Commit
•
202a98e
1
Parent(s):
fc7ebd9
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 sha256:00b77288d7de9928f0d4944f30ceaa295b505628b9edd8e5d47eb8a4bd9e9692
|
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 sha256:3217a20517ef38c58a8da957d08c71a1c0546fe4766b19a5c5e8998ff14a0214
|
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:f55ebe991e4838deda9ff3044672335e03697b65b3fe0753cca61998e974ee51
|
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": 43.695,
|
568 |
"eval_steps_per_second": 5.467,
|
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": 1.2136116027832031,
|
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": 43.695,
|
568 |
"eval_steps_per_second": 5.467,
|
569 |
"step": 4000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 2.99,
|
573 |
+
"learning_rate": 0.0002,
|
574 |
+
"loss": 1.2033,
|
575 |
+
"step": 4100
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 2.99,
|
579 |
+
"eval_loss": 1.2136116027832031,
|
580 |
+
"eval_runtime": 146.7958,
|
581 |
+
"eval_samples_per_second": 42.74,
|
582 |
+
"eval_steps_per_second": 5.348,
|
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 |
}
|