594a7b3eb7944bb29e89c6e91df08311e0966ab057560b6e9a9bb9bd8325d00f
|
3 |
size 14575
|
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 sha256:79ad06f468520eb5788f5b1dacc68d3dfe5a2d6bd8c9cc80958aab7e81c44936
|
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": 4.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -166,11 +166,31 @@
|
|
166 |
"eval_samples_per_second": 15.881,
|
167 |
"eval_steps_per_second": 2.648,
|
168 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
169 |
}
|
170 |
],
|
171 |
"max_steps": 9995,
|
172 |
"num_train_epochs": 5,
|
173 |
-
"total_flos": 2.
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
176 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.502251125562782,
|
5 |
+
"global_step": 9000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
166 |
"eval_samples_per_second": 15.881,
|
167 |
"eval_steps_per_second": 2.648,
|
168 |
"step": 8000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 4.25,
|
172 |
+
"learning_rate": 2.991495747873937e-06,
|
173 |
+
"loss": 2.776,
|
174 |
+
"step": 8500
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 4.5,
|
178 |
+
"learning_rate": 1.9909954977488747e-06,
|
179 |
+
"loss": 2.7743,
|
180 |
+
"step": 9000
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 4.5,
|
184 |
+
"eval_loss": 3.094261646270752,
|
185 |
+
"eval_runtime": 133.0331,
|
186 |
+
"eval_samples_per_second": 15.913,
|
187 |
+
"eval_steps_per_second": 2.653,
|
188 |
+
"step": 9000
|
189 |
}
|
190 |
],
|
191 |
"max_steps": 9995,
|
192 |
"num_train_epochs": 5,
|
193 |
+
"total_flos": 2.546671435776e+16,
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|
196 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53a37e89668ae10c59734590a0f0679c1da8a47db00622b7c14188b5f2f462f3
|
3 |
size 1524261149
|
runs/Mar25_07-47-44_6e686009e3a0/events.out.tfevents.1679730482.6e686009e3a0.183.0
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 sha256:8ca88963b1354a0a743bcb3f8951a497b94c20ef931f425dfc8fcf8bac038577
|
3 |
+
size 5983
|