ramdhanfirdaus
commited on
Commit
•
d22329d
1
Parent(s):
934d413
Training in progress, step 4100, 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 50338848
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b8293631d6513b037ed6909323b4f0ad8b6b1fbcbe9e82fbfad82c4fb14362d
|
3 |
size 50338848
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100693001
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b0dc8ac9d3f86a58d73561f91a8908ab196edb7acdb14b1a335c7e6a320854a
|
3 |
size 100693001
|
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 sha256:090c2b75e05740bc86b1f8f8c7f09eb690b5edd74f523995d63f8760f4d18b6e
|
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 sha256:1ef51ed05818f33aebca9592cb64baf0df006aad2a34a7cf944f4a48b70afce3
|
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,
|
@@ -567,13 +567,27 @@
|
|
567 |
"eval_samples_per_second": 43.717,
|
568 |
"eval_steps_per_second": 5.47,
|
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": 2.
|
577 |
"trial_name": null,
|
578 |
"trial_params": null
|
579 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.2128502130508423,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-4100",
|
4 |
+
"epoch": 2.987249544626594,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 4100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
567 |
"eval_samples_per_second": 43.717,
|
568 |
"eval_steps_per_second": 5.47,
|
569 |
"step": 4000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 2.99,
|
573 |
+
"learning_rate": 0.0002,
|
574 |
+
"loss": 1.2012,
|
575 |
+
"step": 4100
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 2.99,
|
579 |
+
"eval_loss": 1.2128502130508423,
|
580 |
+
"eval_runtime": 143.5068,
|
581 |
+
"eval_samples_per_second": 43.719,
|
582 |
+
"eval_steps_per_second": 5.47,
|
583 |
+
"step": 4100
|
584 |
}
|
585 |
],
|
586 |
"logging_steps": 100,
|
587 |
"max_steps": 4116,
|
588 |
"num_train_epochs": 3,
|
589 |
"save_steps": 100,
|
590 |
+
"total_flos": 2.4438234279579648e+17,
|
591 |
"trial_name": null,
|
592 |
"trial_params": null
|
593 |
}
|