Training in progress, step 7300, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3710253c77745e4e929fcf8ad01a80292394da13c9b529a144e865235147680
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:724917710d1f8fec5b014b8ed1ad76417c303a009f1166f38d47cc93e0e44fc8
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:068f8db70a26a07c169c173b5a35587d45af4bbdddcf00ebd3e602553b876cf7
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:344ce659a07552ccc99dec860c995c34c0e218dd58bf3b22fee720e0a697c58a
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 14.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -623,6 +623,13 @@
|
|
| 623 |
"learning_rate": 5.2000000000000004e-05,
|
| 624 |
"loss": 1.2395,
|
| 625 |
"step": 7200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 626 |
}
|
| 627 |
],
|
| 628 |
"logging_steps": 100,
|
|
@@ -642,7 +649,7 @@
|
|
| 642 |
"attributes": {}
|
| 643 |
}
|
| 644 |
},
|
| 645 |
-
"total_flos": 1.
|
| 646 |
"train_batch_size": 8,
|
| 647 |
"trial_name": null,
|
| 648 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.597719106389627,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 623 |
"learning_rate": 5.2000000000000004e-05,
|
| 624 |
"loss": 1.2395,
|
| 625 |
"step": 7200
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 14.597719106389627,
|
| 629 |
+
"grad_norm": 0.2192169427871704,
|
| 630 |
+
"learning_rate": 5.133333333333333e-05,
|
| 631 |
+
"loss": 1.2374,
|
| 632 |
+
"step": 7300
|
| 633 |
}
|
| 634 |
],
|
| 635 |
"logging_steps": 100,
|
|
|
|
| 649 |
"attributes": {}
|
| 650 |
}
|
| 651 |
},
|
| 652 |
+
"total_flos": 1.1393344700552315e+19,
|
| 653 |
"train_batch_size": 8,
|
| 654 |
"trial_name": null,
|
| 655 |
"trial_params": null
|