Training in progress, step 6800, 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 sha256:24a830ff0ef712063cf263061c7715c7e4ab0d373d9ab416fed9dafed056d279
|
| 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 sha256:238448f357f5f9357969c09f556fa44edf59423c99eb066a1c97611e85eb8392
|
| 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 sha256:8815de27fb5e157afb197262352952f1b64bb5354465a8d3442882c2c526a7dd
|
| 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 sha256:0a3bc73ddfd4eb0f55767d8999842e62d8ee283abef545702b66292a0270b4a2
|
| 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,
|
|
@@ -580,6 +580,13 @@
|
|
| 580 |
"learning_rate": 5.5333333333333334e-05,
|
| 581 |
"loss": 1.2431,
|
| 582 |
"step": 6700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 583 |
}
|
| 584 |
],
|
| 585 |
"logging_steps": 100,
|
|
@@ -599,7 +606,7 @@
|
|
| 599 |
"attributes": {}
|
| 600 |
}
|
| 601 |
},
|
| 602 |
-
"total_flos": 1.
|
| 603 |
"train_batch_size": 8,
|
| 604 |
"trial_name": null,
|
| 605 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 13.597875331979377,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 580 |
"learning_rate": 5.5333333333333334e-05,
|
| 581 |
"loss": 1.2431,
|
| 582 |
"step": 6700
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 13.597875331979377,
|
| 586 |
+
"grad_norm": 0.20601199567317963,
|
| 587 |
+
"learning_rate": 5.466666666666666e-05,
|
| 588 |
+
"loss": 1.2365,
|
| 589 |
+
"step": 6800
|
| 590 |
}
|
| 591 |
],
|
| 592 |
"logging_steps": 100,
|
|
|
|
| 606 |
"attributes": {}
|
| 607 |
}
|
| 608 |
},
|
| 609 |
+
"total_flos": 1.0612979001481757e+19,
|
| 610 |
"train_batch_size": 8,
|
| 611 |
"trial_name": null,
|
| 612 |
"trial_params": null
|