Training in progress, step 8200, 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 sha256:9f0152b464b83ad9a4afbb9a469880e3ce5b3472734051ea242a2e697a6fc70e
|
| 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:c9e5905a47031e0fbd479c38ff02d1e1a98a1d3c6c5bb58e5423d31e715986bf
|
| 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:e3f81e0dcc5ccc0ba0e9ce2d2b1e3a5d6b8688a220277c4cc8aac9c1aa9009d3
|
| 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:cb47a103063c46e5c3e001d1790c9dc9c37a3acb38723f7decea3f5bf3396602
|
| 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": 16.
|
| 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,
|
|
@@ -702,6 +702,13 @@
|
|
| 702 |
"learning_rate": 4.600000000000001e-05,
|
| 703 |
"loss": 1.2356,
|
| 704 |
"step": 8100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 705 |
}
|
| 706 |
],
|
| 707 |
"logging_steps": 100,
|
|
@@ -721,7 +728,7 @@
|
|
| 721 |
"attributes": {}
|
| 722 |
}
|
| 723 |
},
|
| 724 |
-
"total_flos": 1.
|
| 725 |
"train_batch_size": 8,
|
| 726 |
"trial_name": null,
|
| 727 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 16.397437900328075,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 8200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 702 |
"learning_rate": 4.600000000000001e-05,
|
| 703 |
"loss": 1.2356,
|
| 704 |
"step": 8100
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 16.397437900328075,
|
| 708 |
+
"grad_norm": 0.23483353853225708,
|
| 709 |
+
"learning_rate": 4.5333333333333335e-05,
|
| 710 |
+
"loss": 1.2298,
|
| 711 |
+
"step": 8200
|
| 712 |
}
|
| 713 |
],
|
| 714 |
"logging_steps": 100,
|
|
|
|
| 728 |
"attributes": {}
|
| 729 |
}
|
| 730 |
},
|
| 731 |
+
"total_flos": 1.2798001127505265e+19,
|
| 732 |
"train_batch_size": 8,
|
| 733 |
"trial_name": null,
|
| 734 |
"trial_params": null
|