Training in progress, step 4000, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0c3172ef44d6f83480c11044466ca5c5ab673eedd6de59f5cc30071f388da23
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4e06e21259e1555f76f85bc4a79e701236c2eca73e35d415d303824e71fe24a
|
3 |
size 18902665
|
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:fe072b43116ea6af1d9839ff9078df37c5fb13f3285b4cbe739c3c5d14228bdf
|
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 sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -553,13 +553,27 @@
|
|
553 |
"eval_samples_per_second": 30.416,
|
554 |
"eval_steps_per_second": 3.806,
|
555 |
"step": 3900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
556 |
}
|
557 |
],
|
558 |
"logging_steps": 100,
|
559 |
"max_steps": 4116,
|
560 |
"num_train_epochs": 3,
|
561 |
"save_steps": 100,
|
562 |
-
"total_flos": 1.
|
563 |
"trial_name": null,
|
564 |
"trial_params": null
|
565 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.9713504314422607,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-4000",
|
4 |
+
"epoch": 2.9143897996357016,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 4000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
553 |
"eval_samples_per_second": 30.416,
|
554 |
"eval_steps_per_second": 3.806,
|
555 |
"step": 3900
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 2.91,
|
559 |
+
"learning_rate": 0.0002,
|
560 |
+
"loss": 1.9401,
|
561 |
+
"step": 4000
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 2.91,
|
565 |
+
"eval_loss": 1.9713504314422607,
|
566 |
+
"eval_runtime": 206.4883,
|
567 |
+
"eval_samples_per_second": 30.384,
|
568 |
+
"eval_steps_per_second": 3.802,
|
569 |
+
"step": 4000
|
570 |
}
|
571 |
],
|
572 |
"logging_steps": 100,
|
573 |
"max_steps": 4116,
|
574 |
"num_train_epochs": 3,
|
575 |
"save_steps": 100,
|
576 |
+
"total_flos": 1.1744177835220992e+17,
|
577 |
"trial_name": null,
|
578 |
"trial_params": null
|
579 |
}
|