Training in progress, step 6200, 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 sha256:5c9efcf5f5ba4174e2f06adef535766903be48be01bba78ab81a9bea4daa8971
|
| 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 sha256:235176e65735e56500c37371ecbd6083a7056627a6fc2c6f86864d4a4b7fcb34
|
| 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 sha256:9804a51692ec905686d71e5b83929428374c0ce20346a6efc9e1f345c46e4daa
|
| 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 sha256:3f49f87fd545ff22d6f42b3517382deaca7e07e108c096a9870e028e72d83335
|
| 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,
|
|
@@ -530,6 +530,13 @@
|
|
| 530 |
"learning_rate": 5.9333333333333343e-05,
|
| 531 |
"loss": 1.2475,
|
| 532 |
"step": 6100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 533 |
}
|
| 534 |
],
|
| 535 |
"logging_steps": 100,
|
|
@@ -549,7 +556,7 @@
|
|
| 549 |
"attributes": {}
|
| 550 |
}
|
| 551 |
},
|
| 552 |
-
"total_flos": 9.
|
| 553 |
"train_batch_size": 8,
|
| 554 |
"trial_name": null,
|
| 555 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.39806280268708,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 530 |
"learning_rate": 5.9333333333333343e-05,
|
| 531 |
"loss": 1.2475,
|
| 532 |
"step": 6100
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 12.39806280268708,
|
| 536 |
+
"grad_norm": 0.21070446074008942,
|
| 537 |
+
"learning_rate": 5.866666666666667e-05,
|
| 538 |
+
"loss": 1.2458,
|
| 539 |
+
"step": 6200
|
| 540 |
}
|
| 541 |
],
|
| 542 |
"logging_steps": 100,
|
|
|
|
| 556 |
"attributes": {}
|
| 557 |
}
|
| 558 |
},
|
| 559 |
+
"total_flos": 9.676538331223032e+18,
|
| 560 |
"train_batch_size": 8,
|
| 561 |
"trial_name": null,
|
| 562 |
"trial_params": null
|