Training in progress, step 9600
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 +19 -3
- pytorch_model.bin +1 -1
- runs/Jun22_01-22-44_ecbe051c6b95/events.out.tfevents.1687398240.ecbe051c6b95.251.0 +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 2117841669
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f6d8ec7bea6a5164cf0191b51df59f7b776fd07ed5e2ca048fe81dce5048a21
|
3 |
size 2117841669
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e77799c2664dfd85c6947b627241d82a9c8c3e2fe6d131704f6ac8cc48fbda5
|
3 |
size 2268278205
|
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 sha256:13820e47d46688c54bf9d1f1c72425ed737db5d331f3bf26cded7a8ef031210a
|
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 sha256:5c61e0b2a90a151c2f1f9e56985eb5fb65d743e30eb961fb3604c13b398477b2
|
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,
|
@@ -334,11 +334,27 @@
|
|
334 |
"eval_samples_per_second": 197.006,
|
335 |
"eval_steps_per_second": 0.77,
|
336 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
337 |
}
|
338 |
],
|
339 |
"max_steps": 953000,
|
340 |
"num_train_epochs": 100,
|
341 |
-
"total_flos":
|
342 |
"trial_name": null,
|
343 |
"trial_params": null
|
344 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0073452256033577,
|
5 |
+
"global_step": 9600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
334 |
"eval_samples_per_second": 197.006,
|
335 |
"eval_steps_per_second": 0.77,
|
336 |
"step": 9000
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 1.0,
|
340 |
+
"learning_rate": 9.900545645330536e-06,
|
341 |
+
"loss": 0.686,
|
342 |
+
"step": 9500
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.01,
|
346 |
+
"eval_accuracy": 0.8796352314480071,
|
347 |
+
"eval_f1": 0.8798913903465643,
|
348 |
+
"eval_loss": 0.6714671850204468,
|
349 |
+
"eval_runtime": 688.5552,
|
350 |
+
"eval_samples_per_second": 196.844,
|
351 |
+
"eval_steps_per_second": 0.77,
|
352 |
+
"step": 9600
|
353 |
}
|
354 |
],
|
355 |
"max_steps": 953000,
|
356 |
"num_train_epochs": 100,
|
357 |
+
"total_flos": 4.0331079569724166e+17,
|
358 |
"trial_name": null,
|
359 |
"trial_params": null
|
360 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e77799c2664dfd85c6947b627241d82a9c8c3e2fe6d131704f6ac8cc48fbda5
|
3 |
size 2268278205
|
runs/Jun22_01-22-44_ecbe051c6b95/events.out.tfevents.1687398240.ecbe051c6b95.251.0
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:f11b813b2f21ab74dd5424521ffcb6eb9ee9e8a4c880dfffec041ac9f2897409
|
3 |
+
size 5561
|