Training in progress, step 6400, 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 sha256:10e51635e22cc4d8257e3998139dd244d3a6d953d81d24c8fa5749cf91708081
|
| 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 sha256:43c5f63ed78dbe211d8e9a6074043dfb4dc7d9bd2f3c157049ec3fccd1fd44d6
|
| 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 sha256:123058a7e1eae93f8ce60cf6d522b62fb472becdaa34f1380b8c150bfd960932
|
| 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:bd83f394af7b27399972a12ed123bbfca08cbedb65ad8f9f3e082310668cc623
|
| 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": 12.
|
| 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,
|
|
@@ -544,6 +544,13 @@
|
|
| 544 |
"learning_rate": 5.8e-05,
|
| 545 |
"loss": 1.2423,
|
| 546 |
"step": 6300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 547 |
}
|
| 548 |
],
|
| 549 |
"logging_steps": 100,
|
|
@@ -563,7 +570,7 @@
|
|
| 563 |
"attributes": {}
|
| 564 |
}
|
| 565 |
},
|
| 566 |
-
"total_flos": 9.
|
| 567 |
"train_batch_size": 8,
|
| 568 |
"trial_name": null,
|
| 569 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.79800031245118,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 544 |
"learning_rate": 5.8e-05,
|
| 545 |
"loss": 1.2423,
|
| 546 |
"step": 6300
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 12.79800031245118,
|
| 550 |
+
"grad_norm": 0.2171526849269867,
|
| 551 |
+
"learning_rate": 5.7333333333333336e-05,
|
| 552 |
+
"loss": 1.2384,
|
| 553 |
+
"step": 6400
|
| 554 |
}
|
| 555 |
],
|
| 556 |
"logging_steps": 100,
|
|
|
|
| 570 |
"attributes": {}
|
| 571 |
}
|
| 572 |
},
|
| 573 |
+
"total_flos": 9.988688273599365e+18,
|
| 574 |
"train_batch_size": 8,
|
| 575 |
"trial_name": null,
|
| 576 |
"trial_params": null
|