Dmitriy007
commited on
Commit
•
5d98ca3
1
Parent(s):
b38615c
Training in progress, step 15000
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 sha256:0c6e63dff736c9825ce32952f68edca644c10a3063e095a8362d1d0b55d19808
|
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 sha256:92e64dc690528c0e8d43d15b21c2682f986d1e72fb770656be30290681f7bb84
|
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 sha256:217d8ab0fff3ee70721ead38ad0d346fd3404acb00cd1fb80f1fab385d42ba31
|
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:d831ab78ba201bc3164beda17a95e52eede4b41273e28d5cdb55e325c07a96ee
|
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": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -286,11 +286,31 @@
|
|
286 |
"eval_samples_per_second": 14.768,
|
287 |
"eval_steps_per_second": 4.925,
|
288 |
"step": 14000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
289 |
}
|
290 |
],
|
291 |
"max_steps": 19990,
|
292 |
"num_train_epochs": 5,
|
293 |
-
"total_flos":
|
294 |
"trial_name": null,
|
295 |
"trial_params": null
|
296 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.7518759379689843,
|
5 |
+
"global_step": 15000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
286 |
"eval_samples_per_second": 14.768,
|
287 |
"eval_steps_per_second": 4.925,
|
288 |
"step": 14000
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 3.63,
|
292 |
+
"learning_rate": 5.492746373186594e-06,
|
293 |
+
"loss": 2.526,
|
294 |
+
"step": 14500
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 3.75,
|
298 |
+
"learning_rate": 4.992496248124062e-06,
|
299 |
+
"loss": 2.5249,
|
300 |
+
"step": 15000
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 3.75,
|
304 |
+
"eval_loss": 3.1433019638061523,
|
305 |
+
"eval_runtime": 143.273,
|
306 |
+
"eval_samples_per_second": 14.776,
|
307 |
+
"eval_steps_per_second": 4.928,
|
308 |
+
"step": 15000
|
309 |
}
|
310 |
],
|
311 |
"max_steps": 19990,
|
312 |
"num_train_epochs": 5,
|
313 |
+
"total_flos": 2.12222619648e+16,
|
314 |
"trial_name": null,
|
315 |
"trial_params": null
|
316 |
}
|
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 sha256:92e64dc690528c0e8d43d15b21c2682f986d1e72fb770656be30290681f7bb84
|
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 sha256:20cb3f8354f7dccc3465b083009a93e7f08186da8c55748d37e94633ccae23f0
|
3 |
+
size 7137
|