Dmitriy007
commited on
Commit
•
1a4dd9c
1
Parent(s):
d424cb7
Training in progress, step 12000
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/Mar21_22-11-09_493485ec0ec3/events.out.tfevents.1679436700.493485ec0ec3.312.0 +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 sha256:207a7e01bdc646d9c356d8a828dedc0cd5b3ae4b86eb20eaab1dcab694337571
|
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:f74e316b53229e421469141121f72218a2a3a801d744198d804d601088e15c76
|
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 sha256:5e52bd69c1b64aeb0e631baf79a8d496730aeee87b3c09448091c59e66e64122
|
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 sha256:7b2f7bf5c914e1b3c9d0649a6843fc3a59fdcbbdc4a3bbcfa727028a2a1a436b
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -226,11 +226,31 @@
|
|
226 |
"eval_samples_per_second": 14.739,
|
227 |
"eval_steps_per_second": 4.915,
|
228 |
"step": 11000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
229 |
}
|
230 |
],
|
231 |
"max_steps": 19990,
|
232 |
"num_train_epochs": 5,
|
233 |
-
"total_flos": 1.
|
234 |
"trial_name": null,
|
235 |
"trial_params": null
|
236 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0015007503751874,
|
5 |
+
"global_step": 12000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
226 |
"eval_samples_per_second": 14.739,
|
227 |
"eval_steps_per_second": 4.915,
|
228 |
"step": 11000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 2.88,
|
232 |
+
"learning_rate": 8.494247123561783e-06,
|
233 |
+
"loss": 2.6277,
|
234 |
+
"step": 11500
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 3.0,
|
238 |
+
"learning_rate": 7.993996998499251e-06,
|
239 |
+
"loss": 2.64,
|
240 |
+
"step": 12000
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 3.0,
|
244 |
+
"eval_loss": 3.123826265335083,
|
245 |
+
"eval_runtime": 143.485,
|
246 |
+
"eval_samples_per_second": 14.754,
|
247 |
+
"eval_steps_per_second": 4.92,
|
248 |
+
"step": 12000
|
249 |
}
|
250 |
],
|
251 |
"max_steps": 19990,
|
252 |
"num_train_epochs": 5,
|
253 |
+
"total_flos": 1.697780957184e+16,
|
254 |
"trial_name": null,
|
255 |
"trial_params": null
|
256 |
}
|
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:f74e316b53229e421469141121f72218a2a3a801d744198d804d601088e15c76
|
3 |
size 1524261149
|
runs/Mar21_22-11-09_493485ec0ec3/events.out.tfevents.1679436700.493485ec0ec3.312.0
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:bb1ad7dc9b343f43883f6aeaf7a17dcbe014e40ecb31c1b8ba3ca952d2627988
|
3 |
+
size 5382
|