Training in progress, step 6700, 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:e1a8180255e4db5808645801739c17671aa6ab5c3a6c439b17337415cfff6408
|
| 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 sha256:08d4cb20e9b3e6eac9aab93f252c65a47addd43cfac95d1113daf6769b42e165
|
| 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:dfbb3bf1adb06d87f35ec23d2e746fbca37594a38f85d3cf6286f3259ab923f1
|
| 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:f8371e208e35cc8c88e6b1ff6effd51aca2306119aa9652552b47cd1808eb4ef
|
| 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": 13.
|
| 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,
|
|
@@ -573,6 +573,13 @@
|
|
| 573 |
"learning_rate": 5.6000000000000006e-05,
|
| 574 |
"loss": 1.2461,
|
| 575 |
"step": 6600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 576 |
}
|
| 577 |
],
|
| 578 |
"logging_steps": 100,
|
|
@@ -592,7 +599,7 @@
|
|
| 592 |
"attributes": {}
|
| 593 |
}
|
| 594 |
},
|
| 595 |
-
"total_flos": 1.
|
| 596 |
"train_batch_size": 8,
|
| 597 |
"trial_name": null,
|
| 598 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 13.397906577097329,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 573 |
"learning_rate": 5.6000000000000006e-05,
|
| 574 |
"loss": 1.2461,
|
| 575 |
"step": 6600
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 13.397906577097329,
|
| 579 |
+
"grad_norm": 0.2096029669046402,
|
| 580 |
+
"learning_rate": 5.5333333333333334e-05,
|
| 581 |
+
"loss": 1.2431,
|
| 582 |
+
"step": 6700
|
| 583 |
}
|
| 584 |
],
|
| 585 |
"logging_steps": 100,
|
|
|
|
| 599 |
"attributes": {}
|
| 600 |
}
|
| 601 |
},
|
| 602 |
+
"total_flos": 1.045690403029359e+19,
|
| 603 |
"train_batch_size": 8,
|
| 604 |
"trial_name": null,
|
| 605 |
"trial_params": null
|