Training in progress, step 7900, 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:c9199c58a0e18f6b20cd590e32c01edcc53cc30d656e858f90c63854fd0b6904
|
| 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 sha256:22e4c03a222e16e99e9720067ab049b60c35901ce97933852ed8035f575d9d35
|
| 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 sha256:9d97fc2860205491c7e62a329fa7e1a38b4205dc52aa4d5fd276acf955995202
|
| 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:c2a0479a2cd7c6c12ef80c1a2f8d1061865d0e9e997e771a694b192ac7bb6fce
|
| 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": 15.
|
| 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,
|
|
@@ -673,6 +673,13 @@
|
|
| 673 |
"learning_rate": 4.8e-05,
|
| 674 |
"loss": 1.234,
|
| 675 |
"step": 7800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 676 |
}
|
| 677 |
],
|
| 678 |
"logging_steps": 100,
|
|
@@ -692,7 +699,7 @@
|
|
| 692 |
"attributes": {}
|
| 693 |
}
|
| 694 |
},
|
| 695 |
-
"total_flos": 1.
|
| 696 |
"train_batch_size": 8,
|
| 697 |
"trial_name": null,
|
| 698 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.797531635681924,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 673 |
"learning_rate": 4.8e-05,
|
| 674 |
"loss": 1.234,
|
| 675 |
"step": 7800
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 15.797531635681924,
|
| 679 |
+
"grad_norm": 0.22062599658966064,
|
| 680 |
+
"learning_rate": 4.7333333333333336e-05,
|
| 681 |
+
"loss": 1.2317,
|
| 682 |
+
"step": 7900
|
| 683 |
}
|
| 684 |
],
|
| 685 |
"logging_steps": 100,
|
|
|
|
| 699 |
"attributes": {}
|
| 700 |
}
|
| 701 |
},
|
| 702 |
+
"total_flos": 1.232978537081104e+19,
|
| 703 |
"train_batch_size": 8,
|
| 704 |
"trial_name": null,
|
| 705 |
"trial_params": null
|