Training in progress, step 7200, 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 sha256:716e71e2034b32be66905e1d08ddaa244ce4bfef6b454a0bf87650a28a389e95
|
| 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:ea5aaafdf355d6ea2901894528a8be1bd1079c1203fb67cb04d709783ba9eebc
|
| 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 sha256:40df2f31c4b6f179ee78e22118511132b77a3774f7a6d1037526e0c296d0c758
|
| 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 sha256:88a0bc9d9f3e84f65767e55a4480c2f80bd10fee61ad9874d02fc04f6496637a
|
| 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,
|
|
@@ -616,6 +616,13 @@
|
|
| 616 |
"learning_rate": 5.266666666666666e-05,
|
| 617 |
"loss": 1.2406,
|
| 618 |
"step": 7100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 619 |
}
|
| 620 |
],
|
| 621 |
"logging_steps": 100,
|
|
@@ -635,7 +642,7 @@
|
|
| 635 |
"attributes": {}
|
| 636 |
}
|
| 637 |
},
|
| 638 |
-
"total_flos": 1.
|
| 639 |
"train_batch_size": 8,
|
| 640 |
"trial_name": null,
|
| 641 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.397750351507577,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 616 |
"learning_rate": 5.266666666666666e-05,
|
| 617 |
"loss": 1.2406,
|
| 618 |
"step": 7100
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 14.397750351507577,
|
| 622 |
+
"grad_norm": 0.22387249767780304,
|
| 623 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 624 |
+
"loss": 1.2395,
|
| 625 |
+
"step": 7200
|
| 626 |
}
|
| 627 |
],
|
| 628 |
"logging_steps": 100,
|
|
|
|
| 642 |
"attributes": {}
|
| 643 |
}
|
| 644 |
},
|
| 645 |
+
"total_flos": 1.1237269729364148e+19,
|
| 646 |
"train_batch_size": 8,
|
| 647 |
"trial_name": null,
|
| 648 |
"trial_params": null
|